Network ResNet Research Articles

Research on Road Pattern Recognition of a Vision-Guided Robot Based on Improved-YOLOv8

In order to promote the accurate recognition and application of visual navigation robots to the environment, this paper carried out research on the road pattern recognition of a vision-guided robot based on improved YOLOv8 on the basis of road pattern calibration and experimental sampling. First, an experimental system for road image shooting was built independently, and 21 different kinds of road pattern image data were obtained by sampling roads with different weather conditions, road materials, and degrees of damage. Second, the road pattern recognition model based on the classical neural network Resnet 18 was constructed for model training and testing, and the initial recognition of road pattern was realized. Third, the YOLOv8 target detection model was introduced to build the road pattern recognition model based on YOLOv8n, and the model was trained and tested, improving road pattern recognition accuracy and recognition response speed by 3.1% and 200%, respectively. Finally, to further improve the accuracy of road pattern recognition, improvement research was carried out on the YOLOv8n road pattern recognition model based on the C2f-ODConv module, the AWD adaptive weight downsampling module, the EMA attention mechanism, and the collaboration of the three modules. Three network architectures, classical CNN (Resnet 18), YOLOv8n, and improved YOLOv8n, were compared. The results show that four different optimization models can further improve the accuracy of road pattern recognition, among which the accuracy of the improved YOLO v8 road pattern recognition model based on multimodule cooperation is the highest, reaching more than 93%.

Determining the quality level of ready to-eat stuffed mussels with Arduino-based electronic nose

In this study, the performance of a pre-designed and low-cost Arduino electronic nose for determining the quality of stuffed mussels was analyzed. In addition, 1000 images were taken on each storage day in order to determine the quality levels of stuffed mussel groups with open and closed shells by machine learning. Freshness limit values of stuffed mussels were determined as 200 for MQ3 and MQ135 sensors and 100 for MQ9 on the 3rd storage day when the total viable count (TVC) value exceeded 3 log CFU/g. In the study, faster neural networks with lower prediction times, such as SqueezeNet and GoogLeNet, were compared with ResNet-50, ResNet-101 and DenseNet-201 neural networks, which have larger prediction times but better accuracy. Study data showed that residual network (ResNet) 50 and Teachable Machine (TM) had high success in determining the quality levels of stuffed mussels.

Comparative Analysis of CNN Architectures for SIBI Image Classification

The classification of images from the Indonesian Sign Language System (SIBI) using VGG16, ResNet50, Inception, Xception, and MobileNetV2 Convolutional Neural Network (CNN) architectures is evaluated in this paper. With Google Colab Pro, a 224 × 224-pixel picture dataset was used for the study. A five-stage technique consisting of Dataset Collection, Dataset Preprocessing, Model Design, Model Training, and Model Testing was applied. Performance evaluation focused on accuracy, precision, recall, and F1-Score. The results identified VGG16 as the top-performing model with an accuracy of 99.60% and an equivalent F1-Score, followed closely by ResNet50 with nearly similar performance. Inception, XCeption, and MobileNetV2 demonstrated balanced performance but with lower accuracy. This study sheds light on the best CNN models to choose for SIBI image classification, and it makes recommendations for further research that include using sophisticated data augmentation methods, investigating novel CNN architectures, and putting the models to practical use.

An accurate object detection of wood defects using an improved Faster R-CNN model

ABSTRACT Wood defect classification and location are crucial for automatic repair and reuse in wood product manufacture, which requires high accuracy and efficiency in the engineering practice. In this paper, a novel modeling method is proposed for faster R-CNN to improve the object detection of wood defect. An improved ResNet-50 network, a focal loss function, and a soft non-maximum suppression (soft NMS) were adopted to replace the counterparts of the initial Faster R-CNN. Experiments were conducted on a wood defect dataset with seven types of defects. The experimental results indicate that the using of the improved ResNet-50 network brings a significant increase in mean average precision (mAP) by 4.4% and reduces the detection time by 3.6% than that of the traditional Faster R-CNN on wood defect detection. Besides, mAPs are 3.4% and 2.8% higher than that of the traditional Faster R-CNN as the employment of the focal loss function and soft NMS, respectively. Finally, the proposed model obtains better mAP than the classic target detection networks. Results demonstrate the effectiveness and feasibility of the proposed modeling method in engineering applications.

