Search

This study utilizes the ResNet18 network to classify and recognize trajectories of planar mechanisms. This research begins by deriving formulas for trajectory points in various typical planar mechanisms, and the resulting trajectory images are employed as samples for training and testing the network. The classification of trajectory images for both upright and inverted configurations of a planar four-bar linkage is investigated. Compared with AlexNet and VGG16, the ResNet18 model demonstrates superior classification accuracy during testing, coupled with reduced training time and memory consumption. Furthermore, the ResNet18 model is applied to classify trajectory images for six different planar mechanisms in both upright and inverted configurations as well as to identify whether the trajectory images belong to the upright or inverted configuration for each mechanism. The test results affirm the feasibility and effectiveness of the ResNet18 network in the classification and recognition of planar mechanism trajectories. [ABSTRACT FROM AUTHOR]

For deep model training, an optimization technique is required that minimizes loss and maximizes accuracy. The development of an effective optimization method is one of the most important study areas. The diffGrad optimization method uses gradient changes during optimization phases but does not update 2nd order moments based on 1st order moments, and the AngularGrad optimization method uses the angular value of the gradient, which necessitates additional calculation. Due to these factors, both of those approaches result in zigzag trajectories that take a long time and require additional calculations to attain a global minimum. To overcome those limitations, a novel adaptive deep learning optimization method based on square of first momentum (sqFm) has been proposed. By adjusting 2nd order moments depending on 1st order moments and changing step size according to the present gradient on the non-negative function, the suggested sqFm delivers a smoother trajectory and better image classification accuracy. The empirical research comparing the performance of the proposed sqFm with Adam, diffGrad, and AngularGrad applying non-convex functions demonstrates that the suggested method delivers the best convergence and parameter values. In comparison to SGD, Adam, diffGrad, RAdam, and AngularGrad(tan) using the Rosenbrock function, the proposed sqFm method can attain the global minima gradually with less overshoot. Additionally, it is demonstrated that the proposed sqFm gives consistently good classification accuracy when training CNN networks (ResNet16, ResNet50, VGG34, ResNet18, and DenseNet121) on the CIFAR10, CIFAR100, and MNIST datasets, in contrast to SGDM, diffGrad, Adam, AngularGrad(Cos), and AngularGrad(Tan). The proposed method also gives the best classification accuracy than SGD, Adam, AdaBelief, Yogi, RAdam, and AngularGrad using the ImageNet dataset on the ResNet18 network. Source code link: https://github.com/UtpalNandi/sqFm-A-novel-adaptive-optimization-scheme-for-deep-learning-model. [ABSTRACT FROM AUTHOR]

The high-accuracy detection of multiple distinct human emotions is crucial for advancing affective computing, mental health diagnostics, and human–computer interaction. The integration of deep learning networks with entropy measures holds significant potential in neuroscience and medicine, especially for analyzing EEG-based emotion states. This study proposes a method combining ResNet18 with differential entropy to identify five types of human emotions (happiness, sadness, fear, disgust, and neutral) from EEG signals. Our approach first calculates the differential entropy of EEG signals to capture the complexity and variability of the emotional states. Then, the ResNet18 network is employed to learn feature representations from the differential entropy measures, which effectively captures the intricate spatiotemporal dynamics inherent in emotional EEG patterns using residual connections. To validate the efficacy of our method, we conducted experiments on the SEED-V dataset, achieving an average accuracy of 95.61%. Our findings demonstrate that the combination of ResNet18 with differential entropy is highly effective in classifying multiple distinct human emotions from EEG signals. This method shows robust generalization and broad applicability, indicating its potential for extension to various pattern recognition tasks across different domains. [ABSTRACT FROM AUTHOR]

Pneumonia is a serious disease that can be fatal, particularly among children and the elderly. The accuracy of pneumonia diagnosis can be improved by combining artificial-intelligence technology with X-ray imaging. This study proposes X-ODFCANet, which addresses the issues of low accuracy and excessive parameters in existing deep-learning-based pneumonia-classification methods. This network incorporates a feature coordination attention module and an omni-dimensional dynamic convolution (ODConv) module, leveraging the residual module for feature extraction from X-ray images. The feature coordination attention module utilizes two one-dimensional feature encoding processes to aggregate feature information from different spatial directions. Additionally, the ODConv module extracts and fuses feature information in four dimensions: the spatial dimension of the convolution kernel, input and output channel quantities, and convolution kernel quantity. The experimental results demonstrate that the proposed method can effectively improve the accuracy of pneumonia classification, which is 3.77% higher than that of ResNet18. The model parameters are 4.45M, which was reduced by approximately 2.5 times. The code is available at https://github.com/limuni/X-ODFCANET. [ABSTRACT FROM AUTHOR]

Abstract Pneumonia is a serious disease that can be fatal, particularly among children and the elderly. The accuracy of pneumonia diagnosis can be improved by combining artificial-intelligence technology with X-ray imaging. This study proposes X-ODFCANet, which addresses the issues of low accuracy and excessive parameters in existing deep-learning-based pneumonia-classification methods. This network incorporates a feature coordination attention module and an omni-dimensional dynamic convolution (ODConv) module, leveraging the residual module for feature extraction from X-ray images. The feature coordination attention module utilizes two one-dimensional feature encoding processes to aggregate feature information from different spatial directions. Additionally, the ODConv module extracts and fuses feature information in four dimensions: the spatial dimension of the convolution kernel, input and output channel quantities, and convolution kernel quantity. The experimental results demonstrate that the proposed method can effectively improve the accuracy of pneumonia classification, which is 3.77% higher than that of ResNet18. The model parameters are 4.45M, which was reduced by approximately 2.5 times. The code is available at https://github.com/limuni/X-ODFCANET .

