This article explores the intricate functioning of the human brain, highlighting how it operates near a critical state to optimize memory storage, adaptability, and the generation of thoughts. Through complex, fractal-like neural networks and brain waves, the brain largely governs our actions via subconscious processes, allowing for rapid, automated responses while reserving conscious thought for novel or complex tasks. Reasoning and planning emerge from the interplay of episodic memory and various neural networks such as Default Mode Network (DMN), Salience Network (SN), and Executive Network (EN), guiding decisions and actions. The "self" and “consciousness” are portrayed as functional illusions, which is being continuously constructed by dynamic neural activity, while free will is examined as a deterministic illusion shaped by prior neural states. We have argued that the brain's response to the physical world is a blend of subconscious automation and conscious sensory processing, thus, reality navigating through an evolving neural plasticity that promotes creativity and the illusion of a coherent, freely acting self. We discuss how does the mind select what to think about, how does it begin? Online and offline state of mind. We address what is an intelligence, understanding, creativity. We propose individual neuronal cells might store information beyond synaptic changes, the pathways through which neuronal thoughts propagate and Darwinian-like evolution of thoughts in minimizing surprises. We have drawn some parallels between the human brain and Large Language Model (LLM) like ChatGPT in terms of their functional roles.

Objective: Scaphoid fractures, particularly occult and non-displaced fractures, are difficult to detect using traditional X-ray methods due to their subtle appearance and variability in bone density. The study proposes a two-stage CNN approach to detect and classify scaphoid fractures using anterior-posterior (AP) and lateral (LA) X-ray views for more accurate diagnosis. Methods: The study emphasizes the use of multi-view X-ray images (AP and LA views) to improve fracture detection and classification. The multi-view fusion module helps integrate information from both views to enhance detection accuracy, particularly for occult fractures that may not be visible in a single view. The proposed method includes two stages that are stage 1: Detect the scaphoid bone using Faster R-CNN and Feature Pyramid Network (FPN) for region proposal and small object detection. The detection accuracy for scaphoid localization is 100% with Intersection over Union (IoU) scores of 0.8662 for AP views and 0.8478 for LA views. And stage 2: Perform fracture classification using a ResNet backbone and FPN combined with a multi-view fusion module to combine features from both AP and LA views. This stage achieves a classification accuracy of 89.94%, recall of 87.33%, and precision of 90.36%. Results: The proposed model performs well in both scaphoid bone detection and fracture classification. The multi-view fusion approach significantly improves recall and accuracy in detecting fractures compared to single-view approaches. In scaphoid detection, both AP and LA views achieved 100% detection accuracy. In fracture detection, using multi-view fusion, the accuracy for AP views reached 87.16%, and for LA views, it reached 83.83%. Conclusion: The multi-view fusion model effectively improves the detection of scaphoid fractures, particularly in cases of occult and non-displaced fractures. The model provides a reliable, automated approach to assist clinicians in detecting and diagnosing scaphoid fractures more efficiently.

Physics is imagined in the human brain which was formed in Darwin's Evolution by responding to certain threats for the survival of our evolutionary ancestors. The struggle to survive prevented us from wasting resources by paying attention to parts of reality that had no survival impact. These parts are of unknown scope and dimension. Can we negotiate this Darwin's barrier? As to reality within our reach, we suffer from imbalance between information absorption capacity and information analysis capacity which resulted in ignoring the overflow of information to match human capacity to make sense of it. Also James Clerk Maxwell suggested that reality has small scale phenomena beyond our human reach. Since we have no brain other than what Darwin equipped us with, this barrier looked unsurmountable. But lo and behold: much as we have built vehicles to carry us further than our biological legs, so we now build artificial intelligence machines that carry us beyond our Darwinist barrier. Physics may transform to building AI capability to ride on. This capability may require a more universal geometry and material representation to fit AI inference engines. Suggesting Depth Unbound Reality Architecture (DURA). AI connects raw data to its conclusion potential, by-passing a storied theory of nature. The objective of physics ahead may be to build theory-replacement AI machines.

Plant diseases not only cause economic losses, but they also pose a health risk. In this regard, aflatoxins are linked to the development of some type of liver cancer, especially the hepatocellular carcinoma. Aflatoxins are usually produced by the fungi Aspergillus flavus and Parsiticus in figs, and their identification is usually carried out using invasive and complex methods or by visual inspection at an advanced stage. Given that Spain is one of the main producers of figs and Extremadura is the leading region in the country, it is necessary to explore alternative ways of detecting the presence of aflatoxins in figs and preventing them from entering the food chain. The aim of this research is to address the early detection of Aspergillus flavus fungus using non-invasive techniques with the aid of hyperspectral imaging and the application of artificial intelligence techniques, in particular deep learning. The images were taken after inoculation of the microtoxin using 3 different concentrations, related to three different classes and healthy figs (healthy controls). The analysis of the hyperspectral images was performed at the pixel level. Firstly, a full connected neural network was used to analyse the spectral signature associated with each pixel; second, the wavelet transform was applied to each spectral signature. The resulting images are fed to a convolutional neural network. The hyperparameters of the proposed models were adjusted based on the parameter tuning process also performed. The results are promising, with 83% accuracy, 82.75% recall and 83.25% F1-measure for the single neural network, and 77.25% accuracy, recall and F1 for the convolution neural network.

In this study, a computational method is proposed that employs Recurrent Convolutional 1 Neural Networks, utilizing meteorological radar images to forecast storm movement and intensity up 2 to 3 hours ahead, a process known as nowcasting. For this purpose, images from a radar situated in 3 southern Brazil were used. These data are publicly accessible on the website of the National Institute 4 for Space Research (INPE) in Brazil. The approach involves evaluating a spatiotemporal learning 5 recurrent convolutional neural network called PredRNN++. The results were validated through 6 case studies of storms within the radar’s coverage area. To evaluate the performance of the neural 7 network, both visual assessments and metrics such as RMSE and SSIM were employed. The findings 8 indicate that PredRNN++ was effective in simulating the shape and location of the meteorological 9 system.

With the urgent need of precise positioning faced by internet of things (IoT) applications, the universality and cost of indoor positioning devices become key factors. Since the 5G network has been widely deployed, new opportunity is brought by tightly fusing the traditional low-cost sensors, i.e., the magnetometer. In this study, using 5G channel state information (CSI) and geomagnetic data, a multi-input convolutional neural network (CNN) localization system was proposed. First, to generate a data tensor that is easy for CNN processing, the raw data was reconstructed individually. Then, to comprehensively incorporate the features of 5G CSI and geomagnetic strength data, the ReLU function was chosen as the activation function of the convolutional layer. After that, a multi-input CNN was trained using the incorporated geomagnetic strength and CSI amplitude in the off-line side, and the trained CNN was recorded as a location fingerprint, which can be used for the user position prediction. Finally, in the online side and using a multi-input CNN, the 2-D coordinates are estimated and tested indoors in a typical conference room scenario. The results showed that longer sampling time of fingerprint data result in better uniqueness of the reference point, while the data collection time of locating points does not need to be long. Taking the positioning efficiency and accuracy into consideration, a sampling time of 3s at the reference point and 0.2s at the locating point are recommended. The positioning accuracy using the proposed method was 1.41 m, with an improvement of 22.9% compared with the 5G positioning, and an improvement of 18.0% compared with the 5G and geomagnetic fusing positioning using single CNN.

A novel approach to optimizing turbomachinery performance is presented in this chapter, which integrates Computational Fluid Dynamics (CFD) simulations, an artificial neural network (ANN) with a modified Non-dominated Sorting Genetic Algorithm II (NSGA-II). Using this enhanced algorithm, substantial performance improvements can be achieved through geometric optimization. The effectiveness of this method is demonstrated in two case studies: an inducer for a centrifugal pump and a Savonius wind turbine. The inducer is designed to maximize head coefficient, hydraulic efficiency, and net positive suction head by optimizing factors such as inlet and outlet blade angles. The optimization process employs the Group Method of Data Handling (GMDH) for objective function modeling, followed by Pareto front plotting and TOPSIS for identifying trade-off optimal points. Results indicate significant improvements in head coefficient, hydraulic efficiency, and NPSHR by 14.3%, 0.3%, and 30.2%, respectively. Twist angle, aspect ratio, and overlap ratio are also optimized for wind turbine blades. The power coefficient is enhanced by 5.32%, the torque coefficient by 13.74%, and the rotational speed by 0.071% through multi-objective optimization. As a result of this approach, efficiency improves, and valuable insights into the optimal design principles for turbomachinery components are also gained.

Detecting people and technical objects in various situations, such as natural disasters and warfare, is critical to search and rescue operations and the safety of the civilian. A fast and accurate detection for people and equipment can significantly increase the effectiveness of search and rescue missions and provide timely assistance to people. Computer vision and deep learning technologies play a key role in detecting the required objects due to their ability to analyse big volumes of visual data in real time. The performance of the neural networks such as YOLOv4-v8, Faster R-CNN, SSD, and EfficientDet has been analysed using COCO2017, SARD, SeaDronesSee, and VisDrone2019 datasets. Main criteria for comparison were mAP, Precision, Recall, F1-Score, and the ability of the neural network to work in real time. The most important metrics for evaluating the efficiency and performance of models for a given task are accuracy (mAP), F1-Score, and processing speed (FPS). These metrics allow us to evaluate both the accuracy of object recognition and the ability to use the models in real-world environments where high processing speed is important. Although different neural networks perform better on certain types of metrics, YOLO outperforms them on all metrics, showing the best results of mAP-0.88, F1 - 0.88, and FPS - 48, so the focus was on these models.

Health management in industrial systems is more critical in maintenance management and it plays an important role in productivity, fault diagnosis, safety, efficiency, and economy in manufacturing industries. Early detection of faults in machinery may increase the effectiveness of maintenance actions and will avoid unwanted consequences in process operations and maintenance. Existing fault diagnosis methods have limitations such as insufficient accuracy, slow detection rate, and handling large and complex data sets. In this digital age, Industry 4.0 techniques have been applied across all fields, including the condition monitoring of machines. This research addresses the gaps in traditional fault diagnosis by using deep learning, a modern AI technique effective for diagnosing faults in various machines. Deep learning algorithms Multilayer Perceptron (MLP), Coevolutionary Neural Network (CNN), and Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) are tested for fault diagnosis using vibration datasets collected from Spectra Quest Machinery Fault Simulator (SQMFS). In this research work, NI-DAQ (National Instruments- Data Acquisition) system, accelerometer, and LabVIEW software are used to collect vibration signals. Preprocessing of the signals has been done using a sampling strategy, shuffling, standardization, and reshaping data augmentation. The result shows that MLP accuracy in the prediction of fault is 0.9, CNN reached 0.95, and RNN and LSTM with 0.57 and 0.45 respectively. The high performance of CNN is due to its ability to effectively capture spatial patterns in vibration data which is crucial for fault diagnosis in rotating machinery followed by MLP due to its faster convergence during training. However, when scaling the data, MLP outperformed CNN, demonstrating superior adaptability to increased data complexity and volume. Due to the need for larger datasets and temporal patterns in the vibration data, which RNN and LSTM are designed to handle, they resulted in a lower accuracy. This study shows that CNN has given better results than other deep learning algorithms MLP, RNN, and LSTM in fault diagnosis of rotating machinery. Future research could explore the application of these techniques to different types of machinery and fault conditions.

Aural rehabilitation with hearing aids can decrease the attentional requirements of cognitive resources by amplifying the deteriorated-frequency sound in hearing loss patients and improve the auditory discrimination ability like speech-in-noise perception. As aural rehabilitation with an intelligible-hearing sound also can be hopeful, the aim of this study was to evaluate the effectiveness of the aural rehabilitation with intelligible-hearing sound for hearing loss patients. Adult native Japanese speakers (17 males and 23 females, 68.43±9.23 years) showed over 30 dB at 125, 250, 500, 1000, 2000, 3000, 4000, 8000, 10000, and 12000Hz on any side, were recruited and underwent Mini-Mental State Examination Japanese. we conducted self-evaluation questionnaire for hearing problems of voice, gap detection test, fast speech test, and speech-in-noise test, pure tone audiogram, speech perception test using Japanese 67-S, cortical auditory evoked fields, and magnetic mismatch negativity before and after the non-intelligible-hearing (N=20) and intelligible-hearing (N=20) sound therapy with listening to music for one hour a day for 35 days. Better hearing ear was defined using a four-frequency pure-tone average at the thresholds of 500, 1000, 2000 and 4000 Hz. After the sound therapy, speech-in-noise test with signal to noise ratio +10 in better hearing ear showed significant improvement (p<0.05), and N1m-P2m amplitudes showed the significant increase in Lt superior temporal gyrus at the stimulus from better hearing ear (p<0.05). The significant enhancement of the magnetic mismatch negativity amplitude at Lt superior temporal gyrus was exhibited after the sound therapy (p<0.01). Intelligible-hearing sound therapy can improve the ability of speech-in-noise perception in better hearing ear and the enhancement of central cortex response, which reflect the ability of working memory, was proved by cortical auditory evoked fields and magnetic mismatch negativity. Intelligible-hearing sound therapy can be a valuable aural rehabilitation method for sensory neural hearing loss as same as hearing aids.

