Surface roughness prediction is a pivotal aspect of the manufacturing industry, as it directly influences product quality and process optimization. This study introduces a predictive model for surface roughness in the turning of complex-structured workpieces, utilizing Gaussian Process Regression (GPR) informed by vibration signals. The model captures parameters from both the time and frequency domains of the turning tool, encompassing the mean, median, standard deviation (STD), and root mean square (RMS) values. The signal is from the time to frequency domain is executed using Welch's method, complemented by time-frequency domain analysis employing three levels of Daubechies Wavelet Packet Transform (WPT). The selected features are then utilized as inputs for the GPR model to forecast surface roughness. Empirical evidence indicates that the GPR model can accurately predict the surface roughness of turned complex-structured workpieces. This predictive strategy has the potential to improve product quality, streamline manufacturing processes, and minimize waste within the industry.

Our study clarified what is the same or not between Tier 1(Tokyo) and Tier 2(Kansai) metropolitan areas on shrinking cities problems. Both of metropolitan areas will dramatically decrease the Housing Asset Value (HAV) where areas of bedroom communities are located. On the other hand, compared to Tokyo, Kansai has been hit by decline at a faster pace. This raises the question of whether Kansai will be more or less impoverished by the deflation of the HAV. According to our results, Kansai municipalities should expect the HAV losses of 38% by 2045, but the HAV losses would be higher in the northern suburbs of Osaka. Kansai has to face the effects of the HAV deflation faster than Tokyo. But Tokyo has a neck of higher residential land price, the income multiplier of the HAV per household is about 4. The HAV deflation hits more severe problems for elderly households in Tokyo. Considering our study, Tier 2 metropolitan area is much faster effects of the HAV deflation, but Tier 1 metropolitan area has more serious social problem than Tier 2. Hence, there are different problems of different natures rather than which one is more severely affected by the deflation of the HAV.

This study investigates the application of regression neural networks, in particular the fitrnet model, in predicting the hardness of steels. The experiments involve extensive tuning of hyperparameters using Bayesian optimization and employ 5-fold and 10-fold cross-validation schemes. The trained models are rigorously evaluated, and their performances are compared using various metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The results provide valuable insights into the effectiveness of the models and their ability to generalize to unseen data. In particular, Model 4208 (8-85-141-1) emerges as the top performer with an impressive RMSE of 1.0790 and an R² of 0.9900. The research paper contains an illustrative example that demonstrates the practical application of the developed model in determining the hardenability band for a specific steel grade and shows the effectiveness of the model in predicting and optimizing heat treatment results.

Transformer models have emerged as frontrunners in the field of natural language processing, primarily due to their adept use of self-attention mechanisms to grasp the semantic linkages between words in sequences. Despite their strengths, these models often face challenges in single-task learning scenarios, particularly when it comes to delivering top-notch performance and crafting strong latent feature representations. This challenge is more pronounced in the context of smaller datasets and is particularly acute for under-resourced languages such as Arabic. In light of these challenges, this study introduces a novel methodology for text classification of Arabic texts. This method harnesses the newly developed Reverse Positional Encoding (RPE) technique. It adopts inductive-transfer learning (ITL) framework combined with a switching self-attention shared encoder, thereby increasing the model's adaptability and improving its sentence representation accuracy. The integration of Mixture of Experts (MoE) and Reverse Positional Encoding (RPE) techniques empowers the model to process longer sequences more effectively. This enhancement is notably beneficial for Arabic text classification, adeptly supporting both the intricate five-point and the simpler ternary classification tasks. The empirical evidence points to its outstanding performance, achieving accuracy rates of 87.20% for the HARD dataset, 72.17% for the BRAD dataset, and 86.89% for the LABR dataset, as evidenced by the assessments conducted on these datasets.

With the growing awareness of entrepreneurs and consumers of the tourism market in the field of sustainable development, it seems necessary to base hotel classification systems on an integrated approach to management quality, including fulfilment of ecological and environmental criteria. The article aims to indicate how environmental standards are implemented in the European system of hotel classification- HotelstarsUnion and the one in force in Poland. With regards to these systems, the differences in the classification criteria taken into account within the systems of hotel categorization by certifying organizations in the European Union in relation to the administrative hotel categorization system in Poland were pointed out. Particular emphasis was placed on the criteria related to environmental management in the hotel industry. Criteria related to environmental management were identified through analysis of the content of criteria of eight environmental management systems that are applicable to the contemporary hotel market. The results of the research proved that even though the HotelstarsUnion system takes into account the principles of sustainable development to a much greater extent than the Polish one, its primary weakness is that most of its criteria related to environmental ones are optional. In addition, the optional ones have higher weights than the obligatory ones. In turn, the Polish classification system makes very little reference to environmental standards. Moreover, it is not detailed and the assessment criteria are not up to date. Therefore, it is recommended that a greater number of environmental criteria is included when updating the HotelstarsUnion system, which should be obligatory for hotels to meet. In addition, the sustainability criteria included in the HotelstarsUnion system should be adapted to the policy system aimed at the hotel industry in Poland and other EU countries.

The strong competition in the automotive industry has required manufacturers to implement lean production, both with methods and techniques specific to Industry 4.0. At the same time, universities must provide graduates with specific skills for applying these new production methods and techniques. In this context, a Lean Learning Factory was developed in the Pitesti University Center, which allows students to learn, experiment, and research, in an environment similar to that of enterprises, the new Lean Manufacturing methods and techniques, and Industry 4.0. The research presented in this study had as its objective identifying the minimum number of repetitions necessary to train operators who serve two differently organized workstations, one classic, the other including digital techniques, but on which the same assembly operation is performed. Several indicators were considered in the analysis, such as the number of errors, the number of stops, the effective duration of the work cycle, and the percentage ratio between the standard duration of cyclical activities and the effective duration of the work cycle. The evolution of these indicators was mathematically modelled by regression functions, using the least squares method. The obtained results also highlight the usefulness of applying the DOJO method as a Lean manufacturing-specific learning technique and the efficiency of implementing digital techniques in work organization.

In recent years, researches on combining wavelet decomposition and convolutional neural network (CNN) together to classify hyperspectral images (HSI) have emerged, and some effective classification models have been proposed and achieved good classification results. However, there are two problems for most of the proposed models. One is the heavy training parameters and the other is that there is no distinction between the classification effectiveness of low frequency and high frequency features after wavelet decomposition. In this paper, a new light-weighted HSI classification model (LLFWCNN) is proposed, which performs multi-layer wavelet decomposition for HSI after dimensionality reduction, and only arranges the low frequency features in a specific stack mode, then classifies them through a well-designed convolutional neural network. Compared with other classification models, the number of parameters is only 2.5% of that of other models. And only the low frequency features after wavelet decomposition are used, while the high frequency features are abandoned. The results showed that compared with the state-of-the-art classification models, LLFWCNN could obtain the same or even better classification results with fewer network parameters and proved that the low frequency features after wavelet decomposition provide LLFWCNN with more favorable information for HSI classification as well.

In recent times, using image-based deep learning techniques has been very useful for classifying fruits. However, mango is a particular challenge because its shelf life is directly related to the degree of maturity at the time of harvest, which is determined mainly through the visual assessment of the operators when sorting them, doing it incorrectly, coupled with the blows and compressions exposed during storage and transport, trigger the deterioration in their quality, hence the importance of this operation. In this sense, the purpose of this study focuses on designing a computational model based on Deep Learning that uses a convolutional neural network (CNN) parameterized to select mangoes according to their color tone based on their maturity stage. A dataset was established from 201 labeled images, then a CNN architecture was built, obtaining a model on which 3 criteria were evaluated: the number of convolution and grouping layers, the resolution of the input images and the number of training epochs required. As a result, an input image resolution of 32 x 32 pixels was achieved, the process included a convolution layer followed by pooling that fed another layer that processed the results and ended in an output layer with 2 neurons under the One Hot Encoding representation. The model required 20 epochs to perfect its training, achieving 96.04 % accuracy in mango image selection. This study supports the potential of CNNs in quality analysis through mango color selection, even in uncertainty scenarios.

An existing simplified simulation model of global climate, population, economy, and governance is extended, through statistical and other data analysis, to include several measures of human well-being and population displacement. The revised model is used to explore (in testing to the year 2060) vicious cycles and causal cascades that, some have warned, could lead to acceleration of climate change in the coming decades. Model scenario testing addresses two uncertainties, namely the strength of the effect of climate change on governance erosion, and the strength of the “heat trap” effect from physical tipping points such as ice loss and permafrost thaw. This testing indicates that a strong heat trap effect could very well accelerate climate change, but that even a strong governance erosion effect is unlikely to do so. Governance erosion would hurt human well-being but is probably not much of a climate threat per se. These results are tentative but point to the possibility of formally modeling causal cascades beyond what the larger climate models have done to date.

In this paper, a distributed algorithm is proposed to solve a consensus convex optimization problem. It is a Jacobi-proximal alternating direction method of multipliers with a damping parameter $\gamma$ in the iteration of multiplier. Compared with existing algorithms, it has the following nice properties: (1) The restriction on proximal matrix is relaxed substantively, thus alleviating the weight of the proximal term. Therefore, the algorithm has a faster convergence speed. (2) The convergence analysis of the algorithm is established for any damping parameter $\gamma\in(0,2]$, which is larger ones in the literature. In addition, some numerical experiments and an application to a logistic regression problem are provided to validate the effectiveness and the characteristics of the proposed algorithm.

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diag-nosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obsta-cles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate clas-sification. As such, skilled clinicians often struggle to differentiate benign moles from early ma-lignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to confront difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification which combines snake models of Active Contour (AC) Segmentation, ResNet50 for feature ex-traction and a Capsule Network with a fusion of lightweight attention mechanisms, to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimi-nation, and improve accuracy. We employed the Stochastic Gradient Descent (SGD) optimization algorithm to optimize the model's parameters. The proposed model is implemented on publicly available datasets, namely HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated derma-tological diagnosis and provide a helpful tool for medical practitioners.

In response to the growing challenges in drone security and airspace management, this study introduces an advanced drone classifier, capable of detecting and categorizing Unmanned Aerial Vehicles (UAVs) based on acoustic signatures. Utilizing a comprehensive database of drone sounds across EU-defined classes (C0 to C3), this research leverages machine learning (ML) techniques for effective UAV identification. The study primarily focuses on the impact of data augmentation methods—pitch shifting, time delays, harmonic distortion, and ambient noise integration—on classifier performance. These techniques aim to mimic real-world acoustic variations, thus enhancing the classifier's robustness and practical applicability. Results indicate that moderate levels of augmentation significantly improve classification accuracy. However, excessive application of these methods can negatively affect performance. The study concludes that sophisticated acoustic data augmentation can substantially enhance ML-driven drone detection, providing a versatile and efficient tool for managing drone-related security risks. This research contributes to UAV detection technology, presenting a model that not only identifies but also categorizes drones, underscoring its potential for diverse operational environments.

Building energy demand impacts a myriad of interconnected economic, societal, and environmental aspects. As a result, Buildings Energy Models (BEM) play an important role in the process of urban design and planning. While previous studies have investigated the effects of building interventions on energy efficiency, their applicability may be limited due to the BEM’s high computational complexity. This limits their ability to systematically study important aspects of energy demand on a large scale. The development of Machine Learning Models (MLM) allows to design the required detailed analysis and solutions, while reducing the computational burden, making MLM attractive for urban designers. The capability of MLM to generalize well for multiple contexts (in our case, multiple buildings) is a crucial contributor to their applicability. However, the validation process in a wider context is often overlooked, therefore its generalization capabilities are not quantified. In this paper, we present a framework to train and validate a surrogate model derived from a physics-based BEM. Our method employs a Multiple Linear Regression model to predict Energy Use Intensity (EUI) for office buildings in Singapore using 36 input parameters (covariates), based on a training dataset of 23,000 samples. Model validation is performed by comparing the results of the Surrogate Model (SM) to a widely used BEM for a sample of 120 buildings. Our results indicate that the SM has an accuracy of NRMSE of 13%, NMBE of −3.56%, and R2 of 0.92, which suggests it can effectively and accurately predict building EUI. We also conduct a sensitivity analysis, which indicates that the parameters associated with internal loads and internal space usage are the most influential. Additionally, we present a reduced order model trained with only the 11 most influential parameters, which exhibits negligible loss in accuracy compared to the full SM while providing reduced complexity. Finally, we demonstrate an application of our SM to evaluate energy efficiency under uncertainty scenarios. The analytically derived results indicate a potential reduction of EUI of offices in Singapore from 227kWh/m2 to 99kWh/m2 by altering the building parameters that were identified as most influential.