Machine learning and computer vision have proven to be valuable tools for farmers to streamline their resource utilization to lead to more sustainable and efficient agricultural production. These techniques have been applied to strawberry cultivation in the past with limited success. To build on this past work, in this study, two separate sets of strawberry images, along with their associated diseases, were collected and subjected to resizing and augmentation. Subsequently, a combined dataset consisting of nine classes was utilized to fine-tune three distinct pretrained models: vision transformer (ViT), MobileNetV2, and ResNet18. To address the imbalanced class distribution in the dataset, each class was assigned weights to ensure nearly equal impact during the training process. To enhance the outcomes, new images were generated by removing backgrounds, reducing noise, and flipping them. The performances of ViT, MobileNetV2, and ResNet18 were compared after being selected. Customization specific to the task was applied to all three algorithms, and their performances were assessed. Throughout this experiment, none of the layers were frozen, ensuring all layers remained active during training. Attention heads were incorporated into the first five and last five layers of MobileNetV2 and ResNet18, while the architecture of ViT was modified. The results indicated accuracy factors of 98.4%, 98.1%, and 97.9% for ViT, MobileNetV2, and ResNet18, respectively. Despite the data being imbalanced, the precision, which indicates the proportion of correctly identified positive instances among all predicted positive instances, approached nearly 99% with the ViT. MobileNetV2 and ResNet18 demonstrated similar results. Overall, the analysis revealed that the vision transformer model exhibited superior performance in strawberry ripeness and disease classification. The inclusion of attention heads in the early layers of ResNet18 and MobileNet18, along with the inherent attention mechanism in ViT, improved the accuracy of image identification. These findings offer the potential for farmers to enhance strawberry cultivation through passive camera monitoring alone, promoting the health and well-being of the population. [ABSTRACT FROM AUTHOR]

The timely detection of malnutrition in children is of paramount importance, as it allows for early intervention and treatment. This proactive approach not only prevents further health deterioration but also fosters proper growth, minimizing the long-term consequences of malnutrition, such as stunted growth, impaired cognitive development, and increased vulnerability to diseases. Our work encompasses the creation of a new dataset comprising images of children in Healthy, Undernourished, Stunting, and Wasting categories. The core objective is to assess the deep learning model performance in classifying these children images. The experimentation is carried out by varying epochs, batch size, optimizers AdamW, Adamax, and RMSprop; and different values of the learning rate 0.1, 0.01, 0.001, and 0.0001 during model training. The model is trained on image dataset constructed by cleaning images generated by the stable diffusion model. The model is tested on randomly selected child images from websites. The model successfully classified two classes with 95% accuracy, 97.6% F1 score, precision 97.6%, and 97.6% recall with Adam optimizers, 0.0001 learning rate, and Batch size 4. Additionally, for the four-class categorization scenario, the study broadens the classification. The model achieved 88.87% accuracy, 90.3% recall, 90.2% precision, and an F1 score of 90% for four-class categorization with AdamW optimization, 0.0001 learning rate, and batch size 6. These results are satisfactory for prediction of malnutrition category in children. [ABSTRACT FROM AUTHOR]

Brain cancer is a life-threatening disease requiring close attention. Early and accurate diagnosis using non-invasive medical imaging is critical for successful treatment and patient survival. However, manual diagnosis by radiologist experts is time-consuming and has limitations in processing large datasets efficiently. Therefore, efficient systems capable of analyzing vast amounts of medical data for early tumor detection are urgently needed. Deep learning (DL) with deep convolutional neural networks (DCNNs) emerges as a promising tool for understanding diseases like brain cancer through medical imaging modalities, especially MRI, which provides detailed soft tissue contrast for visualizing tumors and organs. DL techniques have become more and more popular in current research on brain tumor detection. Unlike traditional machine learning methods requiring manual feature extraction, DL models are adept at handling complex data like MRIs and excel in classification tasks, making them well-suited for medical image analysis applications. This study presents a novel Dual DCNN model that can accurately classify cancerous and non-cancerous MRI samples. Our Dual DCNN model uses two well-performed DL models, i.e., inceptionV3 and denseNet121. Features are extracted from these models by appending a global max pooling layer. The extracted features are then utilized to train the model with the addition of five fully connected layers and finally accurately classify MRI samples as cancerous or non-cancerous. The fully connected layers are retrained to learn the extracted features for better accuracy. The technique achieves 99%, 99%, 98%, and 99% of accuracy, precision, recall, and f1-scores, respectively. Furthermore, this study compares the Dual DCNN's performance against various well-known DL models, including DenseNet121, InceptionV3, ResNet architectures, EfficientNetB2, SqueezeNet, VGG16, AlexNet, and LeNet-5, with different learning rates. This study indicates that our proposed approach outperforms these established models in terms of performance. [ABSTRACT FROM AUTHOR]

