Real-time Recognition Research Articles

Multichannel EMG-based gesture recognition utilizing advanced machine learning techniques: A random forest classifier for high-precision signal classification

This research examines how advanced machine learning algorithms can be used to classify multichannel electromyographic (EMG) signals with a high level of accuracy to assist in recognizing hand gestures. The goal is to create a robust and scalable system for gesture-based virtual control using EMG signals with potential applications in assistive technologies, rehabilitation, and human-computer interaction. Data were gathered using a MYO Thalmic bracelet containing eight EMG sensors on thirty-six subjects, and a Random Forest classifier was trained to identify seven distinct types of hand gestures (rest, fist clench, wrist flexion/extension, and radial/ulnar deviations). The machine learning pipeline included extensive preprocessing (i.e., EMG signal normalization and signal feature extraction; root mean square, waveform length, and zero crossing rate) and several hyperparameter tuning procedures to improve model performance. The Random Forest model (100 decision trees) achieved an overall classification accuracy of 98.68%, with a range of accuracies for each class (e.g., 95.2% wrist flexion and 91.8% ulnar deviation) when evaluated using cross-validation (i.e., average F1-score = 0.92, precision = 0.94, recall = .91). Overall, the study provides strong evidence for the effectiveness of ensemble learning methods at analyzing complex, multidimensional EMG signals. The high classification accuracy reported, in particular, demonstrates that the system could function for real-time recognition of hand gestures in a virtual environment. Ultimately, the initial work sets the stage for future exploration of a model that may be integrated with actuation models to control prosthetic limbs, virtual actors/avatars, and robotic devices. By demonstrating a scalable and efficient method of gesture recognition using EMG signals, these early findings enable future pathways and possibilities to design innovative, assistive solutions for digital systems that increase accessibility and interaction for users who are motor impaired or have a limited range of motion.

Zn-Modified TiO2 Thin-Films for Real-Time Formaldehyde Sensing at Room Temperature

Abstract This study explores the fabrication and application of zinc-modified titanium dioxide (Zn-TiO2) thin-films for real-time recognition of volatile organic compounds (VOCs), with a particular emphasis on formaldehyde (HCHO) sensing at room temperature. The Zn-TiO2 thin-films were produced using an economical spray-pyrolysis method. Structural, morphological, and optical characterizations confirmed the successful integration of zinc with varied Wt.% (0, 2, 4, and 6) into the TiO2 lattice. The real-time monitoring capabilities of the sensors were assessed against a range of VOCs, highlighting its specificity for formaldehyde detection amidst diverse environmental constituents. The fabricated thin film sensors with zinc dopant were optimized to enhance the sensor's performance. 4 Wt.% Zn-TiO2 demonstrated excellent sensitivity to formaldehyde vapor at ambient conditions, showcasing a rapid and selective response. The underlying sensing mechanism was explored, emphasizing the role of zinc doping in tailoring the material's surface properties and facilitating enhanced adsorption of formaldehyde molecules. The study underscores the potential of Zn-modified TiO2 thin films as a reliable and efficient platform for real-time VOC monitoring, with a specific focus on HCHO sensing at room-temperature. The sensor shows remarkable stability and repeatability, making it a promising candidate for continuous monitoring applications.

Identification strategy of wild and cultivated Astragali Radix based on REIMS combined with two-dimensional LC-MS

A rapid and real-time method was established based on the combination of rapid evaporative ionization mass spectrometry (REIMS) and two-dimensional liquid chromatography mass spectrometry (2DLC-MS) for identification of wild Astragali Radix (WAR) and cultivated AR (CAR). The samples were analyzed under ambient ionization without time-consuming sample preparation. The phenotypic data of WAR and CAR were used to develop a real-time recognition model. Subsequently, the compounds in these two species were comprehensively characterized based on 2DLC-MS, and 45 different compounds were screened out by multivariate statistical analysis. A semi-quantitative method for 45 different compounds was established based on ultrahigh-performance liquid chromatography/quadrupole-linear ion trap mass spectrometry (UHPLC-QTRAP-MS). The results showed that the relative content of most compounds in WAR was higher than in CAR. In summary, the method has demonstrated remarkable performance in distinguishing between WAR and CAR, providing a reference in the field of traditional Chinese medicine (TCM) analysis and identification.