Analyzing horse behavior is crucial for assessing training quality, particularly in accurately identifying actions like standing, walking, and running. Research has been conducted both domestically and internationally in this regard; however, challenges persist, including reliance on single sensors, poor real-time performance, and low identification accuracy. In view of these challenges, this study investigated real-time identification of horse behavior based on wearable devices. The system, centered around a microcontroller and utilizing a 4G network as a carrier, employs multi-axis IMU sensors as input sources to perceive horse posture. The study proposed a behavior classification method based on analysis of acceleration thresholds. The method consists primarily of two sequential stages: first, the resultant acceleration interval counting method, which employs a nonlinear segmentation approach for initial behavior classification; and second, the statistical analysis of variance parameters between segments, which when coupled with multi-level threshold processing, achieves a refined classification. Experimental results indicated that the interval counting method alone achieved an accuracy of 87.55%, while for the variance analysis method alone the accuracy was 90.87%. The proposed method, comprising the two stages, reached a classification accuracy of 91.57%, underpinning its usefulness in supporting future equine research.

The use of hyperthermia is one of the effective methods of treating cancer. In this case, the problem arises of constructing and predicting the distribution of the thermal field inside tissues depending on their type. This paper discusses the use of linear and polynomial regression methods, as well as regression algorithms based on decision tree, random forest and K nearest neighbors methods to recover missing temperature values. The influence of the size of the training sample when performing regression on the quality of the reconstructed values is investigated. Experimental recommendations on sample size are given for the selected decision tree and random forest methods. The possibility of a significant (10 times or more) reduction in the initial sample size, without leading to a decrease in the R² metric by more than 0.05 for various tissues, has been shown.

In the discussion on environmental policies, the notion of eco-efficiency is often used. Eco-efficiency is defined as the delivery of products and services with competitive values, while reducing the ecological impacts and satisfying human needs. In an environment of great competitiveness in which the companies operate, the improvements in the productive process is one of the differentiating factors for guaranteeing a strong competition. Also it is essential rationalizing energy consumption and natural resources. For this it is necessary to understand the main operations and dynamics of the company. This work presents an empirical study of a Portuguese company in the industrial sector. The problematic here presented is based on the company’s growing concern to reduce the amount of scrap produced. From the literature research that was performed, a strong dependence relation between the different variables in the extrusion process was found. The main objective of this work is to model the aluminium extrusion process, with the aim of minimizing the production of scrap. For this several variables involved in the process are taking into account. Using statistical techniques, in particular multiple linear regressions, it was possible to identify the importance of the variables under study for the scrap production.

In the evolving landscape of vibration analysis, the integration of machine learning technologies for semi-automated analytical processes presents challenges in establishing clear cause-and-effect relationships in decision-making formulas. This research addresses this gap by exploring analytical diagnosis through residual signals, enabling the identification of anomalies and underperformance in machinery. Vibration signature analysis, focusing on distinctive vibration patterns, proves instrumental in detecting bearing defects and optimizing maintenance for enhanced operational efficiency and safety. Mathematical modeling, particularly worst-case analysis, provides a structured framework for decision-making under uncertainty. The research employs descriptive methods to analyze bearing wear data, transforming it into quantitative data for multiple regression equations. The derived equations reveal the dominance of harmonics in determining bearing wear stages, with PeakVue and overall vibration further indicating damage progression. The findings emphasize the significance of harmonic detection and high-frequency vibration analysis in predicting bearing health, offering a comprehensive approach to enhance machinery reliability. The study concludes with practical recommendations for bearing damage diagnosis based on the developed mathematical models, providing valuable insights for predictive maintenance strategies.

Different severe energy crises episodes occurred in the world in the last five decades. Energy crises lead to deterioration of international relations, economic crises, changes in monetary systems and social problems in countries. This paper aims to show the essential determinants of energy crises by developing a binary logit model which estimates the predictive ability of thirteen indicators in a sample that covers the period from January 1973 to December 2022. The empirical results show that the energy crises are mainly due to energy supply-demand imbalances (petroleum stocks, fossil energy production-consumption imbalance and changes in energy imports by country groups), energy investments (oil and natural gas drilling activities), economic and financial disruptions (inflation, dollar index, index of global real economic activity) and geopolitical risks. Additionally, the model is capable of accurately predicting the world energy crisis event months with 99% probability.

In-depth insights into the profound impacts of climate change and human activities on water resources are garnered through the dynamic changes in surface water, a crucial aspect of effective water resource management and the preservation of aquatic ecosystems. This paper introduces an innovative approach employing the random forest algorithm for the systematic extraction and monitoring of surface water at large regional or national scales. This method integrates spectral bands, spectral indices, and digital elevation model data, offering a novel perspective on this critical task. A data filling model is proposed to mitigate the impact of missing data due to cloud cover. Leveraging the capabilities of the Google Earth Engine (GEE), detailed information on surface water dynamics during the rainy and dry seasons in the Yangtze River Basin (YRB) from 1991 to 2021 is extracted using Landsat time series imagery. The analysis encompasses spatial-temporal variation characteristics and trends, with a specific focus on the intricate interplay between the areal extent of surface water and hydro-meteorological factors in each sub-basin of the YRB. Importantly, this includes considerations of potential groundwater contributions to surface water. Key findings from our research include: (1) Achieving a remarkable overall accuracy of 0.96 ± 0.03 in obtaining reliable surface water datasets with the support of GEE. (2) Identifying significant trends, such as a noteworthy increase in rainy season surface water bodies (+248.0 km2·yr−1) and a concerning decrease in surface ice/snow cover during both rainy and dry seasons, with change rates of −39.7 km2·yr−1 and −651.3 km2·yr−1, respectively. (3) Uncovering the driving mechanisms behind these changes, revealing positive correlations between the areal extent of rainy season surface water bodies and precipitation, as well as negative correlations between surface ice/snow cover area and average surface skin temperature. It is crucial to note that these driving factors exhibit variation among secondary river systems, underscoring the complexity of surface water dynamics. Furthermore, comparative analyses with existing surface water products are conducted, contributing to a deeper understanding of the advantages and uncertainties inherent in our proposed extraction method. The proposed method for large-scale surface water extraction not only enhances the monitoring of spatio-temporal surface water dynamics in the YRB but also provides valuable insights for the sustainable utilization and protection of water resources, considering the potential role of groundwater in supplementing surface water.

When it comes to financial transactions and counterfeit detection systems, banknote classification is crucial. In this paper, we propose an approach for the classification of Kazakhstan banknote images integrating Learning Vector Quantization (LVQ) with Statistical Texture Feature Extraction using the Gray Level Co-occurrence matrix (GLCM). Our methodology demonstrates effectiveness in accurately classifying banknote images, as evidenced by experimental results. The comprehensive testing scenarios show promising outcomes, with the combination of GLCM and Color Histogram under the LVQ algorithm achieving a high accuracy of 94.87 percent at distance 1 and 90°. These findings indicate the robustness and practical viability of the proposed method for authenticating banknotes.

The electrical energy supply relies on the satisfactory operation of insulators. The ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty insulators. The random convolutional kernel transform (Rocket) algorithms use convolutional filters to extract various features from time series data. This paper proposes the combination of Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), empirical wavelet transform (EWT), and variational mode decomposition (VMD). The results show that the EMD methods combined with MiniRocket, significantly improve the accuracy of logistic regression in insulator fault diagnosis. The proposed strategy achieves respectively an accuracy of 0.992 using CEEMDAN, 0.995 with EWT, and 0.980 with VMD. These results highlight the potential of incorporating EMD methods in insulator failure detection models to enhance the safety and dependability of power systems.

Abdominal aortic aneurysm (AAA) is a chronic disease in which the abdominal aorta expands until it ruptures. AAA incidence: 10 million/year (India), deaths: 40%-90% (13th leading cause of death in the USA). Current treatment methods make diagnosis difficult due to the lack of noticeable symptoms and inaccurately planned operations. Rupture Scope is a mathematical model to dramatically reduce AAA deaths and improve treatment efficiency. Using a case-specific replica/simulation of real-time abdominal aortic blood flow for monitoring without frequent imaging scans and a novel derived mathematical linear regression model to predict rupture date and expansion rate with an overall accuracy of 95.64%.

Durum wheat is an important staple food used to obtain several products. At first the wheat is milled to obtain different products: bran, semolina and flour. These products are the base of several artifacts with varying properties both from a nutritional point of view and flavoring characteristics. It is known that most elements concentrate in the outer layers of the wheat seed (pericarp and aleurone) so that the content of the elements vary a lot in the ground products. The present study investigates the characterizing elements of the milled products and the effect of cultivation protocol applied. We measured, by ICP-OES, the concentration of 28 elements in the whole seed and in any grinding products; the results show that only few elements characterize each product. Few elements, but different for each product, permit to disclose the kind of agri-cultural method used: organic or conventional protocol. Five elements: B, Cd, Cu, K, Se, are the most important to distinguish between organic and conventional agriculture by PCA and PLS analysis; these elements also permit some differentiation of products.

Based on recent popular money priming research results, which conclude that money makes self-sufficient (e.g. less interest in other people), we assumed that people are less interested in finding out whether others are lying or telling the truth. In a laboratory experiment, 163 students (85 women, 78 men, M_Age = 23.08, ranging from 18 to 36 years) were primed by actively handling money (versus paper sheets). Afterwards, they classified 24 video statements as true or deceptive (senders describing their most/least favorite movie), rated their classification confidence for each decision and then answered control questions. Results revealed no influence of priming condition on judgmental bias, classification accuracy, and classification confidence. Also the level of self-reported motivation to find out who lied or told the truth did not differ between conditions. Higher motivation was correlated to higher classification confidence. Additionally, and in line with Reinhard (2010) and Reinhard et al. (2011), higher classification accuracy correlated to a higher use of verbal content cues for classification decisions. Thus, while we were able to replicate these findings, our results contradict the assumption of a money prime influence on lie detection ability. Concluding, our results make self-sufficiency in this context questionable and offer next steps for research.

To enhance the overall reliability of the power system, engineers have redirected their focus toward health monitoring and early detection of faults in transformers. Among these faults, transformer core defects demand particular attention. While fault simulation using software has traditionally been the preferred approach, these methods suffer from data inaccuracies in real-world conditions. Consequently, conducting actual experimental setups with induced faults is imperative to investigate core issues. This study uses Hilbert Transform (HT) as a signal processing technique to extract crucial data characteristics, thereby enhancing the performance of the classifier model. The research involves analyzing electric current signals from a single-phase 1kVA transformer. A comparative assessment of our proposed model was conducted using raw data and Fast Fourier Transform (FFT), evaluating accuracy, precision, recall, F1-score, and computational time. The results demonstrate a significant improvement in all metrics for the classifier models, particularly the k-nearest neighbor (KNN) algorithm, which exhibited values of 83.89%, 84.39%, 83.89%, 83.79%, and 0.0156 seconds, respectively. Future work aims to extend this analysis under different loading conditions.

Lightning is responsible for most annually burned area by wildfires in the extratropical region of the Northern Hemisphere. Hence, predicting the occurrence of wildfires requires reliable forecasting of the chance of cloud-to-ground lightning strikes during storms. Here, we describe the development and verification of a probabilistic lightning-strike algorithm designed to run on a uniform 20-km grid over the Continental USA and Alaska. The algorithm consists of a large set of logistic equations parameterized via logistic regression using long-term data records of observed lightning strikes and meteorological reanalysis fields from NOAA. Principal Component Analysis was employed to extract 13 Principal Components (strong predictors) from a list of 611 potential predictors. Our statistical analysis revealed that the occurrence of cloud-to-ground lightning strikes primarily depends on three factors: horizontal temperature distribution by pressure levels, amount of low-level atmospheric moisture, and wind vectors. These physical variables impact the vertical separation of electric charges in the lower troposphere during storms causing the voltage potential between ground and the cloud deck to increase to a level that triggers electrical discharges. Results from a forecast verification using independent data showed excellent model skill, thus making this algorithm suitable for inclusion into software systems forecasting the chance of wildfire ignitions.

Drones are being used more and more frequently and in various ways to attack people and critical infrastructures, which increases their level of danger and makes early detection and risk assessment even more difficult. There is no ultimate drone sensor. Rather, drones can only be effectively detected, if suitable sensor technologies are integrated within a system. Among the best suited sensorics for this purpose are radar and optical sensors, because the advantage of the radar, given by the long detection range, can be well combined with the additional visual-based information gained from a camera in the mid- and short-range, where usually the radar fails detecting micro drones. In this paper, a modular drone detection and assistance system MODEAS is presented, which can be used to automatically detect and track drones within a range up to some kilometers on the sky, but also in complex urban environments, where buildings and vegetation offer a perfect background for camouflage. The system provides an early detection of flying objects as potential drones, when those are not at all or only as small dots visible for the human eye. Main strengths of the system are the robust AI detection to differentiate such an object against clutter (birds, clouds) and its further classification by model and payload recognition, the latter aspect being considered as an indication of dangerousness. Moreover, once a drone is detected, the system follows it automatically, precisely and smoothly with a high-resolution pan-tilt-camera, measuring the distance to the sensor station with a laser rangefinder, compute the geocoordinates and visualize them live on a map. To improve the precision of the detection, a multisensorial fusion of all sensor detections is performed. Furthermore, alarms may be generated when a drone enters a restricted area.

