In the modern days the data is coming from various devices like mobiles, tabs, laptops, computers, IOT devices e.tc and is stored in the electronics form in the systems using the concept of files or data bases. Clustering Technique is used to extract data from these sources. Improving the accuracy of the model is improved using the feature selection or feature engineering or both. The feature engineering is used to add a new feature based on the global mean. Along with that new feature in addition to the feature selection increase the overall accuracy of the model.

The dynamic landscape of 3D printing has experienced a notable surge in the development of diverse filaments tailored for a wide range of applications in medicine. This experimental study thoroughly examines the mechanical properties of nine popular 3D printer filaments, namely PLA, ABS, HIPS, PETG, PA, Carbon Fiber, Ceramic, PMMA, and Metal composite. Focusing on key aspects such as tensile strength and compressive tests, the study delves into the intricate mechanical characteristics of these 3D printer filaments. In addition to the mechanical properties, the study provides a comprehensive exploration of essential filament attributes, including melting point, bed temperature requirements, and density of nine different filament properties. Furthermore, the study addresses crucial considerations in material selection for different applications. Through insightful comparisons, the article illuminates the advantages and limitations of various available filaments within the realm of applications. This study serves as a valuable resource, offering nuanced insights for researchers, engineers, and medical professionals seeking a deeper understanding of the mechanical characteristics of 3D printer filaments and their potential applications.

Intrauterine growth restriction (IUGR) and being born small for gestational age (SGA) are two distinct conditions with different implications for child development. IUGR is associated with greater perinatal morbidity and mortality and can be identified by additional abnormalities (pathological Doppler sonography, oligohydramnios, lack of growth in the interval, estimated weight <3rd percentile). IUGR may also be present in neonates with birth weights above the 10th percentile. Recognizing fetuses being “at risk” of a higher perinatal mortality and morbidity rate in order to monitor them accordingly and deliver them in good time is still challenging. This review article summarizes approaches to increase the diagnostic accuracy of IUGR and presents current concepts of pathophysiology with a focus on oxidative stress and consecutive inflammatory and metabolic changes. Since prenatal influences affect the risk of later diseases, we also discuss the need for interdisciplinary follow-up strategies during childhood and look at future scientific challenges. It should be emphasized that prenatal and postnatal care of IUGR neonates should be regarded as a continuum.

In this paper, a relatively new hyper convolution spectra for characterization liquid, viscoelastic and solid samples is presented. Special attention is paid to the biophysical characterization of epithelial tissues and early detection of cancer of the skin, cervix, colon, and oral cavity. The method is based on the use of two types of white light, diffuse and polarized, from the same LED light sources. Based on the subtraction of the intensity values of these two lights and using the hyper convolution algorithm, the ratio of paired and unpaired electrons of tissue is obtained. This ratio correlates well with the state of the tissue: normal, irritating, precancerous, and cancerous. First, a proof-of-concept studies were performed, and later clinical studies on samples from one thousand two hundred fifteen people were performed. It showed that hyper Opto-Magnetic Imaging Spectroscopy (OMIS) can detect epithelial tissue cancers with an accuracy of 85-96%. Bearing in mind that the OMIS method also acquires the biophysical characteristics of the deeper skin layers (epidermis, basement membrane, dermis) by analysing convolution spectra of RGB channels of both diffuse and polarized white light, it is possible to apply this method in cosmetics (skin hydration, collagen, and elastin states, etc.). During OMIS applications, we noticed places where improvements could be made to increase method’s accuracy using advanced machine learning methodologies.

Polyamide 11 (PA11) is a plant-based nylon made from castor beans. Powder bed fusion laser sintering (PBF-LS) is an additive manufacturing process used for PA11 which allows the reuse of the unsintered powder. The unsintered powder is mixed with virgin powders at different refresh rates which has been studied extensively for most semi-crystalline polyamides. However, there is lack of information on the effect of using 100% reused PA11 powder and the number of times it is reused on its own during powder bed fusion laser sintering. This paper investigates the effect of reusing PA11 powder in PBF-LS and number of times it is reused on the dimensional accuracy, density, thermal and tensile properties. From 100% virgin powder to 3rd use of the powder, there is a decrease in powder wastage, decrease in crystallinity and tensile strength. These was associated with the polymerisation and cross-linking process of polymer chains, upon exposure to high temperature. This results in a higher molecular weight and hence density. From the 4th use to 10th reuse, the opposite was observed which was associated to an increase in high-viscosity and un-molten particles which resulted in defects in the PBF-LS parts.

Satellite-based data classification performance remains a challenge for research community in the field of land use/land cover mapping. Here we investigated supervised per-pixel classifications performance under different scenarios, based on single and seasonal multispectral data combi-nations of different sensors (Landsat-8 OLI and Sentinel-2 MSI). In case of Landsat, seasonal spectral indices (EVI and NDMI) were included. A typical Mediterranean watershed with a complex landscape comprised of various forest and wetland ecosystems, crops, artificial surfaces, and lake water was selected to test our approach. All available geospatial data from national databases (Forest Map, LPIS, Natura2000 habitats, cadastral parcels, etc.) are used as ancillary data for clas-sification training and validation. We examined and compared the performance of ML, RF, KNN and SVM classifiers under different scenarios for land use/land cover mapping, according to Copernicus Land Cover (CLC2018) nomenclature. In total, eight land use/land cover classes were identified in Landsat-8 OLI and nine in Sentinel-2a MSI for an acceptable overall accuracy over 85%. A comparison of the overall classification accuracies shows that Sentinel-2a overall accuracy was slightly higher than Landsat-8 (96.68% vs. 93.02%). Respectively, the best-performed algorithm was ML in Sentinel-2 while in Landsat-8 was KNN. However, machine-learning algorithms have similar results regardless the type of sensor. We concluded that best classification performances achieved using seasonal multispectral data. Future research should be oriented towards inte-grating time-series multispectral data of different sensors and geospatial ancillary data for land use/land cover mapping.

A method of accuracy error compensation for the time interval is examined, allowing to eliminate the dependence of accuracy error on the duration of measured intervals and minimising the influence of destabilising factors - ambient temperature changes and the initial deviation of the meter clock generator frequency from the nominal value. The compensation method is based on a calibration procedure that measures precise time intervals under conditions of changing ambient temperature. Then the dependence of the accuracy error on temperature for a particular meter is recorded. Based on these data, a correction table is compiled containing correction factors and temperature values at which these factors were determined. Under real measurement conditions, the correction factor corresponding to the current temperature is determined from the table for measured results correction. The table with correction factor values could be stored in the memory of the meter or processing computer. Experimental verification of the method showed that applying a correction for a meter with a standard XO class clock generator (certificated instability of ±50 ppm) can obtain an equivalent clock generator instability of ±0.15 ppm. The application of the method is efficient in cases where the use of high-end clocking to ensure the required measurement accuracy is not economically feasible.

To validate the accuracy and reliability of onboard sensors for object detection and localization in driver assistance, as well as autonomous driving applications under realistic conditions (indoors and outdoors), a novel tracking system is presented. This tracking system is developed to determine the position and orientation of a slow-moving vehicle (e.g. car during parking maneuvers), independent of the onboard sensors, during test maneuvers within a reference environment. One requirement is a 6 degree of freedom (DoF) pose with a position uncertainty below 5 mm (3σ), an orientation uncertainty below 0.3° (3σ) at a frequency higher than 20 Hz, and a latency smaller than 500 ms. To compare the results from the reference system with the vehicle’s onboard system, a synchronization via Precision Time Protocol (PTP) and a system interoperability to Robot Operating System (ROS) is implemented. The developed system combines motion capture cameras mounted in a 360° panorama view set-up on the vehicle with robotic total stations. A point cloud of the test site serves as a digital twin of the environment, in which the movement of the vehicle is simulated. Results have shown that the fused measurements of these sensors complement each other, so that the accuracy requirements for the 6 DoF pose can be met, while allowing a flexible installation in different environments.

We scrutinize the reliability of multilooked interferograms for deformation analysis. Designing a simple approach in the evaluation of the accuracy of the estimated deformation signals, we reveal a prominent bias in the deformation velocity maps. The bias is the result of propagation of small phase error of multilooked interferograms through the time series and can sum up to 6.5 mm/yr in case of using the error prone short temporal baseline interferograms. We further discuss the role of the phase estimation algorithms in reduction of the bias and put recommend a unified intermediate InSAR product for achieving high-precision deformation monitoring.

This report describes the collection of a large dataset (6930 measurement) on dimensional error in the fused deposition modeling (FDM) additive manufacturing process for full-density parts. Three different print orientations were studied, as well as seven raster angles (0°, 15°, 30°, 45°, 60°, 75°, and 90°) for the rectilinear infill pattern. All measurements were replicated ten times on ten different samples to ensure a comprehensive dataset. Eleven polymer materials were considered: acrylonitrile butadiene styrene (ABS), polylactic acid (PLA), high-temperature PLA, wood-composite PLA, carbon-fiber-composite PLA, copper-composite PLA, aluminum-composite PLA, high-impact polystyrene (HIPS), polyethylene terephthalate glycol-enhanced (PETG), polycarbonate, and synthetic polyamide (nylon). The samples were ASTM-standard impact testing samples, since this geometry allows the measurement of error on three different scales; the nominal dimensions were 3.25mm thick, 63.5mm long, and 12.7mm wide. This dataset is intended to give engineers and product designers a benchmark for judging the accuracy and repeatability of the FDM process for use in manufacturing of end-user products.

