Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Institution
- Keyword
-
- Simulation (38)
- Numerical simulation (14)
- Genetic algorithm (13)
- Virtual reality (13)
- Neural network (10)
-
- Modeling and simulation (9)
- Particle swarm optimization (9)
- Deep learning (8)
- Modeling (8)
- Path planning (8)
- Fault diagnosis (7)
- Model (7)
- Permanent magnet synchronous motor (7)
- Optimization (6)
- Simulation system (6)
- System simulation (6)
- Visual simulation (6)
- Visualization (6)
- Aircraft cabin (5)
- Augmented reality (5)
- Collision detection (5)
- Differential evolution algorithm (5)
- Electric vehicle (5)
- Flight simulator (5)
- Machine learning (5)
- Parameter identification (5)
- Sensitivity analysis (5)
- System dynamics (5)
- Traffic engineering (5)
- Traffic simulation (5)
- Publication
- Publication Type
Articles 31 - 60 of 864
Full-Text Articles in Systems Science
Short-Term Wind Power Prediction Based On Improved Firefly Algorithm, Jiale Ding, Guochu Chen, Kuo Yuan
Short-Term Wind Power Prediction Based On Improved Firefly Algorithm, Jiale Ding, Guochu Chen, Kuo Yuan
Journal of System Simulation
Abstract: A wind power prediction model based on improved complementary set empirical mode decomposition and improved firefly algorithm to optimize echo state network is proposed to solve the problems of low accuracy in wind power with large randomness and strong volatility prediction of traditional echo state network prediction model. The wind speed series are decomposed into a series of intrinsic modes by using the improved complementary ensemble empirical mode decomposition. The new modes are used to predict wind power by using echo state network, the optimal weight of the model is found by the improved firefly algorithm. The output results …
Downhole Drilling Processing Data Acquisition And Stick Slip Characteristic Analysis, Huang Sheng, Zhang Tao, Chongjun Huang, Yumei Li, Deng Hu, Zhang Xia
Downhole Drilling Processing Data Acquisition And Stick Slip Characteristic Analysis, Huang Sheng, Zhang Tao, Chongjun Huang, Yumei Li, Deng Hu, Zhang Xia
Journal of System Simulation
Abstract: During oil drilling process, drill string vibrations are detrimental to the bit and drill string, which even causes failure of equipment. Researches show that, studying the law of near bit vibration data can reduce non-production time (NPT) and improve drilling efficiency. This paper uses power spectral density and wavelet transform to analyze vibration signals, then compares with normal drilling situation to find out stick slip characteristics. The results show that, when stick slip occurs, the mean value of lateral vibration fluctuates greatly, which indicates stick slip is mainly based on torsional vibration. From the perspective of power spectral density …
Fault Identification Of High-Speed Train Bogie Based On Siamese Convolutional Neural Network, Yunpu Wu, Weidong Jin, Junxiao Ren
Fault Identification Of High-Speed Train Bogie Based On Siamese Convolutional Neural Network, Yunpu Wu, Weidong Jin, Junxiao Ren
Journal of System Simulation
Abstract: The performance degradation and failure of high-speed train bogie components will threaten the operation security of train. This paper proposes a fault type identification method based on siamese convolutional neural network to address the scarcity of data and the high-dimension of monitoring signals. Deep residual network with one-dimension convolution layers is employed for features extraction and fusion of vibration signals from multiple sensors. The siamese structure is employed to obtain the similarities between samples. Fault types are identified by ranking similarities in the support set. The experimental results show that the proposed method can identify the fault types with …
On Operational Experiment Systematization, Xiaogang Qiu, Duan Hong, Bin Chen
On Operational Experiment Systematization, Xiaogang Qiu, Duan Hong, Bin Chen
Journal of System Simulation
Abstract: With the complexity of military simulation object, the way of operational experiment is changing. Based on the discussion of operational experiment requirements, we first present the concepts, objectives, requirements, ideas and related technologies of operational experiment systematization, discuss the requirements, objectives and tasks of the construction of the operational experiment system and point out that simulation engineering in military field is the basis of efficient systematic operational experiment. After that, we describe the concept of domain simulation briefly, and analyze the work needed to be carried out in military simulation engineering from the perspective of sharing the results of …
Evaluation Method Of Simulation Results Based On Principal Component Analysis, Rusheng Ju, Zimin Cai, Yang Mei, Wang Song
Evaluation Method Of Simulation Results Based On Principal Component Analysis, Rusheng Ju, Zimin Cai, Yang Mei, Wang Song
Journal of System Simulation
Abstract: A large amount of result data are produced by complex system simulation. These data types are diverse and complex. Usually they cannot be used directly. The inner pattern can only be found by effective evaluation. Based on the characteristics of complex combat simulation results, this paper utilizes the Principal Component Analysis method to reduce the dimension of data analysis and explore the relationship between the system input data and output data. The key influence factors of the measure of force effectiveness is found. The application verification is done by typical examples. The selected principle factors are explored in …
Research On Mechanical Configuration Of Automatic Container Terminals Based On Simulation Optimization Method, Shaozheng Yu, Dongshi Sun, Chen Jing, Yongchao Li
Research On Mechanical Configuration Of Automatic Container Terminals Based On Simulation Optimization Method, Shaozheng Yu, Dongshi Sun, Chen Jing, Yongchao Li
Journal of System Simulation
Abstract: In the study of mechanical configuration problem of automated container terminal, a system simulation model based on discrete event simulation is constructed. The key parameters and interference factors that affect the performance of the system are fully considered in the model and a mechanical scheduling algorithm interface to ensure the effectiveness of the simulation model is designed. On the premise of ensuring the reliability of the container terminal system, a cycle optimization method of mechanical configuration scheme is proposed to minimize the cost. An example is given to solve the mechanical configuration scheme of an automatic container terminal. …
Research On The Simulation Technology For Multi-Aerocraft Cooperative Guidance, Li Jing, Han Jian, Zhang Qing
Research On The Simulation Technology For Multi-Aerocraft Cooperative Guidance, Li Jing, Han Jian, Zhang Qing
Journal of System Simulation
Abstract: The formal system of multi- aerocraft cooperative simulation system is identified as the discrete event system & different equation system specifications (DEV&DESS) through the analysis of the composition and running mechanism. The running control problem of cooperative simulation system is transformed into simulation control problem of a specific DEV&DESS system. A dynamic operation control method for cooperative guidance simulation system based on coordinator is proposed, and this method is validated by real-time mathematical simulation experiments.