The purpose of this article is to consider modern video stream classification algorithms and select the optimal option suitable for application in video hosting applications. The study analyzed various neural network architectures, including ResNet18, architectures with skip-connections, as well as architectures with multiple parallel branches, on a specially prepared dataset containing video clips from films of various genres. The main attention was paid to finding a balance between accuracy and the dimensionality of processed data. The research results show that different neural network architectures demonstrate varying effectiveness depending on the size of input images and the specifics of genre classification tasks. The obtained data allow conclusions to be drawn about the potential application of deep learning in video content analysis and the selection of the most suitable methods for classifying film genres, which can contribute to improving the quality of video hosting services. [ABSTRACT FROM AUTHOR]

In recent years, the development of intelligent sensor systems has experienced remarkable growth, particularly in the domain of microwave and millimeter wave sensing, thanks to the increased availability of affordable hardware components. With the development of smart Ground-Based Synthetic Aperture Radar (GBSAR) system called GBSAR-Pi, we previously explored object classification applications based on raw radar data. Building upon this foundation, in this study, we analyze the potential of utilizing polarization information to improve the performance of deep learning models based on raw GBSAR data. The data are obtained with a GBSAR operating at 24 GHz with both vertical (VV) and horizontal (HH) polarization, resulting in two matrices (VV and HH) per observed scene. We present several approaches demonstrating the integration of such data into classification models based on a modified ResNet18 architecture. We also introduce a novel Siamese architecture tailored to accommodate the dual input radar data. The results indicate that a simple concatenation method is the most promising approach and underscore the importance of considering antenna polarization and merging strategies in deep learning applications based on radar data. [ABSTRACT FROM AUTHOR]

Abstract As the scale of water conservancy projects continues to expand, the amount and complexity of analytical data have also correspondingly increased. At present, it is difficult to realize project management decision support based on a single data source, and most manual analysis methods not only have high labor costs, but also are prone to the risk of misjudgment, resulting in huge property losses. Based on this problem, this paper proposes visual analysis method for unmanned pumping stations on dynamic platforms based on data fusion technology. First, the method uses the transfer learning method to enable ResNet18 obtain generalization ability. Secondly, the method uses ResNet18 to extract image features, and outputs fixed length sequence data as the input of long short-term memory (LSTM). Finally, the method uses LSTM outputs the classification results. The experimental results demonstrate that the algorithm model can achieve an impressive accuracy of 99.032%, outperforming the combination of traditional feature extraction and machine learning methods. This model effectively recognizes and classifies images of pumping stations, significantly reducing the risk of accidents in these facilities.

Machine learning and deep neural network developments have evolved image classification. This study offers a new neural network design with segmentation and localization, different crack types, categorization accuracy, and efficiency. In the proposed work, an advanced and innovative Spliced Multimodal Residual18 Neural Network (SMR18-NN) Model is presented that departs from previous models. For data authentication, augmentation is done by proposing the new and effective model known as an Augmented Minority Over-sampling Technique (AMOST). The SMR18 NN model combines the well-established ResNet18 framework with the Faster RCNN architecture, incorporating parts from the modified Fast RCNN and the Region Proposal Network. This work aims to revolutionize crack-type recognition and categorization in images. A Support Vector Machine strategically improves the network’s data classification. A modified ResNet18 model is ultimately implemented and compared with the proposed innovative SMR18-NN model. Both network’s parameters, such as epochs, number of iterations, etc., were kept the same for fair evaluation. Innovative frameworks and properly selected benchmark datasets supported this. The empirical results of this comparison study are convincing. ResNet18 training and testing accuracy was 90.60% and 85.20%, respectively. The SMR18-NN outperformed these results with 96.20 training and 92.00% testing accuracy. The experiment concluded with SMR18-NN accurately detecting image features, proving its superiority in image classification.

Objective Modic changes (MCs) are the most prevalent classification system for describing intravertebral MRI signal intensity changes. However, interpreting these intricate MRI images is a complex and time‐consuming process. This study investigates the performance of single shot multibox detector (SSD) and ResNet18 network‐based automatic detection and classification of MCs. Additionally, it compares the inter‐observer agreement and observer‐classifier agreement in MCs diagnosis to validate the feasibility of deep learning network‐assisted detection of classified MCs. Method A retrospective analysis of 140 patients with MCs who underwent MRI diagnosis and met the inclusion and exclusion criteria in Tianjin Hospital from June 2020 to June 2021 was used as the internal dataset. This group consisted of 55 males and 85 females, aged 25 to 89 years, with a mean age of (59.0 ± 13.7) years. An external test dataset of 28 patients, who met the same criteria and were assessed using different MRI equipment at Tianjin Hospital, was also gathered, including 11 males and 17 females, aged 31 to 84 years, with a mean age of 62.7 ± 10.9 years. After Physician 1 (with 15 years of experience) annotated all MRI images, the internal dataset was imported into the deep learning model for training. The model comprises an SSD network for lesion localization and a ResNet18 network for lesion classification. Performance metrics, including accuracy, recall, precision, F1 score, confusion matrix, and inter‐observer agreement parameter Kappa value, were used to evaluate the model's performance on the internal and external datasets. Physician 2 (with 1 year of experience) re‐labeled the internal and external test datasets to compare the inter‐observer agreement and observer‐classifier agreement. Results In the internal dataset, when models were utilized for the detection and classification of MCs, the accuracy, recall, precision and F1 score reached 86.25%, 87.77%, 84.92% and 85.60%, respectively. The Kappa value of the inter‐observer agreement was 0.768 (95% CI: 0.656, 0.847),while observer‐classifier agreement was 0.717 (95% CI: 0.589, 0.809).In the external test dataset, the model's the accuracy, recall, precision and F1 scores for diagnosing MCs reached 75%, 77.08%, 77.80% and 74.97%, respectively. The inter‐observer agreement was 0.681 (95% CI: 0.512, 0.677), and observer‐classifier agreement was 0.519 (95% CI: 0.290, 0.690). Conclusion The model demonstrated strong performance in detecting and classifying MCs, achieving high agreement with physicians in MCs diagnosis. These results suggest that deep learning models have the potential to facilitate the application of intelligent assisted diagnosis techniques in the field of spine research.