In this paper, a new approach is proposed for designing ultra-low-power FFT (Fast Fourier Transform) system suitable for use in energy harvesting powered sensors. Bit-serial architecture is adopted to reduce the power consumption of butterfly operation. Simulation results show that, compared with state-of-the-art bit-serial and conventional parallel processors, the proposed technique is superior in terms of silicon area, power consumption, dynamic energy use due to variable precision arithmetic. A sample design of a 64-point FFT shows that the implementation can save about 40% area and 36% leakage power compared with a conventional parallel counterpart, accordingly achieving significant power benefits at a low sample rate and low voltage domain. The dynamic variation of the arithmetic precision can be achieved through a simple modification of the controller with hardware area overhead of 10% gate count.

The CT (computed tomography) scanner has been used for many years now not only for medical measurements, but also in many industries, mostly for tasks such as defectoscopy, measuring sheet thickness, checking the joining of materials, but also for measuring the geometry of individual components. It is a good complement to coordinate contact and non-contact measurements for intra-structural measurements and inaccessible places. The variety of materials, however, makes it very difficult to select individual CT parameters. In this paper, a curve for selecting the maximum and minimum voltage of the lamp depending on the density of a given material has been determined and an interpolation polynomial (1d third-degree polynomial) has been used, by defining 3rd-degree glued functions (cubic spline) to determine intermediate voltage values to a given material density, so as to determine full data ranges. This approach will facilitate the work of selecting scanning parameters for nondestructive testing, as this is a difficult process and sometimes consumes half of the measurement time. Work is underway at the Accredited Coordinate Metrology Laboratory to develop a multi-criteria matrix for selecting CT measurement parameters for measurement accuracy.

This paper presents an advanced methodology for processing radar imagery stacks using Persistent Scatterer and Distributed Scatterer Interferometry (PSDS) to enhance spatial coherence and improve displacement detection accuracy. The workflow leverages Level 2 Coregistered Single Look Complex (L2-CSLC) images generated by the open-source COMPASS (COregistered Multi-temPorAl Sar SLC) framework in combination with the Combined eigenvalue maximum likelihood Phase Linking (CPL) approach as implemented in MiaplPy. Starting the analysis directly from Level 2 products offers a significant advantage to end-users, as they simplify processing by being pre-geocoded and ready for immediate analysis. Additionally, the open-source nature of the workflow and the use of L2-CSLC products simplify the processing pipeline, making it easier to distribute directly to users for practical applications in monitoring infrastructure stability in dynamic environments. The ISCE3-MiaplPy workflow is compared against ISCE2-MiaplPy and the European Ground Motion Service (EGMS) to assess its performance in detecting infrastructure deformation in dynamic environments, such as the Algeciras port. Results indicate that ISCE3-MiaplPy delivers significantly denser measurements, albeit with increased noise, compared to its counterparts. This higher resolution enables a more detailed understanding of infrastructure stability and surface dynamics, which is critical for environments with ongoing human activity or natural forces.

Objective: The diagnostic efficacy of the apparent diffusion coefficient (ADC) on diffusion-weighted magnetic resonance imaging for lymph node metastasis in biliary tract cancer was investigated in the present study. Methods: Surgically resected 112 lymph nodes from 35 biliary tract cancer (BTC) patients were examined in this study. Values of the ADC mean and minimum of lymph nodes, as well as short-axis and long-axis diameters of lymph nodes were assessed by computed tomography (CT). The relationship between these parameters and the presence of histological lymph node metastasis was evaluated. Results: Histological lymph node metastasis was detected in 31 (27.7%) out of 112 lymph nodes. The short-axis diameter in metastatic lymph nodes was significantly larger than that in non-metastatic lymph nodes (P = 0.002), but the long-axis diameter was not significantly different between metastatic and non-metastatic lymph nodes. Both ADC mean and minimum values in metastatic lymph nodes were significantly lower than those in non-metastatic lymph nodes (P < 0.001, respectively). However, the ADC minimum value showed the highest accuracy for the diagnosis of histological lymph node metastasis, with an area under the curve of 0.877, sensitivity of 87.1%, specificity of 82.7%, and accuracy of 83.9%. Conclusions: The ADC minimum value on diffusion-weighted magnetic resonance imaging was very useful for the diagnosis of lymph node metastasis in BTC.

The Range–Doppler (R-D) model is extensively employed for the geometric processing of Synthetic Aperture Radar (SAR) images. Refining the sensor motion state and imaging parameters is the most common method for achieving high-precision geometric processing using the R-D model, comprising a process that involves numerous parameters and complex computations. In this study, we introduce a novel approach to improve the positioning accuracy of the R-D model, implementing a low-order polynomial to compensate for the original imaging errors without altering the initial positioning parameters. We also design low-order polynomial compensation models with different parameters. The models are evaluated on various SAR images from different platforms and bands, including spaceborne TerraSAR-X and GF3-C images, manned airborne SAR-X images, and unmanned aerial vehicle-mounted miniSAR-Ku images. Furthermore, image positioning experiments involving the use of different polynomial compensation models and various numbers and distributions of Ground Control Points (GCPs) are conducted. The experimental results demonstrate that geometric processing accuracy comparable to that of the classical rigorous positioning method can be achieved even when applying only an affine transformation model to the images. Compared to classical refinement models, however, the proposed image-compensated R-D model is much simpler and easy to implement. Thus, this study provides a convenient, robust, and widely applicable method for the geometric positioning processing of SAR images, offering a potential approach for the joint-positioning processing of multi-source SAR images.

Cuffless sphygmomanometers may be useful alternative blood pressure monitors for screening and home healthcare. The main requirements for these devices are accuracy in the resting state, accuracy during dynamic blood pressure changes, and long-term stability. Intermittent measurements can ensure that the accuracy of active measurements mirrors that of measurements in the resting and dynamic states. This brief report proposes a new protocol to evaluate long-term stability based on a comparison with a medically approved cuff-based automated sphygmomanometer rather than an auscultatory sphygmomanometer. Dynamic changes in blood pressure are not usually assessed based on intermittent measurement with an over-the-counter (OTC) sphygmomanometer. Thus, validation testing focused on the accuracy of the OTC cuffless sphygmomanometer in the resting state and the long-term stability of the device, and the results were similar to those of the cuff-based sphygmomanometer. Further research and discussions are necessary to develop standards derived from high-quality evidence for manufacturers of OTC sphygmomanometers.

The quality prediction of quaternary structure models of a protein complex, in the absence of its true structure, is known as the Estimation of Model Accuracy (EMA). EMA is useful for ranking predicted protein complex structures and using them appropriately in biomedical research, such as protein-protein interaction studies, protein design, and drug discovery. With the advent of more accurate protein complex (multimer) prediction tools, such as AlphaFold2-Multimer and ESMFold, the estimation of the accuracy of protein complex structures has attracted increasing attention. Many deep learning methods have been developed to tackle this problem; however, there is a noticeable absence of a comprehensive overview of these methods to facilitate future development. Addressing this gap, we present a review of deep learning EMA methods for protein complex structures developed in the past several years, analyzing their methodologies and impacts. We also provide a prospective summary of some potential new developments for further improving the accuracy of the EMA methods.

In the literature, the question of the amount of data necessary and sufficient to validate different models of the occurrence of risk of adverse events for patients or the classification of the presence or absence of pathological features has been repeatedly raised. In the presented study, we propose a new approach to determine the necessary and enough studies for validation of medical software based on artificial intelligence technology, whose main task is to classify medical X-rays according to the presence of normality and pathology. It is shown that for several studies in a dataset, when AUC ROC has maximum heterogeneity, it varies depending on the balance of "norm"/"pathology" classes. Thus, for a balance of "normal"/"abnormality", where 90% is "normal" and 10% is "abnormality", maximum heterogeneity is achieved for 190 studies, for a balance of 80% ("normal")/20% ("abnormality") for 80 studies, for a balance of 70% ("norm")/30% ("abnormality") - 120 trials, for a balance of 60% ("norm")/40% ("abnormality") the maximum heterogeneity is reached at 110 trials, and for a balance of 50% ("norm")/50% ("abnormality") - at 70 trials. The obtained data are in good agreement with the previous results. They allow us to determine a sufficient (necessary) number of studies in the dataset to perform an unbiased assessment of AUC ROC.