In-wheel motor vehicles are gaining attention as a new type of electric vehicle due to their efficient power units located inside each wheel hub. However, they are more susceptible to wheel resonance due to the increase in unsprung mass caused by the motor's weight. This can result in decreased both the ride comfort and driving stability. To resolve this issue, this study aims to apply an optimal switching controller with a semi-active n actuator; magnetorheological (MR) damper. For the implementation of the optimal switching controller, a road type classification is also carried out. An acceleration sensor is used for road type classification, and control logics include a ride comfort controller; the linear quadratic regulator (LQR _Paved Road) and a wheel motion controller (LQR_Off Road) for improved driving stability. For paved roads, the LQR_Paved Road control input is applied to the MR damper. However, if a road type prone to wheel resonance is detected, the control logic switches to the LQR_Off Road. During the transition, a weighted average of both LQR_ Paved Road and LQR_Off Road control input is applied to the actuator. Computer simulations are undertaken to evaluate vibration control performance, including the ride comfort and driving stability at various road profiles.

Weeds are unwanted and invasive plants that proliferate and compete for resources such as space, water, nutrients, and sunlight, affecting the quality and productivity of the desired crops. Weed detection is crucial for the application of precision agriculture methods and for this purpose machine learning techniques can be used, specifically convolutional neural networks (CNN). This study focuses on the search for CNN architectures and technology used to detect and identify weeds in different crops; 61 articles applying CNN architectures and technology were analyzed in the last five years (2019-2023). The results show the used of different devices to acquire the image for training, such as digital cameras, smartphones, and drone cameras. Additionally, the YOLO family and algorithms are the most widely adopted architectures, followed by VGG, ResNet, Faster R-CNN, AlexNet, and MobileNet, respectively. This study provides an update on CNNs that will serve as a starting point for researchers wishing to implement these weed detection and identification techniques.

Ridge regression is one of the most popular shrinkage estimation methods for linear models. Ridge regression effectively estimates regression coefficients in the presence of high-dimensional regressors. Recently, a generalized ridge estimator was suggested by generalizing the uniform shrinkage of ridge regression to the non-uniform shrinkage, which was shown to perform well under sparse and high-dimensional linear models. In this paper, we introduce our newly developed R package “g.ridge” (the first version published on 2023-12-07 at https://cran.r-project.org/package=g.ridge) that implements both the ridge estimator and generalized ridge estimators. The package equips with the generalized cross-validation for automatic estimation of shrinkage parameters. The package also includes a convenient tool for generating a design matrix. By simulations, we test the performance of the R package under sparse and high-dimensional settings with the normal and skew-normal error distributions. From the simulation results, we conclude that the generalized ridge estimator is superior to the benchmark ridge estimator based on “glmnet”, and hence, it can be the most recommended estimator under sparse and high-dimensional models. We demonstrate the package using the intracerebral hemorrhage data.

This narrative review aims to provide a comprehensive overview of the scientific literature on wheelchair badminton and its distinctive aspects, encompassing abilities and disabilities, propulsion technique, and the use of a racket. The relatively young history of wheelchair badminton is reflected in the scarcity of scientific studies within this domain, highlighting the need for further investigation. The review systematically covers existing articles on wheelchair badminton, offering a nearly exhaustive compilation of knowledge in this area. Findings suggest that WH2 athletes engage in more intense matches with a higher frequency of offensive shots compared to WH1 athletes. Moreover, backward propulsion induces distinct physiological responses and alterations in propulsion kinematics, potentially leading to performance decrements. The use of a badminton racket further influences propulsion kinetics and kinematics, potentially impacting performance and injury risk. Further research is imperative to explore additional perspectives, address existing gaps, and expand the scope of study within the wheelchair badminton domain. This narrative review serves as a foundation for future investigations, emphasizing the necessity of continued research to enhance our understanding of wheelchair badminton.

In Nigeria, Cervical cancer (CC) and lack of Human Papillomavirus (HPV) awareness poses significant HPV infection risk among women. This study was conducted at Ibrahim Badamasi Babangida (IBB) University in Nigeria; focused on assessing HPV awareness and knowledge, particularly concerning its association with CC and oral contraceptive (OC) pills among students and staff. We adapted and validated a 20-item HPV knowledge scale and explored factors influencing knowledge, vaccination rates, awareness, and the impact of ethnicity on HPV knowledge. Also, due to the non-normality of the knowledge score, non-parametric tests were done. Data were summarized using median and interquartile range (IQR), while categorical data were presented in frequency and percentage distribution. We established the reliability of the 20-item knowledge scale with a strong Cronbach's alpha coefficient of 0.913, indicating internal consistency. However, it revealed a concerning lack of awareness and knowledge about HPV, only 34.8% of participants were aware of HPV infection, and only 25.0% knew about HPV vaccine. Additionally, ethnicity was identified as a significant factor affecting HPV knowledge. Considering these findings, this study emphasizes the need for targeted interventions to enhance HPV awareness and knowledge, particularly among specific ethnic groups. Despite the development and validation of a reliable knowledge scale, the study underscores the importance of educational initiatives to address this knowledge gap, ultimately reducing the risk of HPV infection and CC in Nigeria.

Evolutionary Machine Learning (EML) has demonstrated its effectiveness in modeling various real-world application domains, including the dynamics of diseases and the creation of predictive models across diverse fields. However, the challenge of data imbalance adversely impacts the performance of EML models. While strategies involving misclassification costs or cost-sensitive learning exist to address this issue, their integration into EML has yet to be thoroughly explored. This paper aims to fill this gap by investigating the application of cost-sensitive EML for intelligent health risk prediction. More specifically, this paper delves into the utilization of cost-sensitive genetic programming (CSGP) and cost-sensitive genetic algorithms (CSGA), which are among the most widely used algorithms in the EML category. The study entails training CSGP and CSGA to predict the early onset of three chronic conditions (hypertension, diabetes, and fatty acid-related disorders) through the development of an EML model. Subsequently, the model's performance is evaluated through standard fitness functions such as sensitivity, specificity, and F1-score. From the experimental results, EML models demonstrate promising results in identifying the occurrence of chronic diseases. Further optimization of the cost-sensitive EML model holds the potential for enhanced outcomes in modeling medical problems.

This paper investigates the relationship between public debt and economic growth in the context of a panel kink regression with latent group structures. The proposed model allows us to explore the heterogeneous threshold effects of public debt on economic growth based on unknown group patterns. We propose a least squares estimator and demonstrate the consistency of estimating group structures. The finite sample performance of the proposed estimator is evaluated by simulations. Our findings reveal that the nonlinear relationship between public debt and economic growth is characterized by a heterogeneous threshold level, which varies among different groups, and highlight that the mixed results found in previous studies may stem from the assumption of a homogeneous threshold effect.

Digital agricultural technology extension service and sustainable food production have attracted attention from academia. However, the association between digital agricultural technology extension service and sustainable food production has not yet been fully investigated. This research investigates the average and heterogeneous impacts of digital agricultural technology extension service use on eco-efficiency among 1302 maize producing farmers from Northeast China major maize producing area in 2022 to fill this knowledge gap. The slack-based measure model with undesirable outputs is applied to calculate the eco-efficiency of maize production. To obtain an unbiased estimation of the average effect, the self-selection problem generated by observable and unobservable factors is solved by the endogenous switching regression model. Quantile regression is utilized to analyze the heterogeneous effect. Notably, the mediated effects model is utilized to examine the potential mechanism between them. Our findings indicate that digital agricultural technology extension service use can increase maize production's eco-efficiency. Digital agricultural technology extension service users would reduce eco-efficiency by 0.148 (21.11%) if they had not used the digital agricultural technology extension service. Digital agricultural technology extension service nonusers would improve eco-efficiency by 0.214 (35.20%) if they had used it. The robustness check reconfirms the results. Moreover, digital agricultural technology extension service use is more helpful to maize farmers who have lower eco-efficiency than those who have higher eco-efficiency. Digital agricultural technology extension service use can improve eco-efficiency of maize production through the application of organic fertilizers, green pesticides and biodegradable agricultural films.

Vehicular traffic in urban areas continues to be a constant challenge today, due to the continuous population growth and the increase of vehicles in circulation. Vehicular congestion, as a recurrent problem, generates a negative impact on urban mobility and citizens’ quality of life. It is hypothesized that a dynamic clustering method of vehicle trajectory data can provide an accurate and up-to-date representation of real-time traffic behavior. To evaluate this hypothesis, data were collected from three different cities: San Francisco, Rome and Guayaquil. A dynamic clustering algorithm was applied to identify traffic congestion patterns and an indicator was applied to identify and evaluate the congestion conditions of the areas. The results show a high precision and recall in congestion classification compared to a method based on static cells.

Having in view the sustainable management of forests, the intensity of silvotechnical interventions is analyzed and documented for young mixed beech stands regenerated naturally by taking into account the allometric relationships between some representative dendrometric elements, respectively, between the height of the trees and the corresponding diameter of their crowns. For this purpose, a functional dependence is established between the height and diameter of the tree crown from young beech stands within which silvotechnical interventions were or were not applied. A mathematical model based on cubic spline regression was developed, also taking into account the determination of the average diameter of the crown for each stand. This average diameter can be used to determine the optimal number of trees per surface unit (ha) at a given time. The research was carried out in three young beech stands, through statistical-mathematical inventories, on sample plots of 300 square meters with a tolerance of 10% and a coverage probability of 90%. The optimal diameter of the crown was obtained by applying the spline regression model, and the most appropriate functional dependence was established, resulting in a linear regression law with a positive slope.

Leveraging the open-world understanding capacity of large-scale visual-language pre-trained models has become a hot-spot in point cloud classification. Recent approaches rely on transferable visual-language pre-trained models, classifying point clouds by projecting them into 2D images and evaluating consistency with textual prompts. These methods benefit from the robust open-world understanding capabilities of visual-language pre-trained models and require no additional training. However, they face several challenges summarized as prompt ambiguity, image domain gap, view weights confusion, and feature deviation. In response to these challenges, we propose PointBLIP, a zero-training point cloud classification network based on the recently introduced BLIP-2 visual-language model. PointBLIP is adept at processing similarities between multi-images and multi-prompts. We separately introduce a novel method for point cloud zero-shot and few-shot classification, which involves comparing multiple features to achieve effective classification. Simultaneously, we enhance the input data quality for both the image and text sides of PointBLIP. In point cloud zero-shot classification tasks, we outperform state-of-the-art methods on three benchmark datasets. For few-shot classification tasks, to the best of our knowledge, we present the first zero-training few-shot point cloud method, surpassing previous works under the same conditions and showcasing comparable performance to full-training methods.

Research on spatio-temporal geostatistical modelling remains a critical challenge in numerous scientific and engineering disciplines. This work introduces a novel extension of the dual kriging the spatio-temporal dual kriging (ST-DK) whose drift functions with fixed and adaptive coefficients are established. The approach appears to be effective in modelling complex spatio-temporal dynamics, particularly when relevant auxiliary variables exert substantial influence on the target variable. To illustrate its performance, we compare the ST-DK model with the classical spatio-temporal regression kriging (ST-RK) method for estimating temperature and air pressure data across Thailand in 2018. Our findings demonstrate that both ST-DK and ST-RK models, when utilizing adaptive coefficients, outperform their constant coefficient counterparts. Furthermore, the ST-DK method consistently exhibits superior performance compared to the ST-RK model.

Existing reinforced concrete buildings with seismically-deficient column details affect the overall behavior depending on the failure type of column. The purpose of this study is to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used considering previously-collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with the simple column details. Additionally, it was demonstrated that the predicted failure modes from the selected model were exactly same as the failure mode determined from a code-defined equation (traditional method)

In recent years, there has been a growing interest in the prediction of facial age due to its diverse applications in fields such as security, entertainment, and healthcare. The current scourge of underaged voting in Nigeria is a problem and this research delves into the realm of facial age prediction by employing four well-known convolutional neural network (CNN) architectures, namely VGG16, ResNet50, Mobile Net, and VGG19 to predict chronological ages from facial pictures of person. The objective is to achieve precise age estimation from facial images, utilizing two datasets: UTKFace and CASIA African Facial Datasets. The results of this investigation are noteworthy. Specifically, the VGG16 model which demonstrated remarkable performance, yielding a Mean Absolute Error (MAE) of 1.76 when applied to the UTK-Face dataset. Additionally, when utilizing Mobile-Net, an unprecedented MAE of 1.10 was achieved for the Casia Africa Face Dataset. Notably, this marks the first instance of employing the dataset for facial age detection with CNNs, and this approach outperformed previous works, yielding the lowest MAE among all the studies reviewed.

Multispectral and 3D LiDAR remote sensing data sources are valuable tools for characterizing the 3D vegetation structure and thus understanding the relationship between forest structure, biodiversity and microclimate. This study focuses on mapping riparian forest species in the canopy strata using a fusion of Airborne LiDAR data and multispectral multi-sources and multi-resolution satellite imagery; Sentinel-2 and Pleiades at tree level. The idea is to assess the contribution of each data source in the tree species classification at the considered level. The data fusion was processed at feature-level and decision level. At feature level, LiDAR 2D attributes were derived and combined with vegetation indices. At decision level, LiDAR data was used for 3D tree crown delimitation providing unique trees or groups of trees that are used as a support for the species classification. Data augmentation techniques were used to improve the training process. Best results were obtained by the fusion of Sentinel-2 time series and LiDAR data with a Kappa of 0.66 thanks to red-edge based indices that better discriminate vegetation species and the temporal resolution of Sentinel-2 images that allows monitoring the phenological stages helping to discriminate the species.