Due to its low cost and privacy protection, Channel-State-Information (CSI)-based activity detection has gained interest recently. However, to achieve high accuracy, which is challenging in practice, a significant number of training samples are required. To address the issues of the small sample size and cross-scenario in neural network training, this paper proposes a WiFi human activity-recognition system based on transfer learning using an antenna array: Wi-AR. First, the Intel5300 network card collects CSI signal measurements through an antenna array and processes them with a low-pass filter to reduce noise. Then, a threshold-based sliding window method is applied to extract the signal of independent activities, which is further transformed into time–frequency diagrams. Finally, the produced diagrams are used as input to a pretrained ResNet18 to recognize human activities. The proposed Wi-AR was evaluated using a dataset collected in three different room layouts. The testing results showed that the suggested Wi-AR recognizes human activities with a consistent accuracy of about 94%, outperforming the other conventional convolutional neural network approach. [ABSTRACT FROM AUTHOR]

As the scale of water conservancy projects continues to expand, the amount and complexity of analytical data have also correspondingly increased. At present, it is difficult to realize project management decision support based on a single data source, and most manual analysis methods not only have high labor costs, but also are prone to the risk of misjudgment, resulting in huge property losses. Based on this problem, this paper proposes visual analysis method for unmanned pumping stations on dynamic platforms based on data fusion technology. First, the method uses the transfer learning method to enable ResNet18 obtain generalization ability. Secondly, the method uses ResNet18 to extract image features, and outputs fixed length sequence data as the input of long short-term memory (LSTM). Finally, the method uses LSTM outputs the classification results. The experimental results demonstrate that the algorithm model can achieve an impressive accuracy of 99.032%, outperforming the combination of traditional feature extraction and machine learning methods. This model effectively recognizes and classifies images of pumping stations, significantly reducing the risk of accidents in these facilities. [ABSTRACT FROM AUTHOR]

Objective: Modic changes (MCs) are the most prevalent classification system for describing intravertebral MRI signal intensity changes. However, interpreting these intricate MRI images is a complex and time‐consuming process. This study investigates the performance of single shot multibox detector (SSD) and ResNet18 network‐based automatic detection and classification of MCs. Additionally, it compares the inter‐observer agreement and observer‐classifier agreement in MCs diagnosis to validate the feasibility of deep learning network‐assisted detection of classified MCs. Method: A retrospective analysis of 140 patients with MCs who underwent MRI diagnosis and met the inclusion and exclusion criteria in Tianjin Hospital from June 2020 to June 2021 was used as the internal dataset. This group consisted of 55 males and 85 females, aged 25 to 89 years, with a mean age of (59.0 ± 13.7) years. An external test dataset of 28 patients, who met the same criteria and were assessed using different MRI equipment at Tianjin Hospital, was also gathered, including 11 males and 17 females, aged 31 to 84 years, with a mean age of 62.7 ± 10.9 years. After Physician 1 (with 15 years of experience) annotated all MRI images, the internal dataset was imported into the deep learning model for training. The model comprises an SSD network for lesion localization and a ResNet18 network for lesion classification. Performance metrics, including accuracy, recall, precision, F1 score, confusion matrix, and inter‐observer agreement parameter Kappa value, were used to evaluate the model's performance on the internal and external datasets. Physician 2 (with 1 year of experience) re‐labeled the internal and external test datasets to compare the inter‐observer agreement and observer‐classifier agreement. Results: In the internal dataset, when models were utilized for the detection and classification of MCs, the accuracy, recall, precision and F1 score reached 86.25%, 87.77%, 84.92% and 85.60%, respectively. The Kappa value of the inter‐observer agreement was 0.768 (95% CI: 0.656, 0.847),while observer‐classifier agreement was 0.717 (95% CI: 0.589, 0.809).In the external test dataset, the model's the accuracy, recall, precision and F1 scores for diagnosing MCs reached 75%, 77.08%, 77.80% and 74.97%, respectively. The inter‐observer agreement was 0.681 (95% CI: 0.512, 0.677), and observer‐classifier agreement was 0.519 (95% CI: 0.290, 0.690). Conclusion: The model demonstrated strong performance in detecting and classifying MCs, achieving high agreement with physicians in MCs diagnosis. These results suggest that deep learning models have the potential to facilitate the application of intelligent assisted diagnosis techniques in the field of spine research. [ABSTRACT FROM AUTHOR]