Wheat growth stage identification method based on multimodal data

Accurate identification of crop growth stages is a crucial basis for implementing effective cultivation management. With the development of deep learning techniques in image understanding, research on intelligent real-time recognition of crop growth stages based on RGB images has garnered significant attention. However, the small differences and high similarity in crop morphological characteristics during the transition between adjacent growth stages pose challenges for accurate identification. To address this issue, this study proposes a multi-scale convolutional neural network model, termed MultiScalNet-Wheat (MSN-W), which enhances the algorithm's ability to learn complex features by utilizing multi-scale convolution and attention mechanisms. This model extracts key information from redundant data to identify winter wheat growth stages in complex field environments. Experimental results show that the MSN-W model achieves a recognition accuracy of 97.6 %, outperforming typical convolutional neural network models such as VGG19, ResNet50, MobileNetV3, and DenseNet. To further address the difficulty in recognizing growth stages during transition periods, where canopy morphological features are highly similar and show small differences, this paper introduces an innovative approach by incorporating sequential environmental data related to wheat growth stages. By extracting these features and performing multi-modal collaborative inference, a multi-modal feature-based wheat growth stage recognition model, termed MultiModalNet-Wheat (MMN-W), is constructed on the basis of the MSN-W model. Experimental results indicate that the MMN-W model achieves a recognition accuracy of 98.5 %, improving by 0.9 % over the MSN-W model. Both the MSN-W and MMN-W models provide accurate methods for observing wheat growth stages, thereby supporting the scientific management of winter wheat at different growth stages.

High-sensitivity and high-resolution triboelectric acoustic sensor for mechanical equipment monitoring

Traditional sensors for mechanical equipment monitoring often face challenges such as high cost, difficult installation and removal, and reliance on power sources. Herein, we introduced a polyvinylidene fluoride (PVDF) nanofiber membrane doped with BaTiO3 for constructing a triboelectric acoustic sensor (PB-TAS), innovatively designed for monitoring and recognizing the working conditions of mechanical equipment. This represents the first application of a triboelectric acoustic sensor for mechanical equipment monitoring. The PB-TAS demonstrates an ultra-broad frequency response range of 20–20,000 Hz, effectively covering the characteristic frequency spectrum (within 2000 Hz) during piston pump operation. It also exhibits extraordinarily sensitivity of 4.40 V Pa−1 at 85 dB, and ultra-high frequency resolution down to 0.1 Hz, enabling precise matching of the piston pump's acoustic characteristic frequencies. Integrated with deep learning techniques, the PB-TAS achieves real-time recognition of 15 distinct working conditions of a piston pump, with an impressive accuracy of 95.2 %. The PB-TAS, boasting exceptional sensitivity and frequency resolution, offers a cost-effective, miniaturized, self-powered, non-contact, and highly accurate solution for intelligent monitoring of hydraulic piston pumps.

Real Time Recognition of Face Covered with Facemask using CNN for Application in Classroom Attendance System

Because each person has a different face identity, facial recognition relies on the distinctness of individual facial traits. However, the recent Covid-19 pandemic has substantially altered daily living, required the usage of facemasks while walking outside, including for educational activities such as attending lectures at schools and universities. Facemasks' widespread use presents a significant problem to facial recognition systems since they obscure a significant area of the face, limiting the availability of important facial clues. In response to this critical issue, this project aims to create a Convolutional Neural Network (CNN) architecture suitable for use in a classroom attendance system. The research process begins with the creation of a large training dataset that includes five different students with four different facial circumstances, including facemask covering. The best CNN design is determined through painstaking testing to enhance accuracy during both the training and validation phases. The empirical findings demonstrated that the finalized CNN architecture has a remarkable validation accuracy of up to 96.2%. The trained system demonstrated outstanding precision in recognizing persons during real-time recognition tests. This experiment highlights the CNN's ability to recognize students with high accuracy even while they are wearing facemasks, indicating its potential in solving the issues provided by the prevailing public health measures.