Bearing fault diagnosis is crucial for ensuring the stable operation of mechanical equipment. With the continuous development of deep learning technology, Convolutional Neural Networks (CNNs) have demonstrated significant advantages in the field of fault diagnosis. This paper proposes a new method that combines various CNN architectures to improve the accuracy of bearing fault diagnosis. We designed five different convolutional network structures, including SerConv, ResConv, One-Shot Aggregation Convolution (OSAConv), Cross-Stage Aggregation Convolution (CSAConv), and MD-DAConv. Experimental results on the Case Western Reserve University (CWRU) bearing dataset show that the proposed method exhibits high accuracy and robustness in fault diagnosis. The results indicate that strategies such as multi-directional, multi-scale, and residual connections play a crucial role in enhancing the depth and breadth of feature extraction, while simple and effective feature fusion and information transmission mechanisms are key to ensuring the robustness and generalization ability of the model.

The study compares three machine learning and deep learning models—Support Vector Regression (SVR), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM)—for predicting market prices using the NGX All-Share Index dataset. The models were evaluated using multiple error metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Percentage Error (MPE), and R-squared. RNN and LSTM were tested with both 30 and 60-day windows, with performance compared to SVR. LSTM delivered better R-squared values, with a 60-day LSTM achieving the best accuracy (R-squared = 0.993) when using a combination of endogenous market data and technical indicators. SVR showed reliable results in certain scenarios but struggled in fold 2 with sudden spike that shows high probability of not capturing the entire underlying NGX pattern in the dataset correctly as witnessed with the high validation loss during the period. Additionally, RNN faced the vanishing gradient problem that limits its long-term performance. Despite challenges, LSTM's ability to handle temporal dependencies, especially with the inclusion of On-Balance Volume, led to significant improvements in prediction accuracy. The use of the Optuna optimization framework further enhanced model training and hyperparameter tuning, contributing to the performance of the LSTM model.

This article compares the predictive capabilities of six models namely the Linear Discriminant Analysis (LDA), Logistic Regression (LR), Support Vector Machine (SVM), XGBoost, Random Forest (RF) and Deep Neural Network (DNN) to predict the default behaviour of credit card holders in Taiwan using data from the UCI machine learning database. Python programming language was used for data analysis. Statistical methods were compared with machine learning algorithms using the confusion matrix measured in metric terms of prediction accuracy, sensitivity, specificity, precision, G-mean, F1 score, ROC and AUC. The dataset contains 30,000 credit card user’s information with 6636 default observations and 23,364 non-default cases. The study results found that modern machine learning methods outperformed traditional statistical methods in terms of predictive performance measured by F1 score, G-mean and AUC. Traditional methods like logistic regression were marginally better than linear discriminant analysis and support vector machines in terms of predictive performance measured by area under the receiver operating characteristic curve. In the modern machine learning methods, deep neural networks were better in most of the predictive performance metrics than XGBoost and Random Forest methods.

There are considerable benefits in applying Artificial Intelligence to automation in modern industries including Oil and Gas Industries. Oil and Gas Industries have many complex systems in their production and flow line. The failure of gas equipment will have serious consequences including financial and environmental issues. Condition monitoring of oil and gas equipment provides the condition of components, machines, systems, equipment, data hardware, and even software. The predictive maintenance and industry 4.0 applications have more advantages in petrochemical industries to make a safer economic environment and this paper addresses the Artificial Intelligence (AI) application of condition monitoring for Oil and Gas Industries. To understand the effectiveness of AI in condition monitoring for oil and gas industries, a case study related to the condition monitoring of drilling machine is conducted and applied Artificial Neural Network (ANN) algorithm to analyze and predict the potential failures. The novelty of this work is the proposal of an approach for tool wear monitoring in drilling using acoustic emission sensors for feature extraction and considering wavelet packet decomposition for further analysis. The extracted features from WPD are given as input for ANN to identify the healthiness of the drill bit and machine. This work aims to find the effectiveness of AI-based condition monitoring in enhancing effectiveness of monitoring and the safety of equipment in Oil and Gas Industries.

Artificial neural networks are highly efficient tools for numerous kinds of tasks, which include forecasting, regression, and recognizing patterns in classification and pattern recognition. An artificial neural network is a model for processing information using essential components called artificial neurons that are inspired by the human brain. Two significant aspects of delayed neural networks dynamic activity are their stability and the synchronization phenomenon. This work presents a bidirectional associative memory (BAM) incommensurate fractional-order delay neural network model. The incommensurate fractional orders are calculated within the stability region through the corresponding eigenvalues and their points of equilibrium. The involved neuron states are synchronized with each other for the calculated incommensurate stable fractional orders. The reduction of the time delay will give more relaxation time for the state variable $w_4(t)$ to be stable as compared to the state variable $w_3(t)$ due to the induction of extra activation functions. The theoretical findings of this research have significance for providing guidance and controlling the dynamic behavior of artificial neural networks.

Breast cancer remains a global health problem requiring effective diagnostic methods for early detection in order to achieve WHO’s ultimate goal of breast self-examination (BSE). A literature review indicates the urgency of improving diagnostic methods and identifies thermography as a promising, cost-effective, and non-invasive and adjunctive and complementary detection method. This research explores the potential of using machine learning (ML) techniques, specifically Bayesian Networks (BN) combined with Convolutional Neural Networks (CNN) to improve breast cancer diagnosis at early stages. Explainable artificial intelligence (XAI) aims to clarify the reasoning behind any output of artificial neural networks based models. The proposed integration adds interpretability of the diagnosis, which is particularly significant for a medical diagnosis. We have constructed two diagnostic expert models. In research model A, combining thermal images after XAI process together with medical records, an accuracy of 84.07% has been achieved, while model B, that includes also CNN prediction, achieved an accuracy of 90.93%. These results demonstrate the potential of XAI to transform breast cancer diagnosis, increasing accuracy and reducing the risk of misdiagnosis.

This study investigates the capabilities of high-resolution Sentinel-2 observations and deep learning (DL) segmentation models, specifically convolutional neural networks (CNNs), for accurate mapping of small and fragmented agricultural burn areas in Punjab, India. Initially, the model was trained using ICNF burn area data from Portugal to capture large fire and burn area delineation, achieving moderate accuracy. Subsequent fine-tuning using annotated data from Punjab improved the model’s ability to detect small burn patches, demonstrating higher accuracy and precision than the baseline Normalised Burn Ratio (NBR) Index method. On-ground validation using buffer zone analysis and crop field images confirms the DL approach effectiveness. Cloud interference and temporal gaps in satellite data posed some challenges. Despite these limitations, the study highlights the methodological advancements and potential of using DL models for small burn area detection in agricultural settings. The model achieved overall testing accuracy of 0.64 in Dice score assessment. This report presents a promising approach for improved mapping of the burn area, which might engender better estimation of emissions and the management practices in regions with little available ground truth data.

Recently, deep neural networks (DNNs) have been widely used in various fields such as autonomous vehicles and smart homes. Since these DNNs can be directly implemented on edge devices, they offer advantages such as real-time processing in low-power and low-bandwidth environments. However, deployment of DNNs in embedded systems, including edge devices, exposes them to threats such as fault injection attacks. In this paper, we introduce two methods to induce misclassifications by using clock and voltage glitch-based fault attacks in devices where DNN models are executed. As a result of experiments on a microcontroller implemented with a DNN for image classification, we show that glitch injection attacks can lead with high probability to serious misclassifications. Furthermore, we propose a countermeasure to glitch attacks on the softmax function, and confirm that this method is effective in preventing misclassifications.

The traditional understanding of brain function has predominantly focused on chemical and electrical processes. However, new research in fruit fly (Drosophila) binocular vision reveals ultrafast photomechanical photoreceptor movements significantly enhance information processing, thereby impacting a fly's perception of its environment and behaviour. The coding advantages resulting from these mechanical processes suggest that similar physical motion-based coding strategies may affect neural communication ubiquitously. The theory of neural morphodynamics proposes that rapid biomechanical movements and microstructural changes at the level of neurons and synapses enhance the speed and efficiency of sensory information processing, intrinsic thoughts, and actions by regulating neural information in a phasic manner. We propose that morphodynamic information processing evolved to drive predictive coding, synchronising cognitive processes across neural networks to match the behavioural demands at hand effectively.

Short-circuit blowing is an important technical means to ensure the rapid surfacing of submersible. In order to study the impact of seven multiple manipulation factors of three levels on blowing, a proportional short-circuit blowing model test bench had been built and L18(37) orthogonal experiments were carried out; then, using Back propagation neural network and Pearson correlation analysis, the experimental data were trained and predicted, correlation between individual factor and blowing was further studied as supplement of orthogonal experiments. It had been proved that both multi-factor combination and individual including blowing duration, sea tank back pressure, the gas blowing pressure of the cylinder group, and sea valve flowing area had larger influence, whose correlation coefficients were 0.6535, 0.8105, 0.5569, 0.5373, of which the F-ratio of blowing duration is over critical value 3.24. And statistical evaluation indicators of Back propagation neural network were between 10e-2 and 10e-13, relative error was less than 3%, and prediction error accuracy was 100%. Based on the results above, a reasonable prediction method for submersible short-circuit blowing had been formed and suggestions on engineering design and operations were proposed, including advantage of short-circuit blowing method, initial condition settings and manipulation strategy.

The article focusses on detecting the unbalance of a mechanical component in the electric drive system of a two-mass servomechanism with a PMSM motor, which is connected to the load via a long, flexible shaft. In the example analysed, the degree of unbalance was determined using the reference current signal from the speed controller of the FOC control system. The authors pre-sented a two-mass model with an unbalanced mechanical system. The STFT transform was used to analyse the symptoms of unbalance and an artificial neural network MLP was used for system state inference. The effectiveness of the presented analysis, based on the reference current signal from the sensor embedded in the control system, was experimentally confirmed.

This paper explores how smart cities can cope with land subsidence and liquefaction in the context of rapid urbanization in Japan. Since the 1960s, liquefaction has become an important topic in geotechnical engineering, and great efforts have been made to evaluate the resistance of soil to liquefaction. There is currently a lack of machine learning applications specifically for smart cities in areas such as geological hazards. This study uses two machine learning techniques, artificial neural networks and ensemble learning, to obtain a prediction model with high performance in predicting the bearing layer depth to improve the accuracy of geo-engineering surveys. The model was developed by analyzing actual survey data from 433 locations in Setegaya, Tokyo, by using artificial neural networks (ANNs) and bagging, respectively. The results show that machine learning has great advantages in predicting the bearing layer depth. In addition, compared with a single model such as artificial neural networks, the prediction performance of ensemble learning can be improved by about 20%. Both interdisciplinary approaches can help predict address risks and thus promote sustainable urban development, highlighting the potential of smart cities in the future.

Late-onset Alzheimer’s disease (LOAD) is a dementia category disease that starts after the age of 65. Progressive problems in thinking, behaviour, learning etc. are its characteristics. Due to its progressive nature, early diagnosis is crucial. A complex pathway mechanism with different risk factors is involved in LOAD progression. A comprehensive study is done on factors causing LOAD, biomarkers used for diagnosis in clinical and preclinical stage of the disease, ML (Machine Learning) techniques to identify disease stage. We reviewed research papers on clinical and preclinical diagnosis of LOAD using ML techniques from biomarker data: MRI, PET image, MMSE, Genome / Gene expression, DNA / RNA binding sites with protein, Epigenetic expression /DNA, methylation, Speech and text. We have listed improvement scope after finding the gaps and scope of using Generative AI and SMOTE (Synthetic Minority Oversampling Technique) for data augmentation. At the end, we have elaborated current use of DL (Deep Learning) and CNN (‘Convolution Neural Network’) in Alzheimer’s disease (AD) diagnosis.

