Search

Demand for perishable food is sensitive to product prices and is affected by the prices of similar or alternative products. While brand loyalty influences the demand for products, determining a reasonable price requires a precise pricing strategy. In this paper, a pricing model for perishable food is presented in which the brand value of the product and the price of other manufacturers as competitors are considered. To this end, this study first predicts the price of competitors using a combination of optimized Neural Networks and presents an optimized model using a Genetic Algorithm. This algorithm combines a Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and a Genetic Algorithm (GA). The proposed model is then used to merge with a game-theory model for the pricing of perishable foods. In this game-theory model, pricing approaches are developed based on identified prices of competitors. In the coordination contract game-theory model, Multi Retailer- one Supplier and Price-sensitive demand of Perishable product are developed with and without quantity discount contract. Obtained results indicate that independent procurement provides retailers with higher profit, while lower profit will be presented when coordination is not considered. Also, with coordination, the ordering cycle increases, and the ordering frequency decrease. [ABSTRACT FROM AUTHOR]

Automatic determination of manufacturing process sequences for the physical production of given part designs is key to facilitate on-demand cyber manufacturing. In this work, we propose an integrated framework that (i) identifies manufacturing features from 3D part designs using a Graph Neural Network (GNN), (ii) identifies the manufacturing processes necessary to produce all features in the part using a Convolutional Neural Network (CNN) that considers shape, material properties, and quality information, and (iii) outputs an ordered manufacturing sequence that can produce the designed part with the help of sequence mining. Using these methods, the knowledge required to enable automated manufacturing process selection is easily scalable and updatable without requiring manual population of ad-hoc or rule-based descriptions. We present exemplar implementations of the proposed framework by suggesting manufacturing sequences for discrete parts with multiple features. The suggested manufacturing sequences demonstrate the potential of the proposed framework for use in future on-demand cyber manufacturing applications. [ABSTRACT FROM AUTHOR]

BACKGROUND: Noninvasively detecting epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma patients before targeted therapy remains a challenge. This study aimed to develop a 3-dimensional (3D) convolutional neural network (CNN)-based deep learning model to predict EGFR mutation status using computed tomography (CT) images. METHODS: We retrospectively collected 660 patients from 2 large medical centers. The patients were divided into training (n=528) and external test (n=132) sets according to hospital source. The CNN model was trained in a supervised end-to-end manner, and its performance was evaluated using an external test set. To compare the performance of the CNN model, we constructed 1 clinical and 3 radiomics models. Furthermore, we constructed a comprehensive model combining the highest-performing radiomics and CNN models. The receiver operating characteristic (ROC) curves were used as primary measures of performance for each model. Delong test was used to compare performance differences between different models. RESULTS: Compared with the clinical [training set, area under the curve (AUC) =69.6%, 95% confidence interval (CI), 0.661-0.732; test set, AUC =68.4%, 95% CI, 0.609-0.752] and the highest-performing radiomics models (training set, AUC =84.3%, 95% CI, 0.812-0.873; test set, AUC =72.4%, 95% CI, 0.653-0.794) models, the CNN model (training set, AUC =94.3%, 95% CI, 0.920-0.961; test set, AUC =94.7%, 95% CI, 0.894-0.978) had significantly better predictive performance for predicting EGFR mutation status. In addition, compared with the comprehensive model (training set, AUC =95.7%, 95% CI, 0.942-0.971; test set, AUC =87.4%, 95% CI, 0.820-0.924), the CNN model had better stability. CONCLUSIONS: The CNN model has excellent performance in non-invasively predicting EGFR mutation status in patients with lung adenocarcinoma and is expected to become an auxiliary tool for clinicians.

Cervical cancer is one of the biggest challenges in global health, thus it forms a critical need for early detection technologies that could improve patient prognosis and inform treatment decisions. This development in the form of an early detection mechanism increases the chances of successful treatment and survival, as early diagnosis promptly offers interventions that can dramatically reduce the rate of deaths attributed to this disease. Here, a customized Convolutional Neural Network (CNN) model is proposed for cervical cancerous cell detection. It includes three convolutional layers with increasing filter sizes and max-pooling layers, followed by dropout and dense layers for improved feature extraction and robust learning. By using ResNet models as inspiration, the model further innovates by incorporating skip connections into the CNN design. By enabling direct feature transmission from earlier to later layers, skip links enhance gradient flow and help preserve important spatial information. By boosting feature propagation, this integration increases the model's ability to recognize minute patterns in cervical cell images, hence increasing classification accuracy. In our methodology, the SIPaKMeD dataset has been employed which contains 4049 cervical cell images that are arranged into five different categories. To address class imbalance, Generative Adversarial Networks (GANs) have been applied for data augmentation; that is, synthetic images have been created, that improve the diversity of the dataset and further enhance the robustness of the same. The present model is astonishingly accurate in classifying five cervical cell types: koilocytes, superficial-intermediate, parabasal, dyskeratotic, and metaplastic, thus significantly enhancing early detection and diagnosis of cervical cancer. The model gives an excellent performance because it has a validation accuracy of 99.11% and a training accuracy of 99.82%. It is a reliable model in the diagnosis of cervical cancerous cells because it ensures advancement in the computer-assisted cervical cancer detection system. [ABSTRACT FROM AUTHOR]