Featured Application: In this paper, the vibration data of CWRU motor bearings is used as the original data to simulate the real working conditions of motor bearings in the working environment of hydrogen station by simulating the noise signal of hydrogen station. Then, the BOA-ResNet18 model is used to diagnose the faults of the added noise signals, and the accuracy of the fault diagnosis is very high, and the experimental results show that this model can be applied in the fault diagnosis of hydrogen station equipment under the working conditions of hydrogen station. The harsh working environment of hydrogen refueling stations often causes equipment failure and is vulnerable to mechanical noise during monitoring. This limits the accuracy of equipment monitoring, ultimately decreasing efficiency. To address this issue, this paper presents a motor bearing vibration signal diagnosis method that employs a Bayesian optimization (BOA) residual neural network (ResNet). The industrial noise signal of the hydrogenation station is simulated and then combined with the motor bearing signal. The resulting one-dimensional bearing signal is processed and transformed into a two-dimensional signal using Fast Fourier Transform (FFT). Afterwards, the signal is segmented using the sliding window translation method to enhance the data volume. After comparing signal feature extraction and classification results from various convolutional neural network models, ResNet18 yields the best classification accuracy, achieving a training accuracy of 89.50% with the shortest computation time. Afterwards, the hyperparameters of ResNet18 such as InitialLearnRate, Momentum, and L2Regularization Parameter are optimized using the Bayesian optimization algorithm. The experiment findings demonstrate a diagnostic accuracy of 99.31% for the original signal model, while the accuracy for the bearing signal, with simulated industrial noise from the hydrogenation station, can reach over 92%. [ABSTRACT FROM AUTHOR]

This study utilizes the ResNet18 network to classify and recognize trajectories of planar mechanisms. This research begins by deriving formulas for trajectory points in various typical planar mechanisms, and the resulting trajectory images are employed as samples for training and testing the network. The classification of trajectory images for both upright and inverted configurations of a planar four-bar linkage is investigated. Compared with AlexNet and VGG16, the ResNet18 model demonstrates superior classification accuracy during testing, coupled with reduced training time and memory consumption. Furthermore, the ResNet18 model is applied to classify trajectory images for six different planar mechanisms in both upright and inverted configurations as well as to identify whether the trajectory images belong to the upright or inverted configuration for each mechanism. The test results affirm the feasibility and effectiveness of the ResNet18 network in the classification and recognition of planar mechanism trajectories.

The high-accuracy detection of multiple distinct human emotions is crucial for advancing affective computing, mental health diagnostics, and human–computer interaction. The integration of deep learning networks with entropy measures holds significant potential in neuroscience and medicine, especially for analyzing EEG-based emotion states. This study proposes a method combining ResNet18 with differential entropy to identify five types of human emotions (happiness, sadness, fear, disgust, and neutral) from EEG signals. Our approach first calculates the differential entropy of EEG signals to capture the complexity and variability of the emotional states. Then, the ResNet18 network is employed to learn feature representations from the differential entropy measures, which effectively captures the intricate spatiotemporal dynamics inherent in emotional EEG patterns using residual connections. To validate the efficacy of our method, we conducted experiments on the SEED-V dataset, achieving an average accuracy of 95.61%. Our findings demonstrate that the combination of ResNet18 with differential entropy is highly effective in classifying multiple distinct human emotions from EEG signals. This method shows robust generalization and broad applicability, indicating its potential for extension to various pattern recognition tasks across different domains.

Wheat is a significant cereal for humans, with diverse varieties. The growth of the wheat industry and the protection of breeding rights can be promoted through the accurate identification of wheat varieties. To recognize wheat seeds quickly and accurately, this paper proposes a convolutional neural network-based image-recognition method for wheat seeds, namely GC_DRNet. The model is based on the ResNet18 network and incorporates the dense network idea by changing its residual module to a dense residual module and introducing a global contextual module, reducing the network model's parameters and improving the network's recognition accuracy. Experiments were conducted on the self-constructed wheat-seed dataset and the publicly available dataset CIFAR-100 by combining GC_DRNet with network models such as ResNet18, ResNet34, ResNet50, and DenseNet121. The GC_DRNet model achieved a recognition accuracy of 96.98% on the wheat-seed dataset, which was improved by 2.34%, 1.43%, 2.05%, and 1.77% compared to ResNet18, ResNet34, ResNet50, and DenseNet121, respectively. On the CIFAR-100 dataset, the recognition accuracy of the GC_DRNet model was 80.77%, which improved the accuracy of ResNet18, ResNet34, ResNet50, and DenseNet121 by 8.19%, 1.6%, 9.59%, and 16.29%, respectively. Analyzing the confusion-matrix results of the wheat-seed dataset, the average recognition precision of the test set was 97.02%, the recall rate was 96.99%, and the F1 value was 96.98%. The parameter size of the GC_DRNet model was smaller than that of the other three models, only 11.65MB. The experimental results show that the GC_DRNet has a high level of recognition accuracy and detection capability for images of wheat seeds and provides technical support for wheat-seed identification. [ABSTRACT FROM AUTHOR]

By the end of the 2020s, full autonomy in autonomous driving may become commercially viable in certain regions. However, achieving Level 5 autonomy requires crucial collaborations between vehicles and infrastructure, necessitating high-speed data processing and low-latency capabilities. This paper introduces a vehicle tracking algorithm based on roadside LiDAR (light detection and ranging) infrastructure to reduce the latency to 100 ms without compromising the detection accuracy. We first develop a vehicle detection architecture based on ResNet18 that can more effectively detect vehicles at a full frame rate by improving the BEV mapping and the loss function of the optimizer. Then, we propose a new three-stage vehicle tracking algorithm. This algorithm enhances the Hungarian algorithm to better match objects detected in consecutive frames, while time–space logicality and trajectory similarity are proposed to address the short-term occlusion problem. Finally, the system is tested on static scenes in the KITTI dataset and the MATLAB/Simulink simulation dataset. The results show that the proposed framework outperforms other methods, with F1-scores of 96.97% and 98.58% for vehicle detection for the KITTI and MATLAB/Simulink datasets, respectively. For vehicle tracking, the MOTA are 88.12% and 90.56%, and the ID-F1 are 95.16% and 96.43%, which are better optimized than the traditional Hungarian algorithm. In particular, it has a significant improvement in calculation speed, which is important for real-time transportation applications. [ABSTRACT FROM AUTHOR]