Software is increasingly vital, with automated systems regulating critical functions. As development demands grow, manual code review becomes more challenging, often making testing more time-consuming than development. A promising approach to improving defect detection at the source code level is the use of artificial intelligence combined with natural language processing (NLP). Source code analysis, leveraging machine-readable instructions, is an effective method for enhancing defect detection and error prevention. This work explores source code analysis through NLP and machine learning, comparing classical and emerging error detection methods. To optimize classifier performance, metaheuristic optimizers are used, and a modified algorithm is introduced to meet the study’s specific needs. The proposed two-tier framework uses a convolutional neural network (CNN) in the first layer to handle large feature spaces, with AdaBoost and XGBoost classifiers in the second layer to improve error identification. Additional experiments using Term Frequency-Inverse Document Frequency (TF-IDF) encoding in the second layer demonstrate the framework’s versatility. Across five experiments with public datasets, the CNN achieved an accuracy of 0.768799. The second layer, using AdaBoost and XGBoost, further improved these results to 0.772166 and 0.771044, respectively. Applying NLP techniques yielded exceptional accuracies of 0.979781 and 0.983893 from the AdaBoost and XGBoost optimizers.

Pedestrian object detection plays a significant role in intelligent systems such as intelligent traffic and monitoring. Traditional machine learning methods on pedestrian detection have shown various drawbacks, e.g., low accuracy, slow speed, etc. The Convolutional Neural Network (CNN) based object detection algorithms have demonstrated remarkable advantages in the field of pedestrian detection. However, the mainstream CNNs still face the problems of slow speed and low detection accuracy, especially on small and occluded targets from aerial perspective. In this paper, we propose Multi-Scale Attention YOLO (MSA-YOLO) detection algorithm to address the above issues. MSA-YOLO includes a Squeeze, Excitation and Cross Stage Partial (SECSP) channel attention module for CNNs to extract richer pedestrian features with a small number of extra parameters. It also contains a multi-scale prediction module to capture the information among different pedestrian scales, which can recognize the small objects with higher accuracy and significantly reduce the missed detection. To sufficiently evaluate our proposed model, we manually collect and annotate a new benchmark dataset, Aerial Pedestrian Dataset, which has much more sample annotations, features, scenes and image view angles than the existing benchmark datasets. In addition, the images in our dataset have higher resolution than most of benchmark pedestrian detection datasets, which can provide more detailed features of pedestrians and thus improve the model performance. When tested on Aerial Pedestrian Dataset, our proposed MSA-YOLO algorithm significantly outperforms the most used baseline models with almost the same model size. This shows the efficiency of our proposed model. (The code and new dataset will be released to the public later.)

This paper proposes a novel hybrid control strategy for quadrotor unmanned aerial vehicles (UAVs) based on bio-inspired neural dynamics. This strategy addresses the velocity jump issue prevalent in traditional backstepping control and the control signal chattering problem common in traditional sliding mode control. The control system comprises an outer-loop bio-inspired backstepping controller and an inner-loop bio-inspired sliding mode controller, ensuring smooth trajectory tracking even in the presence of external disturbances. The stability of the quadrotor UAV control system is rigorously analyzed using Lyapunov stability theory. Extensive comparative simulation experiments are conducted to assess the robustness and effectiveness of the control system. Results demonstrate superior trajectory tracking performance of the proposed control system compared to other control systems for quadrotor UAVs.

Electric vehicles are in focus and growing, with new adoptions every day. Its wide use represents a new scenario and challenge for the electrical power system due to the high charge storage requirements. Predicting these loads using artificial neural networks proves to be a very efficient tool for solving time series. This work uses a multilayer perceptron network through supervised backpropagation training with Bayesian regularization to improve generalization, reducing overfit- ting errors. In this research, the aggregation of the actual consumption of 200 homes and 348 plug-in electric vehicles is used in the training and forecasting process, and to validate the method developed, MAPE was used. Short-term forecasts were made considering the year’s four seasons, predicting the next 24 hours of total aggregate demand from homes and vehicles. The methodology presented significant and relevant results using hybrid training for the problem, with the potential to be applied in the real world.

In this study, we consider the valuation of rainbow options using unsupervised machine learning methods. In particular, we consider the pricing of multi-asset (rainbow) European and American options, using Physics Informed Neural Net- works (PINNS). After developing the PINNS architecture, we benchmark the method by using it to price vanilla and exotic options with one and two un- derlying assets. We then use the methodology to price a multi-asset European option, followed by the pricing of the multi-asset American option by solving the linear complementarity problem. We compare our results to those obtained using preexisting numerical methods and note excellent agreement. Unlike con- ventional numerical methods, we note that this methodology does not suffer from the ’curse of dimensionality’. The time complexity of our method is con- siderably less than that of the conventional techniques. Thus PINNS may offer a faster more efficient solution to the pricing of rainbow options.

In modern agriculture, decision-making is deeply intertwined with data, yet essential agricultural knowledge remains encased within dense scientific texts such as journals, manuals, and free-text reports. This necessitates specialized search systems capable of distilling and delivering precise information in response to specific queries from agricultural users. This study introduces AgriQuery, a sophisticated agent designed to field natural language questions from the agricultural sector by exploring vast troves of scientific documents. A comprehensive review and analysis of farmers' information needs have been conducted, leading to the creation of an information retrieval test collection that includes actual queries, a vast array of scientific documents segmented into passages, and a set of ground truth relevance assessments that map these passages to corresponding queries. We explore and benchmark several information retrieval models, highlighting the efficacy of advanced neural ranking models in this context. AgriQuery's proposed deployment architecture features a client interface on the Telegram platform and a backend model on standard hardware. This test collection aims to catalyze further research into matching natural language queries with scientific text answers, with implications extending beyond agriculture.

We explore the integration of smart pixel light modulators (SPLMs) into bidirectional optical neural networks (BONNs), highlighting their advantages over traditional spatial light modulators (SLMs). SPLMs enhance BONN performance by enabling faster light modulation in both directions, significantly increasing the refresh rate of neural network weights to hundreds of megahertz, thus facilitating the practical implementation of the backpropagation algorithm and two-mirror-like BONN structures. The architecture of an SPLM-based BONN (SPBONN) features bidirectional modulation, simplifying hardware with electrical fan-in and fan-out. Scalability limitations of the projection system restrict input and output array sizes but achieve high throughput, up to 4.3 × 10¹⁷ MAC/s with 100 layers. Energy assessments showed that the SPLM array, despite its higher power consumption compared to the SLM array, is manageable via effective heat dissipation. Smart pixels with programmable memory in the SPBONN provide a cost-effective solution for expanding network node size and overcoming scalability limitations without the need for additional hardware.

Stock price prediction has long been a critical area of research in financial modeling. The inherent complexity of financial markets, characterized by both short-term fluctuations and long-term trends, poses significant challenges in accurately capturing underlying patterns. While Long Short-Term Memory (LSTM) networks have shown strong performance in short-term stock price prediction, they struggle with effectively modeling long-term dependencies. In this paper, we propose an advanced stock price prediction model based on the Extended Long Short-Term Memory (xLSTM) algorithm, designed to enhance predictive accuracy over both short and long-term periods. We conduct extensive experiments by building and evaluating models based on xLSTM and LSTM architectures for multiple stocks. Our results demonstrate that the xLSTM model consistently outperforms the LSTM model across all stocks and time horizons, with the performance gap widening as the prediction period extends. The observations underscore the superior capability of the xLSTM-based model to capture long-term patterns in financial data, offering a promising approach for more accurate and reliable stock price predictions.

Reconstructing 3D indoor scenes from 2D images has always been an important task in computer vision and graphics applications. For indoor scenes, traditional 3D reconstruction methods suffer from the lack of surface details, poor reconstruction of large flat surface textures and areas with uneven lighting, and many falsely reconstructed floating debris noises in the reconstructed models. We add adaptive normal priors to the neural implicit reconstruction process to optimize the network, and improve the accuracy of volume density prediction by adding regularization terms to the neural radiation field to constrain the volume density obtained by weight distribution, and learn a smooth SDF surface from the network to obtain an explicit mesh model. Experiments show that the method proposed in this paper outperforms the state-of-the-art methods on ScanNet, Hypersim, and Replica datasets.

Real time condition monitoring and precision health assessment system is a mandatory need for effective maintenance program in industrial sector. Rapid advancement in the information technology and other engineering technologies have invited more proactive attention from research and development in industrial sectors and particularly in condition monitoring of machines and related Industrial processes. In this work, drill bit condition monitoring techniques have been developed based on wavelet analysis and artificial neural networks (ANN) for automatic drill bit fault detection and classification. An experimental work has been conducted to capture the vibration signals for analysis. In this experiment, the CNC drill machine is used with high carbon steel drill bit and mild steel material as work piece. The cutting condition parameters are kept constant and the wear level is varied from 0.2 to 0.6 mm. The Data Acquisition system (DAQ) with Lab VIEW software is used to capture the vibration signals for drill bit with different wear conditions using accelerometer. The captured vibrations data are analyzed using continuous wavelet transform (CWT) with Morlet wavelet and Daubechies wavelet as a prime function. In general, the CWT coefficient is used to generate the inputs features to ANN for automatic tool condition classification, with two outputs (0, 1) for healthy and (1, 0) for faulty. The outcome of ANN showed 98% of accuracy in the wear prediction and this results show the effectiveness of the combed WT and ANN for automatic classification of tool wear conditions with high success rate.

Endogenous bioelectrical patterns are an important regulator of anatomical pattern during embryogenesis, regeneration, and cancer. While there are three known classes of instructive bioelectric patterns: directly encoding, indirectly encoding, and binary trigger, it is not known how these design principles could be exploited by evolution and what their relative advantages might be. To better understand the evolutionary role of bioelectricity in anatomical homeostasis, we developed a neural cellular automaton (NCA). We used evolutionary algorithms to optimize these models to achieve reliable morphogenetic patterns driven by the different ways in which tissues can interpret their bioelectrical pattern for downstream anatomical outcomes. We found that: (1) All three types of bioelectrical codes allow the reaching of target morphologies; (2) Resetting of the bioelectrical pattern and the change in duration of the binary trigger alter morphogenesis; (3) Direct pattern organisms show an emergent robustness to changes in initial anatomical configurations; (4) Indirect pattern organisms show an emergent robustness to bioelectrical perturbation; (5) Direct and indirect pattern organisms show an emergent generalizability competency to new (rotated) bioelectrical patterns; (6) Direct pattern organisms show an emergent repatterning competency in post-developmental-phase. Because our simulation was fundamentally a homeostatic system seeking to achieve specific goals in anatomical state space, we sought to understand the role of anxiolytics that reduced concern over the distance to those goals. We simulated selective serotonin reuptake inhibitors, which diminished ability of artificial embryos to correctly interpret bioelectric patterns due to an altered organismal reward machinery, leading to higher variance of developmental outcomes, global morphological degradation, and induced in some organisms anatomical bistability. These computational findings were validated by data collected from in vivo experiments in SSRI exposure in planarian flatworm regeneration.

Drug development is a lengthy process with a high failure rate. Increasingly, machine learning is utilized to facilitate the drug development processes. These models aim to enhance our understanding of drug characteristics, including their activity in biological contexts. However, a major challenge in drug response (DR) prediction is model interpretability as it aids in the validation of findings. This is important in biomedicine, where models need to be understandable in comparison with established knowledge of drug interactions with proteins. drGAT, a graph deep learning model, leverages a heterogeneous graph composed of relationships between proteins, cell lines, and drugs. drGAT is designed with two objectives: DR prediction as a binary sensitivity prediction and elucidation of drug mechanism from attention coefficients. drGAT has demonstrated superior performance over existing models, achieving 78\% accuracy (and precision), and 76\% F1 score for 269 DNA-damaging compounds of the NCI60 drug response dataset. To assess the model's interpretability, we conducted a review of drug-gene co-occurrences in Pubmed abstracts in comparison to the top 5 genes with the highest attention coefficients for each drug. We also examined whether known relationships were retained in the model by inspecting the neighborhoods of topoisomerase-related drugs. For example, our model retained TOP1 as a highly weighted predictive feature for irinotecan and topotecan, in addition to other genes that could potentially be regulators of the drugs. Our method can be used to accurately predict sensitivity to drugs and may be useful in the identification of biomarkers relating to the treatment of cancer patients.