Computer-aided Medical Image Segmentation (MIS) plays a leading role in diagnosing diseases automatically. MIS is used extensively in diagnosing medical ailments to obtain clinically relevant information of the shapes and volumes of the target organs and tissues. In order to facilitate accurate segmentation, a Block Attention Based Deep Residual Neural Network, i.e., CBAR-UNet model, is proposed to perform cardiac image segmentation on short axis Magnetic Resonance Images (MRI) stacks from top to bottom slice. The Automated Cardiac Diagnosis Challenge (ACDC) dataset is used in the proposed work, which comprise of a 3D MRI of 100 patients (i.e., 200 MRI stacks). Further, 3D MRIs are converted into 2D by slicing each image to train the model, and Contrast Limited Adaptive Histogram Equalization (CLAHE) is performed on the 2D dataset. Residual connections are introduced that aid in training deeper models. Convolutional Block Attention Module (CBAM) is also added in the proposed network, which consists of Spatial and Channel attention that enhances the spatial and channel-wise features in the image by providing information like 'what' and 'where' to pay attention respectively. To test and validate the proposed methodology, extensive experimentations were conducted and it was observed that proposed image segmentation model delivers better results by 2.47% when compared to both 2D and 3D State-Of-The-Art (SOTA) methods with a Dice Score of 0.9428. [ABSTRACT FROM AUTHOR]

A proper system for identifying leaf disease, which is crucial for developing agricultural areas, has been addressed in this research using a neural network approach. This study helps find plant illnesses and their stages whenever they occur. Fungal, bacterial, and viral infections are very harmful to plants. Five major tomato diseases have been classified in this research: bacterial spot, early blight, late blight, leaf mold, tomato mosaic virus, and healthy tomato plant leaves. The study underscores the importance of algorithmic adaptability to attain precision in leaf disease identification and emphasizes the potential for customized strategies in achieving accuracy. The classification is done by extracting color, shape, and texture features from a healthy tomato plant leaf image. The feature extraction method is carried out to proceed with the segmentation phase. Features extracted from segmented pictures are used as inputs to a classification algorithm. These five categories were used to finalize the illness categorization stage. The variety of five kinds of tomato leaf images yielded almost 99% classification accuracy. Furthermore, various research gaps have been identified to achieve a more open approach to detecting tomato diseases. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, intracerebral hemorrhage (ICH) has garnered significant attention as a severe cerebrovascular disorder. To enhance the accuracy of ICH detection and segmentation, this study proposed an improved fuzzy C-means (FCM) algorithm and performed a comparative analysis with both traditional FCM and advanced convolutional neural network (CNN) algorithms. Experiments conducted on the publicly available CT-ICH dataset evaluated the performance of these three algorithms in predicting ICH volume. The results demonstrated that the improved FCM algorithm offered notable improvements in computational time and resource consumption compared to the traditional FCM algorithm, while also showing enhanced accuracy. However, it still lagged behind the CNN algorithm in areas such as feature extraction, model generalization, and the ability to handle complex image structures. The study concluded with a discussion of potential directions for further optimizing the FCM algorithm, aiming to bridge the performance gap with CNN algorithms and provide a reference for future research in medical image processing. [ABSTRACT FROM AUTHOR]

Identifying events using surveillance videos is a major source that reduces crimes and illegal activities. Specifically, abnormal event detection gains more attention so that immediate responses can be provided. Video processing using conventional techniques identifies the events but fails to categorize them. Recently deep learning-based video processing applications provide excellent performances however the architecture considers either spatial or temporal features for event detection. To enhance the detection rate and classification accuracy in abnormal event detection from video keyframes, it is essential to consider both spatial and temporal features. Earlier approaches consider any one of the features from keyframes to detect the anomalies from video frames. However, the results are not accurate and prone to errors sometimes due to video environmental and other factors. Thus, two-stream hybrid deep learning architecture is presented to handle spatial and temporal features in the video anomaly detection process to attain enhanced detection performances. The proposed hybrid models extract spatial features using YOLO-V4 with VGG-16, and temporal features using optical FlowNet with VGG-16. The extracted features are fused and classified using hybrid CNN-LSTM model. Experimentation using benchmark UCF crime dataset validates the proposed model performances over existing anomaly detection methods. The proposed model attains maximum accuracy of 95.6% which indicates better performance compared to state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