Outcomes of ventricular tachycardia ablation with intracardiac echocardiography-a retrospective cohort study of the national inpatient sample

Abstract Background Intracardiac echocardiography (ICE) is being increasingly used in VT ablation. Sparse literature indicates that ICE reduces repeat VT ablation and VT-related admissions (1). Objective To determine if ICE reduced procedural complications, mortality, length of stay, and hospitalization costs in VT ablation. Methods Utilizing the National Inpatient Sample (NIS) of the years 2016 to 2020, we compared the differences between patients who had VT ablation with and without ICE. We used multivariable logistic and linear regression models as appropriate to determine if ICE was associated with improved outcomes as defined above. Results We included 15,480 hospitalizations (95% CI 14,513-16,446) with VT ablations. ICE was used in 1815 (11.7%) of the patients. The mortality rate was 2.2%(95% CI 1.1-4.3) in the ICE group and 3.2% (95% CI 2.6-3.9) in the non-ICE group, and composite complications rate was 18.4% (95% CI 14.7-22.7) in the ICE group and 19.2% (17.7-20.8) in the non-ICE group. On univariate and multivariate analysis, ICE was not associated with a decrease in mortality, composite complications, or hospitalization charges but with a reduction in length of stay (Tables 1 and 2). ICE was associated with sepsis on univariate analysis but not on multivariate analysis (aOR 0.51, 95% CI 0.26-1.00, P=0.051) Conclusion Our study demonstrates that ICE was not associated with a reduction in mortality or complications in VT ablation but was associated with a slightly shorter length of stay. Although our observational study did not demonstrate a major benefit with ICE, given the multiple advantages of ICE in VT ablations, such as real-time recognition of myocardial substrate, identification of anatomical structures to guide ablation, and prompt recognition of intra-procedural complications, we recommend randomized controlled studies to evaluate the efficacy of ICE(2). Our study is limited by its retrospective nature and reliance on ICD codes for data extraction.

A Candy Defect Detection Method Based on StyleGAN2 and Improved YOLOv7 for Imbalanced Data.

Quality management in the candy industry is a vital part of food quality management. Defective candies significantly affect subsequent packaging and consumption, impacting the efficiency of candy manufacturers and the consumer experience. However, challenges exist in candy defect detection on food production lines due to the small size of the targets and defects, as well as the difficulty of batch sampling defects from automated production lines. A high-precision candy defect detection method based on deep learning is proposed in this paper. Initially, pseudo-defective candy images are generated based on Style Generative Adversarial Network-v2 (StyleGAN2), thereby enhancing the authenticity of these synthetic defect images. Following the separation of the background based on the color characteristics of the defective candies on the conveyor belt, a GAN is utilized for negative sample data enhancement. This effectively reduces the impact of data imbalance between complete and defective candies on the model's detection performance. Secondly, considering the challenges brought by the small size and random shape of candy defects to target detection, the efficient target detection method YOLOv7 is improved. The Spatial Pyramid Pooling Fast Cross Stage Partial Connection (SPPFCSPC) module, the C3C2 module, and the global attention mechanism are introduced to enhance feature extraction precision. The improved model achieves a 3.0% increase in recognition accuracy and a 3.7% increase in recall rate while supporting real-time recognition scenery. This method not only enhances the efficiency of food quality management but also promotes the application of computer vision and deep learning in industrial production.