Finite element discretizations of problems in computational physics often rely on hand-generated initial mesh and adaptive mesh refinement (AMR) to preferentially resolve regions containing important features during simulation. We propose Adaptnet, a Graph Neural Networks (GNNs) framework for learning mesh generation and adaptation. The model is composed of two GNNs: the first one, Meshnet, learns mesh parameters commonly used in open-source mesh generators, to generate an initial mesh from a Computer Aid Design (CAD) file; while the second one, Graphnet, learns mesh-based simulations to predict the components of an Hessian-based metric to perform anisotropic mesh adaptation. Our approach is tested on structural (Deforming plate - Linear elasticity) and fluid mechanics (Flow around cylinders - steady-state Stokes) problems. Our results show it can accurately predict the dynamics of the system and adapt the mesh accordingly. The adaptivity of the model supports learning resolution-independent dynamics and can scale to more complex state spaces at test time.

The ever-increasing industrialization of certain areas of the planet combined with the simultaneous degradation of the natural environment are alarming phenomena, especially in the field of human health. The concentration of Particulate Matter with an aerodynamic diameter of 2.5μm (PM2.5) and 10μm (PM10), nitrogen oxides (NOx), carbon monoxide (CO), sulfur dioxide (SO2), and ozone (O3) needs constant monitoring, as they consist the main cause for many diseases. Based on the existence of statutory limits, by the World Health Organization (WHO), for the concentration of each of the aforementioned air pollutants, it is considered necessary to develop forecasting systems that will have the ability to correlate the current meteorological data with the concentrations of the above pollutants. In this work, the attempt to predict the air pollutants concentrations in the wider area of Beijing, China, is successfully carried out using artificial neural networks (ANNs) models. In the frame of the specific work, a significant number of ANNs was developed. For this purpose, an open-access meteorological and air pollution database was used. Finally, a statistical evaluation of the developed prognostic models was carried out. Results showed that ANNs present a re-markable prognostic ability in order to forecast the air pollution levels in an urban environment.

Underwater natural gas pipelines constitute critical infrastructure for energy transportation. Any damage or leakage in these pipelines poses serious security risks, directly threatening marine and lake ecosystems and potentially causing operational issues and economic losses in the energy supply chain. Due to the difficulty in detecting deterioration over time and regularly inspecting these submerged pipelines by divers, the use of unmanned underwater vehicles (UUVs) becomes crucial in this field. In this study, an underwater pipeline tracking experiment was carried out by providing autonomous features to a remote-controlled unmanned underwater vehicle. During the tracking of the underwater pipeline, damages were identified, and the locations of these damages were determined. The navigation information of the underwater vehicle, including orientation in the x, y, z axes (roll, pitch, yaw) from a gyroscope integrated with magnetic compass, speed and position information in the three axes from an accelerometer, and the distance to the water surface from a pressure sensor, was integrated into the vehicle. Pre-tests determined the necessary pulse width modulation values for the thrusters of the vehicle, enabling autonomous operation by providing these values as input to the thruster motors. In this study, the vehicle moves in 3D was achived by the vertical thruster of the vehicle was activated to maintain a specific depth, and applying equal force to the vehicle’s right and left thrusters forward movement, while differential force induced deviation angles. In pool experiments, the unmanned underwater vehicle autonomously tracked the pipeline as intended, identifying damages on the pipeline using images captured by the vehicle's camera. The images for damage assessment were processed using a convolution neural network (CNN) algorithm, which is a deep learning method. The position of the damage relative to the vehicle was estimated from the pixel dimensions of the identified damage. The location of the damage relative to its starting point was obtained by combining these two positional pieces of information from the vehicle's navigation system. The all study was performed within the Python environment.

Brain aging in mammals is characterized by morphological and functional changes of neural cells. Macroscopically, this process leading to progressive cerebral volume loss and functional decline, includes memory and motor neuron defiance and behavioral disorders as well. Morphologically, brain aging is associated with aged neurons and astrocytes, appearing enlarged and flattened, and expressing an enhanced pH-dependent β-galactosidase activity. Multiple mechanisms are considered hallmarks of cellular senescence in vitro. Among them, cell cycle arrest, increased lysosomal activity, telo-mere shortening, oxidative stress and DNA damage. The most common markers for senescence identification were identified in: i) proteins implicated in cell cycle arrest, such as p16, p21, p53 ii) increased lysosomal mass iii) increased reactive oxygen species (ROS) and senescence associated secretory phenotype (SASP) expression. Finally, dys-functional autophagy, a process occurring during aging, contributes to alter brain homeostasis. The aim of this review is to summarize and update the most recent knowledge about brain aging with a comparative approach, where similarities and differences in some mammalian species are considered.

Human Pose Estimation (HPE) is a critical technology in computer vision with diverse applications ranging from healthcare to sports analysis. This project presents a method for detecting the 2D stance of multiple persons in an image using a nonparametric representation known as Part Affinity Fields (PAFs). By leveraging the first 10 layers of the VGG-19 convolutional neural network and training on the COCO dataset, our model effectively identifies and associates key points of the human body.The architecture employs a two-branch system that jointly learns part locations and their associations through sequential prediction. This enables the model to maintain real-time performance while achieving high accuracy, regardless of the number of persons in the image. To enhance accessibility, we developed a mobile application using Flutter and TensorFlow Lite, allowing real-time pose estimation via a mobile device’s front camera. The app provides immediate feedback on physical exercises and yoga poses, making it an invaluable tool for fitness enthusiasts and healthcare professionals. Visual outputs such as heatmaps and PAFs confirm the model’s capability to accurately localize and connect key points. Despite potential challenges such as data quality and hyperparameter tuning, the results indicate that our approach is both reliable and practical for real-world deployment. This project not only advances the state-of-the-art in HPE but also opens up possibilities for future enhancements, including integrating 3D pose estimation and applying the technology in augmented and virtual reality applications.

Researchers are dedicated to providing effective solutions for serious problems such as mental health. This field of study ranges from understanding the impact of mental health ailments on individuals to identifying trends in mental health diseases based on various data points. Unfortunately, the journey from diagnosis to receiving a proper mental health regimen is costly and inaccessible to many. This necessitates the introduction of an affordable alternative that enables individuals with internet access to connect to a platform to determine whether they require the services of a mental health professional. Additionally, such a platform can assist mental health professionals in quickly identifying patients with mental health conditions. Our proposed solution leverages hidden trends in data obtained from 700 mental health patients at The local mental hospital in Pakistan. We have used this data to train a machine learning classifier capable of distinguishing between Psychotic and Neurotic disorders. Psychotic disorders are a group of mental health conditions characterized by a loss of touch with reality whereas neurotic disorders are a group of mental health conditions characterized by excessive worry, anxiety, or stress that does not involve a loss of touch with reality. Our model achieved an overall accuracy score of 73%, indicating successful prediction of the correct diagnosis in 73 out of 100 pipeline tests. While these results may not seem significant, an increase in data points would surely allow for further improvements in these results and the overall solution we propose.

Countless disasters have resulted from climate change, causing severe damage to infrastructure and the economy. These disasters have significant societal impacts, necessitating mental health services for the millions affected. To prepare for and respond effectively to such events, it is crucial to understand people's emotions and the life incidents they experience both before and after a disaster strikes. In this case study, we mined the emotions and life incidents expressed on Twitter during the 2017 Hurricane Harvey. Between August 20 and August 30, we collected a dataset of approximately 400,000 public tweets related to the storm. Using a BERT-based model, we predicted the emotions associated with each tweet. Following emotion prediction, we applied various natural language processing techniques to analyze the content of the tweets, aiming to uncover the 'topics' discussed alongside specific 'emotions.' To efficiently identify these topics, we utilized the Latent Dirichlet Allocation (LDA) technique for topic modeling, which allowed us to bypass manual content analysis and extract meaningful patterns from the data. However, rather than stopping at topic identification, we further refined our analysis by integrating Graph Neural Networks (GNN) and Large Language Models (LLM). The GNN was employed to generate embeddings and construct a similarity graph of the tweets, which was then used to optimize clustering. This step ensured that related tweets were accurately grouped together based on their content and context. Subsequently, we used an LLM to automatically generate descriptive names for each event cluster. This advanced approach allowed us to identify and label life incidents automatically, providing a nuanced understanding of the key issues faced by the community during the hurricane. The results revealed significant emotional shifts as the hurricane reached its most devastating phase. These shifts coincided with pressing concerns and demands from the population, such as evacuation plans, animal safety, safety updates, public policy, help requests, flood impacts, and the spread of fake news. By combining GNN and LLM for automatic event name prediction, our study not only mapped out the emotions but also accurately categorized the specific life incidents that were most relevant during the disaster, offering critical insights for disaster preparedness and response strategies.

The finite-time turnpike property describes the situation in an optimal control problem where an optimal trajectory reaches the desired state before the end of the time interval and remains there. We consider a machine learning problem with a neural ordinary differential equation that can be seen as a homogenization of a deep ResNet. We show that with appropriate scaling of the quadratic control cost and the non-smooth tracking term the optimal control problem has the finite-time turnpike property, that is the desired state is reached in the interior of the time interval and the optimal state remains there until the terminal time $T$. This property is useful to achieve a compromise between the depth of the network and the size of the optimal system parameters which we hope will be useful to determine optimal depths for neural network architectures in the future.

Kolmogorov–Arnold Network (KAN) is an emerging interpretable neural network compared to fully black-box MLPs. Recently, emerging works focus on comprehensive and fair comparisons between KAN and MLP in various tasks. However, these works didn't focus on the strongest advantage of KAN: generating symbolic outputs. The ability of KAN to provide scientific insights or even discover new science is under-examined. In this work, we propose several novel metrics to measure how well a KAN performs on symbolic function fitting: R^2-Mean, weighted R^2-complexity loss, and ranking metrics. We also propose a metric to determine mathematical complexity of a target function and evaluate KAN with several functions of different mathematical complexity. Additionally, we also tried inputs with different ranges to find the effect of normalization.

Recently, the destructive impact of wildfires has proliferated; for instance, the August Complex wildfire in 2020 burned around 4% of California's landmass. This has caused increased economic damage and risk to human life. Additionally, climate change is anticipated to increase the severity of wildfires, making it imperative for accurate and efficient detection of wildfires. Machine Learning approaches allow for the automatic detection of wildfires, simultaneously prioritizing accuracy and efficiency, with minimal human intervention, thus decreasing the likelihood of increased economic damage and increasing firefighting responses. Convolutional Neural Networks (CNNs), while showing promise, are often limited by their inability to learn and capture deep spatial dependencies in satellite imagery tasks. In this paper, we propose FlameViT, a novel wildfire detection architecture based on Vision Transformers (ViT). Satellite images are more efficient to obtain and can cover wide areas prone to wildfires. We obtain a dataset of 40K+ satellite images from Canada's Open Government Portal, allowing FlameViT to be optimized to detect wildfires in satellite imagery. FlameViT uses Patch Extractor and Patch Embedding layers, followed by multiple Transformer Encoder layers with Multi-Head Self-Attention and feed-forward neural networks. FlameViT is hyperparameter-tuned and achieves a validation accuracy of 95%, outperforming various baselines in the wildfire detection task. FlameViT shows the power of Vision Transformers for wildfire detection tasks, and in conjunction with the use of satellite imagery, can provide an efficient and accurate way of detecting wildfires.

Deep convolutional neural networks (CNNs) have revolutionised computer vision technology by automatically learning hierarchical representations of image data, leading to state-of-the-art performance in visual recognition tasks. This article presents a comprehensive review of deep CNNs, from their evolution and architectures to the current state-of-the-art research. The review also provides the core concepts and building blocks of CNNs and their concise mathematical representations. Furthermore, it explores applications of deep CNNs in three popular domains, including medical diagnosis, remote sensing, and facial recognition. This review will benefit researchers and practitioners in computer vision and artificial intelligence, as well as industry professionals seeking to leverage the latest advancements in deep learning technologies.