The advancement in satellite image sensors has enabled the acquisition of high-resolution remote sensing (HRRS) images. However, interpreting these images accurately and obtaining the computational power needed to do so is challenging due to the complexity involved. This manuscript proposed a multi-stream convolutional neural network (CNN) fusion framework that involves multi-scale and multi-CNN integration for HRRS image recognition. The pre-trained CNNs were used to learn and extract semantic features from multi-scale HRRS images. Feature extraction using pre-trained CNNs is more efficient than training a CNN from scratch or fine-tuning a CNN. Discriminative canonical correlation analysis (DCCA) was used to fuse deep features extracted across CNNs and image scales. DCCA reduced the dimension of the features extracted from CNNs while providing a discriminative representation by maximizing the within-class correlation and minimizing the between-class correlation. The proposed model has been evaluated on NWPU-RESISC45 and UC Merced datasets. The accuracy associated with DCCA was 10% and 6% higher than discriminant correlation analysis (DCA) in the NWPU-RESISC45 and UC Merced datasets. The advantage of DCCA was better demonstrated in the NWPU-RESISC45 dataset due to the incorporation of richer within-class variability in this dataset. While both DCA and DCCA minimize between-class correlation, only DCCA maximizes the within-class correlation and, therefore, attains better accuracy. The proposed framework achieved higher accuracy than all state-of-the-art frameworks involving unsupervised learning and pre-trained CNNs and 2–3% higher than the majority of fine-tuned CNNs. The proposed framework offers computational time advantages, requiring only 13 s for training in NWPU-RESISC45, compared to a day for fine-tuning the existing CNNs. Thus, the proposed framework achieves a favourable balance between efficiency and accuracy in HRRS image recognition. [ABSTRACT FROM AUTHOR]

Traditional methods for measuring single-cell mechanical characteristics face several challenges, including lengthy measurement times, low throughput, and a requirement for advanced technical skills. To overcome these challenges, a novel machine learning (ML) approach is implemented based on the convolutional neural networks (CNNs), aiming at predicting cells' elastic modulus and constitutive equations from their deformations while passing through micro-constriction channels. In the present study, the computational fluid dynamics technology is used to generate a dataset within the range of the cell elastic modulus, incorporating three widely-used constitutive models that characterize the cellular mechanical behavior, i.e., the Mooney-Rivlin (M-R), Neo-Hookean (N-H), and Kelvin-Voigt (K-V) models. Utilizing this dataset, a multi-input convolutional neural network (MI-CNN) algorithm is developed by incorporating cellular deformation data as well as the time and positional information. This approach accurately predicts the cell elastic modulus, with a coefficient of determination R2 of 0.999, a root mean square error of 0.218, and a mean absolute percentage error of 1.089%. The model consistently achieves high-precision predictions of the cellular elastic modulus with a maximum R2 of 0.99, even when the stochastic noise is added to the simulated data. One significant feature of the present model is that it has the ability to effectively classify the three types of constitutive equations we applied. The model accurately and reliably predicts single-cell mechanical properties, showcasing a robust ability to generalize. We demonstrate that incorporating deformation features at multiple time points can enhance the algorithm's accuracy and generalization. This algorithm presents a possibility for high-throughput, highly automated, real-time, and precise characterization of single-cell mechanical properties. [ABSTRACT FROM AUTHOR]

This research displays inspect a study on the classification of human skin diseases using medical imaging, with a focus on data privacy preservation. Skin disease diagnosis is primarily done visually and can be challenging due to variant colors and complex formation of diseases. The proposed solution involves an image dataset with seven classes of skin disease, a convolutional neural network (CNN) model, and image augmentation to increase dataset size and model generalization. The suggested CNN model attained an average precision of 86% and an average recall of 81% for all seven classes of skin diseases. To safeguard the privacy of the data, a federated learning method was used, in which the information was split among 500, 1000, and 2000 users. With the proposed scheme which based on CNN for disease classification and the federated learning method, the average accuracy was 82.42%, 87.26%, and 93.25% for the different numbers of clients. The findings show that it may be possible to effectively categorize skin illnesses by employing a CNN-based approach coupled with federated learning in order to achieve this goal. This would be conducted without compromising the confidentiality of patient data. [ABSTRACT FROM AUTHOR]