Hybrid Artificial Intelligence Approach to COVID-19 Diagnosis from CT Images: Deep Networks and Classification Analysis

Using lung images obtained by computed tomography (CT), this study aims to detect coronavirus (Covid-19) disease with deep learning (DL) techniques. The study included 751 lung CT images from 118 Covid-19 patients and 628 lung CT images from 100 healthy individuals. In total, 70% of the 1379 images were used for training and 30% for testing. In the study, two different methods were proposed on the same dataset. In the first method, the images were trained on AlexNet, VGG-16, VGG-19, GoogleNet and a proposed network. The performance metrics obtained from the five networks were compared and it was observed that the proposed network achieved the highest accuracy value with 95.61%. In the second method, the images were trained on VGG-16, VGG-19, DenseNet-121, ResNet-50 and MobileNet networks. Among the image features obtained from each of these networks, the best 1000 features were selected by Principal Component Analysis (PCA). The best 1000 features were classified with Random Forest (RF) and Support Vector Machines (SVM). According to the classification results, the best 1000 features selected from the features extracted by the VGG-16 and MobileNet networks were obtained with the highest accuracy rate of 93.94% using SVM. It is thought that this study can be a helpful tool in the diagnosis of Covid-19 disease while reducing time and labor costs with the use of artificial intelligence (AI).

Osteoporosis Prediction Using VGG16 and ResNet50

Low bone mass and structural degradation are the hallmarks of osteoporosis, a disorder that increases the risk of fractures, especially in the elderly. For prompt intervention and fracture prevention, early identification is essential. However, osteoporosis is frequently not detected until advanced stages by existing diagnostic techniques. In order to overcome this difficulty, scientists suggest using machine learning to automatically identify osteoporosis early in X-ray pictures. Utilizing two cutting- edge convolutional neural network architectures, ResNet50 and VGG16, their system was pretrained on extensive datasets and refined on a carefully selected dataset of X-ray pictures. When identifying images as suggestive of osteoporosis or normal bone density, the ResNet50 model showed an accuracy of 98%, whereas the VGG16 model achieved 78% accuracy. By combining these models and using sophisticated image segmentation methods, the system detects early osteoporosis indications with an overall accuracy of 96%. This automated method has the potential to decrease the incidence of fractures linked to osteoporosis, enable early treatment initiation, and increase the rate of early diagnosis.

Deep neural network for the prediction of KRAS, NRAS, and BRAF genotypes in left-sided colorectal cancer based on histopathologic images

BackgroundThe KRAS, NRAS, and BRAF genotypes are critical for selecting targeted therapies for patients with metastatic colorectal cancer (mCRC). Here, we aimed to develop a deep learning model that utilizes pathologic whole-slide images (WSIs) to accurately predict the status of KRAS, NRAS, and BRAFV600E. Methods129 patients with left-sided colon cancer and rectal cancer from the Third Affiliated Hospital of Sun Yat-sen University were assigned to the training and testing cohorts. Utilizing three convolutional neural networks (ResNet18, ResNet50, and Inception v3), we extracted 206 pathological features from H&E-stained WSIs, serving as the foundation for constructing specific pathological models. A clinical feature model was then developed, with carcinoembryonic antigen (CEA) identified through comprehensive multiple regression analysis as the key biomarker. Subsequently, these two models were combined to create a clinical-pathological integrated model, resulting in a total of three genetic prediction models. Result103 patients were evaluated in the training cohort (1782,302 image tiles), while the remaining 26 patients were enrolled in the testing cohort (489,481 image tiles). Compared with the clinical model and the pathology model, the combined model which incorporated CEA levels and pathological signatures, showed increased predictive ability, with an area under the curve (AUC) of 0.96 in the training and an AUC of 0.83 in the testing cohort, accompanied by a high positive predictive value (PPV 0.92). ConclusionThe combined model demonstrated a considerable ability to accurately predict the status of KRAS, NRAS, and BRAFV600E in patients with left-sided colorectal cancer, with potential application to assist doctors in developing targeted treatment strategies for mCRC patients, and effectively identifying mutations and eliminating the need for confirmatory genetic testing.

