Search

Electrical discharge machining (EDM) is a complex process renowned for shaping intricate geometries in hard materials, though optimizing its performance is costly due to extensive experimental testing. We introduce EDMNet, a novel machine learning (ML) benchmark framework for predicting EDM performance, specifically in smart powder mixed-electrical discharge machining (PM-EDM) with electrode vibration, enabling in situ, online monitoring of the EDM process. EDMNet integrates ML into the PM-EDM process, reducing reliance on trial-and-error experimentation and allowing real-time performance optimization. We evaluate 12 ML regressor models, including deep neural networks (DNN), support vector regression (SVR), and ensemble methods, across four key metrics: mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), and R-squared (R2). This multi-metric evaluation highlights the strengths and weaknesses of different models, with DNN and ensemble methods demonstrating superior performance. EDMNet serves as a standardized, reproducible benchmarking framework, facilitating the comparison of ML models in the EDM context. The integration of in situ monitoring with predictive accuracy provided by EDMNet holds significant potential for improving manufacturing processes, reducing costs, and boosting efficiency in engineering applications. Our results validate EDMNet as an effective tool for optimizing EDM, paving the way for enhanced precision in smart manufacturing. [ABSTRACT FROM AUTHOR]

Data containing noises, outliers, and imbalanced class distributions pose challenges to the traditional classifiers. By incorporating both the membership and non-membership functions, the intuitionistic fuzzy (IF) set has shown potential in designing robust learning algorithms for classifiers. However, the non-membership function used in these IF-based classifiers usually only utilizes the local distribution information of the training samples, and the classifiers are built upon single-hidden layer networks, which degrade the performance of the corresponding classifiers. Broad learning system (BLS) is an emerging neural network model with fast learning speed and flexible network architecture; however, it still fails to distinguish n samples. To this end, in this paper, we propose a new definition of the non-membership function within intuitionistic fuzzy sets and subsequently propose an intuitionistic fuzzy broad learning system (IFBLS) model. The proposed non-membership function incorporates two ratio numbers based on four distances, allowing for the utilization of global information on the distribution of samples and mitigating misclassification of valid samples as noise which is often observed in traditional methods. By using a score function that considers both the membership and non-membership functions to redistribute the importance of the training samples, the proposed IFBLS benefits from both the powerful representation capability of the original BLS and the robust learning of IF-based models. Extensive experiments conducted on 21 imbalanced binary classification problems sourced from the UCI and KEEL repositories illustrate that the proposed IFBLS achieves state-of-the-art performance by attaining the highest testing accuracy in 17 out of the 21 problems. [ABSTRACT FROM AUTHOR]

Ternary nanofluids have been an interesting field for academics and researchers in the modern technological era because of their advanced thermophysical properties and the desire to increase heat transfer rates. Furthermore, the innovative, sophisticated artificial neural network strategy with the Levenberg–Marquardt backpropagation technique (LMBPT) is proposed for research on heat and mass transport over non-Newtonian ternary Casson fluid on a radially extending surface with magnetic field and convective boundary conditions. The main objective of the current research is to conduct a comparative study of numerical solutions of the ternary nanofluid model of heat/mass transport utilizing the artificial neural network (ANN) together with the (LMBPT). To accurately represent complex patterns, neural networks modify their parameters flexibly, resulting in more accurate predictions and greater generalization with numerical outcomes. The model equations were reduced from partial to ODEs through applying appropriate similarity variables. The shooting technique and the byp-4c algorithm were then used to analyze the numerical data. The current study reveals that a rise in the Casson parameter diminishes the fluid velocity but an opposite nature is seen in thermal distribution for rising behavior of heat source/sink and Biot number, and the concentration profile tends to deteriorate when the mass transfer is elevated. Furthermore, the resulting values of the significant engineering coefficients are numerically analyzed and tabulated. [ABSTRACT FROM AUTHOR]

This work presents the use of artificial neural networks (ANNs) with deep evidential regression to model the tensile stress response of a thermoplastic elastomer (TPE) considering uncertainty. Three Gaussian noise scenarios were added to a previous dataset of a TPE to simulate noise in the stress response. The trained ANN models were able to address stress–strain data that were not used for their training or validation, even in the presence of noise. The uncertainty in all tested ANN scenarios comprised, within ± 3 σ , the noisy data of the TPE stress response. The method was extended to other grades of Hytrel material with ANN architectures that obtained results with a coefficient of determination of about 0.9. These results suggest that shallow neural networks, equipped and trained using evidential output layers and an evidential regression loss, can predict, generalize, and simulate noisy tensile stress responses in TPE materials. [ABSTRACT FROM AUTHOR]

Circadian rhythms are driven by an internal molecular clock which controls physiological and behavioral processes. Disruptions in these rhythms have been associated with health issues. Therefore, studying circadian rhythms is crucial for understanding physiology, behavior, and pathophysiology. However, it is challenging to study circadian rhythms over gene expression data, due to a scarcity of time labels. In this paper, we propose a novel approach to predict the phases of un-timed samples based on a deep neural network (DNN) architecture. This approach addresses two challenges: (1) prediction of sample phases and reliable identification of cyclic genes from high-dimensional expression data without relying on conserved circadian genes and (2) handling small sample-sized datasets. Our algorithm begins with initial gene screening to select candidate cyclic genes using a Minimum Distortion Embedding framework. This stage is then followed by greedy layer-wise pre-training of our DNN. Pre-training accomplishes two critical objectives: First, it initializes the hidden layers of our DNN model, enabling them to effectively capture features from the gene profiles with limited samples. Second, it provides suitable initial values for essential aspects of gene periodic oscillations. Subsequently, we fine-tune the pre-trained network to achieve precise sample phase predictions. Extensive experiments on both animal and human datasets show accurate and robust prediction of both sample phases and cyclic genes. Moreover, based on an Alzheimer's disease (AD) dataset, we identify a set of hub genes that show significant oscillations in cognitively normal subjects but had disruptions in AD, as well as their potential therapeutic targets. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the method of solving partial differential equations (PDEs) using artificial neural network (ANN) structures, which have been actively applied in artificial intelligence models. The ANN model for solving PDEs offers the advantage of providing explicit and continuous solutions. However, the ANN model for solving PDEs cannot construct a conventionally solvable linear system with known matrix solvers; thus, computational speed could be a significant concern. We study the implementation of the multigrid method, developing a general concept for a coarse-grid correction method to be integrated into the ANN-PDE architecture, with the goal of enhancing computational efficiency. By developing a reduced form of the multigrid method for ANN, we demonstrate that it can be interpreted as an equivalent representation of the classic multigrid expansion. We validated the applicability of the proposed method through rigorous experiments, which included analyzing loss decay and the number of iterations along with improvements in terms of accuracy, speed, and complexity. We accomplished this by employing the gradient descent method and the Broyden–Fletcher–Goldfarb–Shanno (BFGS) method to update the gradients while solving the given ANN systems of PDEs. [ABSTRACT FROM AUTHOR]

Coronary Artery Bypass Graft (CABG) is a common cardiac surgery, but it continues to have many associated risks, including the need for blood transfusions. Previous research has shown that blood transfusion during CABG surgery is associated with an increased risk for infection and mortality. The current study aims to use modern techniques, such as deep neural networks and data synthesis, to develop models that can best predict the need for blood transfusion among CABG patients. Results show that neural networks with synthetic data generated by DataSynthesizer have the best performance. Implications of results and future directions are discussed. [ABSTRACT FROM AUTHOR]