This study advances the field of solar irradiance nowcasting by introducing a discrete-level classification approach, diverging from traditional continuous measurement methods. Grounded in a need for cost-effective and modular solutions, the research employs high-resolution computer vision coupled with a deep learning framework to predict Direct Normal Irradiance (DNI). By harnessing the capabilities of a Logitech C900 1080p HD camera and an NVIDIA Jetson module, the study achieves real-time data processing, pivotal for CSP systems' operational efficiency. The core of the methodology is the ResNet-50 convolutional neural network, refined via transfer learning on a bespoke dataset, culminating in a predictive accuracy of 85.78%. This discrete classification model contrasts with conventional, costly instruments like the MS-57, offering a novel and accessible alternative for DNI estimation. Such innovation not only demonstrates high predictive accuracy but also signifies a shift towards less resource-intensive and more adaptable solar energy forecasting tools, contributing a significant leap towards optimizing renewable energy systems.

There is a growing concern about climate change being a serious threat to insurance business sustainability. Knowing if climate warming is a cause for claims and losses increase, and how this cause-effect relationship will develop in the future are two open major questions. In this article, we answer both questions by particularizing the geographical area of Spain, and a precise risk, hailstorm in crop insurance in the line of business of wine grapes. We measure climate change thanks to the Spanish Actuarial Climate Index (SACI). We use a database containing all the claims caused by hail risk in Spain from 1990 to 2022. With homogenized data, we consider as dependent variables the monthly number of claims, monthly number of loss costs equal to one, and monthly total losses. The independent variable is the monthly Spanish Actuarial Climate Index (SACI). We try to explain the former through the latter using regression and quantile regression models. Our main finding is that climate change as measured by SACI explains these three dependent variables. We also give an estimation of the increase of the monthly total losses Value at Risk, corresponding to a future increase in climate change measured in units of SACI. Spanish crop insurance managers should carefully incorporate these conclusions into their decision-making process to keep this line of business sustainable in the future.

This study assesses the applicability of different-resolution multispectral remote sensing images for mapping and estimating the aboveground biomass (AGB) of Carpobrotus edulis, a prominent invasive species in European coastal areas. The performance of three sets of multispectral images with different resolutions was compared: (i) 2.5 cm Ground Sample Distance (GSD), 5 cm GSD and 10 cm GSD images. The images were classified using the supervised classification algorithm Random Forest and later improved applying a sieve filter. The results show that the three tested image resolutions allow constructing reliable coverage maps of C. edulis, with Overall Accuracy values of 89%, 85% and 88% for the classification of the 2.5 cm, 5 cm and 10 cm GSD images, respectively. Samples were also collected, dried and weighed to estimate AGB using the relationship between the Dry Weight and Vegetation Indices (VI). The regressions were evaluated based on their R² and Normalised RMSE. The best-performing VI-DW regression models achieved: R² = 0.87 and NRMSE = 0.09 for the 2.5 cm resolution; R² = 0.77 and NRMSE = 0.12 for the 5 cm resolution; and, R² = 0.64 and NRMSE = 0.15 for the 10 cm resolution. C. edulis area and total AGB were: 3441.10 m² and 28,327.1 kg (with a Relative Error (RE) = 0.08), for the 2.5 cm resolution; 3070.04 m² and 29,170.8 kg (RE = 0.08), for the 5 cm resolution; and, 2305.06 m² and 22,135.7 kg (RE = 0.11), for the 10 cm resolution. Differences were analysed in detail, spatially, to determine their causes. Final analyses suggest that, for C. edulis, multispectral imagery of up to 5 cm GSD is adequate for the estimation of the species’ distribution and biomass.

In this paper, we propose a method for assessing the effectiveness of entropy features using several chaotic mappings. We anlyze fuzzy entropy (FuzzyEn) and neural network entropy (NNetEn) on four discrete mappings: the logistic map, the sine map, the Planck map, and the two-memristor-based map, with a base length time series of 300 elements. FuzzyEn is shown to have improved global efficiency (GEFMCC) in the classification task compared to NNetEn. At the same time, there are local areas of the time series dynamics in which the classification efficiency NNetEn is higher than FuzzyEn. The results of using horizontal visibility graphs (HVG) instead of the raw time series are also shown. GEFMCC decreases after HVG time series transformation, but there are local areas of the time series dynamics in which the classification efficiency increases after including the HVG. The scientific community can use the results to explore the efficiency of entropy-based classification of time series.

The presence of escaped fish in aquaculture facilities as a result of harsh meteorological conditions (more pressing in a face of climate change) requires a better understanding of these dynamical behaviour through vigilant monitoring and validated numerical models. In this context, data from strain, stress sensors as well as meteorological and current sensors installed at an aquaculture farm in the Region of Murcia (Spain) were collected, processed and analysed. Among them, first results about the relationship between load and currents sensors are presented. Due to the complexity of the time series, various analyses were conducted to examine their interrelation, encompassing regression analysis of raw data and data segmented into different time intervals. Through this analysis, it was observed that employing distinct time windows better elucidated the data variability. Furthermore, an optimal data window of 240 data was identified, demonstrating significantly improved explanatory power, with the coefficient of determination (R2) increasing by approximately 0.8 depending on the section. This pave the way for optimizing the monitoring features that must be carried out to relate cause-and-effect variables in the behaviour of these off-shore infrastructures.

This paper proposes a new method for network screening on rural low-volume roads. These roads are important as they provide critical access to agricultural land and tourist attractions. Most low-volume roads belong to the lowest functional class (local rural roads) and thus are built to lower design standards. The conventional hot spot network screening techniques may not be appropriate for low-volume roads due to the sporadic nature of crashes occurring on these roads. Contrarily sophisticated network screening approaches require extensive roadway and traffic data that are often unavailable to local agencies for lack of resources, and/or lack of technical expertise. This research attempts to address these obstacles in low-volume roads network screening which aims to identify candidate sites for safety improvements. The research used an extensive low-volume road sample from the state of Oregon and the Empirical Bayes expected number of crashes in developing the proposed models for network screening. The proposed models do not require exact measurement of roadway geometric features as all geometric variables were classified into categories that are easy to compile by local agencies. Further, the method could be used with and without traffic data, without compromising the effectiveness of the network screening process.

Background: In America, vaccine-related deaths constitute a significant contributor to child mortality. An essential means of reducing this is through broad vaccine coverage. The COVID-19 pandemic has posed a potential disruption to vaccine coverage due to its effects on the healthcare system. Objectives: This study aims to evaluate the impact of the COVID-19 pandemic on DTP3 vaccination coverage in the Americas, investigating trends from 2012 to 2022 to identify significant changes, regional disparities, and the overall effect of the pandemic on progress towards global immunization targets. Methods: This study used the coverage data for the third dose of the Diphtheria, Tetanus, and Pertussis Vaccine (DTP3) pulled from UNICEF databases spanning 2012 to 2022. We conducted a JoinPoint regression to identify points of significant trend changes. The annual percentage change (APC) and 95% confidence intervals (95% CI) were calculated for America and its regions. We also used segmented regression analysis. Using the Chi-square test, we compared DTP3 vaccination coverage for each country between 2019 and 2022. Results: Overall, America saw a decrease in vaccine coverage during this period, with an APC of -1.4 (95% CI -1.8.; -1.0). This trend varied across regions. In North America, the decrease was negligible (-0.1% APC). South America showed the steepest decrease, with an APC of -2.5%. Central America also signif-icantly declined, with an APC of -1.3%. Our findings suggest a concerning trend of declining DTP vaccination rates in the Americas, exacerbated in certain regions, in the wake of the COVID-19 pandemic. The absolute decrease in vaccine coverage in the Americas was -4 % between 2019 and 2022, with the most significant drop observed in Central America (-7 %). However, six countries reported increased vaccination rates post-COVID-19, led by Brazil, with a 7% increase. Conversely, twenty-two countries registered a decline in DTP3 vaccine coverage, with the average decrease being -7.37%. This decline poses a significant challenge to achieving the WHO's target of 90% coverage for the third dose of DTP by 2030, as evidenced by the reduction in the number of countries meeting this target from 2019 to 2022. Conclusions: The COVID-19 pandemic has impacted vaccine coverage in America, leading to a decrease, especially across Central America.

Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.

The automated transcription of handwritten characters into a legible output is a multi-faceted process with diverse applications. In this paper, a novel approach to optical character recognition (OCR) for handwritten digits is proposed that, in certain components, exceeds current architectures in terms of accuracy, effectiveness, adjustability, temporal efficiency, and/or computational simplicity. This model succeeds in the adoption and enhancement of deprecated or obsolete algorithms across eight steps of image pre-processing—normalization, grayscaling, thresholding/binarization, noise removal, skew-correction, skeletonization/thinning, line separation, and character segmentation. The aforementioned model is evaluated with the use of a Convolutional Neural Network (CNN) leveraging the Balanced eMNIST dataset for training and testing. By suggesting contour-based feature extraction methods as alternatives to pixel-by-pixel iteration, the proposed paradigm demonstrates its capacity to serve as a suitable alternative to current, commonly used algorithms and computational techniques for textual image classification.

This study explores the application of the Fully Convolutional Network (FCN) algorithm to the field of meteorology, specifically for the short-term nowcasting of severe convective weather events such as hail, convective wind gust (CG) and thunderstorms, short-term heavy rain(STHR) in Gansu. Training data comes from the European Center for Medium-Range Weather Forecasts (ECMWF) and real-time ground observations, the performance of the proposed FCN model based on 2017 to 2021 training datasets demonstrate a high prediction accuracy, with an overall error rate of 16.6%. Furthermore, the model exhibited an error rate of 18.6% across both severe and non-severe weather conditions when testing against the 2022 dataset. Operational deployment in 2023 has yielded an average Critical Success Index (CSI) of 24.3%, a Probability of Detection (POD) of 62.6%, and a False Alarm Ratio (FAR) of 71.2% for these convective events. It is noteworthy that the predicting performance for STHR was particularly effective with the highest POD and CSI, as well as the lowest FAR. CG and hail predictions had comparable CSI and FAR scores, although the POD for CG surpassed that for hail. The FCN model’s optimal performance for hail prediction occurred at the 4th, 8th, and 10th forecast hours, while for CG, the 6th hour was most accurate, and for STHR, the 2nd and 4th hours were most effective. These findings underscore the FCN model's ideal suitability for short-term forecasting of severe convective weather, presenting extensive prospects for the automation of meteorological operations in the future.

The purpose of this study is to analyze the causes of cost variation in natural disaster prevention projects (NDPP) in Gyeongsangbuk-do and to develop effective cost and risk management strategies. The study collected data by conducting an online survey of 244 stakeholders. Binary logistic regression was used to analyze the impact of various variables on cost deviation, in-cluding project management risk (PMR), project costing and execution risk (PCER), project exe-cution strategy risk (PESR), construction project risk (CPR), project cost and schedule risk (PCSR), project management challenges (PMC), and construction project subcontractor and safety man-agement (CPSSM). The results showed that PMR (OR=3.744, 95% C.I. [1.657, 8.457]), PCER (OR=5.068, 95% C.I. [2.236, 11.484]), PESR (OR=3.447, 95% C.I. [1. 853, 6.413]), CPR (OR=2.292, 95% C.I. [1.020, 5.151]), PCSR (OR=4.817, 95% C.I. [2.250, 10.317]), PMC (OR=2.954, 95% C.I. [1.452, 6. 013]), and CPSSM (OR=2.419, 95% C.I. [1.297, 4.515]) had statistically significant effects on cost deviation. In particular, PMR, PCER, and PESR were identified as the main causes, and the effects of additional factors such as CPSSM were also important. The developed predictive model plays an important role in helping stakeholders of NDPP to manage risks in advance and take appro-priate preventive measures to ensure the success of the project. This study empirically supports the theoretical hypotheses of previous studies and provides a clear understanding of the causes of cost deviation in NDPP, which provides important insights for strategic decision-making and provides a new perspective on risk management.

The increasing importance of batteries in the 21st century and the challenges posed by the anticipated growth in end-of-life batteries, particularly in Europe, are addressed. Projections indicate a significant increase in battery waste, with a specific focus on the recycling of black mass (BM)—a complex and hazardous byproduct of the battery recycling process. The research employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to systematically analyze the hazardousness of BM derived from various types of batteries. The findings reveal the inherently hazardous nature of BM, classifying it under multiple hazardous properties (HPs) according to European regulations. The urgent need for a definitive legislative classification of the hazardousness of BM is emphasized, and the potential of innovative technologies and strategies to improve recycling performance while mitigating risks is highlighted. The research significantly contributes to understanding the complexities of BM recycling, providing a foundation for future advancements in this area and emphasizing the need for further exploration and economic feasibility analysis of recycling technologies.

