Improved Multi-Stream Convolutional Block Attention Module for sEMG-Based Gesture Recognition

A novel deep-learning based weighted feature fusion architecture for precise classification of pressure injury

Introduction: Precise classification has an important role in treatment of pressure injury (PI), while current machine-learning or deeplearning based methods of PI classification remain low accuracy. Methods: In this study, we developed a deeplearning based weighted feature fusion architecture for fine-grained classification, which combines a top-down and bottom-up pathway to fuse high-level semantic information and low-level detail representation. We validated it in our established database that consist of 1,519 images from multi-center clinical cohorts. ResNeXt was set as the backbone network. Results: We increased the accuracy of stage 3 PI from 60.3% to 76.2% by adding weighted feature pyramid network (wFPN). The accuracy for stage 1, 2, 4 PI were 0.870, 0.788, and 0.845 respectively. We found the overall accuracy, precision, recall, and F1-score of our network were 0.815, 0.808, 0.816, and 0.811 respectively. The area under the receiver operating characteristic curve was 0.940. Conclusions: Compared with current reported study, our network significantly increased the overall accuracy from 75% to 81.5% and showed great performance in predicting each stage. Upon further validation, our study will pave the path to the clinical application of our network in PI management.

The Impact of Feature Extraction on Classification Accuracy Examined by Employing a Signal Transformer to Classify Hand Gestures Using Surface Electromyography Signals

Interest in developing techniques for acquiring and decoding biological signals is on the rise in the research community. This interest spans various applications, with a particular focus on prosthetic control and rehabilitation, where achieving precise hand gesture recognition using surface electromyography signals is crucial due to the complexity and variability of surface electromyography data. Advanced signal processing and data analysis techniques are required to effectively extract meaningful information from these signals. In our study, we utilized three datasets: NinaPro Database 1, CapgMyo Database A, and CapgMyo Database B. These datasets were chosen for their open-source availability and established role in evaluating surface electromyography classifiers. Hand gesture recognition using surface electromyography signals draws inspiration from image classification algorithms, leading to the introduction and development of the Novel Signal Transformer. We systematically investigated two feature extraction techniques for surface electromyography signals: the Fast Fourier Transform and wavelet-based feature extraction. Our study demonstrated significant advancements in surface electromyography signal classification, particularly in the Ninapro database 1 and CapgMyo dataset A, surpassing existing results in the literature. The newly introduced Signal Transformer outperformed traditional Convolutional Neural Networks by excelling in capturing structural details and incorporating global information from image-like signals through robust basis functions. Additionally, the inclusion of an attention mechanism within the Signal Transformer highlighted the significance of electrode readings, improving classification accuracy. These findings underscore the potential of the Signal Transformer as a powerful tool for precise and effective surface electromyography signal classification, promising applications in prosthetic control and rehabilitation.

Recognition of rare antinuclear antibody patterns based on a novel attention-based enhancement framework

Rare antinuclear antibody (ANA) pattern recognition has been a widely applied technology for routine ANA screening in clinical laboratories. In recent years, the application of deep learning methods in recognizing ANA patterns has witnessed remarkable advancements. However, the majority of studies in this field have primarily focused on the classification of the most common ANA patterns, while another subset has concentrated on the detection of mitotic metaphase cells. To date, no prior research has been specifically dedicated to the identification of rare ANA patterns. In the present paper, we introduce a novel attention-based enhancement framework, which was designed for the recognition of rare ANA patterns in ANA-indirect immunofluorescence images. More specifically, we selected the algorithm with the best performance as our target detection network by conducting comparative experiments. We then further developed and enhanced the chosen algorithm through a series of optimizations. Then, attention mechanism was introduced to facilitate neural networks in expediting the learning process, extracting more essential and distinctive features for the target features that belong to the specific patterns. The proposed approach has helped to obtained high precision rate of 86.40%, 82.75% recall, 84.24% F1 score and 84.64% mean average precision for a 9-category rare ANA pattern detection task on our dataset. Finally, we evaluated the potential of the model as medical technologist assistant and observed that the technologist's performance improved after referring to the results of the model prediction. These promising results highlighted its potential as an efficient and reliable tool to assist medical technologists in their clinical practice.

Multi-scale EMG classification with spatial-temporal attention for prosthetic hands

A classification framework for hand gestures using Electromyography (EMG) signals in prosthetic hands is presented. Leveraging the multi-scale characteristics and temporal nature of EMG signals, a Convolutional Neural Network (CNN) is used to extract multi-scale features and classify them with spatial-temporal attention. A multi-scale coarse-grained layer introduced into the input of one-dimensional CNN (1D-CNN) facilitates multi-scale feature extraction. The multi-scale features are fed into the attention layer and subsequently given to the fully connected layer to perform classification. The proposed model achieves classification accuracies of 93.4%, 92.8%, 91.3%, and 94.1% for Ninapro DB1, DB2, DB5, and DB7 respectively, thereby enhancing the confidence of prosthetic hand users.