A primary strategy for constructing click-through rate models based on deep learning involves combining a multi-layer perceptron (MLP) with custom networks that can effectively capture the interactions between different features. This is due to the widespread recognition that relying solely on a vanilla MLP network is not effective in acquiring knowledge about multiplicative feature interactions. These custom networks often employ product methods, such as inner, Hadamard, and outer products, to construct dedicated architectures for this purpose. Among these methods, the outer product has shown superiority in capturing feature interactions. However, the resulting quadratic form from the outer product operation limits the conveyance of informative higher-order interactions to the MLP. Efforts to address this limitation have led to models attempting to increase interaction degrees to higher orders. However, utilizing matrix factorization techniques to reduce learning parameters has resulted in information loss and decreased performance. Furthermore, previous studies have constrained the MLP's potential by providing it with inputs consisting of homogeneous outer products, thus limiting available information diversity. To overcome these challenges, we introduce DONN, a model that leverages a composite-wise bilinear module incorporating factorized bilinear pooling to mitigate information loss and facilitate higher-order interaction development. Additionally, DONN utilizes a feature-wise bilinear module for outer product computations between feature pairs, augmenting the MLP with combined information. By employing heterogeneous outer products, DONN enhances the MLP's prediction capabilities, enabling the recognition of additional nonlinear interdependencies. Our evaluation on two benchmark datasets demonstrates that DONN surpasses state-of-the-art models in terms of performance. [ABSTRACT FROM AUTHOR]

Radial basis function (RBF) neural network training presents a challenging optimization task, necessitating the utilization of advanced algorithms that can fully train the network so as to produce accurate and computationally efficient models. To achieve this goal, this work introduces a new framework where the original RBF training problem is divided into two simpler subproblems; the linear parameters, namely the network weights, are projected out of the problem using variable projection (VP), thus leaving a reduced functional, which depends only on nonlinear parameters, i.e., the RBF centers. The centers are updated using the Levenberg–Marquardt (LM) algorithm, while the optimal values of the synaptic weights are calculated in each iteration of the LM algorithm using linear regression. The proposed VP-LM scheme is coupled with the fuzzy means (FM) algorithm, which helps to select the number of RBF centers and enhances the overall search procedure, thus resulting to a framework that produces parsimonious models with enhanced accuracy in shorter training times. The proposed training scheme is evaluated on 12 both real-world and synthetic benchmark datasets and tested against various RBF training algorithms, as well as different neural network architectures. The experimental results underscore the effectiveness of the VP-FM algorithm in producing neural network models that outperform those generated by alternative methods in many aspects; to be more specific, the proposed approach achieves very competitive model accuracy, while resulting to smaller network sizes and thus lower complexity, which leads to shorter training times. [ABSTRACT FROM AUTHOR]

We have developed a neural network model that imitates the central nervous system's control of motor sensors (Sánchez-Torres and Rodríguez-Romo in Neurocomputing 581:127511, 2024). Our research explored various levels of connectivity in our neural network related to neuroplasticity in the central nervous system. We have conducted a study comparing healthy individuals to those with motor impairments by utilizing reinforcement learning and transfer entropy. In our previous research (Sánchez-Torres and Rodríguez-Romo in Neurocomputing 581:127511, 2024), we have simulated human walking while encountering obstacles as an instance of gross motor activities. Now, we have used the same model to simulate fine motor activities. Our goal is to identify differences in information transmission between gross and fine motor activities among healthy individuals and those with motor impairments by evaluating the effective connectivity of our network. To regulate learning accuracy in our model, we introduced a variable called numClusterToFire. However, we discovered that the value for this variable requires careful calibration. If the value is too small, agent exploration is insufficient, and network learning is inefficient. Conversely, learning times increase exponentially, often unnecessarily if the value is too large. We conducted simulations for gross and fine motor skills using three different numClusterToFire values and found that as we increased numClusterToFire, the time required for the network to memorize the outputs for each of the objects in the test set also increased. Our findings indicate that in gross motor skills, which do not require precision, changes in the numClusterToFire variable do not affect information transfer behavior. Conversely, in fine motor skills, information transfer decreases as numClusterToFire increases. On the other hand, our model revealed that for healthy and disabled individuals, the transfer of information between the input layer and the first hidden layer is higher for fine motor skills; this important biological fact suggests the influence of external cues in performing this activity successfully. Additionally, our neural network model showed that movements that do not require precision do not necessarily require a high level of neuroplasticity. Increasing neuroplasticity may cause some neurons to transmit more information than others. Whereas, increasing neuroplasticity through practice is essential for precise movements like fine motor skills. We also found that information transfer in the network's hidden layers is similar for fine and gross motor activities, as we observed identical patterns. However, the distribution and proportion of these patterns differ, concluding that more neurons are involved in fine motor activities, and more information is transferred compared to gross motor activities. Finally, a pattern was observed in the transfer of information in the last hidden layer, which is only present in fine motor skills. This pattern is associated with the precision of the movements. [ABSTRACT FROM AUTHOR]

In deep neural networks, the filters of convolutional layers play an important role in extracting the features from the input. Redundant filters often extract similar features, leading to increased computational overhead and larger model size. To address this issue, a two-step approach is proposed in this paper. First, the clusters of redundant filters are identified based on the cosine distance between them using hierarchical agglomerative clustering (HAC). Next, instead of pruning all the redundant filters from every cluster in single-shot, we propose to prune the filters in a systematic manner. To prune the filters, the cluster importance among all clusters and filter importance within each cluster are identified using the ℓ 1 -norm based criterion. Then, based on the pruning ratio filters from the least important cluster to the most important ones are pruned systematically. The proposed method showed better results compared to other clustering-based works. The benchmark datasets CIFAR-10 and ImageNet are used in the experiments. After pruning 83.92% parameters from VGG-16 architecture, an improvement over the baseline is observed. After pruning 54.59% and 49.33% of the FLOPs from ResNet-56 and ResNet-110, respectively, both showed an improvement in accuracy. After pruning 52.97% of the FLOPs, the top-5 accuracy of ResNet-50 drops by only 0.56 over ImageNet. [ABSTRACT FROM AUTHOR]

Power electronic converters play a crucial role in integrating distributed generation, renewable energy sources, microgrids, and HVDC transmission networks into the grid. The control technique used in the voltage source inverters (VSI) is essential for handling load variations, system nonlinearity, stability, and fast transient response. This study focuses on improving the robustness and control performance of VSIs by integrating a Kalman filter adaptive observer into a finite control set model predictive control (FCS-MPC), resulting in an improved FCS-MPC strategy (IMPC). The classical FCS-MPC can be affected by inaccuracies due to measurement noise and uncertainties in system models, leading to less accurate predictions and suboptimal control actions. By employing the Kalman filter adaptive observer, real-time estimates of unmeasured variables are provided, compensating for uncertainties, and enhancing control performance. To further enhance flexibility and adaptivity, an artificial neural network (ANN)-based controller is designed. The ANN controller is trained offline using IMPC as baseline thus eliminating the need for online predictions and optimization. The ANN controller directly generates inverter switching configuration states, resulting in high-quality sinusoidal output voltage with low distortions. Comparative analysis is conducted for the classical FCS-MPC, IMPC, support vector machine (SVM), convolutional neural network (CNN), and ANN-based controllers under diverse operating conditions and system parameters. Although it has reduced interpretability, the ANN controller exhibits superior harmonic reduction, outperforming both MPC-based controllers and SVM. Evaluation against CNN-based controls also validates the ANN's robustness and effectiveness in handling uncertainties, emphasizing its adaptability, efficiency, and practical applicability in power electronic applications. [ABSTRACT FROM AUTHOR]

The design of a helicopter is an intricate and challenging process. Decisions made during the preliminary design phase can significantly impact subsequent design stages, making it crucial to base these decisions on a solid foundation. A range of methods, including hand calculations, finite element analyses, and experimental tests, can be employed to establish the conceptual design parameters. However, these methods often come with the drawbacks of being time-intensive and costly, especially when testing various structures during the early design phase. To address this issue, this study introduces an artificial neural network-based design tool to evaluate the static structural characteristics of a helicopter's horizontal stabilizer. The tool was built in Python using the Keras library. The required database for the training of the artificial neural network model was established using finite element analyses of the horizontal stabilizer subjected to the aerodynamic load for diverse design variables. The model's performance was evaluated, and the model's outputs were compared to the results derived from the finite element analyses. Moreover, the Hammersley sampling methodology was employed to reduce the size of the database without compromising on accuracy. The study also assessed the impact of decreasing the amount of data fed into the network model. [ABSTRACT FROM AUTHOR]