This article explores the crucial task of estimating State of Charge (SOC) in Hybrid Electric Vehicles (HEVs) and examines the applicability of various regression models for this purpose. We delve into the strengths and limitations of Linear Regression, Support Vector Regression (SVR), and Neural Network Regression (NNR) in the context of SOC estimation. Linear regression provides a simple and interpretable baseline, SVR extends this to nonlinear relationships, while NNR emerges as a powerful tool with adaptive capabilities. The choice of model depends on factors such as data characteristics, interpretability, and computational resources. As the field evolves, the article advocates for a nuanced approach, possibly incorporating hybrid models, to achieve robust and accurate SOC estimation, contributing to the ongoing enhancement of HEV efficiency and sustainability.

The paper aims to develop and test an algorithm for classifying Russian-language text reviews of patients’ experiences with medical facilities and physicians, extracted from social media. This is motivated by the limitations of conventional methods of surveying consumers to assess their satisfaction with the quality of services, which are being replaced by automatic processing of text data from social media. This approach enables to get more objective results due to the increased representativeness and independence of the sample of service consumers. The authors have tested machine learning methods using various neural network architectures. A hybrid method was developed to classify text reviews of medical facilities posted by patients on the two most popular physician review websites in Russia. Overall, more than 60,000 reviews were analysed. The main results are as follows: 1) the classification algorithm developed by the authors has a high efficiency, the best result being achieved by the GRU-based architecture (val_accuracy = 0.9271); 2) applying the named entity search method to text messages following their partitioning improved the classification efficiency for each of the classifiers based on artificial neural networks. To further enhance the classification quality, reviews need to be semantically partitioned by target and sentiment and the resulting fragments need to be analysed separately.

Neurodegenerative illnesses, such as Parkinson’s disease (PD), have a substantial impact on the overall well-being of those who are affected. This study investigates and contrasts the capabilities of convolutional neural networks (CNN) in detecting Parkinson’s disease (PD) by utilising hand-drawn images alongside wave and spiral images as input data. This study employs pre-trained CNN models, specifically MobileNet, ResNet50, EfficientNet-B1, and InceptionV3, to classify Parkinson’s disease (PD). The findings demonstrate that MobileNet surpasses other architectural designs, as evidenced by the F1-Score of the four classes: Spiral Normal (0.87), Spiral Parkinson (0.86), Wave Normal (0.97), and Wave Parkinson (0.97). MobileNet has also shown a remarkable accuracy of 0.92 in diagnosing Parkinson’s disease. The result demonstrates the efficacy of MobileNet in extracting features from images. The results of this study enhance the application of deep learning methods in the early detection of PD, as well as help indicate the effectiveness of patient therapy and exercise, promising better patient outcomes through timely intervention and treatment.

We investigated how Artificial Intelligence (AI) reveals factors shaping COVID-19 vaccine hesitancy among healthcare providers by examining their open-text comments. We conducted a longitudinal survey starting in spring of 2020 with 38,788 current and former female nurses in three national cohorts to assess how the pandemic has affected their livelihood. In January and March-April 2021 surveys, participants were invited to contribute open-text comments and answer specific questions about COVID-19 vaccine uptake. A closed-ended question in the survey identified vaccine-hesitant (VH) participants who either had no intention or were unsure of receiving a COVID-19 vaccine. We collected 1,970 comments from VH participants and trained two Machine Learning (ML) algorithms to identify behavioral factors related to VH. The first predictive model classified each comment into one of three Health Belief Model (HBM) constructs (barriers, severity, and susceptibility) related to adopting disease prevention activities. The second predictive model used the words in January comments to predict the vaccine status of VH in March-April 2021; vaccine status was correctly predicted 89% of the time. Our results showed that 35% of VH participants cited barriers, 17% severity, and 7% susceptibility to receiving a COVID-19 vaccine. Out of the HBM constructs, the VH participants citing a barrier, such as allergic reactions and side effects, had the most associated change in vaccine status from VH to later receiving a vaccine.

A non-destructive analysis of proximate parameters (moisture content, MC; volatile matter, VM; fixed carbon, FC; and ash content) for a variety of chipped and ground biomasses was investigated through a combination of thermogravimetric analysis (TGA) and near-infrared spectroscopy (NIRS) with partial least squares regression (PLSR). In this study, the thermogravimetric method was employed as a tool to determine the proximate analysis data of biomass samples through TG and DTG curves, which were generated by tracking changes in biomass mass loss over time or temperature. NIRS non−destructively scanned the chipped biomass in diffuse reflectance while ground biomass using transflectance mode, covering the wavenumber range of 3594.87 to 12,489.48 cm−1. The PLSR−based models: Full−PLSR, genetic algorithm (GA)−PLSR, successive projection algorithm (SPA)−PLSR, the spectral multi−preprocessing (MP) PLSR− 5 range method, and the MP PLSR−3 range method were developed. Model performance was assessed, compared, and selected based on the coefficient of determination in the prediction set (R2P), root mean square error in the validation set (RMSEP), and the ratio of prediction to deviation (RPD). Based on the comprehensive analysis of model performance, MC and FC models of chip biomass have demonstrated satisfactory performance which makes it applicable cautiously in any application, including research. The optimum models for MC and FC in chip biomass were constructed using GA−PLSR with 2nd derivative and Full−PLSR with a constant offset, resulting in R2P values of 0.8654 and 0.8773, RMSEP values of 0.85% and 2.12%, and RPD values of 2.9 and 3.0, respectively. Other parameters such as MC and FC in ground biomass as well as VM and ash content in both chip and ground biomass were found suitable for rough screening. The sensitivity of the selected model was assessed by calculating the limit of quantification (LOQ), and the results indicated that the calculated LOQ values for VM in both chip and ground biomass and FC in chip biomass are lower than the minimum reference values used during model development, signifying a high level of sensitivity. However, for the remaining parameters, the LOQ values surpass the established minimum reference value, suggesting the model could not predict the future samples with reference value lower than the calibration range. Nevertheless, enhancing the models by incorporation an ample number of representative biomass samples and consistently validating the models with unknown samples is imperative to ensure accurate predictions.

The classification and summarization of online reviews using machine learning and deep learningbased approaches are the subject of this systematic literature review. Consumers, companies, and researchers can now find vital information from online reviews. Automatically categorizing and summarizing these reviews can offer useful information and facilitate decision-making. The purpose of this study is to offer a thorough overview of the current methodology, approaches, and developments in this area. The review concentrates on machine learning-based methods for categorization and summarizing tasks, highlighting their advantages, drawbacks, and new developments. This systematic review provides insights into the most recent methodologies and indicates prospective directions for further investigation by synthesizing the data from a wide range of pertinent research publications

Hypertension stands as the foremost modifiable risk factor for cardiovascular disorders in South Asia. This research demonstrates the superiority of statistical models over traditional approaches in identifying clinical risks related to hypertension. Leveraging individual-level data from the Bangladesh Demographic and Health Survey (2017-18), a unified dataset was created. Adhering to JNC7 and ACC/AHA guidelines for hypertension classification, two prominent regression models were employed to estimate the prevalence of undiagnosed hypertension. A substantial 16% of hypertension cases in Bangladesh remain undetected. The study identifies undiagnosed hypertension as a heightened risk, particularly among the youth and residents of Sylhet and Rangpur divisions. Statistical models exhibit efficacy in discerning undiagnosed hypertension and associated factors in South Asia. Subsequent investigations should incorporate biological markers to enhance statistical models and ascertain their practicality.

Atrial Fibrillation (AF) is known as one of the dominant cardiac disease that is associated with severe consequences such as risk of strokes. This cardiac arrhythmia can be efficiently diagnosed using EEG signals. However, AF episodes in EEG records are not always permanent for all subjects. In addition, lengthy subject preparation and ECG recording sessions makes this practice time consuming and not attractive for efficient diagnosis. One attractive solution for this problem will be the use of wearable Internet of Medical Things IoMT devices for EEG recording and AF detection. From another side the use machine learning for efficient diagnosis could provide high accurate diagnosis. However, the deployment of these wireless wearable devices faces the problems of limited processing capabilities and of energy scarcity. In this context, the design of energy efficient accurate on-sensor AF detection scheme using machine learning algorithms still requires a focused research effort. This paper proposes a wearable solution for ECG-based processing scheme for embedded AF detection. The proposed method achieved 100% sensitivity and 94.5% of specificity and accuracy of around 97.4 % for wide range of subjects while showing low energy-consumption. The obtained results show the efficiency of using Logistic Regression algorithm for accurate AF detection and attest about practical feasibility of the proposed approach in wearable IoMT devices.

The research presented in this paper examines a new proposed approach for identifying safety improvement sites on rural highways. Unlike conventional approaches, the proposed approach does not require crash history, but rather utilizes classified variables for traffic volume, geometric features, and roadside characteristics that do not require access to exact data or extensive technical expertise. The research validates the performance of the proposed approach using field data from a large sample of rural two-lane highway segments in the state of Oregon including traffic, roadway, and crash data. Using observed crash history as a reference, the performance of the proposed ap-proach was compared to two of the well-established methods in practice, namely: the Empirical Bayes (EB) and the Potential for Safety Improvement (PSI) methods. The study results suggest that, using crash density for highway segments, the performance of the proposed method was lower than that of the EB and PSI methods. This is despite the high R-square value of the predictive model used in the proposed method. However, when using crash frequencies for highway segments, the per-formance of the proposed method was found comparable to the well-established EB and PSI methods.

The paradigm of leveraging code as a dataset has recently gained traction, offering innovative solutions in domains such as automated commit message generation, pull request description automation, and program repair mechanisms. Consider the challenge in generating commit messages: traditional methods treat source code as a mere token sequence, applying neural machine translation models. This approach, however, overlooks the critical syntactic structures inherent in programming languages, which could offer deeper insights and improved accuracy. Building upon prior research, specifically the Code2Seq framework, which utilized Abstract Syntax Tree (AST) structural data for source code representation to automate method name generation, this paper extends and refines this concept. We introduce "CSR", a novel methodology adapted to represent code edits effectively. This paper investigates the impact of employing syntactic structure, focusing on the classification of code edits. Drawing inspiration from Code2Seq, "CSR" utilizes AST's structural properties, particularly the paths connecting leaf nodes, to enhance the task of code edit classification. This approach is rigorously evaluated on two distinct datasets, comprising fine-grained syntactic edits. Our comprehensive experiments reveal that incorporating syntactic structures does not significantly outperform simpler methodologies. While methods like Code2Seq and our proposed "CSR" show potential, our findings highlight that there is considerable scope for improvement and refinement before such techniques can be universally applied for learning representations of code edits. We anticipate that our findings will spark further research in this field, paving the way for more effective use of syntactic structures in code representation.

AbstractIntroduction: Increasing knowledge of obstetric danger signs (ODS) and encouraging birth preparedness and complication readiness (BPCR) practices are strategies to increase skilled maternal health service utilization in low-income countries. One of the methods to increase mothers' knowledge about ODS and promote BPCR practice is through health education intervention (HEI). However, the effect of context-specific community-based health education led by women's groups on these outcomes has not been comprehensively studied, and the existing evidence is inconclusive. Thus, we aimed to evaluate the effect of a context-specific community-based HEI led by women's groups on mothers' knowledge regarding ODS and BPCR practices in southern Ethiopia.Methods: An open-label, two-arm parallel group cluster-randomized controlled trial was conducted from January to August 2023 on pregnant women from 24 clusters (kebeles) (12 interventions and 12 controls) in the northern zone of the Sidama region. The Open Data Kit smartphone application was utilized to collect data. The intention-to-treat analysis was used to compare outcomes between groups. We fitted multi-level mixed-effects modified Poisson regression with robust standard error to account for between and within cluster effects. Results: One thousand and seventy pregnant women (540 in the intervention and 530 in the control clusters) responded to this study, making the overall response rate 95.02%. Excessive vaginal bleeding (94.3% in the interventional group vs. 88.7% in the control group) was the commonest ODS mentioned during childbirth. Overall, 68.7% of women in the intervention group and 36.2% of mothers in the control group had good knowledge of ODS (P-value < 0.001). Saving money and materials (97.1% in the interventional group vs. 92.7% in the control group) was the most frequently practiced BPCR plan. Overall, 64.3% of women in the intervention group and 38.9% of mothers in the control group practiced BPCR (P-value < 0.001). HEI significantly increased overall knowledge of ODS (adjusted risk ratio [ARR]: 1.71; 99% CI: 1.14-2.57) and improved overall BPCR practice (ARR: 1.55; 99% CI: 1.02-2.39). Conclusions: A community-based HEI led by women's groups improved mothers' knowledge regarding ODS and BPCR practices in a rural setting in southern Ethiopia. Interventions designed to increase women's knowledge of ODS and improve BPCR practice must implement context-specific, community-based HEI that aligns with World Health Organization recommendations. Trial registration: NCT05865873

Accurate agricultural commodity price models enable efficient allocation of limited natural resources, leading to improved sustainability in agriculture. Because of climate change, price volatility and uncertainty for the sector are expected to increase in the future, increasing the need for improved price modeling. With the emergence of machine learning (ML) algorithms, novel tools are now available to enhance the modeling of agricultural commodity prices. This research uses both univariate and multivariate ML techniques to perform probabilistic price prediction modelling for the Canadian beef industry, taking into account beef production, commodity market, and international trade features to enhance accuracy. We apply multivariate algorithms by using support vector regression (SVR), random forest (RF), and adaboost (AB) and univariate algorithms by using autoregressive integrated moving average (ARIMA), seasonal ARIMA (SARIMA), and the seasonal autoregressive integrated moving average with exogenous factors (SARIMAX). We apply these models to monthly fed steer price data between January 2005 and September 2023 and compare predicted prices with observed prices using several validation metrics. The outcomes indicate that both random forest (RF) and adaboost (AB) in multivariate modeling show superior performance in accurately predicting Alberta fed steer prices in comparison to other algorithms. To better account for the variance of the best model performance, we subsequently adopted a probabilistic approach by considering uncertainty in our best-selected ML model. The beef industry can use these improved price models to minimize resource waste and inefficiency in the sector and improve the long-term sustainability prospects for beef producers in Canada.