In this study, our primary objective was to analyze the tradeoff between accuracy and complexity in machine learning models, with a specific focus on the impact of reducing complexity and entropy on the production of landslide susceptibility maps. We aimed to investigate how simplifying the model and reducing entropy can affect the capture of complex patterns in the susceptibility maps. To achieve this, we conducted a comprehensive evaluation of various machine-learning algorithms for classification tasks. We compared the performance of these algorithms in terms of accuracy and complexity, considering both "before" and "after" scenarios of dimensionality reduction using Principal Component Analysis (PCA). Our findings revealed that reducing complexity and lowering entropy can lead to an increase in model accuracy. However, we also observed that this reduction in complexity comes at the cost of losing important complex patterns in the produced landslide susceptibility maps. By simplifying the model and reducing entropy, certain intricate relationships and uncertain patterns may be overlooked, resulting in a loss of information and potentially compromising the accuracy of the susceptibility maps. The analysis encompassed a diverse range of machine learning algorithms, including Random Forest (RF), Extra Trees (EXT), XGboost, LightGBM, Catboost, Naive Bayes (NB), K-Nearest Neighbors (KNN), Gradient Boosting Machine (GBM), and Decision Trees (DT). Each algorithm was evaluated for its strengths and limitations, considering the tradeoff between accuracy and complexity. Before dimensionality reduction, the algorithms demonstrated promising results, with RF exhibiting excellent AUC/ROC scores and average accuracy. However, computational costs were noted as a potential drawback for RF, especially when dealing with large datasets. EXT showcased robust performance and good accuracy, while XGboost demonstrated its ability to handle complex relationships within large datasets, albeit requiring careful hyperparameter tuning. The efficiency and scalability of LightGBM made it a suitable choice for large datasets, although it displayed sensitivity to class imbalance. Catboost excelled in handling categorical features, but longer training times were observed for larger datasets. NB showcased simplicity and computational efficiency but assumed independence among features. KNN, known for its capability to capture local patterns and spatial relationships, was found to be sensitive to the choice of distance metric. GBM, while capturing complex relationships effectively, was prone to overfitting without proper regularization. DT, with its interpretability and ease of understanding, faced limitations in terms of overfitting and limited generalization. After dimensionality reduction, certain algorithms exhibited improvements in their AUC/ROC scores and average accuracy, including RF, EXT, XGboost, and LightGBM. However, for a few algorithms, such as NB and DT, a decrease in performance was observed. This study provides valuable insights into the performance characteristics, strengths, and limitations of various machine learning algorithms in classification tasks. Researchers and practitioners can utilize these findings to make informed decisions when selecting algorithms for their specific datasets and requirements. We also aim to identify the potential factors contributing to the high accuracy rates obtained from these ensembled algorithms and explore possible shortcomings of non-ensembled algorithms that may result in lower accuracy rates. By conducting a comprehensive analysis of these algorithms, we seek to provide valuable insights into the benefits and limitations of ensembled approaches for landslide susceptibility mapping. Our study sheds light on the challenges faced when balancing accuracy and complexity in machine learning models for landslide susceptibility mapping. It emphasizes the importance of carefully considering the level of complexity and entropy reduction in relation to the specific patterns and uncertainties present in the data. By providing insights into this tradeoff, our research aims to assist researchers and practitioners in making informed decisions regarding model complexity and entropy reduction, ultimately improving the quality and interpretability of landslide susceptibility maps.

Background: Multiple system atrophy (MSA) is a rapidly progressive neurodegenerative disorder that has no curative treatment. Diagnosis is based on a set of criteria established by Gilman (1998 and 2008) and recently updated by Wenning (2022). We aim to determine the effectiveness of [123I]Ioflupane SPECT in MSA, especially at the initial clinical suspicion. Methods: Cross-sectional study of patients at initial clinical suspicion of MSA, referred for [123I]Ioflupane SPECT. Results: 139 patients (68 men, 71 women) were included, 104 being MSA-probable and 35 MSA-possible. MRI was normal in 89.2% while SPECT was positive in 78.45%. SPECT showed high sensitivity (82.46%) and positive predictive value (86.24), reaching maximum sensitivity in MSA-P (97.26%). Significant differences were found when relating both SPECT assessments in the healthy-sick and inconclusive-sick groups. We also found an association when relating SPECT to the subtype (MSA-C or MSA-P), as well as to the presence of parkinsonian symptoms. Lateralization of striatal involvement was detected (left side). Conclusions: [123I]Ioflupane SPECT is a useful and reliable tool for diagnosing MSA, with good effectiveness and accuracy. Qualitative assessment shows a clear superiority when distinguishing between the healthy-sick categories, as well as between the parkinsonian (MSA-P) and cerebellar (MSA-C) subtypes at initial clinical suspicion.

A time integration scheme based on semi-Lagrangian advection and Laplace transform adjustment has been implemented in a baroclinic primitive equation model. The semi-Lagrangian scheme makes it possible to use large time steps. However, errors arising from the semi-implicit scheme increase with the time step size. In contrast, the errors using the Laplace transform adjustment remain relatively small for typical time steps used with semi-Lagrangian advection. Numerical experiments confirm the superior performance of the Laplace transform scheme relative to the semi-implicit reference model. The algorithmic complexity of the scheme is comparable to the reference model, making it computationally competitive, and indicating its potential for integrating weather and climate prediction models.

The study aims to examine the effects of artificial intelligence (AI) on the consistency and analysis of financial statements in hotels in ASEZA, Jordan. This research is an exploratory, empirical study, which uses the methodology of data collection and interpretation to draw conclusions. The researchers used the arithmetic mean, standard deviation, T-test and ANOVA test to calculate the degree of significance of the study questions. The findings of a basic linear regression study of the impact of AI implemented in Jordanian hotels on the integration of accounting information systems and the association between AI and the integration of accounting information systems (R = 59.6%) also indicate that the fixed limit value amounted to (2.060) and the value of (Beta) for T-test

We are concerned with the use of some classical spectral collocation methods as well as with the new software system Chebfun in order to compute high order (index) eigenpairs of singular as well as regular Schrodinger eigenproblems. We want to highlight both the qualities as well as the shortcomings of these methods and evaluate them vis-a-vis the usual ones. In order to resolve a boundary singularity we use Chebfun with the simple domain truncation technique. Although this method is equally easy to apply with spectral collocation, things are more nuanced in the case of these methods. A special technique to introduce boundary conditions as well as a coordinate transform which maps an unbounded domain to a nite one are the ingredients. A challenging set of "hard" benchmark problems, for which usual numerical methods (f. d., f. e. m., shooting etc.) fail, are analysed. In order to separate "good"and "bad"eigenvalues we estimate the drift of the set of eigenvalues of interest with respect to the order of approximation and/or scaling of domain parameter. It automatically provides us with a measure of the error within which the eigenvalues are computed and a hint on numerical stability. We pay a particular attention to problems with almost multiple eigenvalues as well as for problems with a mixed (continuous) spectrum. In the latter case we try to numerically highlight its existence. Special attention will be paid to the higher eigenpairs (the pair of eigenvalue and the corresponding eigenfunction approximated by an eigenvector spanning its nodal values).

The Coronavirus disease (COVID-19) caused by a novel coronavirus, SARS-CoV-2, has been declared as a global pandemic. Due to its infection rate and severity, it has emerged as one of the major global threats of the current generation. To support the current combat against the disease, this research aims to propose a Machine Learning based pipeline to detect the COVID-19 infection using the lung Computed Tomography scan images (CTI). This implemented pipeline consists of a number of sub-procedures ranging from segmenting the COVID-19 infection to classifying the segmented regions. The initial part of the pipeline implements the segmentation of the COVID-19 affected CTI using Social-Group-Optimization and Kapur’s Entropy thresholding, followed by k-means clustering and morphology-based segmentation. The next part of the pipeline implements feature extraction, selection and fusion to classify the infection. PCA based serial fusion technique is used in fusing the features and the fused feature vector is then employed to train, test and validate four different classifiers namely Random Forest, k-Nearest Neighbors (KNN), Support Vector Machine with Radial Basis Function, and Decision Tree. Experimental results using benchmark datasets show a high accuracy (> 91%) for the morphology-based segmentation task and for the classification task the KNN offers the highest accuracy among the compared classifiers (> 87%). However, this should be noted that this method still awaits clinical validation, and therefore should not be used to clinically diagnose the ongoing COVID-19 infection.

Simulator training for image-guided surgical interventions may benefit from artificial intelligence systems that control the evolution of task skills in terms of time and precision of a trainee's performance on the basis of fully automatic feed-back systems. At the earliest stages of training, novice trainees frequently focus on getting faster at the task, and may thereby compromise the optimal evolution of the precision of their performance. For automatically guiding them towards attaining an optimal speed-accuracy trade-off, an effective control system for the reinforcement/correction of strategies must be able to exploit the right individual performance criteria in the right way, reliably detect individual performance trends at any given moment in time, and alert the trainee, as early as necessary, when to slow down and focus on precision, or when to focus on getting faster. This article addresses several aspects of this challenge for speed-accuracy controlled simulator training before any training on specific surgical tasks or clinical models should be envisaged. Analyses of individual learning curves from the simulator training sessions of novices and benchmark performance data of one expert surgeon, who had no specific training in the simulator task, validate the suggested approach.

This study investigates the adoption of Robotic Process Automation (RPA) in marketing operations, exploring its impact on efficiency, data accuracy, and overall effectiveness. RPA has emerged as a transformative technology, automating routine tasks such as data entry, report generation, and campaign management, which has significantly enhanced operational efficiency within marketing departments. By automating repetitive processes, RPA enables marketing professionals to focus on strategic and creative tasks, resulting in accelerated campaign execution and improved productivity. Additionally, the integration of RPA with Customer Relationship Management (CRM) systems has led to more accurate and consistent data, providing valuable real-time insights that enhance decision-making and personalization in marketing strategies. Despite these benefits, the study also highlights several challenges associated with RPA adoption. These include concerns about workforce implications, such as job displacement and the need for reskilling, as well as implementation difficulties related to system compatibility and workflow design. Ethical and regulatory considerations, particularly regarding data privacy and compliance, are also critical factors that organizations must address to maintain customer trust and adhere to legal standards. The study further explores the potential of integrating artificial intelligence (AI) with RPA to drive future innovations in marketing automation. AI-driven RPA offers advanced capabilities, including predictive modeling and personalized marketing, which promise to enhance the effectiveness of automation strategies. The findings underscore the need for organizations to adopt best practices in RPA implementation and remain adaptable to technological advancements to fully leverage the benefits of automation and maintain a competitive edge in the dynamic marketing landscape.