A contemporary technique for calculating seismic risk is earthquake nowcasting (EN), which analyzes the progression of the earthquake (EQ) cycle in fault systems. 'Natural time' is a novel idea of time that serves as the foundation for EN assessment. The earthquake potential score (EPS), which has been discovered to have useful uses regionally and worldwide, is a unique tool EN uses to predict seismic risk. For the estimation of the EPS for the occurrences with the highest magnitude among these applications, we have since 2021 concentrated on Greece territory, applying sophisticated Artificial Intelligence (AI) algorithms, both wise (semi)supervised and unsupervised models, along with a customized dynamic sliding window technique that performs as a stochastic filter able to fine-tune the geo seismic occurrences. Long short-term memory (LSTM) neural networks, random forests, and clustering (geospatial) models are three machine learning techniques that are particularly good at finding patterns in vast databases and may be used to enhance earthquake prediction performance. In this study, we attempt to forecast whether practical Machine-learning and AI/Game-theoretic-based approaches can help predict big earthquakes and the normal future seismic cycle for 6-12 months. Specifically, we focus on answering two questions for a given region: (1) Is there a chance that a significant earthquake—say, one with a magnitude of M ≥ 6.0 will happen in the upcoming year? (2) What is the largest earthquake magnitude predicted in the upcoming year, and with which exact geographic coordinates (GCS)? Our results are quite promising and project a high precision accuracy score (≥ 98%) for seismic nowcasting in terms of four predictive parameters: the approximate (a) latitude, (b) longitude, (c) focal depth, and (d) magnitude of the phenomena.

Image captioning aims at generating meaningful verbal descriptions of a digital image. Our paper focuses on the classic encoder-decoder deep learning model that consists of several components – sub-networks, each performing a separate task that, combined, form an effective caption generator. We investigate image feature extractors, recurrent neural networks, word embedding models, and word generation layers and discuss how each component influences the captioning model’s overall performance. Our experiments are performed on the MS COCO 2014 dataset. The results help design efficient models with optimal combinations of their components.

Interaction between multiple phases especially liquid-gas is one of the most common phenomena in industrial systems. Computer Vision enables modern systems to derive an automated and robust image-processing technique to address this issue. However, diverse experimental conditions still make it a challenging task to overcome. In Deep Learning, instance segmentation has created a niche in various computer vision applications as it aims to provide different instance IDs to objects belonging to the same class. In this paper, we propose a novel approach employing the YOLO (You Look Only Once) an end-to-end deep learning architecture for the detection and segmentation of bubbles in fluid flows. YOLOv5 offers significant improvements in both speed and accuracy compared to its predecessors like YOLOv3. Therefore, we train the YOLOv5 network on a dataset consisting of annotated images representing instances of bubbles across varied fluid flow environments. This paper provides both qualitative and quantitative evaluation of three YOLOv5 networks (small, medium, and extra-large) in detecting and segmenting bubbles with high accuracy and efficiency. Based on the metrics all three YOLOv5 models achieved high precision above 0.98 for bounding box detection and 0.97 for segmentation mask, and high recall value greater than 0.97 for box and 0.96 for mask quality was achieved. The achieved results indicate that the models accurately localize bubbles within the image frame, and distinguish bubble pixels from the background. Also, mean average precision (mAP50-95) consistently exceeds 0.84 across all models for the bounding box and 0.73 for the segmentation mask. The ascertained results emphasize the potential of YOLOv5 architecture as a powerful tool for automated bubble analysis in real-world applications. Our research contributes to advancing the field of deep neural networks in fluid systems and provides a fresh approach for future developments in automated bubble analysis.

In this study a novel approach of designing automatic control systems with the help of AI tools is proposed. Given plant dynamics, expected references, and expected disturbances, design of optimal neural-network based controller is done automatically. Several common reference types are studied including step, square, sine, sawtooth and trapezoid functions. Expected reference-disturbance pairs are used to train the system for finding optimal neural-network controller parameters. A separate test set is used to test the system for unexpected reference-disturbance pairs to show the generalization performance of the proposed system. Parameters of a real DC motor are used to test the proposed approach. Real DC motor’s parameters are estimated using particle swarm optimization (PSO) algorithm. Initially, a proportional-integral (PI) controller is designed using PSO algorithm for finding simple controller’s parameters optimally and automatically. Starting with neural-network equivalent of optimal PI controller, optimal neural-network controller is designed using PSO algorithm for training again. Simulations are conducted with estimated parameters for diverse set of training and test patterns. Results are compared with optimal PI controller’s performance and reported in the corresponding section. Encouraging results are obtained suggesting further research in the proposed direction.

Abstract: The future of transportation is being reshaped by autonomous vehicles (AVs), which promise to revolutionize road safety, accessibility, and environmental sustainability. Central to their evolution are advancements in artificial intelligence (AI), which enable real-time perception, decision-making, and control. This paper explores the future trajectory of AI in AVs, highlighting innovative AI paradigms such as explainable AI, federated learning, and adaptive regulatory frameworks. It delves into the development of sophisticated perception algorithms for environmental understanding, advanced decision-making systems employing reinforcement learning and deep neural networks, and precise control mechanisms through predictive modeling and optimization. By addressing current challenges, including regulatory hurdles and the complexity of AI algorithms, this paper provides a comprehensive outlook on the potential and implications of AV technology. It envisions a future where AI-driven AVs are seamlessly integrated into society, offering profound insights into their impact on transportation and societal dynamics.

Gaussian mixture models (GMMs) are powerful tools specifically suited for problems where data distributions are multi-modal. Inspired by Fourier expansion, we propose a concept called GMM expansion to approximate arbitrary densities. A simple learning method is introduced under this framework. Theoretical and numerical analyses are provided to show that densities under GMM expansion are able to approximate arbitrary densities with certain accuracy. The proposed learning algorithm demonstrates better accuracy and time efficiency compared to classic density approximation methods such as the Expectation Maximization (EM) algorithm and Bayesian variational inference (BVI) for Gaussian mixture models. The proposed framework also shows better accommodation of neural networks. Three neural network applications are built to demonstrate its usability. The accuracy of density estimation in neural networks is reported to be significantly improved in one of the applications. Another application shows that latent variables can be easily turned into random variables. This user-friendly method opens up more possibilities in terms of latent manipulation, embedding techniques, and many other potential uses.

This comprehensive study looks at how operational conditions affect the performance of a novel seven-channel titania ceramic ultrafiltration membrane for the treatment of produced water. A Full factorial design experiment (23) was conducted to study the effect of the cross-flow operating factors on the membrane permeate flux decline and the overall permeate volume. Eleven experimental runs were performed for three important process operating variables: Transmembrane Pressure (TMP), Crossflow Velocity (CFV), and Filtration Time (FT). Steady final membrane fluxes and permeate volumes were recorded for each experimental run. Under the optimized conditions (1.5 bar, 1 m/s, and 2 hours), the membrane performance index demonstrated an oil rejection rate of 99%, a flux of 297 liters/m2·hr (LMH), a 38% overall initial flux decline, and a total permeate volume of 8.14 L. The regression models used for the steady-state membrane permeate flux decline and overall permeate volume led to the highest goodness of fit to the experimental data with a correlation coefficient of 0.999. A Multiple Linear Regression method and an Artificial Neural Network approach were also employed to model the experimental membrane permeate flux decline and analyze the impact of the operating conditions on membrane performance. The predictions of the Gaussian regression and the Levenberg-Marquardt backpropagation method were validated with a determination coefficient of 99 % and a mean square error of 0.07.

In this study, a novel method is proposed to estimate surface-spectral reflectance from camera responses that combines model-based and training-based approaches. An imaging system is modeled using the spectral sensitivity functions of an RGB camera, spectral power distributions of multiple light sources, unknown surface-spectral reflectance, additive noise, and a gain parameter. The estimation procedure comprises two main stages: (1) selecting the local optimal reflectance dataset from a reflectance database and (2) determining the best estimate by applying a neural network to the local optimal dataset only. In stage (1), the camera responses are predicted for the respective reflectances in the database, and the optimal candidates are selected in the order of lowest prediction error. In stage (2), most reflectance training data are obtained by a convex linear combination of local optimal data using weighting coefficients based on random numbers. A feed-forward neural network with one hidden layer is used to map the observation space onto the spectral reflectance space. In addition, the reflectance estimation is repeated by generating multiple sets of random numbers, and the median of a set of estimated reflectances is determined as the final estimate of the reflectance. Experimental results show that the estimation accuracies exceed those of other methods.

This research proposes a near-infrared hyperspectral imaging/two-branch convolutional neural network (NIR-HSI/2B-CNN) algorithmic scheme to detect mango anthracnose of the species Colletotrichum asianum at the early stages of disease development. In the algorithmic model development, root mean square propagation was used as the solver to train the neural network, given 150 epochs. In addition, spectral raw data was preprocessed to transform it into an understandable and efficient format. The optimal classification model was the 2B-CNN model with 1st-derivative preprocessing, achieving an accuracy of 0.94 for the calibration set and 0.71 for the prediction set. The proposed NIR-HSI/2B-CNN scheme could detect anthracnose mangoes since the the first day of inoculation of the spore suspension (i.e., day 0) through to day 3, achieving a moderate classification accuracy. Meanwhile, the accuracy of conventional convolutional neural networks (CNN) were within a range of 0.66-0.67 for the calibration set and 0.55-0.57 for the prediction set. The results indicated that incorporating spatial features in the 2B-CNN modeling enhanced the prediction performance of the algorithm. The proposed NIR-HSI/2B-CNN algorithmic scheme needs refinements to be able to reliably sort mango fruits into those suitable for premium fresh consumption and export without anthracnose and those for domestic consumption or processing. The novelty of this research lies in the use of NIR-HSI and 2B-CNN algorithm to detect plant pathogens at the early stages of disease development. In addition, the new method of natural simulation to deposit the fungal spores onto the mango surface by spraying spore suspension onto the mango surface where the conidia penetrated unaided into the underneath of the mango peel is proposed.

In Brain-Computer Interface Motor Imagery (BCI-MI) systems, Convolutional Neural Networks (CNNs) have traditionally dominated as the deep learning method of choice, demonstrating significant advancements in state-of-the-art studies. Recently, Transformer models with attention mechanisms have emerged as a sophisticated technique, enhancing the capture of long-term dependencies and intricate feature relationships in BCI-MI. This research investigates the performance of EEG-TCNet and EEG-Conformer models, which are trained and validated using various hyperparameters and bandpass filters during preprocessing to assess improvements in model accuracy. Additionally, this study introduces the EEG-TCNTransformer, a novel model that integrates the convolutional architecture of EEG-TCNet with a series of self-attention blocks employing a multi-head structure. The EEG-TCNTransformer achieves an accuracy of 82.97% without the application of bandpass filtering. The source code of EEG-TCNTransformer is available on GitHub.

Standard ANNs lack flexibility when handling corrupted input due to their fixed structure. Spiking Neural Networks (SNNs) can utilize biological temporal coding features, such as noise-induced stochastic resonance and dynamical synapses to increase a model’s performance when its parameters are not optimized for a given input. Using the analog XOR task as a simplified Convolutional Neural Network analog, this paper demonstrates two key results: (1) SNNs solve the problem linearly inseparable in ANN with over 10% improvement in the optimal setting, and (2) in SNNs, the synaptic noise and dynamical synapses compensate for non-optimal parameters, achieving near-optimal results.

This paper explores innovative approaches to determining eigenvalues and eigenvectors through the combination of neural networks and traditional numerical methods. Traditional methods like the Newton-Raphson and Durand-Kerner algorithms are proven effective but often require good initial approximations and can be sensitive to the choice of starting points. In this study, we propose a hybrid approach that uses neural networks to generate better initial approximations, which are then iteratively refined using traditional methods. By combining the pattern recognition power of neural networks with the adaptability of traditional numerical methods, we demonstrate faster convergence and higher accuracy in determining eigenvalues and eigenvectors. Experimental results on various polynomials of different degrees and characteristics show that our hybrid approach outperforms individual methods, providing a more robust and efficient solution.

Large language models (LLMs) have shown impressive performance and versatility. However, their billions of parameters and high computational costs hinder the development of personalized and privacy-preserving AI assistants operating locally on user devices. In this work, we explored the potential of pruning LLMs to create lightweight models suitable for user devices, using the moderate-sized Llama-2 7B model as an example. By adopting a simple yet effective pruning method, we found that up to 60% of the weights in the Llama-2 7B model could be pruned without significantly impairing its language modeling capabilities. Furthermore, despite occasional factual inaccuracies, the pruned model at the sparsity limit generated fluent and helpful answers to daily queries, demonstrating its feasibility of on-device AI assistants. These inaccuracies might originate from forgetting or hallucination due to pruning. We proposed a simple protocol to distinguish between the two mechanisms, as well as future directions to improve the pruned models for local AI assistants.