To support pathologists in breast tumor diagnosis, deep learning plays a crucial role in the development of histological whole slide image (WSI) classification methods. However, automatic classification is challenging due to the high-resolution data and the scarcity of representative training data. To tackle these limitations, we propose a deep learning-based breast tumor gigapixel histological image multi-classifier integrated with a high-resolution data augmentation model to process the entire slide by exploring its local and global information and generating its different synthetic versions. The key idea is to perform classification and augmentation in feature latent space, reducing the computational cost while preserving the class label of the input. We adopt a deep learning-based multi-classification method and evaluate the contribution given by a Conditional Generative Adversarial Network-based data augmentation model on the classifier’s performance for three tumor classes in the BRIGHT Challenge dataset. The proposed method has allowed us to achieve an average F1 equal to 69.5, considering only the WSI dataset of the Challenge. The results are comparable to those obtained by the Challenge winning method (71.6), also trained on the annotated tumor region dataset of the Challenge.

Sleep disorder is a disease that can be categorized as both an emotional and physical problem. It imposes several difficulties and problems, such as distress during the day, sleep-wake disorders, anxiety, and several other problems. Hence, the main objective of this research is to utilize the strong capabilities of machine learning in the prediction of sleep disorders. In specific, this research aims to meet three main objectives. These objectives are to identify the best regression model, the best classification model, and the best learning strategy that highly suits sleep disorder datasets. Considering two related datasets and several evaluation metrics that are related to the tasks of regression and classification, the results revealed the superiority of the MultilayerPerceptron, SMOreg, and KStar regression models compared with the other twenty-three regression models. Also, IBK, RandomForest, and RandomizableFilteredClassifier showed superior performance compared with other classification models that belong to several learning strategies. Finally, the Function learning strategy showed the best predictive performance among the six considered strategies in both datasets and with respect to the most evaluation metrics.

In recent years, Synthetic Aperture Radar (SAR) has received attention in the Automatic Target Recognition (ATR) field due to its ability to acquire images both day and night, combined with the superior resolution offered by the latest sensors. However, despite advances, there remains a deficiency in dataset quality and quantity. This has necessitated the use of simulated data to overcome challenges associated with obtaining large quantities of high-quality images of targets and their subsequent labeling. In this study, we trained a Convolutional Neural Network (CNN) using a simulated dataset, subsequently employing it to classify real images from the MSTAR dataset. Traditional training methodologies often struggle with generalization when confronted with domain disparities between simulated and real data. To mitigate this, we exploited Margin Disparity Discrepancy (MDD), a domain adaptation technique not previously explored in SAR context. Findings from this study showcased a 13% increase in classification accuracy and improved generalization using MDD. Through Explainable AI (XAI) techniques such as t-SNE and other metrics like Kullback Leibler Divergence (KLD), we revealed a more distinct alignment of feature spaces between the two domains after domain adaptation, emphasizing MDD’s role in enhancing model accuracy and generalization.

Few-shot fine-grained image classification (FSFGIC) methods refer to machine learning methods which aim to classify images (e.g., bird species, flowers, and airplanes) belonging to subordinate object categories of the same entry-level category with only a few samples. It is worth to note that feature representation learning is used not only to represent training samples, but also to construct classifiers for performing various FSFGIC tasks. In this paper, starting from the definition of FSFGIC, a taxonomy of feature representation learning for FSFGIC is proposed. According to this taxonomy, we discuss key issues on FSFGIC (including data augmentation, local or/and global deep feature representation learning, class representation learning, and task specific feature representation learning). The existing popular datasets and evaluation standards are introduced. Furthermore, a novel classification performance evaluation mechanism is designed with a 0.95 confidence interval for judging whether the classification accuracy obtained by a certain specified method is good or bad. Moreover, current challenges and future trends of feature representation learning on FSFGIC are elaborated.

This work develops a new method for vector data augmentation. The proposed method applies the Principal Component Analysis (PCA) and determines the Eigenvectors of a set of training vectors for a Machine Learning (ML) method and uses them to generate the distilled vectors. The training and the PCA distilled vectors have the same dimension. The user chooses the number of vectors to be distilled and augmented to the set of training vectors. A statistical approach determines the lowest number of vectors to be distilled such that when augmented to the original vectors the extended set trains a ML classifier to achieve a required accuracy. Hence, the novelty of this study is, the distillation of vectors with the PCA method and their use to augment the original set of vectors. The advantage that comes from the novelty is that it increases the statistics of ML classifiers. To validate the advantage, we conducted experiments with four public databases and applied four classifiers: Neural Network, Logistic Regression, Support Vector Machine with linear and polynomial kernels. For the purpose of augmentation, we conduct several distillations including nested (double distillation). The latter notion means that new vectors were distilled from already distilled vectors. We train the classifiers with three sets of vectors: original vectors; original augmented with vectors distilled by PCA; original augmented with distilled and double distilled, by PCA, vectors. The experimental results are presented in the paper, and they confirm the advantage that the PCA distilled vectors increase the classification statistics of ML methods, if the distilled vectors augment the original training vectors.

The field of program classification, a critical aspect of software engineering, facilitates understanding and categorization of code across various applications, including anomaly detection, and code quality assessment. The advancement of cross-language program classification opens up avenues for efficient code translation among different programming languages, significantly aiding developers in rapid coding and reducing development cycles. Existing research primarily focuses on semantic code analysis, with limited emphasis on cross-linguistic challenges. To address this, we introduce an innovative neural network model, CodeSemanticsNN, which leverages a refined Syntax Structure (SS) approach. This model consists of two integral mechanisms: first, it adopts a novel SS representation that combines sequential and graph-based SS structures, enhancing semantic feature capture. Second, it employs a 'unified vocabulary' strategy to bridge the gap between diverse programming languages, facilitating efficient cross-language classification. Additionally, we have compiled a comprehensive dataset of 20,000 files spanning five programming languages, serving as a benchmark for cross-language classification. Our experiments on this dataset demonstrate that CodeSemanticsNN surpasses existing models in four key metrics: Precision, Recall, F1-score, and Accuracy.

During geomagnetic storms, which are a result of solar wind interaction with the Earth’s magnetosphere, geomagnetically induced currents (GICs) begin to flow in the long-distance high-voltage power grids on the Earth’s surface. It causes a number of negative phenomena that affect the normal operation of the entire electric power system. To investigate the nature of the phenomenon and its possible effects on transformers, a GIC monitoring system was created in 2011, the devices of which were installed at five substations of the Kola-Karelian power transit in northwestern Russia. Over 12 years of operating the system a large amount of data has been accumulated, which cannot be analyzed manually within a reasonable amount of time. To analyze the constantly growing volume of recorded data effectively, a method for automatic classification of GIC in autotransformer neutral was proposed. The method is based on a continuous wavelet transform of the neutral current data combined with a convolutional neural network (CNN) to classify the obtained scalogram images. As the result of comparing four CNNs with different architectures, a model that showed excellent GIC classification performance on the validation set (100.00% accuracy and loss of 0.0115) was chosen.

Audio classification using deep learning models, essential for applications like voice assistants and music analysis, faces challenges when deployed on edge devices due to their limited computational resources and memory. Achieving a balance between performance, efficiency, and accuracy is a significant obstacle in optimizing these models for such constrained environments. In this investigation, we evaluate diverse deep learning architectures, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for audio classification tasks on the ESC 50, UrbanSound8k, and Audio Set datasets. Our empirical findings indicate that Mel Spectrograms outperform raw audio data, attributing this enhancement to their synergistic alignment with advanced image classification algorithms and their congruence with human auditory perception. To address the constraints of model size, we apply model compression techniques, notably magnitude pruning, Taylor Pruning, and 8-bit quantization. The research demonstrates that a hybrid pruned model achieves a commendable accuracy rate of 89 percent, which, although marginally lower than the 92 percent accuracy of the uncompressed CNN, strikingly illustrates an equilibrium between efficiency and performance. Subsequently, we deploy the optimized model on Raspberry Pi 4 and NVIDIA Jetson Nano platforms for audio classification tasks. These findings highlight the significant potential of model compression strategies in enabling effective deep learning applications on resource-limited devices, with minimal compromise on accuracy.

Hyperspectral (HS) imaging plays a pivotal role in various fields, including medical diagnostics, where precise human vein detection is crucial. Hyperspectral image data are very large and can cause computational complexities. Dimensionality reduction techniques are often employed to streamline HS image data processing. This paper investigates the effectiveness of three dimensionality reduction techniques, namely: Principal Component Analysis (PCA), Folded PCA (FPCA), and Ward’s Linkage Strategy using Mutual Information (WaLuMI) for vein detection using HS images. A HS image dataset, encompassing left and right-hand images captured from 100 subjects with varying skin tones was created and annotated using anatomical data to represent vein and non-vein areas within the images. To generate experimental results, the HS image dataset was divided into train and test datasets. Optimum performing parameters for each of the dimensionality reduction techniques in conjunction with The Support Vector Machine binary classification were determined using the Training dataset. The performance of the three dimensionality reduction based vein detection methods was then assessed and compared using the test image dataset. Results show that the FPCA-based method outperforms the other two methods in terms of accuracy. For visualization purposes, the classification prediction image for each technique is post-processed using morphological operators, and results show the significant potential of HS imaging in vein detection.

OSI model used to be common network model for years. In the case of ad hoc networks with dynamic topology and difficult radio communications conditions, gradual departure is happening from the classical kind of OSI network model with a clear delineation of layers (physical, channel, network, transport, application) to the cross-layer approach. The layers of the network model in ad hoc networks strongly influence each other. Thus, the cross-layer approach can improve the performance of an ad hoc network by jointly developing protocols using interaction and collaborative optimisation of multiple layers. The existing cross-layer methods classification is too complicated, because it’s based on the whole manifold of network model layers combinations, regardless their importance. In this work, we review ad hoc networks cross-layer methods, propose the new useful classification of cross-layer methods, and show future research directions in ad hoc networks cross-layer methods development. The proposed classification can help to simplify the goal-oriented cross-layer protocol development.

This paper considers the direction of arrival (DOA) estimation problem of phase ambiguity for unfolded coprime linear array (UCLA). The existing most common stacking subarray-based method can tackle the phase ambiguity problem. However, the method is not always true. For a given DOA, it has its corresponding steering vector, but if there are two DOAs which have the same steering vectors with the given DOA for different subarrays, the phase ambiguity problem still arises. A modified method, which defines a decision variable and uses the classic beamforming technique to estimate the DOAs is proposed. However, this method needs additional algorithm to distinguish the true DOAs besides multiple signal classification (MUSIC) spectrum. And sometimes this method is not reliable if the decision variable is not chosen appropriately. Therefore, based on the UCLA, we reconstruct the array to design an improved UCLA called IUCLA. With moving the reference element, the linear relationship among the directional vectors can be broken. In this way, we can directly utilize the MUSIC algorithm to estimate with no additional algorithm. The proposed method can solve the phase ambiguity problem and it does not demand other technique to decrease the complexity. Moreover, the Cramer-Rao Bound (CRB), as the lower bound of the unbiased estimation, is provided and numerical simulations are given to demonstrate the effectiveness and superiority of the proposed method.

The aim of this paper is to study a semi-functional partial linear regression model (SFPLR) for spatial data with responses missing at random. The estimators are constructed by the kernel method, and some asymptotic properties such as probability convergence rates of the nonparametric component and asymptotic distribution of the parametric and nonparametric components are established under certain conditions. Next, the performances and the superiority of these estimators are presented and examined using a study on simulated data and on real data by carrying out a comparison between our semi-functional partially linear model with MAR estimator (SFPLRM), the semi-functional partially linear model with the full-case estimator (SFPLRC) and the nonparametric functional model estimator with MAR (FNPM). The results show that the proposed estimators outperform existing estimators as the number of random missing data increases.