Our image recognition system mainly judges whether the left upper limb in the image is the left upper limb or the right upper limb through our deep learning model in the image. The doctor then could give the correct surgical position. From the experimental results, it could be found that the precision rate and recall rate of the intelligent image recognition system proposed in this paper for preventing the upper limb dislocation surgery could reach 98% and 93%, respectively. It proved that our artificial intelligent image recognition system, AIIRS, could indeed assist orthopedic surgeons to prevent the occurrence of left and right dislocation in upper limb surgery. At the same time, this paper also completes the IRB application approval through the prototype experimental results and will conduct the second phase of human trials in the future. It showed that the research results of this paper will be of great benefit and research value to upper limb orthopedic surgery.

Our image recognition system mainly judges whether the left upper limb in the image is the left upper limb or the right upper limb through our deep learning model in the image. The doctor then could give the correct surgical position. From the experimental results, it could be found that the precision rate and recall rate of the intelligent image recognition system proposed in this paper for preventing the upper limb dislocation surgery could reach 98% and 93%, respectively. It proved that our intelligent image recognition system could indeed assist orthopedic surgeons to prevent the occurrence of left and right dislocation in upper limb surgery. At the same time, this paper also completes the IRB application approval through the prototype experimental results and will conduct the second phase of human trials in the future. It showed that the research results of this paper will be of great benefit and research value to upper limb orthopedic surgery.

The accuracy of multi-parametric MRI (mpMRI) in pre-operative staging of prostate cancer (PCa) remains controversial. Objective: To evaluate the ability of mpMRI to accurately predict PCa extra-prostatic extension (EPE) on a side-specific basis using a risk-stratified 5-point Likert scale. This study also aimed to assess the influence of mpMRI scan quality on diagnostic accuracy. Patients and Methods: We included 124 men who underwent robot-assisted RP (RARP) as part of the NeuroSAFE PROOF study at our centre. Three radiologists retrospectively reviewed mpMRI blinded to RP pathology and assigned a Likert score (1-5) for EPE on each side of the prostate. Each scan was also ascribed a Prostate Imaging Quality (PI-QUAL) score for assessing the quality of the mpMRI scan, where 1 represents poorest and 5 represents best diagnostic quality. Outcome measurements and statistical analyses: Diagnostic performance is presented for binary classification of EPE including 95% confidence intervals and area under the receiver operating characteristic curve (AUC). Results: A total of 231 lobes from 121 men (mean age 56.9 years) were evaluated. 39 men (32.2%), or 43 lobes (18.6%) had EPE. Likert score ≥3 had sensitivity (SE), specificity (SP), NPV, PPV of 90.4%, 52.3%, 96%, 29.9%, respectively, and AUC was 0.82 (95% CI: 0.77-0.86). AUC was 0.63 (95% CI: 0.37-0.9), 0.77 (0.71-0.84) and 0.92 (0.88-0.96) for biparametric scans, PI-QUAL 1-3 and PI-QUAL 4-5 scans, respectively. Conclusions: MRI can be used effectively by genitourinary radiologists to rule out EPE and help inform surgical planning for men undergoing RARP. EPE prediction was more reliable when the MRI scan was a) multi-parametric and b) of a higher image quality according to the PI-QUAL scoring system.

(1) Background: The purpose of this study is to evaluate the full arch scan accuracy (precision and trueness) of nine digital intra-oral scanners and four lab scanners. Previous studies have compared the accuracy of some intra-oral scanners, but as this is a field of quickly developing technologies, a more up-to-date study was needed to assess the capabilities of currently available models.; (2) Methods: The present in vitro study compared nine different intraoral scanners (Omnicam 4.6; Omnicam 5.1; Primescan; CS 3600; Trios 3; Trios 4; Runyes; i500 and DL206) as well as four lab light scanners (Einscan SE; 300e; E2 and Ineos X5) to investigate the accuracy of each scanner by examining the overall trueness and precision. Ten aligned and cut scans from each of the intra-oral and lab scanners in the in vitro study were brought into CloudCompare. A comparison was made with the master STL using the CloudCompare 3D analysis best-fit algorithm. The results were recorded along with individual standard deviation and a colorimetric map of the deviation across the surface of the STL mesh; a comparison was made to the master STL, quantified at specific points. ; (3) Results: In the present study, the Primescan had the best overall trueness (17.3 ± 4.9). Followed by (in order of increasing deviation) the Trios 4 (20.8 ± 6.2), i500 (25.2 ± 7.3), CS3600 (26.9 ± 15.9), Trios 3 (27.7 ± 6.8), Runyes (47.2 ± 5.4), Omnicam 5.1 (55.1 ± 9.5), Omnicam 4.6 (57.5 ± 3.2) and Launca DL206 (58.5 ± 22.0). Regarding the lab light scanners, the Ineos X5 had the best overall trueness with (0.0 ± 1.9). Followed by (in order of increasing deviation) the 3Shape E2 (3.6 ± 2.2), Up3D 300E (12.8 ± 2.7), and Einscan SE (14.9 ± 9.5); (4) Conclusions: This study confirms that all current generations of intra-oral digital scanners can capture a reliable, reproducible full arch scan in dentate patients. Out of the intra-oral scanners tested, no scanner produced results significantly similar in trueness to the Ineos X5. However, the Primescan was the only one to be statistically of a similar level of trueness to the 3Shape E2 lab scanner. All scanners in the study had mean trueness of under 60-micron deviation. While this study can compare the scanning accuracy of this sample in a dentate arch, the scanning of a fully edentulous arch is more challenging. The accuracy of these scanners in edentulous cases should be examined in further studies.

Precision and accuracy estimation is an important index used to reflect the measurement performance and quality of a measurement system. To reveal the significance and connotations of the precision and accuracy estimation index of a close-range photogrammetry system, several common precision and accuracy estimation methods used in close-range photogrammetry are explained from a theoretical perspective, and the mechanism of the internal coincidence precision estimation and the external coincidence accuracy estimation are deduced, respectively. Through detailed experimental design and testing, the validity and reliability of the proposed precision and accuracy estimation methods are verified, which provides strong evidence for the quality control, optimisation, and evaluation of the measurement results from a close-range photogrammetry system. At the same time, it has significance for the further development of precision and accuracy estimation analysis of close-range photogrammetry systems.

This study presents a novel approach to enhance Large Language Models (LLMs) like Alpaca by dynamically integrating real-time information. This method addresses the issue of content hallucination and data relevancy by automatically collecting and integrating current data from credible sources into model prompts. Experiments show a significant improvement in accuracy and a decrease in content hallucination, with a manageable increase in response time. The research underscores the potential of real-time data integration in making LLMs more accurate and contextually relevant, setting a foundation for future advancements in dynamic data processing in AI.

In this review we collect some recent achievements in the accurate and efficient solution of the Nonlinear Schrödinger Equation (NLSE), with the preservation of its Hamiltonian structure. This is achieved by using the energy-conserving Runge-Kutta methods named Hamiltonian Boundary Value Methods (HBVMs) after a proper space semi-discretization. The main facts about HBVMs, along with their application for solving the given problem, are here recalled and explained in detail. In particular, their use as spectral methods in time, which allows efficiently solving the problems with spectral space-time accuracy.

In this work, we offer a novel and accurate method in order to find the solution of the linear differential equations over the intervals [0, 1) based on the generalization of Legendre wavelets. The mechanism is still upon workable implementation of the operational matrix of integration and its derivatives. This method reduces the problems into algebraic equations via the properties of generalized Legendre wavelet (GLW) together with the operational matrix of integration. The function approximation has been picked out in such a way so as to enumerate the connection coefficients in an facile manner. The proposed numerical technique, based on the GLW, has been examined on three linear problems as a consequence of this investigation. The outcomes have shown that this method, as opposed to some other existing numerical and analytical methods, is a very useful and advantageous for tackling such problems.

Background. We aimed to assess the validity of the Mat-O-Covid Job Exposure Matrix (JEM) on SARS-CoV2 using compensation data from the French National Health Insurance compensation system for occupational-related COVID-19. Methods. Deidentified compensation data for occupational COVID-19 in France were obtained between August 2020 and August 2021. The acceptance was considered as the reference. Mat-O-Covid is an expert based French JEM on workplace exposure to SARS-CoV2. Bivariate and multivariate models were used to study the association between the exposure assessed by Mat-O-Covid and the reference, as well as the Area Under Curves (AUC), sensitivity, specificity, predictive values, and likelihood ratios. Results. In the 1140 cases included, there was a close association between the Mat-O-Covid index and the reference (p&lt;0.0001). The overall predictivity was good, with an AUC of 0.78 and an optimal threshold at 13 per thousand. Using Youden’s J statistic resulted in 0.67 sensitivity and 0.87 specificity. Both positive and negative likelihood ratios were significant: respectively 4.9 [2.4-6.4] and 0.4 [0.3-0.4]. Discussion. It was possible to assess Mat-O-Covid’s validity using data from the national compensation system for occupational COVID-19. Though further studies are needed, Mat-O-Covid exposure assessment appears to be accurate enough to be used in research.