Transfer learning with YOLOV8 for real-time recognition system of American Sign Language Alphabet

Sign language serves as a sophisticated means of communication vital to individuals who are deaf or hard of hearing, relying on hand movements, facial expressions, and body language to convey nuanced meaning. American Sign Language (ASL) exemplifies this linguistic complexity with its distinct grammar and syntax. The advancement of real-time ASL gesture recognition has explored diverse methodologies, including motion sensors and computer vision techniques. This study specifically addresses the recognition of ASL alphabet gestures using computer vision through Mediapipe for hand movement tracking and YOLOv8 for training the deep learning model. The model achieved notable performance metrics: precision of 98%, recall rate of 98%, F1 score of 99%, mean Average Precision (mAP) of 98%, and mAP50-95 of 93%, underscoring its exceptional accuracy and sturdy capabilities.

Real-time traffic conflict prediction at signalized intersections using vehicle trajectory data and deep learning

Real-time conflict prediction at signalized intersections is crucial for urban road safety management. This study developed a real-time conflict prediction framework for signalized intersections using video data real-time recognition technology and deep learning techniques, incorporating lane-level information and feature interactions. The modeling framework consists of three stages: real-time video data extraction and processing, the development of a Deep and Cross Network (DCN)-based real-time traffic conflict prediction model, and conflict-driven factor interpretability analysis through SHapley Additive exPlanations (SHAP). In the first stage, an efficient automated trajectory extraction system is designed to obtain vehicle trajectories in real time for dynamic traffic parameters and conflict frequency identification. In the second stage, a DCN model is developed to construct the relationships between dynamic traffic parameters, including their interactions, and traffic conflicts. In the third stage, SHAP explores the impact mechanisms of different dynamic traffic parameters on traffic conflicts. The model’s predictive performance and interpretability are evaluated using intersection video data from Changsha City, China. The results show that: (1) In real-time traffic conflict prediction at signalized intersections across different modified time-to-conflict thresholds (1.5 s and 3.0 s), the DCN model consistently outperformed statistical and machine learning models. (2) High traffic flow on main and secondary roads at signalized intersections significantly increases the complexity and frequency of conflicts, with varying sensitivity depending on the interaction of traffic flow, speed, and platoon length. (3) The proposed framework provides a safety measurement standard for data-driven road safety management methods.

Real-time segmentation of biliary structure in pure laparoscopic donor hepatectomy

Pure laparoscopic donor hepatectomy (PLDH) has become a standard practice for living donor liver transplantation in expert centers. Accurate understanding of biliary structures is crucial during PLDH to minimize the risk of complications. This study aims to develop a deep learning-based segmentation model for real-time identification of biliary structures, assisting surgeons in determining the optimal transection site during PLDH. A single-institution retrospective feasibility analysis was conducted on 30 intraoperative videos of PLDH. All videos were selected for their use of the indocyanine green near-infrared fluorescence technique to identify biliary structure. From the analysis, 10 representative frames were extracted from each video specifically during the bile duct division phase, resulting in 300 frames. These frames underwent pixel-wise annotation to identify biliary structures and the transection site. A segmentation task was then performed using a DeepLabV3+ algorithm, equipped with a ResNet50 encoder, focusing on the bile duct (BD) and anterior wall (AW) for transection. The model’s performance was evaluated using the dice similarity coefficient (DSC). The model predicted biliary structures with a mean DSC of 0.728 ± 0.01 for BD and 0.429 ± 0.06 for AW. Inference was performed at a speed of 15.3 frames per second, demonstrating the feasibility of real-time recognition of anatomical structures during surgery. The deep learning-based semantic segmentation model exhibited promising performance in identifying biliary structures during PLDH. Future studies should focus on validating the clinical utility and generalizability of the model and comparing its efficacy with current gold standard practices to better evaluate its potential clinical applications.

Implementation of resource-efficient fetal echocardiography detection algorithms in edge computing.