Accurate measurement of pedaling kinetics and kinematics is vital for optimizing rehabilitation, exercise training, and understanding musculoskeletal biomechanics. Pedal reaction force, the main external force in cycling, is essential for musculoskeletal modeling and closely correlates with lower limb muscle activity and joint reaction forces. However, sensor instrumentation like 3-axis pedal force sensors is costly and requires extensive post-processing. Recent advancements in machine learning (ML), particularly neural network (NN) models, provide promising solutions for kinetic analyses. In this study, an NN model was developed to predict radial and mediolateral forces, providing a low-cost solution to study pedaling biomechanics with stationary cycling ergometers. Fifteen healthy individuals performed a 2-minute pedaling task at two different self-selected (58±5 rpm) and higher (72±7 rpm) cadences. Pedal forces were recorded using a 3-axis force system. The dataset included pedal force, crank angle, cadence, power, and participants' weight and height. The NN model achieved an inter-subject normalized root mean square error (nRMSE) of 0.15±0.02 and 0.26±0.05 for radial and mediolateral forces at high cadence, respectively, and 0.20±0.04 and 0.22±0.04 at self-selected cadence. The NN model's low computational time suits real-time pedal force predictions, matching the accuracy of previous ML algorithms for estimating ground reaction forces in gait.

Emergency departments (EDs) are critical in urgent care, where accurate triage optimizes patient flow and resource allocation. Manual triage faces challenges due to increasing volume and com-plexity. This study compares logistic regression, gradient boosting, neural network, and random forest models in predicting Emergency Severity Index (ESI) triage levels for non-traumatic pa-tients at Lampang Hospital's ED. Using data from January 1, 2023, to April 30, 2024, we ana-lyzed 45,245 complete records. The gradient boosting model achieved the highest accuracy (0.81), significantly outperforming logistic regression (accuracy 0.64). Pain scale, sex, and mean arterial pressure were key predictors. This is the first comparison of these models for ESI triage in a Thai hospital, highlighting their potential to improve triage accuracy and efficiency. Implementing these models could enhance patient outcomes and resource management in ED.

A novel approach is developed to improve the convergence of Physics-Informed Neural Networks (PINNs), aiming to employ them as real-time computational models within the framework of the digital twin for manufacturing processes. This method entails the weighting of physical equations, boundary conditions, and initial conditions to ensure their comparable magnitudes, with power being the chosen quantity in this study. The approach is applied to thermal problems, which are crucial for predicting manufacturing part defects. Different configurations, including complex boundary conditions and complex physics, were tested to assess the model’s robustness. The W-PINN demonstrates good predictions and strong stability compared to the classical PINN.

To improve the current density distribution and electromagnetic performance of air-core inductors, a structural optimization method combining BP neural network and genetic algorithm was proposed for the study of axial and radial spiral multi-winding inductors. The Monte Carlo method was used to extract the structural size samples of the inductors, and the training dataset was obtained through finite element calculation of electromagnetic fields. Based on BP neural networks, nonlinear mapping models between the inductance value, volumetric inductance density, current distribution non-uniformity coefficient, and inductor structural parameters were constructed. The sensitivity analysis of the inductor inductance value affected by structural parameters was conducted through the Sobol index calculation. Using the current distribution non-uniformity coefficient as the fitness function and the volumetric inductance density as the constraint condition, the genetic algorithm was applied to optimize the structural parameters of the inductor globally. The optimization results were verified through finite element comparison. The results show that, under the requirement of satisfying the volumetric inductance density, the current distribution non-uniformity coefficient of AHI type inductor was reduced by 4.57% compared with the best sample in the sampling, while that of RHI type inductor was reduced by 5.33%, demonstrating the practicality of the BP-GA joint algorithm in the structural optimization design of inductors.

In this paper, the neural network is developed for solving the inverse photoacoustic problem aiming to estimate thermo-elastic properties and thickness of a semiconductor sample. The idea was that these sample properties be estimated from the phase characteristic because the phase measurements are more sensitive. The neural network has been trained on a large basis of photoacoustic phases calculated from a theoretical Si n-type model in the range of 20Hz to 20kHz, on which random Gaussian noise has been applied. It is shown that high accuracy and precision could be reached in solving of inverse photoacoustic problem using only phase measurement.

The detection and recognition of tables in image-based documents is a challenging and essential task for automated data extraction and anal- ysis. This paper introduces a methodology that utilizes Convolutional Neural Networks (CNNs) to address this problem. By harnessing the ro- bust visual recognition abilities of CNNs, the proposed method effectively detects and extracts tables from image-based documents. Additionally, an Encoder-Dual Decoder (EDD) architecture is employed to extract the textual content from table cells, enabling the transformation of visual data into structured, machine-readable formats. This structured data is then further processed using a Vector Space Model (VSM)-based language modeling technique for query-based table retrieval. The methodology’s accuracy is assessed by analyzing the spatial relationships between the extracted cells and comparing them against a pre-defined table structure. The results provide an evidence to the effectiveness of the proposed ap- proach, with an impressive 85% accuracy rate and a corresponding error rate of 15%. This accurate extraction and recognition of tables from image-based documents can significantly enhance applications in data analysis, information retrieval, and knowledge extraction.

This paper introduces an innovative approach that enables automated and precise prediction of the steel's chemical composition based on the desired Jominy curve. The microstructure, and in fact the presence of martensite, is decisive for the hardness of the steel, so the study considered the occurrence of this phase at particular distances from the quenched-end of the Jominy sample. Steels for quenching and tempering and case hardening were investigated. With representative collected dataset of hardness values from quenched-end of Jominy specimen, microstructure and chemical composition of steels, the complex regression model was made using supervised artificial neural networks. The balance between cost and required hardenability can be achieved through optimizing the chemical composition of steel. This model of designing steel with required hardenability can be of great benefit in the mechanical engineering and manufacturing industry. The model is verified experimentally.

The success of near-infrared spectroscopy (NIRS) analysis hinges on the precision and robustness of the calibration model. Shallow learning (SL) algorithms like partial least squares discriminant analysis (PLS-DA) often fall short in capturing interrelationships between adjacent spectral variables, and the analysis results are easily affected by spectral noise, which dramatically limits the breadth and depth application of NIRS. Deep learning (DL) methods, with their capacity to discern intricate features from limited samples, are progressively integrated into NIRS. In this paper, two discriminant analysis problems including wheat kernels and Yali pears were used as examples, and several representative calibration models to research the robustness and effectiveness of the model. Additionally, this article proposed a near-infrared calibration model, which is based on gramian angular difference field and coordinate attention convolutional neural networks (G-CACNN). The research results show that, compared with SL, spectral preprocessing has a smaller impact on the analysis accuracy of consensus learning (CL) and DL, and the latter has the highest analysis accuracy in the modeling results of using the original spectrum. The accuracy of G-CACNN in two discrimination tasks is 98.48% and 99.39%, respectively. Finally, This research compared the performance of various models under noise to evaluate the robustness and noise resistance of the proposed method.

This work introduces the mathematical framework of the novel “First-Order Comprehensive Adjoint Sensitivity Analysis Methodology for Neural Ordinary Differential Equations (1st-CASAM-NODE)” which yields exact expressions for the first-order sensitivities of NODE decoder-responses to the NODE parameters, including encoder initial conditions, while enabling the most efficient computation of these sensitivities. The application of the 1st-CASAM-NODE is illustrated by using the Nordheim-Fuchs reactor dynamics/safety phenomenological model, which is representative of physical systems that would be modeled by NODE while admitting exact analytical solutions for all quantities of interest (hidden states, decoder outputs, sensitivities with respect to all parameters and initial conditions, etc.). This work also lays the foundation for the ongoing work on conceiving the “Second-Order Comprehensive Adjoint Sensitivity Analysis Methodology for Neural Ordinary Differential Equations (2nd-CASAM-NODE)” which aims at yielding exact expressions for the second-order sensitivities of NODE decoder-responses to the NODE parameters and initial conditions while enabling the most efficient computation of these sensitivities.

Neural Fractional Differential Equations (Neural FDE) represent a neural network architecture specifically designed to fit the solution of a fractional differential equation to given data. This architecture combines an analytical component, represented by a fractional derivative, with a neural network component, forming an initial value problem. During the learning process, both the order of the derivative and the parameters of the neural network must be optimised. In this work, we investigate the non-uniqueness of the optimal order of the derivative and its interaction with the neural network component. Based on our findings, we perform a numerical analysis to examine how different initialisations and values of the order of the derivative (in the optimisation process) impact its final optimal value. Results show that the neural network on the right-hand side of the Neural FDE struggles to adjust its parameters to fit the FDE to the data dynamics for any given order of the fractional derivative. Consequently, Neural FDEs do not require a unique α value, instead, they can use a wide range of α values to fit data. This flexibility is beneficial when fitting to given data is required, and the underlying physics is not known.

Making sustainable business models, especially in manufacturing, is a key approach for organizations to adopt in order to create more sustainable processes. New technologies are needed to implement new policies that can minimize the economic, environmental, and social consequences of industrial activity. Sustainable maintenance is decisive to guarantee the availability, reliability, and safety of assets, surpassing traditional maintenance policies and embracing the principles of the circular economy. The main objective of Maintenance 4.0 is to increase the lifespan and availability of the equipment by preventing unplanned downtime, reducing planned shutdowns, and improving safety. This research focuses on the integration of advanced Industry 4.0 tools with conventional monitoring and control techniques in process industries. The article suggests that while complex neural networks might provide good predictions, simpler solutions can generalize well and have lower prediction errors because they can capture the underlying relationships between variables in a specific asset better. The combination of maintenance function, Industry 4.0 tools, and advanced statistical solutions to obtain sustainable processes can facilitate organizational change and aid decision-making in equipment management. These solutions seek to reduce interruptions and expenses through the unnecessary utilization of labor and spare parts. All these considerations improve communication and data processing, resulting in improved maintenance of a hydrogen compressor in the petrochemical industry.

Property valuation services using artificial intelligence (AI) have been developed, with more than 20 services available in Japan. However, since their algorithms and training data are not publicly available, the extent of differences in the AI property valuations among these services is not clear. This study focuses on the five services handling a lot of properties and uses a sample of 4,295 property valuations for 859 condominium units in six popular residential areas in Tokyo. (1) Multiple comparison tests of the AI property valuations among each service are conducted to confirm their statistical significance and to examine the degree of the difference and variation. (2) The business models of each service are compared to examine the factors contributing to these differences and variations. The results showed that there was a variation of approximately 0.15 in the coefficient of variation between the high and low valuation groups, and the service providers in the high valuation group guided the users to their sales, while those in the low valuation group focused on attracting users as their business models. The contribution of this study is to indicate the possibility that the business models may lead to the differences in the AI property valuations.

The metaverse is gradually expanding. There is a growing number of photo and video recordings of metaverse virtual worlds being used in multiple domains, with growing collections. An essential element of the metaverse and its recordings are avatars. In this paper, we present a novel task of avatar detection in metaverse recordings, supporting semantic retrieval in collections of metaverse recordings and other use cases. Our work addresses the characterizations and definitions of avatars and presents a new model supporting avatar detection. The latest object detection algorithms are trained and tested on a variety of avatar types in metaverse recordings. Our work achieves a higher level of accuracy than existing models, which encourages further research in this field.

Detailed sonographic assessment of the fetal neuroanatomy plays a crucial role in prenatal diagnosis, providing valuable insights into timely well-coordinated fetal brain development and detecting even subtle anomalies that may impact neurodevelopmental outcomes. With recent advancements in artificial intelligence (AI) in general and medical imaging in particular, there has been growing interest in leveraging AI techniques to enhance the accuracy, efficiency, and clinical utility of fetal neurosonography. The paramount objective of this scoping review is to discuss the latest developments in AI applications in this field, focusing on image analysis, automation of measurements, prediction models for neurodevelopmental outcomes, visualization techniques, and integration into clinical routine.

Recommender Systems (RecSys) are crucial in managing information overload and enhancing user satisfaction across various digital platforms, including e-commerce and entertainment. Evolving from traditional models to Deep Neural Networks (DNNs) and, more recently, Large Language Models (LLMs), these systems leverage sophisticated algorithms to analyze user behaviors and preferences. LLMs, such as GPT-4, are trained on extensive datasets to comprehend and generate natural language, significantly advancing their ability to deliver personalized recommendations. This tutorial explores the transformative impact of LLMs on RecSys, discussing their development, application in handling complex datasets, and the integration of contextual insights. Real-world examples illustrate how LLMs enhance recommendation accuracy and user experience, highlighting challenges and future directions in the field.