Abstract Breast Cancer (BC) has been increasing in incidence among women for a variety of reasons, and prompt detection and management are essential to reducing mortality rates. In the context of clinical-level breast cancer screening, the needle biopsy sample is used to generate Breast Histology Images (BHIs), which will then be used to confirm the results. Using a novel Deep-Learning Plan (DLP), the proposed work identifies BHI accurately and confirms the severity of BC by confirming its severity. As part of the proposed DLP implementation, four phases are involved: (i) the collection and enhancement of images, (ii) the extraction of features, (iii) the reduction of features and their integration, and (iv) binary classification and validation. The purpose of this study is to optimize deep features and machine features using particle swarm algorithms. To evaluate the performance of the proposed scheme, we compare the results obtained using individual deep features, dual deep features, and hybrid features. Using the hybrid image features in the classifier, this study has determined that ResNet18 with k-nearest neighbor provides superior classification accuracy (> 94%).

Abstract This study aims to discriminate between leucine-rich glioma-inactivated 1 (LGI1) antibody encephalitis and gamma-aminobutyric acid B (GABAB) receptor antibody encephalitis using a convolutional neural network (CNN) model. A total of 81 patients were recruited for this study. ResNet18, VGG16, and ResNet50 were trained and tested separately using 3828 positron emission tomography image slices that contained the medial temporal lobe (MTL) or basal ganglia (BG). Leave-one-out cross-validation at the patient level was used to evaluate the CNN models. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) were generated to evaluate the CNN models. Based on the prediction results at slice level, a decision strategy was employed to evaluate the CNN models’ performance at patient level. The ResNet18 model achieved the best performance at the slice (AUC = 0.86, accuracy = 80.28%) and patient levels (AUC = 0.98, accuracy = 96.30%). Specifically, at the slice level, 73.28% (1445/1972) of image slices with GABAB receptor antibody encephalitis and 87.72% (1628/1856) of image slices with LGI1 antibody encephalitis were accurately detected. At the patient level, 94.12% (16/17) of patients with GABAB receptor antibody encephalitis and 96.88% (62/64) of patients with LGI1 antibody encephalitis were accurately detected. Heatmaps of the image slices extracted using gradient-weighted class activation mapping indicated that the model focused on the MTL and BG for classification. In general, the ResNet18 model is a potential approach for discriminating between LGI1 and GABAB receptor antibody encephalitis. Metabolism in the MTL and BG is important for discriminating between these two encephalitis subtypes.

In recent years, the development of intelligent sensor systems has experienced remarkable growth, particularly in the domain of microwave and millimeter wave sensing, thanks to the increased availability of affordable hardware components. With the development of smart Ground-Based Synthetic Aperture Radar (GBSAR) system called GBSAR-Pi, we previously explored object classification applications based on raw radar data. Building upon this foundation, in this study, we analyze the potential of utilizing polarization information to improve the performance of deep learning models based on raw GBSAR data. The data are obtained with a GBSAR operating at 24 GHz with both vertical (VV) and horizontal (HH) polarization, resulting in two matrices (VV and HH) per observed scene. We present several approaches demonstrating the integration of such data into classification models based on a modified ResNet18 architecture. We also introduce a novel Siamese architecture tailored to accommodate the dual input radar data. The results indicate that a simple concatenation method is the most promising approach and underscore the importance of considering antenna polarization and merging strategies in deep learning applications based on radar data.

Plant diseases are common factors restricting crop yield and quality. For individuals without training, it is still difficult to identify various diseases accurately because many leaf diseases are similar in colour, shape and other aspects. Requiring an expert diagnosis can cause delays and lead to increasing costs. Therefore, this paper proposes an improved convolutional neural network for recognition of tomato leaf diseases. The experimental dataset was from the publicly available dataset PlantVillage. Based on the original ResNet18 model, a new convolutional neural network, TomatoNet, was constructed by adding a squeeze‐and‐excitation module and modifying the classifier structure. The results show that the average recognition accuracy of the TomatoNet network is 99.63%, which is 0.53% higher than the ResNet18 network. In addition, the recognition accuracy improved from 88.97% to 98.35% after the improvement of the AlexNet network. Finally, the superiority of TomatoNet was verified by comparison with other advanced models. This experiment verifies the feasibility of a deep learning algorithm for plant leaf disease recognition, which can provide a more efficient and convenient solution for detecting plant leaf disease. [ABSTRACT FROM AUTHOR]

Copyright of Electric Power Engineering Technology is the property of Editorial Department of Electric Power Engineering Technology 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.)