Reliable methods to confirm the diagnosis of COVID-19 are essential to the successful management and containment of the virus. Current diagnostic options are limited in type, supply, and reliability. This article explores the controversial unreliability of existing diagnostic methods and maintains that more reliable diagnostic methods, combinations, and sequencing are necessary to effectively assist in reducing the occurrence of discharge of the patient on false negative test results. This reduction would in effect reduce transmission of the disease.

Cognitive deterioration caused by illness or aging often occurs before symptoms arise, and their timely diagnosis is crucial to reducing its medical, personal, and societal impacts. Brain-Computer Interfaces (BCIs) stimulate and analyze key cerebral rhythms, enabling reliable cognitive assessment that can accelerate diagnosis. The BCI system presented analyzes Steady-State Visually Evoked Potentials (SSVEPs) elicited in subjects of varying age to detect cognitive aging, predict its magnitude, and identify its relationship with SSVEP features (band power and frequency detection accuracy), which were hypothesized to indicate cognitive decline due to aging. The BCI system was tested with subjects of varying age to assess its ability to detect aging-induced cognitive deterioration. Rectangular stimuli flickering at theta, alpha, and beta frequencies were presented to subjects, and frontal and occipital EEG responses were recorded. These were processed to calculate detection accuracy for each subject and calculate SSVEP band power. A neural network was trained using the features to predict cognitive age. The results showed potential cognitive deterioration through age-related variations in SSVEP features. Frequency detection accuracy declined after age group 20–40 and band power, throughout all age groups. SSVEPs generated at theta and alpha frequencies, especially 7.5 Hz, were the best indicators of cognitive deterioration. Here, frequency detection accuracy consistently declined after age group 20-40 from an average of 96.64% to 69.23%. The presented system can be used as an effective diagnosis tool for age related cognitive decline.

Cold-water coral reefs are rich, yet fragile ecosystems found in colder oceanic waters. Knowledge of their spatial distribution on continental shelves, slopes, seamounts and ridge systems is vital for marine spatial planning and conservation. Cold-water corals frequently form conspicuous carbonate mounds of varying sizes, which are identifiable from multibeam echosounder bathymetry and derived geomorphometric attributes. However, the often large number of mounds makes manual interpretation and mapping a tedious process. We present a methodology that combines image segmentation and random forest spatial prediction with the aim to derive maps of carbonate mounds and an associated measure of confidence. We demonstrate our method based on multibeam echosounder data from Iverryggen on the mid-Norwegian shelf. We identified the image-object mean planar curvature as the most important predictor. The presence and absence of carbonate mounds is mapped with high accuracy (overall accuracy = 84.4%, sensitivity = 0.827 and specificity = 0.866). Spatially-explicit confidence in the predictions is derived from the predicted probability and whether the predictions are within or outside the modelled range of values and is generally high. We plan to apply the showcased method to other areas of the Norwegian continental shelf and slope where MBES data have been collected with the aim to provide crucial information for marine spatial planning.

Artificial intelligence (AI) is transforming many healthcare fields including pediatric urology. This in-depth review explores recent advances in AI tools for pediatric urology, emphasizing how state-of-the-art technologies can be used to enhance patient treatment. An initial overview of pediatric urology is given to provide context for this interdisciplinary field and the wide spectrum of problems this entails, before discussing potential uses of AI to improve diagnostic accuracy, treatment planning, and surgical results. AI-powered predictive models are already changing pediatric clinical practice by guiding interpretation of medical images and supporting decision making. In addition to outlining the aims, methods, and conclusions of previous studies on AI applications in pediatric urology, this review also highlights knowledge gaps and priority areas for future study. Particular focus is given to specialized surgeries such pyeloplasty, where AI-guided treatment may help overcome specific technical challenges of this complex procedure. Also highlighted are practical, ethical, and legal aspects of integrating AI into pediatric urology, which will be crucial for responsible innovation in patient-centered treatment. Overall, this article aims to enlighten and inspire clinicians, researchers, and other healthcare stakeholders by offering insight into the future of AI in pediatric urology.

This research explores the adoption of advanced analytics in supply chain decision-making, emphasizing its transformative impact on organizational efficiency and strategic advantage. The study investigates the key drivers behind the adoption of advanced analytics, including the growing complexity of data, the need for agility, and the pursuit of competitive advantage and cost reduction. It identifies significant challenges such as data integration difficulties, high implementation costs, and a shortage of skilled professionals, which organizations face when integrating these sophisticated tools. Despite these challenges, the research highlights the substantial benefits of advanced analytics, including enhanced forecasting accuracy, improved supply chain visibility, optimized processes, and cost savings. The findings indicate that while the implementation of advanced analytics varies across different sectors—such as retail, manufacturing, logistics, and healthcare—the overarching themes of improved efficiency and better decision-making are consistently observed. The study also discusses future trends, noting the integration of emerging technologies such as artificial intelligence, machine learning, and blockchain, which promise to further enhance analytics capabilities and accessibility. The successful adoption of advanced analytics relies not only on technological advancements but also on fostering a data-driven organizational culture, investing in continuous learning, and ensuring robust data governance. As supply chain management continues to evolve, advanced analytics will play a crucial role in driving strategic success and maintaining a competitive edge in a complex and dynamic market environment.

Deep learning neural networks require an immense amount of computation, especially in the training phase of the network when networks with multiple layers of intermediate neurons need to be built. In this paper, we will focus on the PSO algorithm with the aim of significantly accelerating the DLNN training phase by taking advantage of the GPGPU architecture and the Apache Spark analytics engine for large-scale data processing tasks. PSO is a bio-inspired stochastic optimization method whose goal is to iteratively improve the solution to a (usually complex) problem by attempting to approximate a given objective. However, parallelizing an efficient PSO is not a straightforward process due to the complexity of the computations performed on the swarm of particles and the iterative execution of the algorithm until a solution close to the objective with minimal error is achieved. In the present work, two parallelizations of the PSO algorithm have been implemented , both designed for a distributed execution environment. The synchronous parallel PSO implementation ensures consistency at the cost of potential idle time due to global synchronization, while the asynchronous parallel PSO approach improves execution time by reducing the need for global synchronization, making it more suitable for large datasets and distributed environments such as Apache Spark. Both variants of PSO have been implemented to distribute the computational load supported by this algorithm –due to the costly fitness evaluation and updating of particle positions– across the different Spark cluster executor nodes to effectively achieve coarse-grained parallelism, resulting in a significant performance increase over current sequential variants of PSO.

We present a novel benchmarking methodology for Large Language Models (LLMs) to evaluate their susceptibility to hallucinations, thereby determining their reliability for real-world applications involving greater responsibilities. This method, called Deception-Based Benchmarking, involves testing the model with a task that requires composing a short paragraph. Initially, the model performs under standard conditions. Then, it is required to begin with a misleading sentence. Based on these outputs, the model is assessed on three criteria: accuracy, susceptibility, and consistency. This approach can be integrated with existing benchmarks or applied to new ones, thus facilitating a comprehensive evaluation of models across multiple dimensions. It also encompasses various forms of hallucination. We applied this methodology to several small opensource models using a modified version of MMLU, DB-MMLU1 . Our findings indicate that most current models are not specifically designed to self-correct when the random sampling process leads them to produce inaccuracies. However, certain models, such as Solar-10.7B-Instruct, exhibit a reduced vulnerability to hallucination, as reflected by their susceptibility and consistency scores. These metrics are distinct from traditional benchmark scores. Our results align with TruthfulQA, a widely used benchmark for hallucination. Looking forward, DB-benchmarking can be readily applied to other benchmarks to monitor the advancement of LLMs.

The Selective Paste Intrusion (SPI) method is a layer-by-layer additive manufacturing technique that allows for the production of complex geometries in concrete elements by selectively bonding aggregates with cement paste in a particle bed. To create reinforced concrete, the Wire and Arc Additive Manufacturing (WAAM) process shall be integrated into SPI. This technique allows the production of almost free-formed reinforcement and thus complements the advantage of SPI to produce free-formed structures of almost any geometry. However, integration of WAAM into SPI poses a considerable challenge, as high temperatures are generated during the welding process. These temperatures can negatively affect the rheological properties of the cement paste, in turn the penetration behavior of the paste in the particle bed and, subsequently, the mechanical properties of the hardened concrete. A possible passive cooling strategy is to increase the protruding length of the reinforcement bars out of the particle-bed. This requires that the distance of the print nozzle to the particle bed is as well increased, since it must be possible to move it across the reinforcement. The objective was thus to investigate the effect of that distance on print quality and to quantify a maximum allowable distance for an adequate print quality (for the printer setting used) in terms of shape accuracy and concrete strength. Compressive and flexural strength tests as well as geometrical measurements using a 3D scanning method were performed on specimen, printed with varying print nozzle to particle bed distances. It can be stated that for the used SPI print-heads, nozzle-types and parameter settings, the distance between the nozzle and the particle bed should not exceed 50 mm to ensure sufficient print quality in both shape accuracy and mechanical strength.