Osteoporosis (OP) is the most prevalent and common bone disease, especially knee osteoporosis. It significantly disables sufferers all over the world. Although laborious and prone to user variation, manual diagnosis, segmentation, and annotation of knee joints continue to be the preferred way to diagnose OP in clinical procedures. Therefore, many deep learning algorithms, particularly the convolutional neural network (CNN), have been created to increase clinical workflow efficiency to overcome the shortcomings of the widely used method as above. Medical imaging procedures can show hidden structures in a volumetric view, particularly those that generate three-dimensional (3D) pictures like MRI. We created a dataset of 240 pictures from patients who had knee X-rays and skeletal bone mineral density assessments at the same time. Four convolutional neural networks (CNN) models were used to analyse the X-ray images and deep neural networks for clinical covariances to determine the degree of osteoporosis. Additionally, we investigated ensemble models that included each CNN with a clinical covariance. For every network, scores for accuracy and error rate were computed. ResNet and Alexnet displayed the highest levels of accuracy when the CNN models were tested using knee X-rays with normal, low BMD, and osteoporosis. An ensemble of DNN with Alexnet, ResNet, and both ResNet and Alexnet are employed resulting in improved accuracy. The ensemble of best-performing CNN and DNN is proposed to diagnose osteoporosis more accurately. The proposed method has produced a highly accurate osteoporosis diagnosis. [ABSTRACT FROM AUTHOR]

Migraine is a common chronic neurological disorder that lacks objective imaging biomarkers, while resting-state functional magnetic resonance imaging (rs-fMRI) can be used to extract potential biomarkers. Recently, graph neural networks (GNNs) have gained significant popularity in the classification of brain disorders because of their powerful ability to model brains. Hypergraph neural networks (HGNNs), a branch of GNNs, are particularly effective in capturing high-order neighborhood information. In this paper, we proposed a hypergraph neural network model, incorporating hypergraph dual attention mechanism and hypergraph pooling strategy (APHGNN), for migraine classification derived from the preprocessed rs-fMRI data. First, we constructed hypergraphs from functional connectivity matrices based on the preprocessed rs-fMRI data. Then, we designed three network layers: in the hypergraph dual attention layer, we introduced attention mechanism in both the hyperedge feature aggregation phase and the node feature aggregation phase, making full use of both node and hyperedge information to update node features; in the hypergraph pooling layer, we employed a node selection-based pooling strategy to score and filter nodes, retaining key node features; in the readout layer, we calculated the average and maximum values of the key node features, concatenated and aggregated them, and used the resulting vectors for classification. The experimental results demonstrate that our model outperforms other baseline methods in classification performance and exhibits good generalization. Additionally, the key brain regions extracted through the hypergraph pooling strategy can serve as potential biomarkers for migraine, providing valuable insights for migraine diagnosis. [ABSTRACT FROM AUTHOR]

Increasing urban traffic and congestion have led to significant issues such as rising air pollution and wasted time, highlighting the need for an intelligent traffic light control (TLC) system to minimize vehicle waiting times. This paper presents a novel TLC system that leverages the Internet of Things (IoT) for data collection and employs the random forest algorithm for preprocessing and feature extraction. A deep belief network predicts future traffic conditions, and a support vector regression network is integrated to enhance prediction accuracy. Additionally, the traffic light control strategy is optimized using reinforcement learning. The proposed method is evaluated through two different scenarios. The first scenario is compared with fixed-time control and the double dueling deep neural network (3DQN) methods. The second scenario compares it with the SVM, KNN, and MAADAC approaches. Simulation results demonstrate that the proposed method significantly outperforms these alternative approaches, showing substantial improvements in average vehicle waiting times by more than 20%, 32%, and 45%, respectively. Using a deep belief network, supplemented by support vector regression, ensures high precision in forecasting traffic patterns. Furthermore, the reinforcement learning-based optimization of the traffic light control strategy effectively adapts to changing traffic conditions, providing superior traffic flow management. The results indicate that the proposed system can substantially reduce traffic congestion and improve urban traffic flow. [ABSTRACT FROM AUTHOR]

Breast cancer is a prevalent and highly lethal cancer affecting women globally. While non-invasive techniques like ultrasound and mammogram are used for diagnosis, histological examination after biopsy is considered the gold standard. However, manual examination of tissues for abnormality is labor-intensive, expensive, and requires prior domain knowledge. Early detection, awareness, and access to specialized medical infrastructure in resource-constrained and remote areas are significant challenges but crucial for saving lives. In recent years, deep learning-based approaches have shown promising results in breast cancer detection, facilitated by advancements in GPU memory, computation power, and the availability of digital data. Motivated by these observations, we propose the Breast-NET deep convolutional neural network model for breast cancer detection and grading using histological images. Our model's performance is evaluated on the BreakHis dataset, and we demonstrate its generalization ability on the Invasive Ductal Carcinoma (IDC) grading and IDC datasets. Extensive experimental and statistical performance analysis, along with an ablation study, validates the efficiency of our proposed model. Furthermore, we demonstrate the effectiveness of transfer learning with seven pre-trained convolutional neural networks for breast cancer detection and grading. Experimental results show that our framework outperforms state-of-the-art approaches in terms of accuracy, space, and computational complexity for the BreakHis, IDC grading, and IDC datasets. [ABSTRACT FROM AUTHOR]

Accidents in the workplace are critical issues that necessitate attention from environmental safety and health perspectives to enhance operational safety. The elevated rate of workplace accidents in Turkey underscores deficiencies in reliability analysis studies. Effective planning of preventive measures, considering factors such as location and timing, is pivotal in accident prevention. Sociological and regional disparities, alongside technical factors such as service type, working hours, and age, contribute significantly to accident causation. Reliability analysis studies aim to identify potential causes of accidents, enabling early detection of hazardous situations and combinations. This proactive approach allows responsible personnel to implement measures that mitigate or eliminate specific types of accidents, thereby safeguarding both lives and business assets. This study utilizes Artificial Neural Network (ANN) to forecast potential occupational accidents in the shipbuilding industry before they occur. Analyzing data from 146 occupational accidents involving ship electricians between 2012 and 2016, out of a total of 1165 occupational accidents in the industry, the study estimates potential accidents for 2017. The results demonstrate that ANN achieves high accuracy in predicting occupational accidents. [ABSTRACT FROM AUTHOR]

Tensile properties of multifilament polyester woven fabrics are of great importance for their end uses such as parachutes, sails, tents, sleeping bags, filters and surgical textiles. The filament fineness, weave type and weave density have a great influence on the tensile properties of these fabrics. In this study, artificial intelligence (AI) models such as artificial neural networks (ANN), fuzzy logic (FL) and genetic algorithms (GA) were developed to forecast breaking strength and breaking elongation values of multifilament polyester woven fabrics. The fabric samples used in the study have three different microfilament finenesses and two different conventional filament finenesses with plain, twill and satin weave types. By applying four different weft density values, totally 60 woven fabric samples were obtained in the experimental design. The regression coefficient values ( R 2 ) between actual and predicted results were obtained as 0.80, 0.90 and 0.92 with ANN, FL and ANN–GA hybrid methods, respectively. The mean absolute percentage error (MAPE) was lower than 6% for all AI techniques used in this study. As a conclusion, it was proved that the breaking strength and breaking elongation properties of multifilament polyester woven fabrics can be forecasted with high accuracy rates by AI techniques. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel keyframe extraction extraction method based on the gray wolf optimization (GWO) algorithm, addressing the challenge of information loss in traditional methods due to redundant and similar frames. The proposed method GWOKConvLSTM prioritizes speed, accuracy, and compression efficiency while preserving semantic information. Inspired by wolf behavior, we construct a fitness function that minimizes reconstruction error and achieves optimal compression ratios below 8%. Compared to traditional methods, our GWO method achieves the lowest reconstruction error for a given compression rate, providing a concise and visually coherent summary of keyframes while maintaining consistency across similar motions. Additionally, we propose a template-based method for video classification tasks, achieving the highest accuracy when combined with pre-trained CNNs and ConvLSTM. Our method effectively prevents dynamic background noise from affecting keyframe selection, leading to significantly improve video classification performance using deep neural networks. [ABSTRACT FROM AUTHOR]