This study aims to discriminate between leucine-rich glioma-inactivated 1 (LGI1) antibody encephalitis and gamma-aminobutyric acid B (GABAB) receptor antibody encephalitis using a convolutional neural network (CNN) model. A total of 81 patients were recruited for this study. ResNet18, VGG16, and ResNet50 were trained and tested separately using 3828 positron emission tomography image slices that contained the medial temporal lobe (MTL) or basal ganglia (BG). Leave-one-out cross-validation at the patient level was used to evaluate the CNN models. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) were generated to evaluate the CNN models. Based on the prediction results at slice level, a decision strategy was employed to evaluate the CNN models' performance at patient level. The ResNet18 model achieved the best performance at the slice (AUC = 0.86, accuracy = 80.28%) and patient levels (AUC = 0.98, accuracy = 96.30%). Specifically, at the slice level, 73.28% (1445/1972) of image slices with GABAB receptor antibody encephalitis and 87.72% (1628/1856) of image slices with LGI1 antibody encephalitis were accurately detected. At the patient level, 94.12% (16/17) of patients with GABAB receptor antibody encephalitis and 96.88% (62/64) of patients with LGI1 antibody encephalitis were accurately detected. Heatmaps of the image slices extracted using gradient-weighted class activation mapping indicated that the model focused on the MTL and BG for classification. In general, the ResNet18 model is a potential approach for discriminating between LGI1 and GABAB receptor antibody encephalitis. Metabolism in the MTL and BG is important for discriminating between these two encephalitis subtypes. [ABSTRACT FROM AUTHOR]

Detection of atrial fibrillation (AF) remains one of the major concerns in the field of medical research. AF is one of the main cause for stroke. AF is characterized by irregular heartbeats and absence of P waves in electrocardiogram (ECG) signal. In this article, we propose a method, combining Poincare plot derived and RR interval‐based features to classify given ECG signal into normal, AF and other rhythms. Classification and regression tree, K‐nearest neighbor, support vector machine, artificial neural network, ResNet18, convolutional neural network (CNN)‐long short term memory (LSTM) are implemented for classification of ECG signal. The class specific accuracies for the three rhythms are computed. Physionet challenge 2017 database is used for evaluation and testing of the developed algorithm. The database has 5154 normal, 771 AF, 2557 other rhythm and 46 noisy signals. Three Poincare derived features viz: SD1, SD2, and ratio of SD1 to SD2, three RR interval features viz: Mean stepping increment of RR interval, approximate entropy and sample entropy are computed and are given to classifiers. During fivefold cross‐validation, CNN‐LSTM classifier showed best result with class specific accuracy for normal of 96.65%, AF of 97.55%, other rhythms of 94.87%, overall accuracy of 96.17% and F1 score of 0.9589. The developed technique can bring change in conventional practice in AF diagnosis and can aid the physician as an assisted tool. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Ordnance Equipment Engineering is the property of Chongqing University of Technology 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.)

Due to its low cost and privacy protection, Channel-State-Information (CSI)-based activity detection has gained interest recently. However, to achieve high accuracy, which is challenging in practice, a significant number of training samples are required. To address the issues of the small sample size and cross-scenario in neural network training, this paper proposes a WiFi human activity-recognition system based on transfer learning using an antenna array: Wi-AR. First, the Intel5300 network card collects CSI signal measurements through an antenna array and processes them with a low-pass filter to reduce noise. Then, a threshold-based sliding window method is applied to extract the signal of independent activities, which is further transformed into time–frequency diagrams. Finally, the produced diagrams are used as input to a pretrained ResNet18 to recognize human activities. The proposed Wi-AR was evaluated using a dataset collected in three different room layouts. The testing results showed that the suggested Wi-AR recognizes human activities with a consistent accuracy of about 94%, outperforming the other conventional convolutional neural network approach.

Human facial emotion detection is one of the challenging tasks in computer vision. Owing to high inter-class variance, it is hard for machine learning models to predict facial emotions accurately. Moreover, a person with several facial emotions increases the diversity and complexity of classification problems. In this paper, we have proposed a novel and intelligent approach for the classification of human facial emotions. The proposed approach comprises customized ResNet18 by employing transfer learning with the integration of triplet loss function (TLF), followed by SVM classification model. Using deep features from a customized ResNet18 trained with triplet loss, the proposed pipeline consists of a face detector used to locate and refine the face bounding box and a classifier to identify the facial expression class of discovered faces. RetinaFace is used to extract the identified face areas from the source image, and a ResNet18 model is trained on cropped face images with triplet loss to retrieve those features. An SVM classifier is used to categorize the facial expression based on the acquired deep characteristics. In this paper, we have proposed a method that can achieve better performance than state-of-the-art (SoTA) methods on JAFFE and MMI datasets. The technique is based on the triplet loss function to generate deep input image features. The proposed method performed well on the JAFFE and MMI datasets with an accuracy of 98.44% and 99.02%, respectively, on seven emotions; meanwhile, the performance of the method needs to be fine-tuned for the FER2013 and AFFECTNET datasets. [ABSTRACT FROM AUTHOR]

Featured Application: The present investigation shows a methodology that can support a speech therapist by automatically classifying various types of speech disorders. This work deals with automatically detecting stuttering and its subclasses. An effective classification of stuttering along with its subclasses could find wide application in determining the severity of stuttering by speech therapists, preliminary patient diagnosis, and enabling communication with the previously mentioned voice assistants. The first part of this work provides an overview of examples of classical and deep learning methods used in automated stuttering classifications as well as databases and features used. Then, two classical algorithms (k-NN (k-nearest neighbor) and SVM (support vector machine) and several deep models (ConvLSTM; ResNetBiLstm; ResNet18; Wav2Vec2) are examined on the available stuttering dataset. The experiments investigate the influence of individual signal features such as Mel-Frequency Cepstral Coefficients (MFCCs), pitch-determining features in the signal, and various 2D speech representations on the classification results. The most successful algorithm, i.e., ResNet18, can classify speech disorders at the F1 measure of 0.93 for the general class. Additionally, deep learning shows superiority over a classical approach to stuttering disorder detection. However, due to insufficient data and the quality of the annotations, the results differ between stuttering subcategories. Observation of the impact of the number of dense layers, the amount of data in the training set, and the amount of data divided into the training and test sets on the effectiveness of stuttering event detection is provided for further use of this methodology. [ABSTRACT FROM AUTHOR]