In the agricultural sector, tomato leaf diseases signify a lot because they result in a lower crop yield and quality. Timely detection and classification of diseases help to ensure early interventions and effective treatment solutions. Nonetheless, the existing methods are confined by the dataset imbalance which affects class distribution negatively and thus results in poor models, especially for rare diseases. The research is designed to improve the capability of tomato leaf disease identification by investing a new deep-learning method beyond the challenge of imbalanced class distribution. By balancing the dataset, we aim to improve classification accuracy as we pay more attention to the under-represented classes. The proposed GAN-based method that combines the Weighted Loss Function to produce tomato leaf disease synthetic images is underrepresented. They improve the quality of the entire dataset, and the images from every class are now in a more balanced proportion. A CNN, which is the convolutional neural network, is trained for the classifier, with the weighted loss function as a part of the model. We used Genetic Algorithm (GA) for hyperparameter optimization of the CNN. It helps in emphasizing the learning process from the under-represented class. The suggested one will not only decrease the accuracy of tomato leaf disease detection but also increase it. Therefore, the synthetic images created by GAN enhance the dataset since the class distribution is brought to equilibrium. The incorporation of the weighted loss function into the model's training process makes it very effective in handling with the class instability problem and consequently, the model can identify both common and rare diseases. From the outcomes of this study, it can be concluded that it is feasible to employ GAN and one loser weights function to solve the problem of class imbalance in tomato leaf disease recognition. A suggested approach that increases the model's accuracy and reliability could be a good move to enhancing a reliable method of disease detection in the agricultural sector. [ABSTRACT FROM AUTHOR]

Video deepfake detection has emerged as a critical field within the broader domain of digital technologies driven by the rapid proliferation of AI-generated media and the increasing threat of its misuse for deception and misinformation. The integration of Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) has proven to be a promising approach for improving video deepfake detection, achieving near-perfect accuracy. CNNs enable the effective extraction of spatial features from video frames, such as facial textures and lighting, while LSTM analyses temporal patterns, detecting inconsistencies over time. This hybrid model enhances the ability to detect deepfakes by combining spatial and temporal analysis. However, the existing research lacks systematic evaluations that comprehensively assess their effectiveness and optimal configurations. Therefore, this paper provides a comprehensive review of video deepfake detection techniques utilising hybrid CNN-LSTM models. It systematically investigates state-of-the-art techniques, highlighting common feature extraction approaches and widely used datasets for training and testing. This paper also evaluates model performance across different datasets, identifies key factors influencing detection accuracy, and explores how CNN-LSTM models can be optimised. It also compares CNN-LSTM models with non-LSTM approaches, addresses implementation challenges, and proposes solutions for them. Lastly, open issues and future research directions of video deepfake detection using CNN-LSTM will be discussed. This paper provides valuable insights for researchers and cyber security professionals by reviewing CNN-LSTM models for video deepfake detection contributing to the advancement of robust and effective deepfake detection systems. [ABSTRACT FROM AUTHOR]

The rapid evolution of computer technology has significantly impacted the field of medicine, particularly in the utilization of information and image evidence. In the realm of sports medicine, this technological advancement plays a crucial role in ensuring sports safety, especially in the context of injury recovery following sports-related activities. The necessity to interpret and utilize a vast amount of sports medical data effectively has emerged as a pivotal research avenue. This paper delves into the challenges associated with extracting, studying, and the accuracy training of complex algorithms essential for analyzing critical sporting medical data. Central to this discussion is introducing an Optimized Convolutional Neural Network (OCNN) model, which is based on deep learning principles. This model is designed to enhance the detection and risk assessment of diseases related to sport medicine. It incorporates a novel Self-Adjustment Resizing algorithm (SAR), augmented by a self-coding method of convolution (SCM). The proposed OCNN model comprises two convolutional layers, two pooling layers, a fully connected layer, and a SoftMax structure. This architecture is tailored for the classification and analysis of sport-related medical data. [ABSTRACT FROM AUTHOR]