The distillation tower is a crucial component of the refining process. Its energy efficiency has been a major area of research, especially following the oil crisis. This study focuses on optimizing energy consumption in the Shiraz refinery's distillation unit. The unit is simulated using ASPEN-HYSYS software. Simulation results are validated against real data to ensure model accuracy. The operational data aligns well with model predictions. Following the creation of a data bank using HYSYS software, the tower's operating conditions are optimized using neural networks and MATLAB software. In this study, a neural network model is developed for the distillation tower. This modeling approach is cost-effective, does not require complex theories, and does not rely on prior system knowledge. Additionally, real-time modeling is achievable through parallel distributed processing. The findings indicate that the optimal feed tray is 9 and the optimal feed temperature is 283.5°C. Furthermore, the optimized number of trays in the distillation tower is 47. Results show that in optimal conditions, cold and hot energy consumption are reduced by approximately 9.7% and 10.8%, respectively. Moreover, implementing optimal conditions results in a reduction of hot energy consumption in the reboiler by 60,000 MW and a reduction of cold energy consumption in the condenser by 30,000 MW. [ABSTRACT FROM AUTHOR]

The recent emergence of the hybrid quantum-classical neural network (HQCNN) architecture has garnered considerable attention because of the potential advantages associated with integrating quantum principles to enhance various facets of machine learning algorithms and computations. However, the current investigated serial structure of HQCNN, wherein information sequentially passes from one network to another, often imposes limitations on the trainability and expressivity of the network. In this study, we introduce a novel architecture termed parallel proportional fusion of spiking and quantum neural networks (PPF-SQNN). The dataset information is simultaneously fed into both the spiking neural network and the variational quantum circuits, with the outputs amalgamated in proportion to their individual contributions. We systematically assess the impact of diverse PPF-SQNN parameters on network performance for image classification, aiming to identify the optimal configuration. On three datasets for image classification tasks, the final classification accuracy reached 98.2%, 99.198%, and 97.921%, respectively, with loss values all below 0.2, outperforming the compared serial networks. In noise testing, it also demonstrates good classification performance even under noise intensities of 0.9 Gaussian and uniform noise. This study introduces a novel and effective amalgamation approach for HQCNN, laying the groundwork for the advancement and application of quantum advantages in artificial intelligence computations. [ABSTRACT FROM AUTHOR]

A comprehensive and high-quality lexicon plays a crucial role in traditional text classification approaches. It improves the utilization of linguistic knowledge. Although it is helpful for this task, the lexicon has received little attention in current neural network models. First, obtaining a high-quality lexicon is not easy. Second, an effective automated lexicon extraction method is lacking, and most lexicons are handcrafted, which is very inefficient for big data. Finally, there is no effective way to use a lexicon in a neural network. To address these limitations, we propose a pre-attention mechanism for text classification in this study, which can learn the attention values of various words based on their effects on classification tasks. Words with different attention values can form a domain lexicon. Experiments on three publicly available and authoritative benchmark text classification tasks show that our models obtain competitive results compared with state-of-the-art models. For the same dataset, when we use the pre-attention mechanism to obtain attention values, followed by different neural networks, words with high attention values have a high degree of coincidence, which proves the versatility and portability of the pre-attention mechanism. We can obtain stable lexicons using attention values, which is an inspiring method of information extraction. [ABSTRACT FROM AUTHOR]

Label noise causes deep neural networks to gradually memorize incorrect labels, leading to a decline in generalization. In this paper, based on three observations from learning behavior in textual noise scenarios, we propose a dynamic training method to enhance model robustness and generalization against textual label noise. This method corrects noisy labels by dynamically incorporating the model's predictions. The combination weight of the original labels is a decay function on training time, which relates to the learning dynamics. Additionally, our method introduces r-drop and prior regularization terms to ensure that the single-model backbone generates reliable predictions, thereby obtaining accurate corrected labels. This design removes the stage splitting and data segmentation required by existing SOTA methods and effectively mitigates the adverse impact of erroneous labels without introducing additional dependencies. Experimental results on four text classification datasets demonstrate that dynamic training outperforms strong baselines designed for class-conditional and instance-dependent noises within the common noise range. Our code is available at https://github.com/shaohuancheng/noisy_label_for_exp_decay. [ABSTRACT FROM AUTHOR]

Near-surface air temperature (Tair) is crucial for assessing urban thermal conditions and their impact on human health. Traditional Tair estimation methods, reliant on sparse weather stations, often miss spatial variability. This study proposes a novel framework using a federated learning artificial neural network (FLANN) for fine-scale Tair prediction. Leveraging spatially complete thermal data from Landsat 8/9, Sentinel 3, and Himawari 8/9 (105 acquisition days, 2013–2023), and data from automatic weather stations, 23 predictor variables were extracted. After rigorous selection processes, nine variables significantly correlated with Tair were identified. Comparative analysis against established machine learning and linear models, using cross-validation data, showed FLANN's superior performance with a Pearson correlation coefficient (r) of 0.98 and a root mean square error (RMSE) of 0.97 K, compared to r and RMSE of 0.85 and 1.09, respectively, for the linear model. FLANN showed greater improvements for urban stations with r and RMSE differences of 0.19 and − 2.03 K. Application of FLANN to predict Tair in Hong Kong in July 2023 enabled detailed urban heat island (UHI) analysis, revealing dynamic spatial and temporal UHI patterns. This study highlights FLANN's potential for accurate Tair prediction and UHI analysis, enhancing urban thermal environment management. [ABSTRACT FROM AUTHOR]

Parasites in fish muscle present a significant problem for the seafood industry in terms of both quality and health and safety, but the low contrast between parasites and fish tissue makes them exceedingly difficult to detect. The traditional method to identify nematodes requires removing fillets from the production line for manual inspection on candling tables. This technique is slow, labor intensive and typically only finds about half the parasites present. The seafood industry has struggled for decades to develop a method that can improve the detection rate while being performed in a rapid, non-invasive manner. In this study, a newly developed solution uses deep neural networks to simultaneously analyze the spatial and spectral information of hyperspectral imaging data. The resulting technology can be directly integrated into existing industrial processing lines to rapidly identify nematodes at detection rates (73%) better than conventional manual inspection (50%). [ABSTRACT FROM AUTHOR]

This study investigates the efficacy of predicting age-related macular degeneration (AMD) activity through deep neural networks (DNN) using a cross-instrument training dataset composed of Optical coherence tomography-angiography (OCTA) images from two different manufacturers. A retrospective cross-sectional study analyzed 2D vascular en-face OCTA images from Heidelberg Spectralis (1478 samples: 1102 training, 276 validation, 100 testing) and Optovue Solix (1003 samples: 754 training, 189 validation, 60 testing). OCTA scans were labeled based on clinical diagnoses and adjacent B-scan OCT fluid information, categorizing activity into normal, dry AMD, active wet AMD, and wet AMD in remission. Experiments explored cross-instrument disease classification using separate and combined datasets for training the DNN. Testing involved 100 Heidelberg and 60 Optovue samples. Training on Heidelberg data alone yielded 73% accuracy on Heidelberg images and 60% on Optovue images. Training on Optovue data alone resulted in 34% accuracy on Heidelberg and 85% on Optovue images. Combined training data from both instruments achieved 78% accuracy on Heidelberg and 76% on Optovue test sets. Results indicate that cross-instrument classifier training demonstrates high classification prediction accuracy, making cross-instrument training viable for future clinical applications. This implies that vascular morphology in OCTA can predict disease progression. [ABSTRACT FROM AUTHOR]