Antimicrobial peptides (AMPs) are essential components of the innate immune system, present across a spectrum of organisms. Their versatility lies in their ability to effectively inhibit a wide range of pathogens including bacteria, fungi, parasites, and viruses. As the challenge of antibiotic resistance escalates and concerns surrounding antibiotic use grow, AMPs have emerged as promising alternatives. Their applications span diverse domains such as medicine, agriculture, food production, animal husbandry, and aquaculture, primarily due to their efficacy against resistant pathogens, signifying their crucial role in combating infections. Beyond their antimicrobial properties, research illuminates their intricate involvement in the immune response network. These peptides impact crucial processes including cytokine release, chemotaxis, wound healing, angiogenesis and the activation of the adaptive immune system. This comprehensive review delves into the multifaceted realm of AMPs, encompassing their classification, varied applications across industries and notably, their significance in diverse disease conditions like infections, skin diseases, cancer, oral diseases, lung diseases and cardiovascular ailments. Special attention is directed towards current advancements in clinical applications of peptide-based therapeutics, offering invaluable insights into their potential future integration within clinical settings.

We performed arthroscopically assisted coracoclavicular (CC) stabilization using a suture button device for modified Neer type IIb lateral clavicle fractures accompanied by CC ligament injury. The purpose of the present study was to evaluate the radiological and clinical outcomes of this procedure. Six consecutive patients with modified Neer type IIb fractures were treated with the technique and followed for 12 months. Postoperative ranges of motion (ROMs) and X-rays were evaluated every 3 months. Shoulder functional scores (University of California Los Angeles score, Japanese Orthopedics Association score), visual analog scale (VAS) scores for pain at rest, at night, and during motion, and VAS score for satisfaction were analyzed at 12 months after surgery. For the clinical outcomes, early ROM recovery and excellent outcomes were achieved. For the radiological outcomes, all patients accomplished bone union, slight superior displacement was noted in the CC distance and Dog Bone distance, and bone hole dilation was observed in the superior coracoid and inferior clavicle, but there were no critical complications. The present findings indicate that arthroscopically assisted CC stabilization with a suture button device for unstable lateral clavicle fractures can produce satisfactory radiological and clinical results.

How crucial is big data in contemporary molecular design? In this publication we elucidate fundamental concepts and terminology in this field, critically addressing overlooked issues. We thoroughly examine the size, accessibility, quality, and structural aspects of big data alongside the primary methodologies employed for their analysis. Within chemical compounds, properties and descriptors represent two distinct data types, forming the basis for categorizing molecular big data. The primary objective of chemistry is property production, which means we are searching for novel drugs or materials rather than chemical compounds, and big data is the central issue of this philosophy. The increasing availability of data in computer-aided technology propels advancements in artificial intelligence (AI), machine learning (ML), and deep learning (DL). Accordingly, a broad chemical audience must comprehend these methods to understand data-centered chemistry. Thus, we aim to systemize big data issues through a simple illustrative framework with fundamental descriptor categories: coding, computer-generated descriptors, and property correlates. Although we employ computer-generated descriptors as big data for predictions, the measured data are irreplaceable for achieving high-quality and reliable outcomes and controlling molecular effects. The scarcity of property data remains a significant hurdle limiting comprehensive studies on the structure-property relationships within big data. Accordingly, guided by pragmatics not-so-big data is an option for drug design. We presented also a brief review of the recent big data literature.

The ultimate analysis parameters including carbon (C), hydrogen (H), nitrogen (N), and oxygen (O) content in biomass was rarely found to be predicted by nondestructive tests until to date. In this research, we developed partial least squares regression (PLSR) models to predict the ultimate analysis parameters of chip biomass using near infrared (NIR) raw spectra of non-wood and wood samples from fast growing tree and agricultural residue and nine different traditional spectral preprocessing techniques. These techniques include first derivative (sd1), second derivative (sd2), constant offset, standard normal variate (SNV), multiplicative scatter correction (MSC), vector normalization, min-max normalization, mean centering, sd1 + vector normalization, and sd1 + MSC. Additionally, we employed a genetic algorithm (GA), successive projection algorithm (SPA), multi-preprocessing (MP) 5−range, and MP 3−range to develop a PLSR model for rapid prediction. A dataset consisting of 120 chip biomass samples was utilized for model development in which the samples was non-wood samples of 65-67% and wood samples was 33-35%, and the model performance were evaluated and compared. The selection of the optimum performing model was mainly based on criteria such as the coefficient of determination in the prediction set (R2P), root mean square error of the prediction set (RMSEP), and the ratio of prediction to deviation values (RPD). The optimal model for weight percentage (wt.%) of C was obtained using GA−PLSR, yielding R2P, RMSEP, and RPD values of 0.6954, 1.1252 wt.%, and 1.8, respectively. Similarly, for wt.% of O, the most effective model was obtained using the multi-preprocessing PLSR−5 range method with R2P of 0.7150, RMSEP of 1.3088 wt.%, and RPD of 1.9. For wt.% of N, the optimal model was obtained using the MP PLSR−3 range method, resulting in R2P, RMSEP, and RPD values of 0.6073, 0.1008 wt.%, and 1.6, respectively. However, wt.% of H model provided R2P, RMSEP, and RPD values of 0.5162, 0.2322 wt.%, and 1.5, respectively. Notably, the limit of quantification (LOQ) values for C, H, and O were lower than the minimum reference values used during model development, indicating a high level of sensitivity. However, the LOQ for N, exceeded the minimum reference value, implying the samples to be predicted by the model must be in the range of reference range in calibration set. By scatter plot analysis, the effect of combined non-wood and wood spectra of biomass chips on rapid prediction of ultimate analysis parameters using NIR spectroscopy was investigated. To include different species in a model, the species have to be not only in the different values of the constituents to make a wider range for robust model but also they must provide their trend line characteristics in the scatter plot i.e. correlation coefficient (R), slope and intercept (same slope and slope approached to 1 and intercept is same (no gap) and approached zero, high R approached to 1). The effect of the R, slope and intercept to obtain the better optimized model were studied. The results show that the different species affected model performance of each parameter prediction in a different manner and by scatter plot analysis which of these species were affecting the model negatively and how the model could be improved was indicated. This is the first time of the effect is studied by the principle of scatter plot.

The soils of the high-altitude mountains along the East African Rift Valley are poorly understood. Understanding the potential of soils for agriculture, climate change mitigation, and environmental functioning necessitates an understanding of their relationship to soil-forming factors. Therefore, this study focuses on the volcanic soils of Mount Guna. Eighty-five soil profiles, between 3000 and 4120 m a.s.l., were described and sampled along seven topographic transects. The samples were analyzed for physicochemical characteristics using standard methods and classified according to WRB 2022. The clay mineralogy of six profiles was analyzed with X-ray diffraction. The first four-factor axes, which are related to elevation, parent material, climate, and land use were found by factor analysis, explaining more than 60% of the total variation. The clay portions are primarily composed of trioctahedral chlorite, trioctahedral mica (phlogopite or biotite), vermiculite, kaolinite, some quartz, some amorphous silicates (most likely pyroclastic glass), and minor feldspar. The presence of weatherable minerals (biotite, amphibole, feldspars, and so on) suggests that these soils have not been weathered extensively. The dominant Reference Soil Groups found in the study area are Andosols, Phaeozems, Leptosols, Regosols, Cambisols, Luvisols, and Vertisols. As a result, our findings suggest that altitudinal variation, climate, lithology, and their contributions to the variability of soil characteristics and development along the toposequence cannot be separated in this study; more similar studies in other high-elevation/altitude mountains are required. There have been no other studies of high-altitude mountains in East Africa where so many soil profiles have been examined.

This research presents a novel Customised Load Adaptive Framework (CLAF) for fault classifica-tion in Induction Motors (IMs), utilizing the Machinery Fault Prevention Technology (MFPT) Bearing Dataset. CLAF represents a pioneering approach that extends traditional fault classification methodologies by accounting for load variations and dataset customization. Through a meticulous two-phase process, it unveils load-dependent fault subclasses that have not been readily identified in traditional approaches. Additionally, new classes are created to accommodate the dataset's unique characteristics. Phase 1 involves the exploration of load-dependent patterns in time and frequency domain features using one-way Analysis of Variance (ANOVA) ranking and validation via bagged tree classifiers. In Phase 2, CLAF is applied to identify mild, moderate, and severe load-dependent fault subclasses through optimal Continuous Wavelet Transform (CWT) selection through Wavelet Singular Entropy (WSE) and CWT energy analysis. The results are compelling, with a 96.3% classification accuracy achieved when employing a wide neural network to classify proposed load-dependent fault subclasses. This underscores the practical value of CLAF in en-hancing fault diagnosis in IMs and its future potential in advancing IM condition monitoring.

This study investigates the suitability of the timestamp approach algorithm for predicting blood pressure (BP) using wearable and comfortable devices, showcasing its accuracy even with low-frequency sampled signals. Developed within the SINTEC European project, the algorithm utilizes Electrocardiogram (ECG) and Photoplethysmogram (PPG) sensors, demonstrating promising results in both laboratory and hospital settings. The research emphasizes the algorithm’s potential to transform continuous and non-invasive BP monitoring through wearable technology, offering frequent measurements with minimal discomfort. While the study shows promise, further exploration is needed, focusing on optimizing machine learning coefficients for long-term monitoring applications and addressing potential changes over time. Technological improvements, including the implementation of edge computing algorithms, hold the key to enhancing BP accuracy, denoising techniques, and integrating alarm systems for future wearable solutions. This study emphasizes the adaptability of the algorithm for diverse healthcare environments, paving the way for broader applications in convenient and reliable BP monitoring.

The aim of this research was to undertake laboratory testing to investigate the beneficial effects of epoxy resin grouts on the physical and mechanical properties of sands with a wide range of granulometric characteristics. Six sands, of different particle size and uniformity coefficients, were grouted using epoxy resin solutions with three ratios of epoxy resin to water (3.0, 2.0 and 1.5). A set of unconfined compressive strength tests were conducted on grouted samples at different curing periods and a set of long-term unconfined compressive creep tests in dry and wet conditions after 180 days of curing were also carried out, in order to evaluate the development of the mechanical properties of the sands, as well as, the impact of water on them. The findings of the investigation showed that epoxy resin resulted in appreciable strength values in the specimens, especially those of fine sands, grouted with the different epoxy resin grouts. In general, the compressive strength varied between 0.68 - 5.60 MPa and the modulus of elasticity between 75 - 480 MPa, after a curing period of 180 days. In terms of physical properties, the permeability and porosity (before and after the grouting process) were estimated. Grouts with an epoxy resin to water ratio of 3 decreased permeability by up to four orders of magnitude. Using laboratory results and regression analysis, three mathematical equations were developed that relate each of the dependent variables; compressive strength, elastic modulus, and coefficient of permeability, with particular explanatory variables.

Machine learning approaches are currently used to understand or model complex physical systems. In general, a substantial number of samples must be collected to create a model with reliable results. However, collecting numerous data is often relatively time-consuming or expensive. Moreover, the problems of industrial interest tend to be more and more complex and depending on a high number of parameters. High dimensional problems intrinsically involve the need of large data amount through the curse of dimensionality. That is why, new approaches based on smart sampling techniques are investigated to minimize the number of samples to be given to train the model, such as Active Learning methods. Here, we propose a technique based on a combination of Fisher information matrix and of Sparse Proper Generalized Decomposition that enables the definition of a new Active Learning informativeness criterion in high dimensions. We provide examples proving the performances of this technique on a theoretical 5D polynomial function and on an industrial crash simulation application. The results prove that the proposed strategy over-perform the usual ones.

Use of fingerprints found at a crime scene is a common practice for identifying suspects in criminal investigations. Over the past two decades, attempts have been made to obtain additional information from fingerprints, beyond locating suspects as part of an investigation. This includes gender, age and nationality. Researchers demonstrated 75%-90% accuracy in gender classification based on fingerprint images. Nonetheless, despite promising results, these studies have several significant shortcomings with respect to their practical feasibility. First, they ignore the low quality and quantity of fingerprints collected from the crime scene since typically the scene of a crime has only one fingerprint collected, and the fingerprint might be partially or of poor quality as well. Second, as most results are based on a single database, public or private, it is difficult to generalize the most suitable method. Third, studies miss the untapped potential of Data-Centric AI (DCAI) approaches for improving results. The aim of this study was to compare, for the first time, the gender classification from a fingerprint using several datasets and with varying fingerprint image quality. The results from four databases are compared, three public and one internal private database. In addition, we utilize the latest Data-Centric AI (DCAI) approaches for improving classification results. The results demonstrate that a conservative Convolutional Neural Networks (CNN) such as VGG is sufficient for this task. Classification accuracy ranges from 80% to 95% depending on the quality of the fingerprint, with DCAI approaches adding 1%-4% improvement. For partially or low-quality fingerprint images, the periphery of a fingerprint is the most significant area for determining gender. The source code is also provided here for practical application.