Automatic classification and segmentation of blast cells using deep transfer learning and active contours.

Acute lymphoblastic leukemia (ALL) presents a formidable challenge in hematological malignancies, necessitating swift and precise diagnostic techniques for effective intervention. The conventional manual microscopy of blood smears, although widely practiced, suffers from significant limitations including labor-intensity and susceptibility to human error, particularly in distinguishing the subtle differences between normal and leukemic cells. To overcome these limitations, our research introduces the ALLDet classifier, an innovative tool employing deep transfer learning for the automated analysis and categorization of ALL from White Blood Cell (WBC) nuclei images. Our investigation encompassed the evaluation of nine state-of-the-art pre-trained convolutional neural network (CNN) models, namely VGG16, VGG19, ResNet50, ResNet101, DenseNet121, DenseNet201, Xception, MobileNet, and EfficientNetB3. We augmented this approach by incorporating a sophisticated contour-based segmentation technique, derived from the Chan-Vese model, aimed at the meticulous segmentation of blast cell nuclei in blood smear images, thereby enhancing the accuracy of our analysis. The empirical assessment of these methodologies underscored the superior performance of the EfficientNetB3 model, which demonstrated exceptional metrics: a recall specificity of 98.5%, precision of 95.86%, F1-score of 97.16%, and an overall accuracy rate of 97.13%. The Chan-Vese model's adaptability to the irregular shapes of blast cells and its noise-resistant segmentation capability were key to capturing the complex morphological changes essential for accurate segmentation. The combined application of the ALLDet classifier, powered by EfficientNetB3, with our advanced segmentation approach, emerges as a formidable advancement in the early detection and accurate diagnosis of ALL. This breakthrough not only signifies a pivotal leap in leukemia diagnostic methodologies but also holds the promise of significantly elevating the standards of patient care through the provision of timely and precise diagnoses. The implications of this study extend beyond immediate clinical utility, paving the way for future research to further refine and enhance the capabilities of artificial intelligence in medical diagnostics.

Enhancing Robotic Grasping Detection Accuracy With the R2CNN Algorithm and Force-Closure

Abstract This study aims to use an improved rotational region convolutional neural network (R2CNN) algorithm to detect the grasping bounding box for the robotic arm that reaches supermarket goods. This algorithm can calculate the final predicted grasping bounding box without any additional architecture, which significantly improves the speed of grasp inferences. In this study, we added the force-closure condition so that the final grasping bounding box could achieve grasping stability in a physical sense. We experimentally demonstrated that deep model-treated object detection and grasping detection are the same tasks. We used transfer learning to improve the prediction accuracy of the grasping bounding box. In particular, the ResNet-101 network weights, which were originally used in object detection, were used to continue training with the Cornell dataset. In terms of grasping detection, we used the trained model weights that were originally used in object detection as the features of the to-be-grasped objects and fed them to the network for continuous training. For 2828 test images, this method achieved nearly 98% accuracy and a speed of 14–17 frames per second.

An attention mechanism module with spatial perception and channel information interaction