Recent breakthroughs in medical AI have proven the effectiveness of deep learning in fetal echocardiography. However, the limited processing power of edge devices hinders real-time clinical application. We aim to pioneer the future of intelligent echocardiography equipment by enabling real-time recognition and tracking in fetal echocardiography, ultimately assisting medical professionals in their practice. Our study presents the YOLOv5s_emn (Extremely Mini Network) Series, a collection of resource-efficient algorithms for fetal echocardiography detection. Built on the YOLOv5s architecture, these models, through backbone substitution, pruning, and inference optimization, while maintaining high accuracy, the models achieve a significant reduction in size and number of parameters, amounting to only 5%-19% of YOLOv5s. Tested on the NVIDIA Jetson Nano, the YOLOv5s_emn Series demonstrated superior inference speed, being 52.8-125.0 milliseconds per frame(ms/f) faster than YOLOv5s, showcasing their potential for efficient real-time detection in embedded systems.

A Lightweight Real-Time Recognition Algorithm for Tomato Leaf Disease Based on Improved YOLOv8

To address the real-time detection challenge of deploying deep learning-based tomato leaf disease detection algorithms on embedded devices, an improved tomato leaf disease detection algorithm based on YOLOv8n is proposed in this paper. It is able to achieve the efficient, real-time detection of tomato leaf diseases while maintaining model’s lightweight requirements. The algorithm incorporated the LMSM (lightweight multi-scale module) and ALSA (Attention Lightweight Subsampling Module) to improve the ability to extract lightweight and multi-scale semantic information for the specific characteristics of tomato leaf disease, which include irregular spot size and lush tomato leaves. The head network was redesigned utilizing partial and group convolution along with a parameter-sharing method. Scalable auxiliary bounding box and loss function optimization strategies were introduced to further enhance performance. After undergoing the pruning technique, computation decreased by 61.7%, the model size decreased by 55.6%, and the FPS increased by 44.8%, all while a high level of accuracy was maintained. A detection speed of 19.70FPS on the Jetson Nano was obtained after undergoing TensorRT quantization, showing a 64.85% improvement compared to the initial detection speed. This method met the high real-time performance and small model size requirements for embedded tomato leaf disease detection systems, indirectly reducing the energy consumption of online detection. It provided an effective solution for the online detection of tomato leaf disease.

276. AI NAVIGATION SURGERY FOR ESOPHAGEAL CANCER

Abstract With recent technological innovations, artificial intelligence (AI) has begun to be used not only in endoscopic diagnosis and pathology diagnosis but also in the field of surgery. AI enables objective and consistent recognition and evaluation, making it suitable for surgical assistance in surgical operations as well as for the evaluation of surgical techniques and learning curves. First, an AI-assisted surgical procedure recognition system for robotic esophagectomy was developed. By focusing on surgical procedures, the system automatically recognizes surgical procedures with 84% accuracy using AI. In particular, more than 90% of accuracy was obtained in the phase for Left RLN lymph node dissection and Post-dissection to completion of surgery. In addition, as intraoperative navigation, a system for automatic recognition of critical organs such as the recurrent laryngeal nerve, trachea, and subclavian artery was developed, and its recognition accuracy is gradually improving, enabling organ recognition in real time. Currently, with data from more than 100 cases, the system is able to predict Intersection over Union (IoU) with an accuracy of 0.3-0.4. Similar developments are underway in other areas, such as automatic recognition of the surgical process in robotic distal gastrectomy, and a surgical difficulty prediction system is being built using this technology. This system is expected to make it possible to automatically determine the degree of difficulty of surgery during the operation, leading to the decision to change the surgical team during the operation and the prediction of the operation completion time. These technologies can be useful not only for intraoperative navigation, but also surgical education and postoperative care. Using them, young surgeons have the opportunity to dive into authentic scenarios and acquire practical experience safely, bypassing the dangers inherent in real-life surgeries. Through the use of AI-powered interactive simulations, they can deeply grasp surgical methods, establishing the groundwork of crucial practical abilities needed for performing successful operations. In the future, we intend to verify the external validity of these systems using data from multiple facilities, and further work on the development of a surgical support system that transcends fields, with the aim of obtaining regulatory approval as a medical device. In addition to the potential clinical applications of the systems under development, we would like to discuss the current status and future of AI-based surgical support systems in the surgical field.