Segregation of granular materials is a critical challenge in many industries, often aimed at being controlled or minimised. The discrete element method (DEM) offers valuable insights into this phenomenon. However, calibrating DEM models is a crucial, albeit time-consuming, step. Recently, using machine learning (ML)-based surrogate models (SMs) in the calibration process has emerged as a promising solution. Nevertheless, developing such SMs is challenging due to the high number of DEM simulations required for training. Additionally, choosing a suitable ML model is not trivial. This study aims to develop SMs that effectively link particle-particle and particle-wall DEM interaction parameters to segregation of a multi-component mixture. We evaluate several ML models, ranging from artificial neural networks to ensemble learning, that are trained on a very cost-effective dataset, employing Bayesian optimisation with cross-validation to tune their hyperparameters. Next, we introduce a novel transfer learning (TL)-based approach that leverages knowledge from a few scenarios to handle new "unseen" ones. This method enables the construction of adaptive SMs for unseen scenarios, such as a new initial configuration (IC) of granular mixtures, without the need for a full-sized dataset. Our findings indicate that Gaussian process regression (GPR) efficiently builds accurate SMs on a very small dataset. We also demonstrate that only a few samples are required to build an accurate SM for the unseen IC, which significantly reduces the data preparation burden. By incorporating one and five samples from unseen scenarios to update the TL-GPR-based surrogate model, the SM's performance (based on ) on unseen scenarios improves by 17 and 47%, respectively. The insights and methodology presented in this study will facilitate and accelerate the development of accurate SMs for DEM calibration, assisting in developing reliable DEM models in a shorter timeframe. [ABSTRACT FROM AUTHOR]

A new control approach based on fuzzy sliding mode control (FSMC) is proposed to regulate the chaotic vibration of an axial string. Hamilton's principle is used to formulate the nonlinear equation of motion of the axial translation string, and the von Kármán equations are used to analyse the geometric nonlinearity. The governing equations are nondimensionalized as partial differential equations and transformed into a nonlinear 3-dimensional system via the third-order Galerkin approach. An active control technique based on the FSMC approach is suggested for the derived dynamic system. By using a recurrent neural network model, we can accurately predict and effectively apply a control strategy to suppress chaotic movements. The necessity of the suggested active control method in the regulation of the nonlinear axial translation string system is proven using different chaotic vibrations. The results show that the study of the chaotic vibrations of axially translating strings requires nonlinear multidimensional dynamic systems of axially moving strings; the validity of the proposed control strategy in controlling the chaotic vibration of axially moving strings in a multidimensional form is demonstrated. [ABSTRACT FROM AUTHOR]

The current study investigates removing tetracycline from water using batch, column, and tank experiments with statistical modelling using ANN for continuous tests. An artificial neural network (ANN) using the Levenberg-Marquardt back-propagation (LMA) training algorithm is constructed to compare the effectiveness of Tetracycline removal from aqueous solution using the sorption technique with prepared adsorbent. Several characterization analyses XRD, FT-IR, and SEM are employed for prepared Brownmillerite (Ca2Fe2O5)–Na alginate beads. The operating conditions of batch tests involved, contact time (0.1–3 h), initial of tetracycline (Co) of (100–250 mg/L), pH (3–12), agitation speed (50–250) rpm and dosage of adsorbent (0.2–1.2 g/50 mL). The outcomes of experiments have demonstrated that the optimum conditions for the batch test to achieve the maximum adsorbent capacity (qmax =7.845 mg/g) are achieved at pH 7, contact time 1.5 h, adsorbent dose 1.2 g/50 mL, agitation speed of 200 rpm, and initial concentration of TC 100 mg/L. Minimum mean square error (MSE) values of 7.09E-04 for 30 hidden neurons and 0.0029 for 59 hidden neurons in the 1D and 2D systems are accomplished, respectively. The artificial neural network model has exhibited excellent performance with correlation coefficients exceeding 0.980 for the operating variables, demonstrating its accuracy and effectiveness in predicting the experimental outcomes. According to sensitivity analysis, the influential parameter in the column test (1D) is the flow rate (mL/min), with a relative importance of 32.769%. However, in the tank test (2D), time (day) is signified as an influential parameter with a relative importance of 31.207%. [ABSTRACT FROM AUTHOR]

This research suggests a robust integration of artificial neural networks (ANN) for predicting swell pressure and the unconfined compression strength of expansive soils (PsUCS-ES). Four novel ANN-based models, namely ANN-PSO (i.e., particle swarm optimization), ANN-GWO (i.e., grey wolf optimization), ANN-SMA (i.e., slime mould algorithm) alongside ANN-MPA (i.e., marine predators' algorithm) were deployed to assess the PsUCS-ES. The models were trained using the nine most influential parameters affecting PsUCS-ES, collected from a broader range of 145 published papers. The observed results were compared with the predictions made by the ANN-based metaheuristics models. The efficacy of all these formulated models was evaluated by utilizing mean absolute error (MAE), Nash–Sutcliffe (NS) efficiency, performance index ρ, regression coefficient (R2), root mean square error (RMSE), ratio of RMSE to standard deviation of actual observations (RSR), variance account for (VAF), Willmott's index of agreement (WI), and weighted mean absolute percentage error (WMAPE). All the developed models for Ps-ES had an R significantly > 0.8 for the overall dataset. However, ANN-MPA excelled in yielding high R values for training dataset (TrD), testing dataset (TsD), and validation dataset (VdD). This model also exhibited the lowest MAE of 5.63%, 5.68%, and 5.48% for TrD, TsD, and VdD, respectively. The results of the UCS model's performance revealed that R exceeded 0.9 in the TrD. However, R decreased for TsD and VdD. Also, the ANN-MPA model yielded higher R values (0.89, 0.93, and 0.94) and comparatively low MAE values (5.11%, 5.67, and 3.61%) in the case of PSO, GWO, and SMA, respectively. The UCS models witnessed an overfitting problem because the aforementioned R values of the metaheuristics were 0.62, 0.56, and 0.58 (TsD), respectively. On the contrary, no significant observation was recorded in the VdD of UCS models. All the ANN-base models were also tested using the a-20 index. For all the formulated models, maximum points were recorded to lie within ± 20% error. The results of sensitivity as well as monotonicity analyses depicted trending results that corroborate the existing literature. Therefore, it can be inferred that the recently built swarm-based ANN models, particularly ANN-MPA, can solve the complexities of tuning the hyperparameters of the ANN-predicted PsUCS-ES that can be replicated in practical scenarios of geoenvironmental engineering. [ABSTRACT FROM AUTHOR]

Manufacturing companies focus on improving productivity, reducing costs, and aligning performance metrics with strategic objectives. In industries like paper manufacturing, minimizing equipment downtime is essential for maintaining high throughput. Leveraging the extensive data generated by these facilities offers opportunities for gaining competitive advantages through data-driven insights, revealing trends, patterns, and predicting future performance indicators like unplanned downtime length, which is essential in optimizing maintenance and minimizing potential losses. This paper explores statistical and machine learning techniques for modeling downtime length probability distributions and correlation with machine vibration measurements. We proposed a novel framework, employing advanced data-driven techniques like artificial neural networks (ANNs) to estimate parameters of probability distributions governing downtime lengths. Our approach specifically focuses on modeling parameters of these distribution, rather than directly modeling probability density function (PDF) values, as is common in other approaches. Experimental results indicate a significant performance boost, with the proposed method achieving up to 30% superior performance in modeling the distribution of downtime lengths compared to alternative methods. Moreover, this method facilitates unsupervised training, making it suitable for big data repositories of unlabelled data. The framework allows for potential expansion by incorporating additional input variables. In this study, machine vibration velocity measurements are selected for further investigation. The study underscores the potential of advanced data-driven techniques to enables companies to make better-informed decisions regarding their current maintenance practices and to direct improvement programs in industrial settings. [ABSTRACT FROM AUTHOR]