Glaucoma, a global leading cause of blindness, necessitates accurate segmentation of the optic disc (OD) and optic cup (OC) for effective screening. However, existing segmentation methods based on convolutional neural networks (CNNs) suffer from high computational complexity and long inference times. In this paper, we propose an end-to-end segmentation method for the OD and OC using a lightweight MobileNetv3 as the feature extraction network. Our approach incorporates boundary branches and an adversarial learning network to achieve multi-label segmentation of the OD and OC. We evaluate the proposed method on three publicly available datasets: Drishti-GS, RIM-ONE-r3, and REFUGE. The experimental results demonstrate segmentation accuracies of 0.974/0.900, 0.966/0.875, and 0.962/0.880 for the OD and OC on the respective datasets, while significantly reducing inference time.

With the rapid development of Intelligent Transportation Systems (ITS), vehicle type classification, as a key link in Automatic Toll Collection systems (ATC), is of great significance in improving traffic efficiency and reducing economic losses. This study proposes an intelligent vehicle classification system based on deep learning and multi-sensor data fusion to address the accuracy issues existing in vehicle classification methods based on optical sensors (OS) and human observers. The system significantly improves the accuracy and robustness of vehicle classification by combining deep Convolutional Neural Networks (CNN), LiDAR sensors, and machine learning algorithms. We first constructed a large-scale annotated dataset containing multiple vehicle types and complex traffic scenes to improve our model's capability to identify different vehicle characteristics. Next, CNN models based on different architectures were designed to extract global and local features of the vehicle, respectively. In addition, the LiDAR sensor was used to achieve the spatial structure architectures of the vehicle and combined with the output of the CNN model to improve classification performance under occlusion and complex scenes.

Geopolymers, made from aluminosilicate raw materials, offer significant environmental advantages over conventional concrete (CC) mixes. This study explores the compressive strength, setting time, and durability of geopolymer concrete (GPC) cylinders, some of which include an additional ordinary portland cement (OPC) mix. Consistent material composition and testing methods are emphasized to achieve reliable results. MATLAB was utilized to develop and assess a neural network model predicting the compressive strength of GPC based on key variables. The model was validated using 16 experimental samples and 1047 samples from various studies. The performance plot displayed the Mean Squared Error (MSE) over iterations, identifying the best training performance at epoch 658 with an MSE of 5.3408. The Error Histogram highlighted distribution errors between predicted and actual compressive strength values, with the highest range from -1.015 to 0.3587, meaning that the predicted values were mostly within a small margin of error from the actual values. This narrow error range indicates that the ANN model has high accuracy in its predictions, as most errors are small and clustered around zero, demonstrating reliable performance in estimating compressive strength. Regression analysis showed varying correlation coefficients (training set R=0.98373, test set R=0.88164, and whole set R=0.96982), indicating adequate predictive accuracy. The results demonstrate that properly trained neural networks can effectively predict the compressive strength of GPC, highlighting its potential as a sustainable construction material.

This paper describes a Long Short-Term Memory (LSTM) neural network model used to simulate the dynamics of the OC3 reference design of a Floating Offshore Wind Turbine Spar unit. It crafts an advanced neural network with an encoder-decoder architecture capable of predicting the Spar’s motion and fairlead tensions time series. These predictions are based on wind and wave excitations across various operational and extreme conditions. The LSTM network, trained on an extensive dataset from over 300 fully coupled simulation scenarios using OpenFAST, ensures a robust framework that captures the complex dynamics of floating platform under diverse environmental scenarios. This framework’s effectiveness is further verified by thoroughly evaluating the model’s performance, leveraging comparative statistics and accuracy assessments to highlight its reliability. This methodology contributes to substantial reductions in computational time. This research aims to provide critical insights that facilitate the optimization of offshore wind turbines, marking a step forward in the quest for more efficient and dependable renewable energy solutions.

Vermicomposting is one of the most important waste management techniques in the process of vermiculture. In this study, a Neural Network-assisted novel paradigm is proposed to predict waste from vermicomposting. The proposed Neural Network Skeleton is based on a Gallium Arsenide Processing Schema, which is used to separate wastes. By comparing the proposed sys-tem with existing methods, it was found that the proposed approach had the highest average prediction ratio of 91.32%, outperforming other techniques like ERD, RNN, and Deep LSTM. The separation ratio analysis also demonstrated the effectiveness of the proposed method, with a range of 45-94%. Furthermore, the study emphasizes the importance of chemical equilibrium and the effectiveness of our proposed Gallium Arsenide Processing Schema in achieving high prediction and separation accuracies, showcasing its potential for practical application in waste management processes. Lastly, the prediction of the process evolution stages is detailed, indicating the efficiency of the proposed system in achieving various levels of waste separation. Overall, the study provides valuable insights into the potential of the proposed methods in op-timizing wastewater management processes, paving the way for more effective and sustainable vermicomposting practices.

This paper presents machine learning methods for approximate solutions of reaction-diffusion equations with multivalued interaction functions. This approach addresses the challenge of finding all possible solutions for such equations, which often lack uniqueness. The proposed method utilizes physics-informed neural networks (PINNs) to approximate generalized solutions.

With prosperous development and successful application of deep learning technologies in the field of remote sensing, numerous deep-learning based methods have emerged for synthetic aperture radar (SAR) automatic target recognition (ATR) tasks over the past few years. Generally, most deep-learning based methods can achieve outstanding recognition performance in condition that an abundant of labeled samples are available to train the model. However, in real application scenarios, it is difficult and costly to acquire and to annotate abundant SAR images due to the imaging mechanism of SAR, which poses a big challenge to existing SAR ATR methods. Thereby, SAR target recognition under the situation of few-shot, where only a scarcely few of labeled samples are available, is a fundamental problem that needs to be solved. In this paper, we put forward a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) to specially tackle the few-shot SAR ATR tasks. To be specific, We first develop a feature extraction network based on a customized and region-aware convolution, which can adaptively adjust convolutional kernels and their receptive fields according to each SAR image’s own characteristics as well as the semantical similarity among spatial regions, thus augmenting its capability to extract more informative and discriminative features. To achieve accurate and robust target identity prediction under the few-shot condition, we then propose an enhanced prototypical network which can improve the representation ability of the class prototype by properly making use of training and test samples together, thus effectively raising the classification accuracy. Meanwhile, a new hybrid loss is designed to learn a feature space with both inter-class separability and intra-class tightness as much as possible, which can further upgrade the recognition performance of the proposed method. Experiments performed on the moving and stationary target acquisition and recognition (MSTAR) dataset and the OpenSARShip dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks.

Accurate and robust deep learning models for facial expression recognition are challenging to achieve, given the diversity of human faces and variations in images, including different facial poses and lighting conditions. In this work, we proposed a clock-driven convolutional Spiking Neural Network (SNN) and STDP fine-tune architecture, meticulously calibrated its hyperparameters, and experimented with various optimization methods. The best model resulted was trained and evaluated on the Fer2013 and FER+ database, obtaining an accuracy of 61.87% and 79.97% without requiring auxiliary training data or face registration. To our best knowledge, the proposed SNN achieved comparable accuracy to CNNs of similar depth and possessed the advantages of low energy consumption and high computational efficiency. The computational efficiency of the proposed SNN is approximately three times that of CNNs. Along with this, we introduced the very recent cumulative spike guided encoder visualization technique and revealed the strong encoding capability of the proposed SNN.

The financial crisis augmented the need to predict real estate prices. The current study examines the application of Artificial Neural Network (ANN) model and Vector Autoregressive (VAR) model in forecasting real estate prices. The study uses daily observations, which accounted for a total of 2955 observations collected. We found that ANN outperformed significantly the VAR model providing evidence that these models can be used for valuation purposes in the area of real estate and financial markets. These findings are novel and important as they provide evidence of the usefulness of more sophisticated methodologies for market participants and regulators in real estate and financial markets.

Accurate forecasting of available energy portion that corresponds to the reservoir inflow of the month(s) ahead provides important decision support for the hydropower plants in energy pro-duction planning for revenue maximization, as well as for the environmental impact prevention, and flood control at the upstream and downstream of a basin. Therefore, a reliable forecasting tool or model is deemed necessary and crucial. Considering the fluctuation and nonlinearity of data which significantly influence the forecasting results, this study develops an effective hybrid model by integrating Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) called “PSO-ANN” model based on the hydrological and meteorological data pre-processed by cross-correlation function (CCF), autocorrelation function (AFC), and normalization techniques for predicting the available energy portion corresponding to the reservoir inflow mentioned above for a case study hydropower plant in Laos namely, Theun-Hinboun hydropower plant (THHP). The model was evaluated by using correlation coefficient (r), relative error (RE), root mean square error (RMSE), and Taylor diagram plots in comparison with the popular single algorithm approaches such as ANN, and NARX models. Results demonstrated the superiority of the proposed PSO-ANN approach over the other two models.

This study presents the Distilled MixUp Squeeze ResNet (DMSResNet), an optimized variant of the Residual Network architecture designed for high accuracy and computational efficiency. By integrating Squeeze-and-Excitation blocks, MixUp data augmentation, and knowledge distillation, it achieves competitive performance within strict parameter constraints and limited training resources. Evaluated on the CIFAR-10 dataset, the model attains a 96.56% accuracy with only 4.3 million total parameters. The results demonstrate that optimization of established architectures can yield performance comparable to newer models, especially in resource-limited scenarios. This work contributes to the development of efficient deep learning models for applications in constrained computational environments.

The symptoms of multiple sclerosis (MS) are determined by the location of demyelinating lesions in the white matter of the brain and spinal cord. Currently, magnetic resonance imaging (MRI) is the most common tool for diagnosing MS, understanding the course of the disease, and analyzing the effects of treatments. However, undesirable components may appear during the generation of MRI, such as noise or intensity variations. Mathematical morphology (MM) is a powerful image analysis technique that helps to filter the image and extract relevant structures. Granulometry is an image measurement tool of MM that determines the size distribution of objects in an image without explicitly segmenting each object. While, several methods have been proposed for the automatic segmentation of MS lesions in MRI, in some cases only simple data preprocessing, such as image resizing to standardize the input dimensions, has been performed before the algorithm training. Therefore, this paper proposes an MRI preprocessing algorithm performing elementary morphological transformations in brain images of MS patients and healthy individuals to delete undesirable components and extract the relevant structures such as MS lesions. Also, the algorithm computes the granulometry in MRI to describe the size qualities of lesions and trains two artificial neural networks (ANN) to predict MS diagnosis. The computing of differences in granulometry measurements of an image with MS lesions and a reference image (without lesions) can determine the size characterization of the lesions. Then, the ANNs were evaluated with the validation set and the performance results (test accuracy = 0.9753, and cross-entropy loss = 0.0247) show the proposed algorithm can support the decision of specialists for diagnosing MS and estimating the disease progress, based on granulometry values.

Temperature and pressure sensors currently encounter challenges such as slow response times, large sizes, and insufficient sensitivity. To address these issues, we developed tetraphenylethylene (TPE)-doped polyvinylidene fluoride (PVDF) nanofiber membranes using electrospinning, with process parameters optimized through a convolutional neural network (CNN). We systematically analyzed the effects of PVDF concentration, spinning voltage, tip-to-collector distance, and flow rate on fiber morphology and diameter. The CNN model achieved high predictive accuracy, resulting in uniform and smooth nanofibers under optimal conditions. Incorporating TPE enhanced the hydrophobicity and mechanical properties of the nanofibers. Additionally, the fluorescent properties of the TPE-doped nanofibers remained stable under UV exposure and exhibited significant linear responses to temperature and pressure variations. The nanofibers demonstrated a temperature sensitivity of -0.976 gray value/°C and pressure sensitivity with an increase in fluorescence intensity from 537 a.u. to 649 a.u. under 600 g pressure. These findings highlight the potential of TPE-doped PVDF nanofiber membranes for advanced temperature and pressure sensing applications.

Machine-learning methods used for classification are challenged by the class imbalance problem, where a certain class is underrepresented. Over/under-sampling the majority/minority class observations or model selection for ensemble methods alone might not be effective if the class imbalance ratio is very high. To address this concern, a novel method is presented for generating synthetic data for minority class observations in conjunction with an optimal tree ensemble classifier (OTEC). This novel synthetic method first generates minority class instances to balance the training data. Then it applies OTEC, where models are selected based on their performance using out-of-bag observations and training subsamples. A total of 20 benchmark problems on binary classification with moderate to extreme class imbalance are used to assess the efficacy of the proposed method against other well-known methods, including optimal tree ensemble, smote random forest, under-sampling random forest, oversampling random forest, k-nearest-neighbor, support vector machine, tree, and artificial neural network, using classification error rate, sensitivity, specificity, precision, recall and F1-score as performance metrics to assess the efficacy of the proposed method. The analyses presented in this study revealed that the proposed method based on data balancing and model selection yielded better results than other methods.