This study introduces an innovative "Big Model" strategy to enhance Bridge Structural Health Monitoring (SHM) using a Convolutional Neural Network (CNN), time-frequency analysis, and fine element analysis. Leveraging ensemble methods, collaborative learning, and distributed computing, the approach effectively manages the complexity and scale of large-scale bridge data. The CNN employs transfer learning, fine-tuning, and continuous monitoring to optimize models for adaptive and accurate structural health assessments, focusing on extracting meaningful features through time-frequency analysis. By integrating Finite Element Analysis, time-frequency analysis, and CNNs, the strategy provides a comprehensive understanding of bridge health. Utilizing diverse sensor data, sophisticated feature extraction, and advanced CNN architecture, the model is optimized through rigorous preprocessing and hyperparameter tuning. This approach significantly enhances the ability to make accurate predictions, monitor structural health, and support proactive maintenance practices, thereby ensuring the safety and longevity of critical infrastructure. [ABSTRACT FROM AUTHOR]

Epilepsy is a brain disorder that causes patients to have multiple seizures. About 30% of patients with epilepsy are not treated with medication or surgery. The abnormal activity of brain before occurring of a seizure (about a few minutes before a seizure occurs) are known as the preictal area. Therefore, if we can predict this state, we can control possible seizures by using appropriate medications. In this study, we present a method for predicting epileptic seizures using electroencephalogram (EEG) signals. The method can identify the preictal region that occurs before the onset of seizures. In our proposed method, first the noise removal of EEG signals is performed, and then the necessary features are extracted using a convolution neural network. Finally, we use the feature vectors in order to train multiple classifiers, fully connected layer, random forest, and support vector machines with linear kernel. Additionally, we apply maximum voting, which is an ensemble method, to classify preictal segments from interictal ones. In this study, using EEG signals of patients from CHB‐MIT dataset, we were able to achieve sensitivity of 90.76%. [ABSTRACT FROM AUTHOR]

Malware poses a significant threat to cybersecurity, continuously evolving to evade traditional detection methods. Deep learning (DL) offers a promising avenue for addressing this challenge by leveraging its ability to learn complex patterns from large amounts of data. This paper introduces a novel deep learning architecture that combines convolutional neural network (CNN), long short-term memory network (LSTM), and radial basis function network (RBF) to extract discriminative features from malware images. Our model captures both low-level visual details and high-level semantic information for robust and accurate malware classification. The Softmax layer assigns probabilities to different malware classes, enabling precise classification. We evaluated the model on three diverse datasets: Malimg, MaleVis, and Microsoft Big 2015, each differing in malware families, image characteristics, and collection methods. The model achieved accuracy rates of 99.06%, 93.55%, and 97.52% on these datasets, respectively, demonstrating its effectiveness and potential in malware image classification. [ABSTRACT FROM AUTHOR]

This study was conducted to improve the process quality and productivity of the scroll compressor fixed parts for high-efficiency air conditioners. We have developed a defect detection technique for scroll fixed components through vision inspection due to lack of manpower when a defect occurs in the processing process and a long time to analyze the cause of the defect. In general, conventional vision inspection has low detection capability when there are various defect items such as complex shapes, defect types, sizes, and locations. However, in this study, we developed improvement measures for process defects through the application of AI algorithms with a machine vision inspection automation system. The model was classified and designed to facilitate AI learning by classifying images by standard based on scroll fixed component images collected with vision in the field, and setting brightness and regions of interest. Defect detection of fixed scroll components was determined by applying a CNN deep learning algorithm by increasing the amount of data using data augmentation techniques. [ABSTRACT FROM AUTHOR]

During the last decades photovoltaic solar energy has continuously increased its share in the electricity mix and has already surpassed 5% globally. Even though photovoltaic (PV) installations are considered to require very little maintenance, their efficient exploitation relies on accounting for certain environmental factors that affect energy generation. One of these factors is the soiling of the PV surface, which could be observed in different forms, such as dust and bird droppings. In this study, visible spectrum data and machine learning algorithms were used for the identification of soiling. A methodology for preprocessing the images is proposed, which puts focus on any soiling of the PV surface. The performance of six classification machine learning algorithms is evaluated and compared—convolutional neural network (CNN), support vector machine (SVM), random forest (RF), k-nearest neighbor (kNN), naïve-Bayes, and decision tree. During the training and validation phase, RF proved to be the best-performing model with an F1 score of 0.935, closely followed by SVM, CNN, and kNN. However, during the testing phase, the trained CNN achieved the highest performance, reaching F1 = 0.913. SVM closely followed it with a score of 0.895, while the other two models returned worse results. Some results from the application of the optimal model after specific weather events are also presented in this study. They confirmed once again that the trained convolutional neural network can be successfully used to evaluate the soiling state of photovoltaic surfaces. [ABSTRACT FROM AUTHOR]