We introduce an advanced model for predicting protein–ligand interactions. Our approach combines the strengths of graph neural networks with physics-based scoring methods. Existing structure-based machine-learning models for protein–ligand binding prediction often fall short in practical virtual screening scenarios, hindered by the intricacies of binding poses, the chemical diversity of drug-like molecules, and the scarcity of crystallographic data for protein–ligand complexes. To overcome the limitations of existing machine learning-based prediction models, we propose a novel approach that fuses three independent neural network models. One classification model is designed to perform binary prediction of a given protein–ligand complex pose. The other two regression models are trained to predict the binding affinity and root-mean-square deviation of a ligand conformation from an input complex structure. We trained the model to account for both deviations in experimental and predicted binding affinities and pose prediction uncertainties. By effectively integrating the outputs of the triplet neural networks with a physics-based scoring function, our model showed a significantly improved performance in hit identification. The benchmark results with three independent decoy sets demonstrate that our model outperformed existing models in forward screening. Our model achieved top 1% enrichment factors of 32.7 and 23.1 with the CASF2016 and DUD-E benchmark sets, respectively. The benchmark results using the LIT-PCBA set further confirmed its higher average enrichment factors, emphasizing the model's efficiency and generalizability. The model's efficiency was further validated by identifying 23 active compounds from 63 candidates in experimental screening for autotaxin inhibitors, demonstrating its practical applicability in hit discovery. Scientific contribution Our work introduces a novel training strategy for a protein–ligand binding affinity prediction model by integrating the outputs of three independent sub-models and utilizing expertly crafted decoy sets. The model showcases exceptional performance across multiple benchmarks. The high enrichment factors in the LIT-PCBA benchmark demonstrate its potential to accelerate hit discovery. [ABSTRACT FROM AUTHOR]

Early detection of Alzheimer's disease (AD) is crucial to maximize clinical outcomes. Most disease progression analyses include people with diagnoses of cognitive impairment, limiting understanding of AD risk among those with normal cognition. The objective was to establish AD progression models through a deep learning approach to analyze heterogeneous, multi-modal datasets, including clustering analyses of population subsets. A multi-head deep-learning architecture was built to process and learn from biomedical and imaging data from the National Alzheimer's Coordinating Center. Shapley additive explanation algorithms for feature importance ranking and pairwise correlation analysis were used to identify predictors of disease progression. Four primary disease progression clusters (slow, moderate and rapid converters or non-converters) were subdivided into groups by race and sex, yielding 16 sub-clusters of participants with distinct progression patterns. A multi-head and early-fusion convolutional neural network achieved the most competitive performance and demonstrated superiority over a single-head deep learning architecture and conventional tree-based machine-learning methods, with 97% test accuracy, 96% F1 score and 0.19 root mean square error. From 447 features, 2 sets of 100 predictors of disease progression were extracted. Feature importance ranking, correlation analysis and descriptive statistics further enriched cluster analysis and validation of the heterogeneity of risk factors. [ABSTRACT FROM AUTHOR]

Biological communication system for neurological disorder patients is similar to the Brain Computer Interface in a way that it facilitates the connection to the outside world in real time. The interdisciplinary field of Electroencephalogram based message depiction is gaining importance as it assists the paralysed person to communicate. In the proposed method a novel approach of feature extraction is done by Empirical Mode Decomposition on non- stationary & non-linear kind of EEG signal. EMD helps in the effective time frequency analysis by disintegrating the EEG signal in the form of six Intrinsic Mode Functions with help of the frequency components. In all nine features are extracted from the decomposed IMFs so as to predict the states or messages of the patient. The above computed features are then served to the Deep Neural Network to perform the classification. The performance of suggested method is studied through applying it to the acquired database generated by the designed hardware as well as also in real time message depiction. The maximum classification accuracy 97% for the acquired database & 85% in real time are obtained respectively by comparative analysis. The command messages generated from the proposed system helps the person suffering from neurological disorder to establish the communication link with the outside world in an efficient way. Thus, the proposed novel method shows better performance in real time message depiction purpose as related to other existing methods. [ABSTRACT FROM AUTHOR]

This scientific paper presents a novel approach to explore and predict the potential of imidazole-based organic dyes for use in Dye-Sensitized Solar Cells (DSSCs) using a machine learning web application. The design of efficient and cost-effective organic dyes is critical to enhance the performance of DSSCs. Traditional experimental methods are time-consuming and resource-intensive, making it challenging to screen a large number of potential dyes. In this study, we propose a machine learning-based approach to accelerate the discovery process by predicting the photovoltaic performance of imidazole-based organic dyes. Machin learning predictions provide valuable insights into the expected PCE% and behaviors of the molecules toward DSSCs. Based on the RDKit library, several fingerprints such as Molecular ACCess System, Avalon, Daylight, Pharmacophore and Morgan with different radius (r2, r3, r4), were studied. In addition, more than 20 ML algorithms using different cross validation (3, 5, 7, 10) were also evaluated. Among of these, Deep Neural Network models of MLPRegressor algorithm based on the daylight fingerprint shows a significant coefficient of determination combined with the lowest errors. Utilize the trained ML models to screen of 50 million SMILE structure for identify promising imidazole and nitrogen-containing derivative as a doner group. By replacing the donor groups in the well-known MK2 dye structure with the top imidazole derivatives proposed by machine learning, significant improvements in PCE were observed, increasing from 7.70% to as high as 11.49%, representing nearly a 50% enhancement over the control. DFT calculations confirm the ML predictions and clarify the significantly higher oscillator strength and charge transfer properties of MK2-DM1, compared to MK2. This result provides a promising pathway for developing new dye materials that can push the efficiency limits of DSSCs, leading to more efficient solar energy conversion technologies in the future. In addition, a developed web application offers a user-friendly interface for researchers to input their molecular structures and obtain PCE% predictions toward DSSCs. This information can guide researchers in designing a new imidazole dye with high photovoltaic performance to validate and refine the predictions without time consuming. [ABSTRACT FROM AUTHOR]

Andean highland soils contain significant quantities of soil organic carbon (SOC); however, more efforts still need to be made to understand the processes behind the accumulation and persistence of SOC and its fractions. This study modeled SOC variables—SOC, refractory SOC (RSOC), and the 13C isotope composition of SOC (δ13CSOC)—using machine learning (ML) algorithms in the Central Andean Highlands of Peru, where grasslands and wetlands ("bofedales") dominate the landscape surrounded by Junin National Reserve. A total of 198 soil samples (0.3 m depth) were collected to assess SOC variables. Four ML algorithms—random forest (RF), support vector machine (SVM), artificial neural networks (ANNs), and eXtreme gradient boosting (XGB)—were used to model SOC variables using remote sensing data, land-use and land-cover (LULC, nine categories), climate topography, and sampled physical–chemical soil variables. RF was the best algorithm for SOC and δ13CSOC prediction, whereas ANN was the best to model RSOC. "Bofedales" showed 2–3 times greater SOC (11.2 ± 1.60%) and RSOC (1.10 ± 0.23%) and more depleted δ13CSOC (− 27.0 ± 0.44 ‰) than other LULC, which reflects high C persistent, turnover rates, and plant productivity. This highlights the importance of "bofedales" as SOC reservoirs. LULC and vegetation indices close to the near-infrared bands were the most critical environmental predictors to model C variables SOC and δ13CSOC. In contrast, climatic indices were more important environmental predictors for RSOC. This study's outcomes suggest the potential of ML methods, with a particular emphasis on RF, for mapping SOC and its fractions in the Andean highlands. [ABSTRACT FROM AUTHOR]