Corona virus disease (COVID-19) has infected over more than 10 million people around the globe and killed at least 500K worldwide by the end of June 2020. As this disease continues to evolve and scientists and researchers around the world now trying to find out the way to combat this disease in most effective way. Chest X-rays are widely available modality for immediate care in diagnosing COVID-19. Precise detection and diagnosis of COVID-19 from these chest X-rays would be practical for the current situation. This paper proposes one shot cluster based approach for the accurate detection of COVID-19 chest x-rays. The main objective of one shot learning (OSL) is to mimic the way humans learn in order to make classification or prediction on a wide range of similar but novel problems. The core constraint of this type of task is that the algorithm should decide on the class of a test instance after seeing just one test example. For this purpose we have experimented with widely known Generalized Regression and Probabilistic Neural Networks. Experiments conducted with publicly available chest x-ray images demonstrate that the method can detect COVID-19 accurately with high precision. The obtained results have outperformed many of the convolutional neural network based existing methods proposed in the literature.

Additive manufacturing (AM) of high strength Al alloys promises to enhance the performance of critical components related to various aerospace and automotive applications. The key advantage of AM is its ability to generate lightweight, robust, and complex shapes. However, the characteristics of the as-built parts may represent an obstacle to satisfy the part quality requirements. The current study investigates the influence of selective laser melting (SLM) process parameters on the quality of parts fabricated from different Al alloys. A design of experiment (DOE) is used to analyze relative density, porosity, surface roughness, and dimensional accuracy according to the interaction effect between the SLM process parameters. The results show a range of energy densities and SLM process parameters for the AlSi10Mg and Al6061 alloys needed to achieve “optimum” values for each performance characteristic. A process map is developed for each material by combining the optimized range of SLM process parameters for each characteristic to ensure good quality of the as-built parts. The second part of this study investigates the effect of SLM process parameters on the microstructure and mechanical properties of the same Al alloys. This comprehensive study is also aimed at reducing the amount of post-processing needed.

This research paper examines the transformative impact of Artificial Intelligence (AI) on the global journalism industry. The integration of AI technologies, such as machine learning and natural language processing, has drastically changed journalistic practices and media operations. The study aims to understand how AI affects news production, distribution, and ethical considerations within journalism. By providing historical context and reviewing existing literature, this paper situates its analysis within the broader academic discourse. A mixed-methods approach is used for data collection and analysis, ensuring comprehensive and reliable findings. Results indicate that AI tools enhance journalistic efficiency and capabilities but also introduce challenges related to accuracy, authenticity, and editorial judgment. The implications for employment in journalism are significant, necessitating new skills and roles. The discussion interprets these findings in the context of media evolution and ethical standards. This study concludes by advocating for a balanced approach to AI adoption in journalism, emphasizing the importance of ethical guidelines, continuous journalist training, and ongoing research to navigate this evolving landscape.

Extramammary Paget disease (EMPD) is an uncommon adenocarcinoma of apocrine gland-rich areas, presenting significant diagnostic challenges due to its nonspecific clinical appearance and frequent misidentification as benign, inflammatory skin conditions. Traditional diagnostic methods such as biopsy are invasive and uncomfortable, often required repeatedly due to high recurrence rates. Dermoscopy and non-invasive imaging techniques have been used but provide limited diagnostic accuracy due to their constraints in depth penetration and resolution. Recent advancements in imaging technologies, such as line-field confocal optical coherence tomography (LC-OCT), show promise in enhancing diagnostic precision while minimizing invasive procedures. LC-OCT merges high-resolution imaging with deep penetration capabilities, capturing detailed horizontal and vertical skin images akin to histopathology. This study evaluated the diagnostic performance of LC-OCT in detecting EMPD and its recurrence in 17 clinically suspicious anogenital regions, belonging to 6 patients. Data were collected prospectively at patient bedside by an LC-OCT expert with poor training for EMPD; and, then, reviewed retrospectively by an independent LC-OCT expert with adequate training for EMPD and no concerns about time. The prospective examination yielded 64.7%-accuracy, 71.4%-sensitivity, and 33.3%-specificity. The retrospective analysis achieved 94.1%-accuracy, 100%-sensitivity, and 66.7%-specificity, with the only false positive case being a difficult-to-diagnose concomitant presentation of a lichen sclerosus et atrophicus. Despite the need for specialized training, our results suggest that LC-OCT represents a valuable tool for accurately identifying EMPD and improve its management by reducing unnecessary biopsies. Further studies are needed to standardize its clinical application.

In this paper, we introduce ResNetMF, a groundbreaking approach that harnesses the power of residual network matrix factorization to revolutionize recommendation systems. ResNetMF integrates residual networks, renowned for their ability to capture intricate patterns and features, with matrix factorization techniques that excel in modelling user-item interactions. This fusion presents a novel solution that surpasses the limitations of traditional recommendation systems. Through comprehensive experimentation and evaluation of diverse datasets, ResNetMF demonstrates remarkable enhancements in recommendation accuracy and efficiency. By effectively capturing both linear and nonlinear relationships in user-item interactions, ResNetMF provides superior recommendation quality. The outcomes from experiments unequivocally highlight the superiority of ResNetMF over existing state-of-the-art recommendation approaches, thereby validating its innovative nature and underscoring its potential to shape the future of recommendation systems. Through the integration of the deep residual network, ResNetMF approach facilitates the training of neural networks, enabling them to explore the underlying data layers more comprehensively. Extensive experimentation and evaluation across various datasets provide compelling evidence for the superiority of ResNetMF. Moreover, the proposed method utilized natural language processing (NLP) techniques for targeted information dissemination in recommendation systems, emphasizing the importance of personalized and relevant recommendations for user satisfaction and engagement.

Synchrotron radiation computed tomography (SRCT) allows more accurate calcified plaque and coronary stenosis assessment as a result of its superior spatial resolution, however, typical micro-computed tomography (micro-CT) systems have even higher resolution. The purpose of this study was to compare performance of high-resolution micro-CT with SRCT in the assessment of calcified plaques and a previously published dataset of coronary stenosis assessment. This experimental study involved micro-CT scanning of three-dimensional printed coronary artery models with calcification in situ used in our previously published SRCT study on coronary stenosis assessment. Measurements of coronary stenosis utilizing both modalities were compared using a paired sample t-test. The degrees of stenosis measured on all but one micro-CT dataset were statistically significantly lower than the corresponding SRCT measurements reported in our previous paper (p&lt;0.0005-0.05). This indicates that the superior spatial resolution of micro-CT was able to further reduce over-estimation of stenosis caused by extensive calcification of coronary arteries and hence false positive results. This study shows that high-resolution micro-CT outperforms SRCT in both calcified plaque and coronary stenosis assessment. This finding will become clinically important for cardiovascular event prediction and enable reclassification of individuals with low and intermediate risk into appropriate risk categories when the technical challenges of micro-CT in clinical practice such as the small field of view and demanding on image processing power are addressed.

Genomic selection (GS) can accelerate variety improvement when training set (TS) size, and its relationship with the breeding set (BS) are optimized for prediction accuracies (PA) of genomic prediction (GP) models. Sixteen GP algorithms were run on phenotypic best linear unbiased predictors (BLUPs) and estimators (BLUEs) of resistance to both fall armyworm (FAW) and maize weevil (MW) in a tropical maize panel. For MW resistance, 37% of the panel was the TS, and BS was the remainder whilst for FAW, random-based training sets (RBTS) and pedigree-based training sets (PBTS) were designed. PAs achieved with BLUPs varied from 0.66 to 0.82 for MW resistance traits, and, for FAW resistance, 0.694 to 0.714 for RBTS of 37%, and 0.843 to 0.844 for RBTS of 85%, and, these were at least two-fold those from BLUEs. For PBTS, FAW resistance PAs were generally higher than those for RBTS, except for one dataset. GP models generally showed similar PAs across individual traits whilst the TS designation was determinant since a positive correlation (R=0.92***) between TS size and PAs was observed for RBTS and, for the PBTS, it was negative (R=0.44**). This study pioneers the use of GS for maize resistance to insect pests in sub-Saharan Africa.

This comprehensive review explores the advancements in processing-in-memory (PIM) techniques for deep learning applications. It addresses the challenges faced by monolithic chip architectures and highlights the benefits of chiplet-based designs in terms of scalability, modularity, and flexibility. The review emphasizes the importance of dataflow-awareness, communication optimization, and thermal considerations in designing PIM-enabled manycore architectures. It discusses different machine learning workloads and their tailored dataflow requirements. Additionally, the review presents a heterogeneous PIM system for energy-efficient neural network training and discusses thermally efficient dataflow-aware monolithic 3D (M3D) NoC architectures for accelerating CNN inferencing. The advantages of TEFLON (Thermally Efficient Dataflow-Aware 3D NoC) over performance-optimized SFC-based counterparts are highlighted. Overall, this review provides valuable insights into the development and evaluation of chiplet and PIM architectures, emphasizing improved performance, energy efficiency, and inference accuracy in deep learning applications.