AbstractThis study compares three transfer learning strategies for adapting convolutional neural network (CNN) models in near-infrared spectroscopy to new instruments. Strategy 1 freezes pre-trained weights except for the output layer; Strategy 2 fine-tunes all weights with new data; Strategy 3 adds new fully connected layers to the pre-trained model. Using tablet spectra to predict active pharmaceutical ingredient content, results show that fine-tuning all network weights (Strategy 2) yields the best performance. The study also finds that moderate training sample sizes balance model accuracy and resource expenditure. Transfer learning is effective for near-infrared model transfer. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Brain tumours are anomalous growths or clusters of cells in or encircling the brain. These tumours are perhaps detected and classified using magnetic resonance imaging (MRI), which plays an influential role in the identification of tumours. Brain tumours are suspiciously difficult to classify because of their heterogeneity. The manual detection of tumours is a time-wasting and complex process that can lead to a misdiagnosis. To overcome these drawbacks, the progression of deep learning (DL)-based convolutional neural network models is used to diagnose brain tumours using MRI. This research proposes a compound scaling with maximum entropy classifier-based deep learning model to classify brain tumours as pituitary, meningioma, glioma, and no tumour. To enhance the quality of the images, various pre-processing techniques are used. Data augmentation techniques are used to add up the number of images to enrich the training of our proposed model. With and without augmentation results are compared and showed that the proposed model with augmentation gives excellent results for classification. Experimental results show that the proposed model achieves 99.86% accuracy during training, 99.65% accuracy during validation, and a great classification accuracy of 99.24% during testing. In addition to the F1 score, recall, precision, micro-average, macro-average, and weighted average were used in this study. The existing state-of-the-art DL algorithms such as VGG16, VGG19, ResNet50, InceptionV3, and DenseNet121 are used for comparative analysis. [ABSTRACT FROM AUTHOR]

Neonatal seizures result from a decreased supply of oxygen to the brain during the neonatal period, leading to neurological disorders and abnormal neuronal activity. Electroencephalography (EEG) is employed to monitor brain signals, and Fourier series and transformations are applied to analyze the frequency of these signals. Feature extraction is performed using the grey-level co-occurrence matrix (GLCM), a statistical method that analyses EEG images by scaling them between 0 and 1 before applying a classifier algorithm. Detecting neonatal seizures is particularly challenging due to the complexity of understanding EEG signals in neonates. Various classification algorithms, such as K-Nearest Neighbour (K-NN), Naïve Bayes, Logistic Regression, Decision Tree (D.T.), and Random Tree, are employed to identify seizure occurrences from EEG signals. The proposed classification approach leverages the AlexNet algorithm, demonstrating superior performance and accuracy compared to existing classification methods in the detection of neonatal seizures. The efficiency of the proposed methodology lies in its ability to train the machine rapidly, achieving a reduced training error rate of 25%, facilitated by the incorporation of maxpooling and softmax layers in the classification algorithms. The overall accuracy of the system reaches 94%, with a specificity of 96%, enabling automated and effective detection of neonatal seizures. [ABSTRACT FROM AUTHOR]

Aiming at the sequential and nonlinear characteristics of power quality data over a long time span, a set of PQ evaluation and early warning system on DG distribution network based on deep learning is proposed. The intelligent power distribution network power quality monitoring and early warning system aims to realize the monitoring and forecasting and early warning functions of multiple indicators of power quality in the distribution network. First, we use the sliding window to convert the power quality data into a number of square graphs with time as the scale; second, we use the feature extraction advantage of (Convolutional Neural Network, CNN) to extract the features of each square graph sample and extract it. The characteristic information is transformed into the input of (Long Short Term Memory, LSTM) in a time series sequence; finally, according to the output of CNN-LSTM is used to complete the power quality data prediction of the active distribution network. Through an IEEE 13-node active distribution network simulation example with distributed power sources, this method decouples the feature extraction, analysis, and prediction tasks of power quality data and simplifies the prediction work. Compared with the selected control model, it is significantly to improve the prediction accuracy. [ABSTRACT FROM AUTHOR]

Background: This paper employs deep learning in the classification of soybean wilting, a plant health indicator affected by external pressures, using a Convolutional Neural Network (CNN) with a pre-trained model. It highlights the promise of deep learning in agriculture by examining the relevance of wilting, evolution in the agricultural sector and applications in crop wellness monitoring. Methods: A CNN is used in the study to classify soybean withering, with special attention to the VGG16 pre-trained model. Deep learning's ability to interpret complex data patterns is harnessed for intelligent and accurate wilting detection. A smart detection system tailored for soybean wilting is developed, incorporating recent advancements and addressing associated challenges. Result: The CNN model, notably VGG16, achieves 76% overall accuracy in distinguishing healthy and wilted soybean leaves, signifying a transformative shift in soybean crop health management. The approach offers a precise, efficient and sustainable solution supported by state-of-the-art CNN technology, advancing soybean cultivation practices. [ABSTRACT FROM AUTHOR]