Video analytics can achieve increased speed and efficiency by operating directly on the compressed video format, thereby alleviating the decoding burden on the analytics server. The encoded video streams are rich in semantic binary information and this information can be utilized more efficiently to train the classifiers. Motivated by the same notion, a deep learning-based video compression-cum-classification network has been proposed. In the proposed work, the binary-coded semantic information is extracted by using an auto encoder-based video compression component and the same fed to the MobileNetv2-based classifier for the classification of the given video streams based on their content. Using large-scale user-generated content provided by YouTube UGC dataset, it has been demonstrated that using deep neural networks for compression not only provides on-par compression results to traditional methods, it makes analytical processing of these videos faster. Video content tagging of YouTube UGC dataset has been used as the analytics task. The proposed DLVCC approach performs 10 × faster with 30 × fewer parameters than MobileNetv2 in video tagging of compressed video with no loss in accuracy. [ABSTRACT FROM AUTHOR]

Sarcasm is often related to something that has created a mass confusion among the general uninformed public. It is always associated with a mockery tone or trenchancy facial expression or weird language. Existing literatures that are profound in the field of sarcasm detection mainly focused on text-based input with sarcastic comments or facial expression-based analysis, i.e., image input. But both text and image input are not sufficient to analyze the underlying sarcasm behind the scene. This kind of analysis can also be misleading sometimes as the emotional expression can change with social circumstances (i.e., audio tone) over time. Hence to address these challenges, "A Smart Video Analytical framework for Sarcasm Detection using Deep Learning" is introduced where sarcasm detection is done by considering video modality. Proposed model extracts three important features from the video, i.e., text using proposed Enhanced-BERT, image using ImageNet and audio using Librosa. After extraction, each modality is addressed individually and is finally fused using proposed adaptive early fusion approach. The final task prediction of classification is done using novel deep neural network called "SarcasNet-99" to detect sarcasm in video over distributed framework called Apache Storm. TedX and GIF Reply datasets are used for model training and testing with around 10,000 + video clips. When compared against existing state-of-the-art techniques such as AlexNet, DenseNet, SqueezeNet and ResNet, the proposed model predicted accuracy 99.005% with LeakyReLU activation function. [ABSTRACT FROM AUTHOR]

This paper introduces AlphaVision, an innovative decision support model designed for stock price prediction by seamlessly integrating real-time news updates and Return on Investment (ROI) values, utilizing various machine learning and deep learning approaches. The research investigates the application of these techniques to enhance the effectiveness of stock trading and investment decisions by accurately anticipating stock prices and providing valuable insights to investors and businesses. The study begins by analyzing the complexities and challenges of stock market analysis, considering factors like political, macroeconomic, and legal issues that contribute to market volatility. To address these challenges, we proposed the methodology called AlphaVision, which incorporates various machine learning algorithms, including Decision Trees, Random Forest, Naïve Bayes, Boosting, K-Nearest Neighbors, and Support Vector Machine, alongside deep learning models such as Multi-layer Perceptron (MLP), Artificial Neural Networks, and Recurrent Neural Networks. The effectiveness of each model is evaluated based on their accuracy in predicting stock prices. Experimental results revealed that the MLP model achieved the highest accuracy of approximately 92%, outperforming other deep learning models. The Random Forest algorithm also demonstrated promising results with an accuracy of around 84.6%. These findings indicate the potential of machine learning and deep learning techniques in improving stock market analysis and prediction. The AlphaVision methodology presented in this research empowers investors and businesses with valuable tools to make informed investment decisions and navigate the complexities of the stock market. By accurately forecasting stock prices based on news updates and ROI values, the model contributes to better financial management and business sustainability. The integration of machine learning and deep learning approaches offers a promising solution for enhancing stock market analysis and prediction. Future research will focus on extracting more relevant financial features to further improve the model's accuracy. By advancing decision support models for stock price prediction, researchers and practitioners can foster better investment strategies and foster economic growth. The proposed model holds potential to revolutionize stock trading and investment practices, enabling more informed and profitable decision-making in the financial sector. [ABSTRACT FROM AUTHOR]

Objective: To develop a deep neural network for the detection of inflammatory spine in short tau inversion recovery (STIR) sequence of magnetic resonance imaging (MRI) on patients with axial spondyloarthritis (axSpA). Methods: A total 330 patients with axSpA were recruited. STIR MRI of the whole spine and clinical data were obtained. Regions of interests (ROIs) were drawn outlining the active inflammatory lesion consisting of bone marrow edema (BME). Spinal inflammation was defined by the presence of an active inflammatory lesion on the STIR sequence. The 'fake-color' images were constructed. Images from 270 and 60 patients were randomly separated into the training/validation and testing sets, respectively. Deep neural network was developed using attention UNet. The neural network performance was compared to the image interpretation by a radiologist blinded to the ground truth. Results: Active inflammatory lesions were identified in 2891 MR images and were absent in 14,590 MR images. The sensitivity and specificity of the derived deep neural network were 0.80 ± 0.03 and 0.88 ± 0.02, respectively. The Dice coefficient of the true positive lesions was 0.55 ± 0.02. The area under the curve of the receiver operating characteristic (AUC-ROC) curve of the deep neural network was 0.87 ± 0.02. The performance of the developed deep neural network was comparable to the interpretation of a radiologist with similar sensitivity and specificity. Conclusion: The developed deep neural network showed similar sensitivity and specificity to a radiologist with four years of experience. The results indicated that the network can provide a reliable and straightforward way of interpreting spinal MRI. The use of this deep neural network has the potential to expand the use of spinal MRI in managing axSpA. [ABSTRACT FROM AUTHOR]

An urban water demand with high accuracy and reliability plays fundamental role in creating a predictive water supply system. This is necessary to implement mechanisms and systems that can be used to estimate water demands. The paper aims to forecast the amounts of clean water given to metropolis with single multiplicative neuron model artificial neural network. For this purpose, a regular data set of Istanbul metropolis was selected as a model and utilised in the application process. Single multiplicative neuron model artificial neural network is a neural network that does not have the hidden layer unit number problem that many shallow and deep artificial neural networks have. In this study, the black hole optimization algorithm is used for the first time in the literature for the training of the single multiplicative neuron model artificial neural network. In line with the analysis results, it is concluded that the proposed new approach achieved better prediction results than the other compared methods for the time series of amounts of clean water given to metropolis. [ABSTRACT FROM AUTHOR]

Background: Mavacamten is a first-in-class cardiac myosin inhibitor approved by the US Food and Drug Administration (FDA) for symptomatic obstructive hypertrophic cardiomyopathy (HCM). This pharmacovigilance study aimed to assess mavacamten-related adverse drug reactions (ADRs) in the real world as reported in the FDA Adverse Event Reporting System (FAERS). Methods: We conducted disproportionality analyses with four signal detection algorithms—reporting odds ratio (ROR), proportional reporting ratio (PRR), Bayesian confidence propagation neural network, and the multi-item gamma Poisson shrinker to identify mavacamten-related ADRs. Results: Out of 4,500,131 reports from the FAERS database, 1004 mavacamten-related ADRs were identified from 1 January 2022 to 30 September 2023. A total of 26 significant disproportionality preferred terms (PTs) conforming to the four signal detection algorithms were noted. Some of the statistically significant cardiac ADRs at PT level include decreased ejection fraction (EF) [ROR 33.60 (95% confidence interval, CI 21.79–51.82), PRR 32.86 (χ2 615.96), information component (IC) 5.03, IC025 4.61, empirical Bayesian geometric mean (EBGM) 32.77, EBGM05 21.25], cardiac failure [ROR 9.39 (95% CI 6.49–13.60), PRR 9.13 (χ2 202.42), IC 3.19, IC025 2.83, EBGM 9.12, EBGM05 6.30], and atrial fibrillation [ROR 16.63 (95% CI 12.72–21.75), PRR 15.66 (χ2 769.93), IC 3.97, IC025 3.71, EBGM 15.64, EBGM05 11.96]. Conclusions: The results of our study were consistent with the safety data of clinical trials, including reduced ejection fraction, atrial fibrillation, dyspnea, and syncope. We also found potential new and unexpected ADR signals, such as urinary tract infection, gout, and peripheral edema. [ABSTRACT FROM AUTHOR]