In the field of deep learning, the attention mechanism, as a technology that mimics human perception and attention processes, has made remarkable achievements. The current methods combine a channel attention mechanism and a spatial attention mechanism in a parallel or cascaded manner to enhance the model representational competence, but they do not fully consider the interaction between spatial and channel information. This paper proposes a method in which a space embedded channel module and a channel embedded space module are cascaded to enhance the model’s representational competence. First, in the space embedded channel module, to enhance the representational competence of the region of interest in different spatial dimensions, the input tensor is split into horizontal and vertical branches according to spatial dimensions to alleviate the loss of position information when performing 2D pooling. To smoothly process the features and highlight the local features, four branches are obtained through global maximum and average pooling, and the features are aggregated by different pooling methods to obtain two feature tensors with different pooling methods. To enable the output horizontal and vertical feature tensors to focus on different pooling features simultaneously, the two feature tensors are segmented and dimensionally transposed according to spatial dimensions, and the features are later aggregated along the spatial direction. Then, in the channel embedded space module, for the problem of no cross-channel connection between groups in grouped convolution and for which the parameters are large, this paper uses adaptive grouped banded matrices. Based on the banded matrices utilizing the mapping relationship that exists between the number of channels and the size of the convolution kernels, the convolution kernel size is adaptively computed to achieve adaptive cross-channel interaction, enhancing the correlation between the channel dimensions while ensuring that the spatial dimensions remain unchanged. Finally, the output horizontal and vertical weights are used as attention weights. In the experiment, the attention mechanism module proposed in this paper is embedded into the MobileNetV2 and ResNet networks at different depths, and extensive experiments are conducted on the CIFAR-10, CIFAR-100 and STL-10 datasets. The results show that the method in this paper captures and utilizes the features of the input data more effectively than the other methods, significantly improving the classification accuracy. Despite the introduction of an additional computational burden (0.5 M), however, the overall performance of the model still achieves the best results when the computational overhead is comprehensively considered.

The use of pretrained neural networks for solving the problem of reverse searching of X-ray images of prohibited items and substances

The paper considers the application of pretrained neural networks to solve the problem of reverse searching of X-ray images of prohibited items and substances. The purpose of the work is to conduct an analysis and substantiate ways to improve the efficiency of baggage and passenger hand luggage X-ray image recognition systems. An analysis of existing domestic and foreign works in the field of baggage and passenger hand luggage X-ray image recognition is presented. It has been revealed that, despite the achieved results in the development of algorithms for recognizing prohibited items and substances, they do not fully cope with such a complexity factor as the overlay of objects. To solve this problem, the paper proposes to additionally analyze X-ray images with low confidence in object recognition. This stage includes the following steps: image segmentation, extraction of features of segmented image elements; search for similar images in the database; decision-making on the class of segmented image elements. This article discusses the last three steps. Variants of approaches to feature extraction from images are analyzed, particularly those based on the application of convolutional autoencoders and pretrained neural networks. The approach based on the application of pretrained neural networks is chosen. The ResNet-50 architecture neural network, pretrained on the ImageNet collection, is used during the work. In order to apply this model to extract image feature vectors, the last classification layer was preliminarily removed. All the previous layers of the model encode the image into a vector. ResNet-50 generates a 2048-dimensional feature vector of images. The principal component analysis is used to reduce the dimensionality of the image feature vectors. The decision of whether the segmented image element is a prohibited item or substance is considered as a reverse search problem using the k-nearest neighbor algorithm. In this case, the class of the X-ray image element is the class most frequently encountered among the K nearest neighbors. In order to test the proposed approach, a training dataset, including 4,635 images of individual items and substances that may be encountered in baggage and passenger hand luggage, was generated. A comparative analysis of image indexing and image search under different algorithms and feature number is presented. A comparative analysis of the model accuracy is provided. It is concluded that the most acceptable is the “Brute force” algorithm in combination with the principal component analysis.

Apriori prediction of chemotherapy response in locally advanced breast cancer patients using CT imaging and deep learning: transformer versus transfer learning.