Chest X-ray imaging is a critical diagnostic tool for identifying pulmonary diseases. However, manual interpretation of these images is time-consuming and error-prone. Automated systems utilizing convolutional neural networks (CNNs) have shown promise in improving the accuracy and efficiency of chest X-ray image classification. While previous work has mainly focused on using feature maps from the final convolution layer, there is a need to explore the benefits of leveraging additional layers for improved disease classification. Extracting robust features from limited medical image datasets remains a critical challenge. In this paper, we propose a novel deep learning-based multilayer multimodal fusion model that emphasizes extracting features from different layers and fusing them. Our disease detection model considers the discriminatory information captured by each layer. Furthermore, we propose the fusion of different-sized feature maps (FDSFM) module to effectively merge feature maps from diverse layers. The proposed model achieves a significantly higher accuracy of 97.21% and 99.60% for both three-class and two-class classifications, respectively. The proposed multilayer multimodal fusion model, along with the FDSFM module, holds promise for accurate disease classification and can also be extended to other disease classifications in chest X-ray images. [ABSTRACT FROM AUTHOR]

Background: Lesion detection is one of the most important clinical tasks in positron emission tomography (PET) for oncology. An anthropomorphic model observer (MO) designed to replicate human observers (HOs) in a detection task is an important tool for assessing task‐based image quality. The channelized Hotelling observer (CHO) has been the most popular anthropomorphic MO. Recently, deep learning MOs (DLMOs), mostly based on convolutional neural networks (CNNs), have been investigated for various imaging modalities. However, there have been few studies on DLMOs for PET. Purpose: The goal of the study is to investigate whether DLMOs can predict HOs better than conventional MOs such as CHO in a two‐alternative forced‐choice (2AFC) detection task using PET images with real anatomical variability. Methods: Two types of DLMOs were implemented: (1) CNN DLMO, and (2) CNN‐SwinT DLMO that combines CNN and Swin Transformer (SwinT) encoders. Lesion‐absent PET images were reconstructed from clinical data, and lesion‐present images were reconstructed with adding simulated lesion sinogram data. Lesion‐present and lesion‐absent PET image pairs were labeled by eight HOs consisting of four radiologists and four image scientists in a 2AFC detection task. In total, 2268 pairs of lesion‐present and lesion‐absent images were used for training, 324 pairs for validation, and 324 pairs for test. CNN DLMO, CNN‐SwinT DLMO, CHO with internal noise, and non‐prewhitening matched filter (NPWMF) were compared in the same train‐test paradigm. For comparison, six quantitative metrics including prediction accuracy, mean squared errors (MSEs) and correlation coefficients, which measure how well a MO predicts HOs, were calculated in a 9‐fold cross‐validation experiment. Results: In terms of the accuracy and MSE metrics, CNN DLMO and CNN‐SwinT DLMO showed better performance than CHO and NPWMF, and CNN‐SwinT DLMO showed the best performance among the MOs evaluated. Conclusions: DLMO can predict HOs more accurately than conventional MOs such as CHO in PET lesion detection. Combining SwinT and CNN encoders can improve the DLMO prediction performance compared to using CNN only. [ABSTRACT FROM AUTHOR]

Currently, the number of vehicles in circulation continues to increase steadily, leading to a parallel increase in vehicular accidents. Among the many causes of these accidents, human factors such as driver drowsiness play a fundamental role. In this context, one solution to address the challenge of drowsiness detection is to anticipate drowsiness by alerting drivers in a timely and effective manner. Thus, this paper presents a Convolutional Neural Network (CNN)-based approach for drowsiness detection by analyzing the eye region and Mouth Aspect Ratio (MAR) for yawning detection. As part of this approach, endpoint delineation is optimized for extraction of the region of interest (ROI) around the eyes. An NVIDIA Jetson Nano-based device and near-infrared (NIR) camera are used for real-time applications. A Driver Drowsiness Artificial Intelligence (DD-AI) architecture is proposed for the eye state detection procedure. In a performance analysis, the results of the proposed approach were compared with architectures based on InceptionV3, VGG16, and ResNet50V2. Night-Time Yawning–Microsleep–Eyeblink–Driver Distraction (NITYMED) was used for training, validation, and testing of the architectures. The proposed DD-AI network achieved an accuracy of 99.88% with the NITYMED test data, proving superior to the other networks. In the hardware implementation, tests were conducted in a real environment, resulting in 96.55% and 14 fps on average for the DD-AI network, thereby confirming its superior performance. [ABSTRACT FROM AUTHOR]