Adulteration Detection of Pork in Mutton Using Smart Phone with the CBAM-Invert-ResNet and Multiple Parts Feature Fusion

To achieve accurate detection the content of multiple parts pork adulterated in mutton under the effect of mutton flavor essence and colorant by RGB images, the improved CBAM-Invert-ResNet50 network based on the attention mechanism and the inversion residual was used to detect the content of pork from the back, front leg, and hind leg in adulterated mutton. The deep features of different parts extracted by the CBAM-Invert-ResNet50 were fused by feature, stitched, and combined with transfer learning, and the content of pork from mixed parts in adulterated mutton was detected. The results showed that the R2 of the CBAM-Invert-ResNet50 for the back, front leg, and hind leg datasets were 0.9373, 0.8876, and 0.9055, respectively, and the RMSE values were 0.0268 g·g-1, 0.0378 g·g-1, and 0.0316 g·g-1, respectively. The R2 and RMSE of the mixed dataset were 0.9264 and 0.0290 g·g-1, respectively. When the features of different parts were fused, the R2 and RMSE of the CBAM-Invert-ResNet50 for the mixed dataset were 0.9589 and 0.0220 g·g-1, respectively. Compared with the model built before feature fusion, the R2 of the mixed dataset increased by 0.0325, and the RMSE decreased by 0.0070 g·g-1. The above results indicated that the CBAM-Invert-ResNet50 model could effectively detect the content of pork from different parts in adulterated mutton as additives. Feature fusion combined with transfer learning can effectively improve the detection accuracy for the content of mixed parts of pork in adulterated mutton. The results of this study can provide technical support and a basis for maintaining the mutton market order and protecting mutton food safety supervision.

IRDC-Net: An Inception Network with a Residual Module and Dilated Convolution for Sign Language Recognition Based on Surface Electromyography

Deaf and hearing-impaired people always face communication barriers. Non-invasive surface electromyography (sEMG) sensor-based sign language recognition (SLR) technology can help them to better integrate into social life. Since the traditional tandem convolutional neural network (CNN) structure used in most CNN-based studies inadequately captures the features of the input data, we propose a novel inception architecture with a residual module and dilated convolution (IRDC-net) to enlarge the receptive fields and enrich the feature maps, applying it to SLR tasks for the first time. This work first transformed the time domain signal into a time-frequency domain using discrete Fourier transformation. Second, an IRDC-net was constructed to recognize ten Chinese sign language signs. Third, the tandem CNN networks VGG-net and ResNet-18 were compared with our proposed parallel structure network, IRDC-net. Finally, the public dataset Ninapro DB1 was utilized to verify the generalization performance of the IRDC-net. The results showed that after transforming the time domain sEMG signal into the time-frequency domain, the classification accuracy (acc) increased from 84.29% to 91.70% when using the IRDC-net on our sign language dataset. Furthermore, for the time-frequency information of the public dataset Ninapro DB1, the classification accuracy reached 89.82%; this value is higher than that achieved in other recent studies. As such, our findings contribute to research into SLR tasks and to improving deaf and hearing-impaired people's daily lives.

Reinforcement learning based variable damping control of wearable robotic limbs for maintaining astronaut pose during extravehicular activity

As astronauts perform on-orbit servicing of extravehicular activity (EVA) without the help of the space station's robotic arms, it will be rather difficult and labor-consuming to maintain the appropriate position in case of impact. In order to solve this problem, we propose the development of a wearable robotic limb system for astronaut assistance and a variable damping control method for maintaining the astronaut's position. The requirements of the astronaut's impact-resisting ability during EVA were analyzed, including the capabilities of deviation resistance, fast return, oscillation resistance, and accurate return. To meet these needs, the system of the astronaut with robotic limbs was modeled and simplified. In combination with this simplified model and a reinforcement learning algorithm, a variable damping controller for the end of the robotic limb was obtained, which can regulate the dynamic performance of the robot end to resist oscillation after impact. A weightless simulation environment for the astronaut with robotic limbs was constructed. The simulation results demonstrate that the proposed method can meet the recommended requirements for maintaining an astronaut's position during EVA. No matter how the damping coefficient was set, the fixed damping control method failed to meet all four requirements at the same time. In comparison to the fixed damping control method, the variable damping controller proposed in this paper fully satisfied all the impact-resisting requirements by itself. It could prevent excessive deviation from the original position and was able to achieve a fast return to the starting point. The maximum deviation displacement was reduced by 39.3% and the recovery time was cut by 17.7%. Besides, it also had the ability to prevent reciprocating oscillation and return to the original position accurately.

Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam

Simultaneous localization and mapping (SLAM) technology can be used to locate and build maps in unknown environments, but the constructed maps often suffer from poor readability and interactivity, and the primary and secondary information in the map cannot be accurately grasped. For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. Our proposed method can not only reduce the absolute positional errors (APE) and improve the positioning performance of the system but also construct the object-oriented dense semantic point cloud map and output point cloud model of each object to reconstruct each object in the indoor scene. In fact, eight categories of objects are used for detection and semantic mapping using coco weights in our experiments, and most objects in the actual scene can be reconstructed in theory. Experiments show that the number of points in the point cloud is significantly reduced. The average positioning error of the eight categories of objects in Technical University of Munich (TUM) datasets is very small. The absolute positional error of the camera is also reduced with the introduction of semantic constraints, and the positioning performance of the system is improved. At the same time, our algorithm can segment the point cloud model of objects in the environment with high accuracy.

Real-Time Target Detection Method Based on Lightweight Convolutional Neural Network

The continuous development of deep learning improves target detection technology day by day. The current research focuses on improving the accuracy of target detection technology, resulting in the target detection model being too large. The number of parameters and detection speed of the target detection model are very important for the practical application of target detection technology in embedded systems. This article proposed a real-time target detection method based on a lightweight convolutional neural network to reduce the number of model parameters and improve the detection speed. In this article, the depthwise separable residual module is constructed by combining depthwise separable convolution and non–bottleneck-free residual module, and the depthwise separable residual module and depthwise separable convolution structure are used to replace the VGG backbone network in the SSD network for feature extraction of the target detection model to reduce parameter quantity and improve detection speed. At the same time, the convolution kernels of 1 × 3 and 3 × 1 are used to replace the standard convolution of 3 × 3 by adding the convolution kernels of 1 × 3 and 3 × 1, respectively, to obtain multiple detection feature graphs corresponding to SSD, and the real-time target detection model based on a lightweight convolutional neural network is established by integrating the information of multiple detection feature graphs. This article used the self-built target detection dataset in complex scenes for comparative experiments; the experimental results verify the effectiveness and superiority of the proposed method. The model is tested on video to verify the real-time performance of the model, and the model is deployed on the Android platform to verify the scalability of the model.

Path Planning Optimization of Intelligent Vehicle Based on Improved Genetic and Ant Colony Hybrid Algorithm

Intelligent vehicles were widely used in logistics handling, agriculture, medical service, industrial production, and other industries, but they were often not smooth enough in planning the path, and the number of turns was large, resulting in high energy consumption. Aiming at the unsmooth path planning problem of four-wheel intelligent vehicle path planning algorithm, this article proposed an improved genetic and ant colony hybrid algorithm, and the physical model of intelligent vehicle was established. This article first improved ant colony optimization algorithm about heuristic function with the adaptive change of evaporation factor. Then, it improved the genetic algorithm on fitness function, adaptive adjustment of crossover factor, and mutation factor. Last, this article proposed the improved hybrid algorithm with the addition of a deletion operator, adoption of an elite retention strategy, and addition of suboptimal solutions obtained from the improved ant colony algorithm to improved genetic algorithm to obtain optimized new populations. The simulation environment for this article is windows 10, the processor is Intel Core i5-5257U, the running memory is 4GB, the compilation environment is MATLAB2018b, the number of ant samples is 50, the maximum number of iterations is 100, the initial population size of the genetic algorithm is 200, and the maximum number of iterations is 50. Simulation and physical experiments show that the improved hybrid algorithm is effective. Compared with the traditional hybrid algorithm, the improved hybrid algorithm reduced by 46% in the average number of iterations and 75% in the average number of turns in a simple grid. The improved hybrid algorithm reduced by 47% in the average number of iterations and 21% in the average number of turns in a complex grid. The improved hybrid algorithm works better to reduce the number of turns in simple maps.

Multi-Objective Optimization Design of Ladle Refractory Lining Based on Genetic Algorithm

Genetic algorithm is widely used in multi-objective mechanical structure optimization. In this paper, a genetic algorithm-based optimization method for ladle refractory lining structure is proposed. First, the parametric finite element model of the new ladle refractory lining is established by using ANSYS Workbench software. The refractory lining is mainly composed of insulating layer, permanent layer and working layer. Secondly, a mathematical model for multi-objective optimization is established to reveal the functional relationship between the maximum equivalent force on the ladle lining, the maximum temperature on the ladle shell, the total mass of the ladle and the structural parameters of the ladle refractory lining. Genetic algorithm translates the optimization process of ladle refractory lining into natural evolution and selection. The optimization results show that, compared with the unoptimized ladle refractory lining structure (insulation layer thickness of 0 mm, permanent layer thickness of 81 mm, and working layer thickness of 152 mm), the refractory lining with insulation layer thickness of 8.02 mm, permanent layer thickness of 76.20 mm, and working layer thickness of 148.61 mm has the best thermal insulation performance and longer service life within the variation of ladle refractory lining structure parameters. Finally, the results of the optimization are verified and analyzed in this paper. The study found that by optimizing the design of the ladle refractory lining, the maximum equivalent force on the ladle lining, the maximum temperature on the ladle shell and the ladle mass were reduced. The thermal insulation performance and the lightweight performance of the ladle are improved, which is very important for improving the service life of the ladle.