Neoadjuvant chemotherapy (NAC) is a key element of treatment for locally advanced breast cancer (LABC). Predicting the response to NAC for patients with Locally Advanced Breast Cancer (LABC) before treatment initiation could be beneficial to optimize therapy, ensuring the administration of effective treatments. The objective of the work here was to develop a predictive model to predict tumor response to NAC for LABC using deep learning networks and computed tomography (CT). Several deep learning approaches were investigated including ViT transformer and VGG16, VGG19, ResNet-50, Res-Net-101, Res-Net-152, InceptionV3 and Xception transfer learning networks. These deep learning networks were applied on CT images to assess the response to NAC. Performance was evaluated based on balanced_accuracy, accuracy, sensitivity and specificity classification metrics. A ViT transformer was applied to utilize the attention mechanism in order to increase the weight of important part image which leads to better discrimination between classes. Amongst the 117 LABC patients studied, 82 (70%) had clinical-pathological response and 35 (30%) had no response to NAC. The ViT transformer obtained the best performance range (accuracy = 71 ± 3% to accuracy = 77 ± 4%, specificity = 86 ± 6% to specificity = 76 ± 3%, sensitivity = 56 ± 4% to sensitivity = 52 ± 4%, and balanced_accuracy=69 ± 3% to balanced_accuracy=69 ± 3%) depending on the split ratio of train-data and test-data. Xception network obtained the second best results (accuracy = 72 ± 4% to accuracy = 65 ± 4, specificity = 81 ± 6% to specificity = 73 ± 3%, sensitivity = 55 ± 4% to sensitivity = 52 ± 5%, and balanced_accuracy = 66 ± 5% to balanced_accuracy = 60 ± 4%). The worst results were obtained using VGG-16 transfer learning network. Deep learning networks in conjunction with CT imaging are able to predict the tumor response to NAC for patients with LABC prior to start. A ViT transformer could obtain the best performance, which demonstrated the importance of attention mechanism.

Automated Identification of Retinal Disorders by Deep Learning with Optical Coherence Tomography Pictures

A crucial problem in computer-aided diagnosis (CAD) for medical applications is the classification of retinal disorders. This paper addresses the 4-class classification problem in optical coherence tomography image analysis (OCT) to automatically identify choroidal neovascularization (CNV), diabetic macular edema (DME), DRUSEN, and NORMAL. Retinal OCT pictures were identified by the proposed classification approach using a set of four classification model instances, each based on an upgraded residual neural network (ResNet50).At the patient level, the experiment employs a 10-fold cross-validation process that is founded on the growth of the OCT retinal picture collection. According to the study's findings, multiple ResNet50 concatenation is a helpful method when the availability of pictures used in medicine is scarce. In order to better understand the decision-making process, we also ran a bottleneck test and a qualitative assessment of the model predictions.

Microscopic investigation and local standard deviation analysis of liquid propane jets in supercritical environment

To improve the thermal efficiency of engines, the temperature and pressure in the combustion chamber are continually increased, potentially reaching the critical points of the fuels. Additionally, light fuels such as liquid ammonia and propane are utilized to reduce carbon emissions. The relatively low critical temperature of light fuels facilitates their transition into a supercritical state, which greatly change the jet characteristics. To gain a deeper understanding of the supercritical transition of fuels, jets of liquid propane are investigated through high-speed microscopic imaging technology, covering subcritical to supercritical environmental conditions. Liquid propane is injected through a transparent flat nozzle to observe the internal flow states within the nozzle. For image and data processing, local standard deviation (LSD) analysis and a Residual Network (ResNet-50) model are employed to identify the structures within the mixing region. Droplets counting and frequency domain analysis are also performed to reveal the features of supercritical transition. The findings highlight the importance of mask size in the jet feature extraction. Large mask highlights large scale structures including jet surface and mixing region structures, while small mask brings about full-scale feature including droplets and all other features. A criterion for mixing regime classification based on reduced temperature (Tr) and reduced pressure (Pr) is established directly from image data using the ResNet-50 model, where a condition of Tr1.6Pr0.4 ≥ 1.067 indicates a transcritical mixing regime. Both droplet counting and frequency domain analysis corroborate this mixing regime criterion. These insights enhance our understanding of supercritical transitions and are useful for simulation verifications.

Defect Detection of Cell Phone Screen Using a Faster Regional Convolutional Neural Network with Multi-head Attention Mechanism