Our daily activities hinge on the flexibility of our fingers, and a fractured finger can significantly disrupt these routines. The finger bones enable us to bend and fold the fingers and thumb to pick up or grasp objects and do all of our daily activities. A broken finger can cause adverse effects on our daily life activities. It is important to treat broken finger as soon as possible. Swift and precise treatment begins with capturing multiple X-rays, followed by the critical step of fracture detection in these images. Relying on the naked eye for this task carries the risk of overlooking small fractures. To address this issue an automated diagnoses of fractured fingers from images is required for which the current research employs advanced deep learning models—ResNet34, ResNet50, ResNet101, ResNet152, VGG-16, and VGG-19—to classify finger images from the Musculoskeletal Radiographs (MURA) dataset as either fractured or non-fractured. The results emphasize the consistently strong performance of ResNet models, attaining an impressive accuracy of 81.9%. This surpasses VGG models by 3.4% and establishes ResNet as the new benchmark for state-of-the-art accuracy.

Chinese calligraphy, revered globally for its therapeutic and mindfulness benefits, encompasses styles such as Regular (Kai Shu), Running (Xing Shu), Official (Li Shu), and Cursive (Cao Shu) scripts. Beginners often start with Regular script, advancing to more intricate styles like Cursive. Each style, marked by unique historical calligraphers' contributions, requires learners to discern distinct nuances. The integration of AI in calligraphy analysis, collection, recognition, and classification are pivotal. This study introduces an innovative Convolutional Neural Network (CNN) architecture, pioneering the application of CNN in the classification of Chinese calligraphy. Focusing on the four principal calligraphers' styles from the Tang dynasty (690-907 A.D), this research spotlights the era when the traditional regular script font (Kai Shu) was refined. A comprehensive dataset of 8282 samples from these calligraphers, representing the zenith of regular style, was compiled for CNN training and testing. The model distinguishes personal styles for classification, showing superior performance over existing networks. Achieving 89.5-96.2% accuracy in calligraphy classification, our approach underscores the significance of CNN in both font and artistic style categorization. This research paves the way for advanced studies in Chinese calligraphy and its cultural implications.

Empirical equations representing, interpolating and smoothing groups of measurement results by regression methods are in widespread use in metrology and other fields of science and engineering. Standard equations for the propagation of measurement uncertainties to values computed from such equations are available but suffer from a lack of general acceptance and are only infrequently applied in practice. One reason for the slow uptake is the lack of clear methods to account for systematic error. In this paper, uncertainty propagation equations in terms of covariance matrices are generalized to allow for systematic errors in least-squares regression, and effects of the resulting uncertainties are investigated analytically. A stochastic ensemble model of systematic error is proposed for the computation of the non-diagonal elements of the weight matrix of the Generalized Least-Squares method (GLS) from the measurement uncertainty. A GLS projector formalism is described which separates the effects of measurement scatter on values calculated by the equation from those on the related “residuals”, i.e., the residual errors in the fitted data. The same projectors act similarly on the associated uncertainties and covariance matrices and permit the effects of systematic errors on the simulation covariance to be quantified. It is demonstrated that, in order to include systematic errors in the uncertainty estimates of GLS, covariance matrices may be substituted by novel, specifically defined dispersion matrices that are not specified yet by the GUM[1]. Systematic measurement errors may be estimated from various sources; a particularly easy way suggested here involves analyzing the structure in the regression residuals. It is demonstrated that GLS projectors exhibit inherent features of “error blindness” also with respect to systematic errors. [1] GUM: Guide to the Expression of Uncertainty in Measurement, http://www.bipm.org/en/publications/guides

In recent years, there has been significant growth in the ubiquity and popularity of three dimensional(3D) point clouds, with an increasing focus on the classification of 3D point clouds. To extract richer features from point clouds, many researchers have turned their attention to various point set regions and channels within irregular point clouds. However, this approach has limited capability in attending to crucial regions of interest in 3D point clouds and may overlook valuable information from neighboring features during feature aggregation. Therefore, this paper proposes a novel 3D point cloud classification method based on global attention and adaptive graph convolution. The method consists of two main branches: the first branch com-putes attention masks for each point, while the second branch employs adaptive graph convolu-tion to extract global features from the point set. It dynamically learns features based on point interactions, generating adaptive kernels to effectively and precisely capture diverse relationships among points from different semantic parts. Experimental results demonstrate that the proposed model achieves 93.8% in overall accuracy and 90.8% in average accuracy on the ModeNet40 dataset.

Crop digital twin is redefining traditional farming practices, offering unprecedented opportunities for real-time monitoring, predictive and simulation analysis, and optimization. This research embarks on an exploration of the synergy between precision agriculture, crop modeling, and regression algorithms to create a digital twin for augmenting farmers the concentration and composition prediction-based crop nutrient recovery. This captures the holistic representation of crop characteristics, considering the intricate relationships between environmental factors, nutrient concentrations, and crop compositions. However, the complexity arising from diverse soil and environmental conditions makes nutrient content analysis expensive and time-consuming. This paper presents the result of a predictive digital twin case study that employs six regression algorithms namely Elastic Net, Polynomial, Stepwise, Ridge, Lasso, and Linear Regression to predict rice nutrient content efficiently, particularly considering the coexistence and composition of multiple nutrients. Our research findings highlight the superiority of the Polynomial Regression model in predicting nutrient content, with a specific focus on accurate nitrogen percentage prediction. This insight can be used for nutrient recovery intervention by knowing the precise amount of nutrient to be added into the crop medium. The adoption of the Polynomial Regression model offers a valuable tool for nutrient management practices in the crop digital twin, potentially resulting in higher-quality rice production and a reduced environmental impact. The proposed method can be replicable in other low-resourced crop digital twin system.

In recent years, ozone (O3) pollution has been rapidly spreading, restricting further improvement of air quality in China. Investigating the interaction of O3 concentration and identifying their driven cities are important for the prevention and control of O3 pollution in China. However, the complex interaction between O3 pollution between the cities and their driven cities has not yet been revealed. In this study, we address this gap based on complex network methods. Specifically, an ozone relational network is constructed using an association calculation method. The driven nodes and spatial clusters were analyzed based on the maximum matching algorithm and the Louvain algorithm. The findings of the study reveal an aggregation phenomenon in the ozone network concerning distance. Furthermore, as the threshold Tc varies, the proportion of driven nodes exhibits a positive correlation. Moreover, a closer threshold value corresponds to a higher coincidence ratio of the driven nodes. The results provide scientific guidance for national O3 pollution prevention and regional synergy formatting. Furthermore, the introduced network-based approaches offer a mythological framework for the study of air pollution in key cities and clusters.

Gelephu, located in the Himalayan region, has experienced one of the strongest development activities due to the suitable topography and geographic location, which has led to rapid urbanization. The main objective of the study is to perform land use land cover (LULC) mapping for Gelephu for 2016 and 2023 by a Random Forest (RF) classifier, using the Semi-automatic Classification Plugin (SCP) in QGIS and identify LULC changes. Furthermore, the study assessed the vegetation change dynamics within the study area by analysing the Normalized Difference Vegetation Index (NDVI) for 2016 and 2023. Additionally, the study characterized the resulting LULC change for Gelephu Thromde, a sub-administrative municipal entity, as a result of the notable intensity of the infrastructure development activities. The current study used a framework to collect Sentiniel-2 satellite data, which was then used for pre- and post-processing to create LULC and NDVI maps. The classification model achieved high accuracy, with an area under the curve (AUC) of up to 0.89. The corresponding LULC and NDVI statistics were analysed to determine the current status of the LULC and vegetation indices, respectively. The LULC change analysis reveals urban growth of 5.65% and 15.05% for Gelephu and Gelephu Thromde, respectively. The NDVI assessment shows significant deterioration in vegetation health with a 75.11% loss of healthy vegetation in Gelephu between 2016 and 2023. This research provides the first version of LULC and NDVI maps of Gelephu. The analysis results indicate possible future implications on sustainable development management in Gelephu Bhutan.

Micro and small wood-processing enterprises represent the heart of the European forest-based industries, being among the key drivers of economic growth in rural, mountainous, and poor regions. Their economic efficiency is of fundamental importance for their existence and the pro-vision of income for the local population in rural areas. Data Envelopment Analysis (DEA) is nonparametric, linear-programming-based approach, commonly used to analyse the efficiency of organizational units. This method allows estimating the economic efficiency of a certain eco-nomic system without assumptions about the functional form between resources and products. Furthermore, DEA determines the efficiency frontier and gives results of whether an enterprise, i.e., a Decision Making Unit (DMU) is efficient or not. The main objective of this study was to investigate and evaluate the economic efficiency of micro and small wood-processing enterpris-es in the EU countries and reveal the hidden inputs that facilitate efficiency generation. The eco-nomic efficiency evaluation was carried out on the basis of the official statistical data for the mi-cro and small wood-processing companies in the EU member states for the period 2015-2020 by performing a two-stage DEA analysis. The data used were standardized by value per employee. In addition to the first stage of DEA, fractional regression probit and logit models with four contextual variables were used to reveal the influence of the hidden inputs in the model. The results showed that the micro and small wood-processing enterprises can be regarded as more scale-efficient than technically-efficient entities. The only contextual variable affecting the eco-nomic efficiency was Investments per Person Employed, improving the efficiency by 2% per 1% increase of the investments.

Memristive spiking neural networks are a promising emerging technology in the field of deep learning. These models can be implemented using neuromorphic hardware and therefore offer low power consumption and low latency, crucial to edge-computing applications. These systems, however, pose several challenges, including on-chip training and connectivity reduction. The latter is essential to ease the manufacturing complexity of the system. On-chip training can be realized using synaptic plasticity enabled by memristors. In this work, we compare two methods of connectivity reduction applicable to memristive spiking networks: an ensemble-based approach and a probabilistic sparse connectivity approach. We evaluate both of these methods in conjunction with a three-layer spiking neural network on the handwritten and spoken digits classification tasks using two memristive plasticity models and a classical time-dependent plasticity rule. On the handwritten digits recognition task, both methods achieve the F1-score of 0.89–0.93, and yield the 0.80–0.96 F1-score on the spoken digits recognition task.

(1) Background: Transcription factors (TFs) are main regulators of eukaryotic gene expression. The cooperative binding of at least two TFs to genomic DNA is the widespread mechanism of transcription regulation. Massive analysis of co-occurrence of overrepresented pairs of motifs (composite elements, CEs) for different target TFs studied in ChIP-seq experiments can clarify the mechanisms of TF cooperation. (2) Methods: We focused on homotypic CEs representing the same motif models and considered only CEs with spacers. We improved the capability of the Motifs Co-Occurrence Tool (MCOT) to predict asymmetric homotypic CEs in which one of par-ticipating motifs has higher conservation than the other. We categorized the target TFs from the data of M. musculus ChIP-seq and A. thaliana ChIP-seq/DAP-seq according to the structure of DNA-binding domains (DBDs) into classes. (3) Results: For all TF classes the predominance of asymmetric CEs over both symmetric and those with no enrichment in both directions was re-vealed. Target TFs from classes Basic helix-loop-helix factors (bHLH) and Basic leucine zipper factors (bZIP) showed the highest fractions of datasets with asymmetric CEs. We showed that pioneer TFs, despite their DBD types, have a higher significance of asymmetry within homotyp-ic CEs compared to other TFs. (4) Conclusion: Asymmetry within homotypic CEs is a promising new feature decrypting the mechanisms of gene transcription regulation.

In this paper, we demonstrate that fixed-weight layers, generated from random distribution or logistic functions, can effectively extract significant features from input data, resulting in high accuracy on a variety of tasks, including Fisher’s iris, Wisconsin Breast Cancer, and MNIST datasets. We have observed that logistic functions yield high accuracy with less dispersion in results. We have also assessed the precision of our approach under conditions of minimizing spikes number generated in the network, it is a practically useful for reducing energy consumption in spiking neural networks. Our findings reveal that the proposed method demonstrates a highest accuracy on Fisher’s iris and MNIST datasets with logistic regression. Furthermore, they surpass the accuracy of the conventional (non-spiking) approach using logistic regression in the case of Wisconsin Breast Cancer. We have also investigated the impact of non-stochastic spike generation on accuracy.

Artificial intelligence techniques are now widely used in various agricultural applications, including the detection of devastating diseases such as late blight (Phytophthora infestans) and early blight (Alternaria solani) affecting potato (Solanum Tuberorsum L.) crops. In this paper, we present a mobile application for potato crop pest detection based on deep neural networks. The images were taken from the PlantVillage dataset with a batch of 1000 images for each of the three identified classes. An exploratory analysis of the architectures used for early and late blight diagnosis in potatoes was performed, achieving an accuracy of 98.76%, with MobileNetv2. Based on the results obtained, an offline mobile application was implemented, supported on devices with Android 4.1 or later, also featuring an information section on the 27 pests affecting potato crops and a gallery of symptoms. For future work, segmentation techniques will be used to highlight the damaged region in the potato leaf by evaluating its extent and possibly identifying different types of pests affecting the same plant.