With the 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 on the condition that an abundance 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. Therefore, SAR target recognition in the situation of few-shot, where only a scarce few labeled samples are available, is a fundamental problem that needs to be solved. In this paper, a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) is put forward to specially tackle the few-shot SAR ATR tasks. To be specific, a feature-extraction network based on a customized and region-aware convolution is first developed. This network 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, an enhanced prototypical network is proposed. This network 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, the OpenSARShip dataset, and the SAMPLE+ dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks. [ABSTRACT FROM AUTHOR]

With limited dynamic range in consumer-level photographs and electronic displays, high dynamic range images can be rendered as the standard dynamic range image by tone mapping algorithms. To quantify the distortion of tone-mapped images (TMIs), different descriptors or network architectures are explored for quality-aware measurement. Although promising performances have been achieved, they are still limited by three problems: (1) The exposure attribute has not been accurately measured; (2) many deep learning methods, only with the extremely limited reliable ground truth data without the exploitation of quality ranking between different TMIs, are difficult to achieve effective backpropagation; and (3) these methods only use single-task learning (i.e., predict quality score), which ignore the promotion of related tasks. In this paper, we propose a Tone-Mapped Quality Index via multi-task and exposure-prior learning, called meTMQI. We first use quality-discriminative TMI pairs which can be obtained in large quantities to train a purpose-designed Siamese network. Second, multi-task learning is employed to predict quality score, rank score pairs, and classify quality levels, aiming to enhance the predict accuracy in terms of quality. Then, we propose an exposure-prior generation module, which helps to measure the exposure attribute for joint optimization. Experiments are executed on the benchmark datasets, and the results show the effectiveness and generalization ability with other image quality assessment models. [ABSTRACT FROM AUTHOR]

As a deep learning method, Convolutional Neural Network (CNN) can be used in image recognition, fault diagnosis and so on. Due to the internal parameter optimisation problem, the Particle Swarm Optimisation (PSO) has been introduced, but PSO is easy to fall into local optimal solution. In this paper, an adaptive CNN based on Quantum Particle Swarm Optimisation (QPSO-CNN) is proposed and applied to rolling bearings fault diagnosis, which increases the richness of particles and makes it easy to find the global optimal solution. Firstly, the one-dimensional time-series data is compressed by piecewise aggregate approximation algorithm and converted into the heat map by the Gramian angular field algorithm; Secondly, QPSO algorithm is used to search the best CNN model to fit the data set; Finally, the training and validation set are used to search the best network architecture, and the test set is used to test the diagnostic accuracy of the best CNN model, which show that the proposed method has high accuracy. [ABSTRACT FROM AUTHOR]

The acoustic signals used by tool wear monitoring systems adopted in microdrilling are degraded by the noise present in manufacturing environments. To overcome this problem, the present study designed a system containing a 4 × 4 microelectromechanical system microphone array and a three-axis accelerometer to achieve accurate tool wear monitoring in noisy manufacturing environments. Features that were moderately to strongly correlated with tool wear were selected as inputs for this system's one-dimensional (1D) convolutional neural network (CNN) model for predicting tool wear. Pearson correlation analysis revealed that the frequency-domain signal features captured by a 4 × 4 microphone array with minimum variance distortion-less response (MVDR) beamforming had stronger correlations with tool wear than did those captured by a 4 × 4 or 1 × 2 microphone array with delay-and-sum beamforming or by a single microphone; this was because the signals captured by the 4 × 4 array with MVDR beamforming were less noisy. For the aforementioned microphone configurations, under the presence of noise, the 1D CNN model predicted severe wear with higher accuracy when it was trained using fused high-correlation features obtained from the signals captured by the 4 × 4 microphone array with MVDR beamforming and an accelerometer (97.6%) than when it was trained using unfused signal features captured by the accelerometer (86.7%) or the 4 × 4 microphone array with MVDR beamforming (90.3%) alone. The tool wear prediction accuracy obtained using the aforementioned fused features was close to that obtained using fused features acquired from the signals of one microphone and an accelerometer in a quiet environment (97.0%). [ABSTRACT FROM AUTHOR]