Since the glass outer screen of a cell phone is the main sensory part of the human eye when using a cell phone, the advantages and disadvantages of the cell phone screen directly affect people's sense of use. Therefore, the defect detection requirements for cell phone screens are high and need to meet the needs of high-volume factory inspection. Most of the traditional defect detection methods use visual methods, the detection results are overly dependent on the subjectivity and experience of workers, the efficiency of this method is low, and the accuracy is poor. Currently, machine learning-based detection methods are applied in numerous industries. In this paper, a faster Regional Convolutional Neural Network (R-CNN) with multi-head attention mechanism for defect detection of cell phone screen is proposed. To enhance the network's capability in extracting feature information, a four-head attention mechanism is added to the last convolutional layer of the ResNet50 network. An improved Region of Interest (ROI) Align is proposed to replace the original ROI Pooling to reduce the localization error of cell phone screen defects. Replace the original Rectified Linear Unit (ReLU) activation function with the Copy Exponential Linear Unit (CELU) activation function to expedite the convergence capability of the network. Finally, by comparing with other classical model training, the evaluation results indicate that the proposed method achieved an average accuracy of 95.71%, which is a 5.34% improvement compared to the original faster R-CNN network.

An optimised YOLOv4 deep learning model for efficient malarial cell detection in thin blood smear images.

Malaria is a serious public health concern worldwide. Early and accurate diagnosis is essential for controlling the disease's spread and avoiding severe health complications. Manual examination of blood smear samples by skilled technicians is a time-consuming aspect of the conventional malaria diagnosis toolbox. Malaria persists in many parts of the world, emphasising the urgent need for sophisticated and automated diagnostic instruments to expedite the identification of infected cells, thereby facilitating timely treatment and reducing the risk of disease transmission. This study aims to introduce a more lightweight and quicker model-but with improved accuracy-for diagnosing malaria using a YOLOv4 (You Only Look Once v. 4) deep learning object detector. The YOLOv4 model is modified using direct layer pruning and backbone replacement. The primary objective of layer pruning is the removal and individual analysis of residual blocks within the C3, C4 and C5 (C3-C5) Res-block bodies of the backbone architecture's C3-C5 Res-block bodies. The CSP-DarkNet53 backbone is simultaneously replaced for enhanced feature extraction with a shallower ResNet50 network. The performance metrics of the models are compared and analysed. The modified models outperform the original YOLOv4 model. The YOLOv4-RC3_4 model with residual blocks pruned from the C3 and C4 Res-block body achieves the highest mean accuracy precision (mAP) of 90.70%. This mAP is > 9% higher than that of the original model, saving approximately 22% of the billion floating point operations (B-FLOPS) and 23MB in size. The findings indicate that the YOLOv4-RC3_4 model also performs better, with an increase of 9.27% in detecting the infected cells upon pruning the redundant layers from the C3 Res-block bodies of the CSP-DarkeNet53 backbone. The results of this study highlight the use of the YOLOv4 model for detecting infected red blood cells. Pruning the residual blocks from the Res-block bodies helps to determine which Res-block bodies contribute the most and least, respectively, to the model's performance. Our method has the potential to revolutionise malaria diagnosis and pave the way for novel deep learning-based bioinformatics solutions. Developing an effective and automated process for diagnosing malaria will considerably contribute to global efforts to combat this debilitating disease. We have shown that removing undesirable residual blocks can reduce the size of the model and its computational complexity without compromising its precision.

CSINet: Channel–Spatial Fusion Networks for Asymmetric Facial Expression Recognition

Occlusion or posture change of the face in natural scenes has typical asymmetry; however, an asymmetric face plays a key part in the lack of information available for facial expression recognition. To solve the problem of low accuracy of asymmetric facial expression recognition, this paper proposes a fusion of channel global features and a spatial local information expression recognition network called the “Channel–Spatial Integration Network” (CSINet). First, to extract the underlying detail information and deepen the network, the attention residual module with a redundant information filtering function is designed, and the backbone feature-extraction network is constituted by module stacking. Second, considering the loss of information in the local key area of face occlusion, the channel–spatial fusion structure is constructed, and the channel features and spatial features are combined to enhance the accuracy of occluded facial recognition. Finally, before the full connection layer, more local spatial information is embedded into the global channel information to capture the relationship between different channel–spatial targets, which improves the accuracy of feature expression. Experimental results on the natural scene facial expression data sets RAF-DB and FERPlus show that the recognition accuracies of the modeling approach proposed in this paper are 89.67% and 90.83%, which are 13.24% and 11.52% higher than that of the baseline network ResNet50, respectively. Compared with the latest facial expression recognition methods such as CVT, PACVT, etc., the method in this paper obtains better evaluation results of masked facial expression recognition, which provides certain theoretical and technical references for daily facial emotion analysis and human–computer interaction applications.