This paper introduces an innovative theoretical framework for quantum-inspired data embeddings, grounded in foundational concepts of quantum mechanics such as superposition and entanglement. This approach aims to advance semi-supervised learning in contexts characterized by limited labeled data by enabling more intricate and expressive embeddings that capture the underlying structure of the data effectively. Grounded in foundational quantum mechanics concepts such as superposition and entanglement, this approach redefines data representation by enabling more intricate and expressive embeddings. Emulating quantum superposition encodes each data point as a probabilistic amalgamation of multiple feature states, facilitating a richer, multidimensional representation of underlying structures and patterns. Additionally, quantum-inspired entanglement mechanisms are harnessed to model intricate dependencies between labeled and unlabeled data, promoting enhanced knowledge transfer and structural inference within the learning paradigm. In contrast to conventional quantum machine learning methodologies that often rely on quantum hardware, this framework is fully realizable within classical computational architectures, thus bypassing the practical limitations of quantum hardware. The versatility of this model is illustrated through its application to critical domains such as medical diagnosis, resource-constrained natural language processing, and financial forecasting—areas where data scarcity impedes the efficacy of traditional models. Experimental evaluations reveal that quantum-inspired embeddings substantially outperform standard approaches, enhancing model resilience and generalization in high-dimensional, low-sample scenarios. This research marks a significant stride in integrating quantum theoretical principles with classical machine learning, broadening the scope of data representation and semi-supervised learning while circumventing the technological barriers of quantum computing infrastructure.

Skin cancer is one of the most prevalent cancers worldwide, with an increasing incidence. Skin cancer is typically classified as melanoma or non-melanoma skin cancer. Melanoma, despite being much less common than basal or squamous cell carcinomas, is the most deadly, with nearly 8,300 Americans expected to die from melanoma each year. Biopsies are currently the gold standard in diagnosing melanoma; however, they can be invasive and expensive and inaccessible to lower-income individuals. Currently, suspicious lesions are triaged with image-based technologies, such as dermatoscopy and confocal microscopy. While these techniques are useful, there is wide inter-user variability and minimal training for dermatology residents on how to properly use these devices. The use of artificial intelligence (AI)-based technologies in dermatology has emerged in recent years to assist in the diagnosis of melanoma that may be more accessible to all patients and more accurate than current methods of screening. This review explores the current status of the application of AI-based algorithms in the detection of melanoma, underscoring its potential to aid dermatologists in clinical practice. We will specifically focus on AI’s application in clinical imaging, dermoscopic evaluation, algorithms that can distinguish melanoma from non-melanoma skin cancers, and in-vivo skin imaging devices.

Sacroiliac (SI) joint dysfunction can lead to debilitating pain but can be treated with minimally invasive sacroiliac joint fusion (SIJF). This treatment is commonly performed using 2D fluoroscopic guidance. This makes placing the implants without damaging surrounding neural structures challenging. Virtual surgical planning (VSP) using simulated fluoroscopic images may improve perioperative guidance. This article describes a workflow with VSP in SIJF using simulated fluoroscopic images and evaluates achieved implant placement accuracy. Routinely collected survey data on the added value of VSP were also evaluated. Ten interventions were performed on 10 patients by the same surgeon, comprising 30 implants; the median age was 39 years, and all patients were female. The overall mean implant placement accuracy was 4.9 ± 1.26 mm and 4.0 ± 1.44°. There were no malpositioning complications. The VSP helped the surgeon understand the anatomy and determine the optimal position and length of the implants. The average Likert scale score of the survey was 4.7, suggesting a positive role of VSP for SIJF. Planned positions of the implants could be reproduced in surgery with clinically acceptable accuracy and VSP was a valuable asset for the surgeon.

Classifying spinal tumors can be challenging due to nonspecific clinical and radiological qualities, and a precise biopsy is crucial for an accurate diagnosis and treatment planning. This study aimed to enhance the accuracy and efficiency of spinal biopsies integrating Cone Beam Computed Tomography (CBCT) and magnetic resonance imaging (MRI) modalities using an O-arm CT navigation system. Eighteen patients with diverse spinal lesions underwent 18 biopsies following the Stealth Station navigation system Spine 8 protocol. Preoperative MRI scans were merged with intraoperative CT navigation systems for continuous monitoring during the biopsy process. The combined imaging technique accurately identified the diseased lesion type in all biopsies, demonstrating 100% sensitivity and specificity. In conclusion, combining MRI and CT imaging modalities significantly improved spinal biopsy accuracy and efficiency, differentiating between pathological entities. However, large-scale studies are desired to validate these findings and investigate potential benefits in different clinical scenarios. Although this method requires general anesthesia, its potential profits in avoiding misdiagnosed lesions and decreasing the need for further invasive procedures make it a promising approach for improving spinal biopsy accuracy and efficiency.

Wetlands are one of the crucial natural resources. They provide invaluable biodiversity resources, aid in water quality improvement, support ground water recharge, help in moderating climate change and support flood control. Environment is in the other hand, where we live and something, we are very familiar with our day to day life. Geographic Information Systems (GIS), Remote Sensing and Global Positioning System (GPS) were a useful tool for wetland and environmental change analysis and to improve on the classification accuracy. This study investigates population and environmental change of Jarmet wetland and its surrounding area change analysis over the period of 1972 to 2015. The purpose of this study was to show land use/ land cover change of Jarmet wetland and its surrounding environment over years as a response to population growth. For this purpose, multi-temporal satellite imageries (Landsat MSS 1972, TM1986, ETM+ 2000, 2005 and 2015 and SRTM 2000) were obtained and used for LULC change analysis, elevation analysis and change detection analysis. ERDAS Imagine 2015, ARC GIS 10.5.1, Global Mapper11, ENVI 5.0 and DNR Garmin softwares were used to process the image data and accuracy assessment analysis. The result of LULC showed that there is spatial reduction in wetland, forest, Shrubland and grassland in the period of 43 years (1972-2015) by -1,722.8 ha, -296.2 ha, -1,718.7 ha and -661.9 ha respectively, due to increase in the farmland and plantation area as a response to overpopulation, lack of environmental policy implementation and irresponsible for natural resource degradation. The accuracy assessment of LULC change are done for recent satellite image showed the overall accuracy of 84.06% with Kappa index 75.19% this means this classification is accurately classified and handle greater than 75% of error. Finally, this study suggests that create strictly natural resource conservation law, stopping illegal expansion of farmland, educating society about the value of natural resource especially wetland and create a source of income for society rather than farming.

Electricity demand forecasting plays a significant role in energy markets. Accurate prediction of electricity demand is the key factor to optimize power generation, consumption, saving energy resources, and determining the energy prices. However, integrating energy mix scenarios, including solar and wind power which are highly non-linear and seasonal, into an existing grid increases uncertainty in generation, adds the challenges for precise forecast. To tackle these challenges, state-of-the-art methods and algorithms have been implemented in literature. We have developed Artificial Intelligence (AI) based deep learning models that can effectively handle the information of long time-series data. Based on the pattern of dataset, four different scenarios were developed and two best scenarios were selected for prediction. Dozens of models were developed and tested in deep AI networks. In the first scenario (Scenario1), data for weekdays excluding holidays was taken and in the second scenario (Scenario2) all the data in the basket was taken. Remaining two scenarios, weekends and holidays were tested and neglected because of their high prediction error. To find the optimal configuration, models were trained and tested within a large space of alternatives called hyper-parameters. In this study, an Aritificial Neural Network (ANN) based Feed-forward Neural Network (FNN) showed the minimum prediction error for Scenario1 while a Recurrent Neural Network (RNN) based Gated Recurrent Network (GRU) showed the minimum prediction error for Scenario2. While comparing the accuracy, the lowest MAPE of 2.47% was obtained from FNN for Scenario1. When evaluating the same testing dataset (non-holidays) of Scenario2, the RNN-GRU model achieved the lowest MAPE of 2.71%. Therefore, we can conclude that grouping of weekdays as Senario1 prepared by excluding the holidays provides better forecasting accuracy compared to the single group approach used in Scenario2, where all the dataset is considered together. However, Scenario2 is equally important to predict the demand for weekends and holidays.

: Mistrust, amplified by numerous artificial intelligence (AI) related incidents, has caused the energy and industrial sectors to be amongst the slowest adopter of AI methods. Central to this issue is the black-box problem of AI, which impedes investments and fast becoming a legal hazard for users. Explainable AI (XAI) is a recent paradigm to tackle this challenge. Being the backbone of the industry, the prognostic and health management (PHM) domain has recently been introduced to XAI. However, many deficiencies, particularly lack of explanation assessment methods and uncertainty quantification, plague this young field. In this paper, we elaborate a framework on explainable anomaly detection and failure prognostic employing a Bayesian deep learning model to generate local and global explanations from the PHM tasks. An uncertainty measure of the Bayesian model is utilized as marker for anomalies expanding the prognostic explanation scope to include model’s confidence. Also, the global explanation is used to improve prognostic performance, an aspect neglected from the handful of PHM-XAI publications. The quality of the explanation is finally examined employing local accuracy and consistency properties. The method is tested on real-world gas turbine anomalies and synthetic turbofan data failure prediction. Seven out of eight of the tested anomalies were successfully identified. Additionally, the prognostic outcome showed 19% improvement in statistical terms and achieved the highest prognostic score amongst best published results on the topic.