Link prediction is a fundamental problem in graphs. Currently, SubGraph Representation Learning (SGRL) methods provide state-of-the-art solutions for link prediction by transforming the task into a graph classification problem. However, existing SGRL solutions suffer from high computational costs and lack scalability. In this paper, we propose a novel SGRL framework called Augmented Feature Diffusion on Sparsely Sampled Subgraph (AFD3S). The AFD3S first uses a conditional variational autoencoder to augment the local features of the input graph, effectively improving the expressive ability of downstream Graph Neural Networks. Then, based on a random walk strategy, sparsely sampled subgraphs are obtained from the target node pairs, reducing computational and storage overhead. Graph diffusion is then performed on the sampled subgraph to achieve specific weighting. Finally, the diffusion matrix of the subgraph and its augmented feature matrix are used for feature diffusion to obtain operator-level node representations as inputs for the SGRL-based link prediction. Feature diffusion effectively simulates the message-passing process, simplifying subgraph representation learning, thus accelerating the training and inference speed of subgraph learning. Our proposed AFD3S achieves optimal prediction performance on several benchmark datasets, with significantly reduced storage and computational costs.

This small article examines the pivotal roles of redundant and degenerate neural networks in the brain across three critical dimensions: evolutionary development, early childhood neural formation, and their implications in neurological diseases. Redundant networks, characterized by parallel neural pathways with similar functions, provide a foundation for cognitive resilience, ensuring continuity of brain functions despite damage or developmental anomalies. Degenerate networks, comprising structurally varied but functionally equivalent pathways, contribute to cognitive flexibility and adaptability, essential for innovative problem-solving and learning. From an evolutionary perspective, these networks have been instrumental in the brain's adaptation to diverse environmental challenges, facilitating cognitive maximization and the development of complex behaviors. The genetic underpinnings and environmental influences that shaped these networks are explored, highlighting their contribution to the evolutionary success of the human species. In the realm of early childhood development, the formation and reinforcement of these networks are crucial. The brain's plasticity during this period leads to the establishment of robust redundant networks and versatile degenerate networks, shaped significantly by environmental stimuli and learning experiences. This developmental phase lays the groundwork for cognitive abilities and resilience to neurological challenges later in life. Furthermore, the paper delves into the implications of these networks in the context of brain diseases. The disruption of the equilibrium between redundancy and degeneracy is linked to various neurological conditions, including Alzheimer's disease, Parkinson's disease, multiple sclerosis, stroke and Huntington's disease. Understanding the roles and balances of these networks offers insights into the pathophysiology of these diseases and potential therapeutic approaches. This review underscores the significance of redundant and degenerate neural networks in the evolutionary context, their critical formation during early childhood, and their profound impact on brain health and disease. It highlights the need for further research into these networks to enhance our understanding of brain function and to develop targeted interventions for neurological disorders.

The present research project entitled "Development of a method for predicting the optimal maturity level of avocado using machine learning" aims to establish an accurate and efficient approach to assess the maturity of avocados using machine learning methodologies. This research specifically focuses on identifying the relevant physical and chemical characteristics of avocados, creating a dataset containing categorized images of maturity levels, and creating machine learning models capable of accurately predicting fruit maturity. The studies reveal that the application of machine learning, in particular convolutional neural networks and multisensor models, has the potential to transform the prediction of avocado maturity and thus improve product quality and customer satisfaction. The findings indicate that the proposed techniques achieve an accuracy rate of over 90%, demonstrating their viability for integration into mobile applications that can benefit growers and suppliers in their decision-making processes.

Aiming at solving difficulties related to aero-engine classification and identification, the infrared spectra of aero-engine hot jets are measured by telemetry Fourier transform infrared spectrometer, and a six types aero-engine hot jet spectrum data set is generated. The spectrum data set were randomly sampled at a ratio of 8:1:1 to generate training set, validation set and prediction set. In this paper, a Peak Finding Siamese Convolutional Neural Network (PF-SCNN) is designed to match and classify spectrum data. In the first place, the matching pairs of training set and validation set are made independently with the labels of positive and negative samples creating. The spectrum feature extraction and distance similarity calculation are carried out by the Siamese convolutional neural network (SCNN). When entering the prediction phase, the prediction set and training set are integrated to predict in the trained model. The prediction set labels are ultimately determined by matching them with the training set labels having the highest similarities to ensure accurate predictions. To improve the operation efficiency of the SCNN, a peak finding method is introduced to extract the spectrum peaks. Peak positions of high frequency are counted, while the peak data are extracted. The peak data are used to take the place of the original data for training and prediction. The performance measures are defined as Accuracy, Precision, Recall, Confusion matrix and F1-score, and the prediction accuracy was up to 99%. The experimental results indicate that the proposed PF-SCNN is suitable for our spectral dataset and can complete the task of infrared spectrum classification of aero-engine hot jets.

The use of artificial intelligence algorithms (AI) has gained importance for dental applications in recent years. Analyzing using IA information from different sensor data such as images or X-ray radiographs can help to improve medical decisions and to achieve early diagnosis of different dental pathologies. In particular, the use of deep learning (DL) techniques based on convolutional neural networks (CNNs) has obtained promising results in dental applications based on images, in which approaches based on classification, detection, and segmentation are being studied with growing interest. However, there are still several challenges to be tackled, such as the data quality and quantity, the variability among categories, and the analysis of the possible bias and variance associated with each dataset distribution. In this work, we compare three different DL object detection models, which are Faster R-CNN, YOLO V2, and SSD. Each object detection architecture was trained, calibrated, validated, and tested with three different feature extraction CNNs which are ResNet-18, ResNet-50, and ResNet-101, which were the networks that best fit our dataset distribution. Based on such detection networks, we detect four different categories of angles in third molars using X-ray panoramic radiographs by using Winter's classification criterion. This criterion characterizes the third molar's position regarding the second molar's longitudinal axis. The detected categories for the third molars are distoangular, vertical, mesioangular, and horizontal. For training, we used a total of 644 panoramic X-ray images. The results obtained in the testing dataset reached up to 99% mean average accuracy performance, demonstrating the YOLOV2 obtained higher effectiveness in solving the third molar angle detection problem. These results demonstrate that the use of CNNs for object detection in panoramic X-rays represents a promising solution in dental applications.

This study examines the feasibility of using event-related potentials (ERPs) obtained from electroencephalographic (EEG) recordings as biomarkers for long-term memory item classification. Previous studies have identified old/new effects in memory paradigms associated with explicit long-term memory and familiarity. Recent advancements in convolutional neural networks (CNNs) have enabled the classification of ERP trials under different conditions and identification of features related to neural processes at the single-trial level. We employed this approach to compare three CNN models with distinct architectures using experimental data. Participants (N = 25) performed an association memory task while recording ERPs that were used for training and validation of the CNN models. The EEGNET-based model achieved the most reliable performance in terms of precision, recall, and specificity compared with the shallow and deep convolutional approaches. The classification accuracy of this model reached 70% for known items and 62% for unknown items. Good overall accuracy requires a trade-off between recall and specificity and depends on the architecture of the model and the dataset size. These results suggest the possibility of integrating ERP and CNN into online learning tools and identifying the underlying processes related to long-term memorization.

Session-based recommendations which aim to predict subsequent user-item interaction based on historical user behavior during anonymous sessions can be challenging tasks. Two main challenges need to be addressed and improved: (1) How to analyze these sessions to accurately and completely capture users’ preferences, and (2) how to identify and eliminate any interference caused by noisy behavior. Existing methods have not adequately addressed these issues since they either neglected the valuable insight that can be gained from analyzing consecutive groups of items or failed to take these noisy data in sessions seriously and handled them properly, which can jointly impede recommendation systems from capturing users’ real intentions. To address these two problems, we designed a multi-order semantic denoising (MSD) model for session-based recommendations. Specifically, we grouped items of different lengths as varying multi-order semantic units to mine the user’s primary intention from multiple dimensions. Meanwhile, a novel denoising network was designed to alleviate the interference of noisy behavior and provide a more precise session representation. The result of extensive experiments on three real-world datasets demonstrated that the proposed MSD model exhibited improved performance compared with existing state-of-the-art methods in session-based recommendation.

Background: Despite recent advancements, medical technology has not yet reached its peak. Precision medicine is growing rapidly, thanks to machine learning breakthroughs powered by increased computational capabilities. This article explores a deep-learning application for computer-aided diagnosis in dermatology. Methods: Using a custom model based on EfficientNetB3 and deep learning, we propose an approach for skin lesion classification that offers superior results with smaller, cheaper, and faster inference times compared to other models. The skin images dataset used for this research includes 8,222 files selected from the authors' collection and the ISIC2019 archive, covering six dermatological conditions. Results: The model achieved 95.4% validation accuracy on four categories—melanoma, basal cell carcinoma, benign keratosis-like lesions, and melanocytic nevi—using an average of 1,600 images per category. Adding two categories with fewer images (about 700 each)—squamous cell carcinoma and actinic keratoses—reduced the validation accuracy to 88.8%. The model maintained accuracy on new clinical test images taken under the same conditions as the training dataset. Conclusions: The custom model demonstrated excellent performance on the diverse skin lesions dataset, with significant potential for further enhancements.

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.

The digital world is increasingly invading our reality, which leads to the formation of a significant reflection of the processes and activities taking place in the smart city. Such activities include well-known urban events, celebrations, and those with a very local character. Due to the mass occurrence, events have a comparable influence on the formation of the spirit and the urban atmosphere. This work presents an enhanced semantic version of the ConvTree algorithm - SemConvTree. It allows considering the semantic component of the data obtained by using semi-supervised learning of topic modeling ensemble (consisting of improved models BERTopic, TSB-ARTM, SBert-Zero-Shot). We also present an improved event search algorithm based on both statistical evaluations and semantic analysis of posts. This algorithm allows fine-tuning the mechanism of discovering the required entities with the specified particularity (such as a particular topic). Experimental studies were conducted within the area of New York City. They showed an improvement in the detection of posts devoted to events (about 40% higher f1-score) due to the accurate handling of events of different scales. These results lead in the long term to talk about the potential perspective in creating a semantic platform for the analysis and monitoring of urban events in the future.

Malware detection is a crucial pillar of cybersecurity and aims to identify and neutralize malware threats. This study investigates how three deep learning algorithms - Convolutional Neural Net-works with One-Dimensional Architecture (CNN1D), Neural Networks (NN), and a hybrid model of one dimensional convolutional neural networks (CNN1D) and Long Short-Term Memory (LSTM) - help detect malware in Portable Executable working (.exe) files. Using a large dataset of tagged malware and benign samples, the effectiveness of these algorithms in distinguishing dangerous from harmless executables is extensively tested. In addition, the study evaluates the computational efficiency of the proposed methods for a variety of hardware configurations, including Central Processing Units (CPU), Graphics Processing Units (GPU), Raspberry Pi (IoT device), and Tensor Processing Units (TPU). Performance metrics provide insight into the scalability and effectiveness of the model across different hardware configurations. The results of this study have significant impact on the development of malware detection, particularly in the context of IoT security. By demonstrating the capabilities and limitations of CNN1D, Neural Networks, and CNN1D with LSTM models, the study provides practitioners with efficient and scalable solutions to real-world malware detection difficulties. In addition, insights from performance tests on various hardware platforms provide important assistance in developing robust security measures in IoT contexts, strengthening cybersecurity defenses in an ever-changing digital landscape.

The representation of intelligence is achieved by patterns of connections among neurons in brains and machines. Brains grow continuously, such that their patterns of connections develop through activity-dependent specification with the continuing ontogenesis of individual experience. The theory of active inference proposes that the developmental organization of sentient systems reflects general processes of informatic self-evidencing, through the minimization of free energy, that may be described in information terms that are not dependent on a specific physical substrate. At a certain level of complexity, self-evidencing of living (self-organizing) information systems becomes hierarchic and reentrant, such that effective consciousness emerges as the consequence of a good regulator. These principles imply that an adequate reconstruction of the computational dynamics of an individual human brain is possible with a sufficient neuromorphic emulation.