Neural harmony: revolutionizing thyroid nodule diagnosis with hybrid networks and genetic algorithms

In the contemporary world, thyroid disease poses a prevalent health issue, particularly affecting women’s well-being. Recognizing the significance of maternal thyroid (MT) hormones in fetal neurodevelopment during the first half of pregnancy, this study introduces the HNN-GSO model. This groundbreaking hybrid approach, utilizing the MT dataset, integrates ResNet-50 and Artificial Neural Network (ANN) within a Glow-worm Swarm Optimization (GSO) framework for optimal parameter tuning. With a comprehensive methodology involving dataset preprocessing and Genetic Algorithm (GA) for feature selection, our model leverages ResNet-50 for feature extraction and ANN for classification tasks. Implemented in Python, the HNN-GSO model outperforms existing models, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), ResNet, GoogleNet, and ANN, achieving an impressive accuracy rate of 98%. This success underscores the effectiveness of our approach in complex classification tasks within machine learning (ML) and pattern recognition, specifically tailored to the Thyroid Ultrasound Images (TUI) Dataset. To provide a comprehensive understanding of performance, additional statistical measures such as precision, recall, and F1 score were considered. The HNN-GSO model consistently outperformed competitors across these metrics, showcasing its superiority in MT classification. The HNN-GSO model seamlessly combines ResNet-50's feature extraction, ANN's classification robustness, and GSO's optimization for unparalleled performance. This research offers a promising framework for advancing ML methodologies, enhancing accuracy, and efficiency in classification tasks related to MT health.

Clustering Method for Signals in the Wideband RF Spectrum Using Semi-Supervised Deep Contrastive Learning

This paper presents the application of self-supervised deep contrastive learning in clustering signals detected in the wideband RF spectrum, presented in the form of spectrograms. Radio clustering is a method of searching for similar signals within the analyzed part of the radio spectrum. Typically, it is based on one or several specific parameters processed from the signal in a given channel. The authors propose a slightly different, innovative approach; thanks to the self-supervised learning of neural networks, there is no need to define specific parameters, and the feature vector, enabling comparison of Euclidean distances between signals, is generated by a deep neural network trained using a contrastive loss function on a dataset containing different radio modulations. The authors describe self-supervised solutions based on contrastive learning and the methods of signal segmentation and augmentation. The training process utilizes a custom database and the Resnet-50 network with a contrastive cost function. Radio clustering is used for autonomous spectrum analysis across wide frequency ranges and enables, among other things, the detection of tactical radio stations operating with widely dispersed frequency-hopping or a significant reduction in computational power required for real-time analysis of a large number of radio signals.

Tool Wear Prediction Based on LSTM and Deep Residual Network

To improve the accuracy and efficiency of tool wear predictions, this study proposes a tool wear prediction model called LSTM_ResNet which is based on the long short-term memory (LSTM) network and the Residual Network (ResNet). The model utilizes LSTM layers for processing, where the first block and loop blocks serve as the core modules of the deep residual network. The model employs a series of methods including convolution, batch normalization (BN), and Rectified Linear Unit (ReLU) to enhance the model’s expression and prediction capabilities. The performance of the LSTM_ResNet model was evaluated using experimental data from the PHM2010 datasets and two different depths (64 and 128 layers), training both LSTM_ResNet models for 200 epochs. The 64-layer model’s root mean square error (RMSE) values are 3.36, 4.35, and 3.59, and the mean absolute error (MAE) values are 2.42, 2.85, and 2.21; using 128 layers, the RMSE values are 3.66, 3.99, and 3.77, and the MAE values are 2.49, 2.73, and 3.01. The results indicate that the 64-layer LSTM has smaller average errors, suggesting that compared to other common network structures, the LSTM_ResNet network has a higher performance. This research provides an effective solution for tool wear prediction and helps to improve the technical level of tool wear prediction in China.