Developing non-contact, non-destructive monitoring methods for marine life is crucial for sustainable resource management. Recent monitoring technologies and machine learning analysis advancements have enhanced underwater image and acoustic data acquisition. Systems to obtain 3D acoustic data from beneath the seafloor are being developed; however, manual analysis of large 3D datasets is challenging. Therefore, an automatic method for analyzing benthic resource distribution is needed. This study developed a system to estimate benthic resource distribution non-destructively by combining high-precision habitat data acquisition using high-frequency ultrasonic waves and prediction models based on a 3D convolutional neural network (3D-CNN). The system estimated the distribution of asari clams (Ruditapes philippinarum) in Lake Hamana, Japan. Clam presence and count were successfully estimated in a voxel with an ROC-AUC of 0.9 and a macro-average ROC-AUC of 0.8, respectively. This system visualized clam distribution and estimated numbers, demonstrating its effectiveness for quantifying marine resources beneath the seafloor. [ABSTRACT FROM AUTHOR]

Arsenic (As) contamination in drinking water has been highlighted for its environmental significance and potential health implications. Iron-based filters are cost-effective and sustainable solutions for As removal from contaminated water. Applying Machine Learning (ML) models to investigate and optimize As removal using iron-based filters is limited. The present study developed Deep Learning Neural Network (DLNN) models for predicting the removal of As and other contaminants by iron-based filters from groundwater. A small Original Dataset (ODS) consisting of 20 data points and 13 groundwater parameters was obtained from the field performances of 20 individual iron-amended ceramic filters. Cubic-spline interpolation (CSI) expanded the ODS, generating 1600 interpolated data points (IDPs) without duplication. The Bayesian optimization algorithm tuned the model hyper-parameters and IDPs in a Stratified fivefold Cross-Validation (CV) setup trained all the models. The models demonstrated reliable performances with the coefficient of determination (R2) 0.990–0.999 for As, 0.774–0.976 for Iron (Fe), 0.934–0.954 for Phosphorus (P), and 0.878–0.998 for predicting manganese (Mn) in the effluent. Sobol sensitivity analysis revealed that As (total order index (ST) = 0.563), P (ST = 0.441), Eh (ST = 0.712), and Temp (ST = 0.371) are the most sensitive parameters for the removal of As, Fe, P, and Mn. The comprehensive approach, from data expansion through DLNN model development, provides a valuable tool for estimating optimal As removal conditions from groundwater. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) have achieved remarkable accuracy for numerous applications, yet their complexity often renders the explanation of predictions a challenging task. This complexity contrasts with easily interpretable statistical models, which, however, often suffer from lower accuracy. Our work suggests that this underperformance may stem more from inadequate training methods than from the inherent limitations of model structures. We hereby introduce the Synced Explanation-Enhanced Neural Network (SEE-Net), a novel architecture integrating a guiding DNN with a shallow neural network, functionally equivalent to a two-layer mixture of linear models. This shallow network is trained under the guidance of the DNN, effectively bridging the gap between the prediction power of deep learning and the need for explainable models. Experiments on image and tabular data demonstrate that SEE-Net can leverage the advantage of DNNs while providing an interpretable prediction framework. Critically, SEE-Net embodies a new paradigm in machine learning: it achieves high-level explainability with minimal compromise on prediction accuracy by training an almost "white-box" model under the co-supervision of a "black-box" model, which can be tailored for diverse applications. [ABSTRACT FROM AUTHOR]

Quantum entanglement acts as a crucial part in quantum computation and quantum information, hence quantifying unknown entanglement is an important task. Due to the fact that the amount of entanglement cannot be achieved directly by measuring any physical observables, it remains an open problem to quantify entanglement experimentally. In this work, we provide an effective way to quantify entanglement for the unknown quantum states via artificial neural networks. By choosing the expectation values of measurements as input features and the values of entanglement measures as labels, we train artificial neural network models to predict the entanglement for new quantum states accurately. Our method does not require the full information about unknown quantum states, which highlights the effectiveness and versatility of machine learning in exploring quantum entanglement. [ABSTRACT FROM AUTHOR]

Clinical sleep diagnosis traditionally relies on polysomnography (PSG) and expert manual classification of sleep stages. Recent advancements in deep learning have shown promise in automating sleep stage classification using a single PSG channel. However, variations in PSG acquisition devices and environments mean that the number of PSG channels can differ across sleep centers. To integrate a sleep staging method into clinical practice effectively, it must accommodate a flexible number of PSG channels. In this paper, we proposed FlexSleepTransformer, a transformer-based model designed to handle varying number of input channels, making it adaptable to diverse sleep staging datasets. We evaluated FlexSleepTransformer using two distinct datasets: the public SleepEDF-78 dataset and the local SleepUHS dataset. Notably, FlexSleepTransformer is the first model capable of simultaneously training on datasets with differing number of PSG channels. Our experiments showed that FlexSleepTransformer trained on both datasets together achieved 98% of the accuracy compared to models trained on each dataset individually. Furthermore, it outperformed models trained exclusively on one dataset when tested on the other dataset. Additionally, FlexSleepTransformer surpassed state-of-the-art CNN and RNN-based models on both datasets. Due to its adaptability with varying channels numbers, FlexSleepTransformer holds significant potential for clinical adoption, especially when trained with data from a wide range of sleep centers. [ABSTRACT FROM AUTHOR]

Soybean (Glycine max) is the world's most cultivated legume; currently, most of its varieties are Bt. Spodoptera spp. (Lepidoptera: Noctuidae) are important pests of soybean. An artificial neural network (ANN) is an artificial intelligence tool that can be used in the study of spatiotemporal dynamics of pest populations. Thus, this work aims to determine ANN to identify population regulation factors of Spodoptera spp. and predict its density in Bt soybean. For two years, the density of Spodoptera spp. caterpillars, predators, and parasitoids, climate data, and plant age was evaluated in commercial soybean fields. The selected ANN was the one with the weather data from 25 days before the pest's density evaluation. ANN forecasting and pest densities in soybean fields presented a correlation of 0.863. It was found that higher densities of the pest occurred in dry seasons, with less wind, higher atmospheric pressure and with increasing plant age. Pest density increased with the increase in temperature until this curve reached its maximum value. ANN forecasting and pest densities in soybean fields in different years, seasons, and stages of plant development were similar. Therefore, this ANN is promising to be implemented into integrated pest management programs in soybean fields. [ABSTRACT FROM AUTHOR]

Temperature-related mortality is the leading cause of weather-related deaths in the United States. Herein, we explore the effect of air masses (AMs) – a relatively novel and holistic measure of environmental conditions – on human mortality across 61 cities in the United States. Geographic and seasonal differences in the effects of each AM on deseasonalized and detrended anomalous lagged mortality are examined using simple descriptive statistics, one-way analyses of variance, relative risks of excess mortality, and regression-based artificial neural network (ANN) models. Results show that AMs are significantly related to anomalous mortality in most US cities, and in most seasons. Of note, two of the three cool AMs (Cool and Dry-Cool) each show a strong, but delayed mortality response in all seasons, with peak mortality 2 to 4 days after they occur, with the Dry-Cool AM having nearly a 15% increased risk of excess mortality. Humid-Warm (HW) air masses are associated with increases in deaths in all seasons 0 to 1 days after they occur. In most seasons, these near-term mortality increases are offset by reduced mortality for 1–2 weeks afterwards; however, in summer, no such reduction is noted. The Warm and Dry-Warm AMs show slightly longer periods of increased mortality, albeit slightly less intensely as compared with HW, but with a similar lag structure by season. Meanwhile, the most seasonally consistent results are with transitional weather, whereby passing cold fronts are associated with a significant decrease in mortality 1 day after they occur, while warm fronts are associated with significant increases in mortality at that same lag time. Finally, ANN modeling reveals that AM-mortality relationships gleaned from a combined meta-analysis can actually lead to more skillful modeling of these relationships than models trained on some individual cities, especially in the cities where such relationships might be masked due to low average daily mortality. [ABSTRACT FROM AUTHOR]