Coal-rock interface real-time recognition based on the improved YOLO detection and bilateral segmentation network

To improve the accuracy and efficiency of coal-rock interface recognition, this study proposes a model built on the real-time detection algorithm, you only look once (YOLO), and the lightweight bilateral segmentation network. Simultaneously, the regional similarity transformation function and dragonfly algorithm are introduced to enhance the quality of coal-rock images. The comparison with three other models demonstrates the superior edge inference performance of the proposed model, achieving a mean Average Precision (mAP) of 90.2 at the Intersection over Union (IoU) threshold of 0.50 (mAP50) and 81.4 across a range of IoU thresholds from 0.50 to 0.95 (mAP[50,95]). Furthermore, to maintain high accuracy and real-time recognition capabilities, the proposed model is optimized using the open visual inference and neural network optimization toolkit, resulting in a 144.97% increase in the mean frames per second. Experimental results on four actual coal faces confirm the efficacy of the proposed model, showing a better balance between accuracy and efficiency in coal-rock image recognition, which supports further advancements in coal mining intelligence.

A mobile-optimized convolutional neural network approach for real-time batik pattern recognition

This research focuses on preserving and sharing knowledge about Indonesian batik, a blend of art and technology symbolizing the nation's creativity. To address declining awareness of batik types, a mobile application is introduced for real-time recognition and classification of batik motifs. The goal is to maintain appreciation and understanding of this cultural heritage. Using the EfficientNet convolutional neural network (CNN) architecture, the study enhances model accuracy with effective scaling. A dataset of 1350 images representing 15 batik types supports robust model training and evaluation. Results demonstrate successful implementation, yielding an Android app capable of deep learning-based real-time recognition with an 83% accuracy rate. This innovation aims to empower users to identify and appreciate distinct batik types, ensuring cultural preservation for current and future generations.

EchoGesture Communication: Gesture-based Systems for Individuals with Disabilities

EchoGesture Communication revolutionizes the interaction of differently-abled individuals using hand gestures. People with disabilities often face difficulties in using the conventional electronic gadgets. The proposed study, utilizes sensors, microcontroller, computer vision, and machine learning, to enable real-time recognition of hand gestures, facilitating effective communication. Additionally, Convolutional Neural Network (CNN) is used in the research to achieve accurate gesture recognition. The proposed system allows individuals with disability to communicate effectively using hand gestures.

Literature Survey on Revolutionizing Fake Currency Detection: CNN-Based Approach for Indian Rupee Notes

The proliferation of counterfeit currency poses a significant challenge in various economies, including India. To address this issue, several studies have proposed innovative image processing and machine learning techniques for detecting counterfeit coins and banknotes. Leveraging digital image processing, these studies aim to enhance the security measures against counterfeit currency through accurate and efficient recognition systems. Techniques such as preprocessing, segmentation, feature extraction, and clustering are employed to identify fraudulent currency. The use of Support Vector Machines (SVM), k-means clustering, and Convolutional Neural Networks (CNN) facilitates the recognition and classification of genuine and counterfeit currency. Moreover, these studies explore the application of spatial coding, component-based recognition, and deep learning algorithms to improve the accuracy and robustness of counterfeit detection systems. By developing real-time recognition systems capable of identifying counterfeit currency, these research efforts contribute to combating financial fraud and safeguarding economic integrity.