This paper presents a novel approach to predicting shot accuracy in badminton by analyzing Quiet Eye (QE) metrics such as QE duration, fixation points, and gaze dynamics. We develop a neural network model that combines visual data from eye-tracking devices with biomechanical data such as body posture and shuttlecock trajectory. Our model is designed to predict shot accuracy, providing insights into the role of QE in performance. The study involved 30 badminton players of varying skill levels from the Singapore Swimming Club. Using a combination of eye-tracking technology and motion capture systems, we collected data on QE metrics and biomechanical factors during a series of badminton shots. Key results include: 1. The neural network model achieved 85% accuracy in predicting shot outcomes, demonstrating the potential of integrating QE metrics with biomechanical data. 2. QE duration and onset were identified as the most significant predictors of shot accuracy, followed by racket speed and wrist angle at impact. 3. Elite players exhibited significantly longer QE durations (M = 289.5 ms) compared to intermediate (M = 213.7 ms) and novice players (M = 168.3 ms). 4. A strong positive correlation (r = 0.72) was found between QE duration and shot accuracy across all skill levels. These findings have important implications for badminton training and performance evaluation. The study suggests that QE-based training programs could significantly enhance players' shot accuracy. Furthermore, the predictive model developed in this study offers a framework for real-time performance analysis and personalized training regimens in badminton. By bridging cognitive neuroscience and sports performance through advanced data analytics, this research paves the way for more sophisticated, individualized training approaches in badminton and potentially other fast-paced sports. Future research directions include exploring the temporal dynamics of QE during matches and developing real-time feedback systems based on QE metrics.

The most effective method of determining the coordinates of the railway track axis is mobile satellite measurements. However, there are situations when the satellite signal may be disturbed (due to field obstructions) or completely disappear (e.g. in tunnels). Then the ability to measure the value of the directional angle of a moving rail vehicle using an inertial system comes in handy. The directional angle is determined on a topographic map as the angle between the direction of the vehicle longitudinal axis (or the direction of a tangent to the track axis) and the reference direction, which is the north. The article presents a method for determining the directional angle of a railway line based on appropriate measurement data. The latter should be Cartesian coordinates of the track axis, allowing for the visualization of a given railway route and obtaining a general orientation about its course. The presented proposal for solving the problem refers to the assumptions made in the method of determining the curvature of the railway track axis using the moving chord.

This study examines the activities conducted at the archaeological site of Aptera in Crete, Greece. The research was part of the DIACHRONIC LANDSCAPES International Design Workshop, organized by the CAM (Center for Mediterranean Architecture), TUC (Technological University of Crete School of Architecture), and UNIFE (University of Ferrara Department of Architecture). This article outlines the methods used for data acquisition and processing on a territorial scale, which generated digital outputs necessary for the analysis and design phases of the workshop, as well as for further examination of the results. The collected data, obtained through low-cost aerial photogrammetric surveying and GNSS terrestrial coordinate detection, were integrated in a Structure from Motion workflow that led to the creation and exportation of various digital outputs, such as point clouds, DTM, DSM, orthophotos, and contour lines. An accuracy analysis was performed to evaluate the effectiveness and efficiency of the digital models compared to the implemented surveying strategies, including the Ground Control Point and Quality Check Point marker positioning strategy. The resulting digital models proved to be valuable assets for analysis and design within the workshop and provided insightful prospects for future research and territorial-scale projects.

For Visually impaired People (VIPs), the ability to convert text to sound can mean a new level of independence or the simple joy of a good book. With significant advances in Optical Character Recognition (OCR) in recent years, a number of reading aids are appearing on the market. These reading aids convert images captured by a camera to text which can then be read aloud. However, all of these reading aids suffer from a key issue – the user must be able to visually target the text and capture an image of sufficient quality for the OCR algorithm to function – no small task for VIPs. In this work, a Sound-Emitting Document Image Quality Assessment metric (SEDIQA) is proposed which allows the user to hear the quality of the text image and automatically captures the best image for OCR accuracy. This work also includes testing of OCR performance against image degradations, to identify the most significant contributors to accuracy reduction. The proposed No-Reference Image Quality Assessor (NR-IQA) is validated alongside established NR-IQAs and this work includes insights into the performance of these NR-IQAs on document images.

Fine-needle aspiration cytology (FNAC) is a pivotal diagnostic tool in oncology, utilized for evaluating suspicious lesions and stratifying tumors. The incorporation of machine learning (ML) into FNAC has revolutionized accuracy, efficiency, and diagnostic precision. This comprehensive review explores recent advances in FNAC, emphasizing the transformative role of ML in image-guided sample collection and tumor stratification. Leveraging deep learning and other ML algorithms, researchers have improved diagnostic accuracy, minimized unnecessary biopsies, and optimized treatment selection. This article highlights the transformative applications of machine learning in FNAC while addressing its current limitations and future potential.

The use of Light Amplification by Stimulated Emission of Radiation (i.e., LASERs or lasers) by the U.S. Department of Defense is not new and includes laser weapons guidance, laser-aided measurements, even lasers as weapons (e.g., Airborne Laser). Lasers in support of telecommunications is also not new. The use of laser light in fiber optics shattered thoughts on communications bandwidth and throughput. Even the use of lasers in space is no longer new. Lasers are being used for satellite-to-satellite crosslinking. Laser communication can transmit orders-of-magnitude more data using orders-of-magnitude less power and can do so with minimal risk of exposure to the sending and receiving terminals. What is new is using lasers as the uplink and downlink between the terrestrial segment and the space segment of satellite systems. More so, the use of lasers to transmit and receive data between moving terrestrial segments (e.g., ships at sea, airplanes in flight) and geosynchronous satellites is burgeoning. This manuscript examines the technological maturation of employing lasers as the signal carrier for satellite communications linking terrestrial and space systems. The purpose of the manuscript is to develop key performance parameters (KPPs) to inform U.S. Department of Defense initial capabilities documents (ICDs) for near-future satellite acquisition and development. By appreciating the history and technological challenges of employing lasers rather than traditional radio frequency sources for satellite uplink and downlink signal carrier, this manuscript recommends ways for the U.S. Department of Defense to employ lasers to transmit and receive high bandwidth, large-throughput data from moving platforms that need to retain low probabilities of detection, intercept, and exploitation (e.g., carrier battle group transiting to a hostile area of operations, unmanned aerial vehicle collecting over adversary areas). The manuscript also intends to identify commercial sector early-adopter fields and those fields likely to adapt to laser employment for transmission and receipt.

Objective: The primary objective of this study was to develop a logistic regression model to predict post-operative in-hospital mortality rates for patients undergoing emergency cardiac surgeries, with the aim of improving predictive accuracy over traditional risk assessment tools and enhancing patient outcomes and clinical decision-making. Methods: Data were collected from 4,855 patients who underwent emergency cardiac surgeries at a tertiary hospital between 2008 and 2017. The analysis incorporated demographic, anthropomet- ric, and clinical factors, including the ASA classification, emergency status, and various preoperative laboratory values. A logistic regression model was developed, and the Elixhauser Comorbidity Index was calculated using standard ICD-10 codes for its comprehensive assessment of comorbidities. Model performance was evaluated using metrics such as AUROC, AUPRC, accuracy, precision, recall, and F1 score. Results: The logistic regression model demonstrated strong predictive performance, with an AUROC of 0.939 and an AUPRC of 0.350. Key pre-operative factors identified included emergency operation status, ASA classification, and preoperative prothrombin time. The model significantly outperformed the traditional ASA classification system, which showed an AUROC of 0.524 and an AUPRC of 0.010. These findings suggest a substantial improvement in predicting post-operative mortality. Conclusion: The logistic regression model significantly improves the prediction of post-operative mortality in emergency cardiac surgeries compared to the ASA classification system. These findings highlight the potential of incorporating comprehensive pre-operative factors into predictive models to enhance clinical decision-making and patient outcomes. Implementing such models in routine clinical practice could lead to more accurate risk assessments, better resource allocation, and improved patient care.

The Mediterranean basin is a hot spot of climate change where the Posidonia oceanica (L.) Delile (PO) and other seagrass are under stress due to its effect on marine habitats and the rising influence of anthropogenic activities (tourism, fishery). The PO and seabed ecosystems, in the coastal environments of Pantelleria and Lampedusa, suffer additional growing impacts from tourism in synergy with specific stress factors due to increasing vessel traffic for supplying potable water, fossil fuels for electrical power generation. Earth Observation (EO) data, provided by high resolution (HR) multi/hyperspectral operative satellite sensors of the last generation (i.e. Sentinel 2 MSI and PRISMA) have been successfully tested, using innovative calibration and sea truth collecting methods, for monitoring and mapping of PO meadows under stress, in the coastal waters of these islands, located in the Sicily Channel, to better support the sustainable management of these vulnerable ecosystems. The area of interest in Pantelleria was where the first prototype of the Italian Inertial Sea Wave Energy Converter (ISWEC) for renewable energy production was installed in 2015, and sea truth campaigns on the PO meadows were conducted. The PO of Lampedusa coastal areas, impacted by ship traffic linked to the previous factors and tropicalization effects of Italy southernmost climate change transitional zone, was mapped through a multi/hyper spectral EO-based approach, using training/testing data provided by side scan sonar data, previously acquired. Some advanced machine learning algorithms (MLA) were successfully evaluated with different supervised regression/classification models to map seabed and PO meadow classes and related Leaf Area Index (LAI) distributions in the areas of interest, using multi/hyperspectral data atmospherically corrected via different advanced approaches.