For the problems of complex model structure and too many training parameters in facial expression recognition algorithms, we proposed a residual network structure with a multi-headed channel attention (MCA) module. The migration learning algorithm is used to pre-train the convolutional layer parameters and mitigate the overfitting caused by the insufficient number of training samples. The designed MCA module is integrated into the ResNet18 backbone network. The attention mechanism highlights important information and suppresses irrelevant information by assigning different coefficients or weights, and the multi-head structure focuses more on the local features of the pictures, which improves the efficiency of facial expression recognition. Experimental results demonstrate that the model proposed in this paper achieves excellent recognition results in Fer2013, CK+ and Jaffe datasets, with accuracy rates of 72.7%, 98.8% and 93.33%, respectively. [ABSTRACT FROM AUTHOR]

For debris flow disasters in valleys image classification problems, this paper improved the Resnet18 network, an improved convolution neural network model is put forward, through adding residual attention in network structure module, solved the original model to extract the image features to solve the problem of poor, edge model accurately capture the debris flow disasters in valleys in the image contour and internal ridge information.In addition, this paper also conducts comparative experiments on various attention mechanism structures, analyzes their differences, and obtains the attention mechanism network most suitable for debris flow disaster gully data.The experimental results show that the classification accuracy of the improved network model in debris flow disaster gullies reaches 75.42%, and its classification performance is improved by 5.1% compared with the Resnet18 network model.

Convolutional Neural Network (CNN) is used to train a Malaysian vanity license plate recognition model to recognize vanity license plate available in Malaysia. A transfer learning method is applied in this project to train the model. The type of transfer learning used is finetuning. A modified pretrained ResNet18 network architecture is used to train the Malaysian vanity license plate recognition model. Some hyperparameters such as batch size, learning rate, step size, gamma and momentum are set before training. The optimizer used in this project is SGD (Stochastic Gradient Descent). The available Malaysian vanity license plate images provided by Tapway Sdn Bhd consist of 3 types of Malaysian vanity license plates, which are MALAYSIA, PUTRAJAYA and NORMAL LP (known as Normal License plate). All the images are randomly split into training set (70 % of the total images), validation set (20 % of the total images), and testing set (10 % of the total images) for training. After that, the images are cropped, normalized and transformed into tensors for training. The training is carried out for 70 epochs. Both models trained from original and modified pretrained ResNet18 network architectures are compared and discussed. The accuracy for both models of Malaysian vanity license plate recognition models is 92%. Both training models using the original ResNet18 and modified ResNet18 network architecture approach can be used to train the Malaysian vanity license plate recognition model and obtain similar results.

Most of the wheat produced and consumed worldwide is generally bread wheat and is used for bread making. Bread wheat varieties can affect the quality of bread. When comparing bread wheat to other varieties, there may be differences in taste, cost, and impact on human health. This study aims to classify bread wheat varieties using deep learning methods. Wheat cultivars used in this research ('Ayten Abla', 'Bayraktar 2000', 'Hamitbey', 'Şanlı', and 'Tosunbey') were obtained from the Central Field Crop Research Institute, Ministry of Agriculture and Forestry, Republic of Türkiye. First, a dataset of 8354 images of these wheat varieties was created. Then, the images in this dataset were trained with tree different Convolutional Neural Networks (CNNs) using the transfer learning method. The CNN models used are Inception-V3, Mobilenet-V2, and Resnet18, and the classification accuracies obtained are 97.37%, 97.07%, and 97.67%, respectively. Finally, the images not used for training and validation of the CNN models were segmented using image processing techniques. The segmented images were classified as bread wheat and unidentified seeds in the Resnet18 CNN model. [ABSTRACT FROM AUTHOR]

Pedestrian inertial navigation technology plays an important role in indoor positioning technology. However, low-cost inertial sensors in smart devices are affected by bias and noise, resulting in rapidly increasing and accumulating errors when integrating double acceleration to obtain displacement. The data-driven class of pedestrian inertial navigation algorithms can reduce sensor bias and noise in IMU data by learning motion-related features through deep neural networks. Inspired by the RoNIN algorithm, this paper proposes a data-driven class algorithm, RBCN-Net. Firstly, the algorithm adds NAM and CBAM attention modules to the residual network ResNet18 to enhance the learning ability of the network for channel and spatial features. Adding the BiLSTM module can enhance the network's ability to learn over long distances. Secondly, we construct a dataset VOIMU containing IMU data and ground truth trajectories based on visual inertial odometry (total distance of 18.53 km and total time of 5.65 h). Finally, the present algorithm is compared with CNN, LSTM, ResNet18 and ResNet50 networks in VOIMU dataset for experiments. The experimental results show that the RMSE values of RBCN-Net are reduced by 6.906, 2.726, 1.495 and 0.677, respectively, compared with the above networks, proving that the algorithm effectively improves the accuracy of pedestrian navigation. [ABSTRACT FROM AUTHOR]