FiberFlex: Real-time FPGA-based Intelligent & Distributed Fiber Sensor System for Pedestrian Recognition

In recent years, security monitoring of public places and critical infrastructure has heavily relied on the widespread use of cameras, raising concerns about personal privacy violations. To balance the need for effective security monitoring with the protection of personal privacy, we explore the potential of optical fiber sensors for this application. This paper proposes FiberFlex, an intelligent and distributed fiber sensor system. Ultizing FPGA high-level synthesis (HLS) acceleration, FiberFlex offers real-time pedestrian detection by co-designing the entire pipeline of optical signal acquisition, processing, and recognition networks based on the principles of optical fiber sensing. As a promising alternative to traditional camera-based monitoring systems, FiberFlex achieves pedestrian detection by analyzing the vibration patterns caused by pedestrian footsteps, enabling security monitoring while preserving individual privacy. FiberFlex comprises three modules: First , fiber-optic sensing system: A fiber-optic distributed acoustic sensing (DAS) system is built and used to measure the ground vibration waves generated by people walking. Second , algorithms: We first collect the training data by measuring the ground vibration waves, label the data, and use the data to train the neural network models to perform pedestrian recognition. Third , hardware accelerators: We use HLS tools to design hardware modules on FPGA for data collection and pre-processing, and integrate them with the downstream neural network accelerators to perform in-line real-time pedestrian detection. The final detection results are sent back from FPGA to the host CPU. We implement our system FiberFlex with the in-house built DAS system and AMD/Xilinx Kintex7 FPGA KC705 board and verify the whole system using the real-world collected data. We conduct recognition tests on 5 test subjects of varying ages, heights, and weights in a fixed sensing area. Each subject experienced 20 real-time recognition tests using their daily walking habits, and the subjects were given adequate rest between tests. After 100 tests on five test subjects, the overall real-time recognition accuracy exceeded \(88.0\%\) . The whole system uses 55 watts of power, 33 watts in the optical DAS system, and 22 watts in the FPGA. Relying on its end-to-end interdisciplinary design, FiberFlex seamlessly combines fiber-optic sensors with FPGA accelerators to enable low-power real-time security monitoring without compromising privacy, making it a valuable addition to the existing security monitoring network. According to FiberFlex, more valuable research can be conducted in the future, such as fall monitoring for the elderly, migration of identification networks between different application scenarios, and improvement of anti-interference performance in more complex environments. In future perception networks, where the “eyes” are not feasible, let's use fiber optic touch instead.

1D-CNN-Transformer for Radar Emitter Identification and Implemented on FPGA

Deep learning has brought great development to radar emitter identification technology. In addition, specific emitter identification (SEI), as a branch of radar emitter identification, has also benefited from it. However, the complexity of most deep learning algorithms makes it difficult to adapt to the requirements of the low power consumption and high-performance processing of SEI on embedded devices, so this article proposes solutions from the aspects of software and hardware. From the software side, we design a Transformer variant network, lightweight convolutional Transformer (LW-CT) that supports parameter sharing. Then, we cascade convolutional neural networks (CNNs) and the LW-CT to construct a one-dimensional-CNN-Transformer(1D-CNN-Transformer) lightweight neural network model that can capture the long-range dependencies of radar emitter signals and extract signal spatial domain features meanwhile. In terms of hardware, we design a low-power neural network accelerator based on an FPGA to complete the real-time recognition of radar emitter signals. The accelerator not only designs high-efficiency computing engines for the network, but also devises a reconfigurable buffer called “Ping-pong CBUF” and two-level pipeline architecture for the convolution layer for alleviating the bottleneck caused by the off-chip storage access bandwidth. Experimental results show that the algorithm can achieve a high recognition performance of SEI with a low calculation overhead. In addition, the hardware acceleration platform not only perfectly meets the requirements of the radar emitter recognition system for low power consumption and high-performance processing, but also outperforms the accelerators in other papers in terms of the energy efficiency ratio of Transformer layer processing.