System Dynamics Modeling For Simulation Of Water Supply And Demand Relationship In Beijing, Longxi Luo, Jianping Wu, Chen Yun, Zhe Xu
System Dynamics Modeling For Simulation Of Water Supply And Demand Relationship In Beijing, Longxi Luo, Jianping Wu, Chen Yun, Zhe Xu
Journal of System Simulation
Abstract: Beijing is a metropolis and the center of politics and education of China. However, located in the region with a low level of rainfall, Beijing has been struggling with supplying water resources to meet its growing demand. The past and future trend of the water supply and demand balance in Beijing is studied. Historical data is collected and compiled for learning its past behaviors. The system dynamics (SD) modeling can simulate the complicated and integrated relationships in water supply and demand system. An SD model is then constructed based on compiled historical data. The SD model is validated by …
Intelligent Sandbox For Geography Teaching, Xianli Ji, Yulong Ding, Shuanghua Yang
Intelligent Sandbox For Geography Teaching, Xianli Ji, Yulong Ding, Shuanghua Yang
Journal of System Simulation
Abstract: An intelligent sandbox geography teaching demonstration system combining the augmented reality technology and related geographic knowledge is designed and implemented on the Unity3D platform. The system has functions of deep data processing, projection matrix transformation, terrain rendering, fluid simulation, physical characteristics, adding entities along the slope, changes in sunshine angle, gesture interaction, etc., which can render virtual terrain and scene in real time according to the change of the sandbox. Students can interact with the system in projection correction, adding entities, seasonal switching, weather effects, disaster simulation and other scenarios and learn knowledge points such as contour lines, …
Spatiotemporal Mode Analysis Of Urban Dockless Shared Bikes Based On Point Of Interests Clustering, Zhang Fang, Bin Chen, Yanghua Tang, Dong Jian, Chuan Ai, Xiaogang Qiu
Spatiotemporal Mode Analysis Of Urban Dockless Shared Bikes Based On Point Of Interests Clustering, Zhang Fang, Bin Chen, Yanghua Tang, Dong Jian, Chuan Ai, Xiaogang Qiu
Journal of System Simulation
Abstract: The city’s dockless shared bikes have developed rapidly, and its features of convenience, economy and efficiency have been widely welcomed. The digital footprint they generate reveals the movement of people in time and space within the city, which makes it possible to quantify the activities of people in the city using shared bikes. In this paper, based on the collected shared bikes data of Beijing, a clustering method based on the point of interests is proposed to divide the urban space, so as to construct a mobile network of urban shared bikes, and analysis the spatiotemporal mode of bike …
An Lstm-Based Motion Recognition Method For Power Operation And Maintenance, Peizhen Liu, Yuxiang Jia, Shihong Xia
An Lstm-Based Motion Recognition Method For Power Operation And Maintenance, Peizhen Liu, Yuxiang Jia, Shihong Xia
Journal of System Simulation
Abstract: The security of power operation and maintenance has always been a subject of great social concern. In order to avoid serious consequences caused by the fault of staffs, a motion recognition method for power operation and maintenance jobs based on LSTM (Long Short-Term Memory) is proposed, which covers the whole process from data collection, data processing to motion classification and recognition, then it can recognise and supervise the behavior of staffs who are at work. In addition, a simulation experiment is conducted between the deep learning algorithm LSTM and the traditional machine learning algorithm KNN based on the newly …
Design Of Feedback Linearization Nonlinear Controller For Asynchronous Motor Power Consumption Efficiency, Li Rui, Yingnian Wu
Design Of Feedback Linearization Nonlinear Controller For Asynchronous Motor Power Consumption Efficiency, Li Rui, Yingnian Wu
Journal of System Simulation
Abstract: In order to realize precise feedback linearization and optimal control of motor power consumption for MIMO nonlinear affine system, we build the model of induction motor within which dynamic power loss factor is included. Based on the differential geometry theory, a nonlinear optimization model of the controller is designed for this model to control the asynchronous motor outputs accurately and enhance the power efficiency. This paper presents an optimal control law for multiple inputs multiple outputs affine nonlinear system and the detailed design steps are given combined with examples for multiple outputs tracking problem. The simulation results show that …
Research On Gear Appearance Defect Recognition Based On Improved Faster R-Cnn, Weixi Ji, Du Meng, Peng Wei, Xu Jie
Research On Gear Appearance Defect Recognition Based On Improved Faster R-Cnn, Weixi Ji, Du Meng, Peng Wei, Xu Jie
Journal of System Simulation
Abstract: In order to achieve automatic identification of gear appearance defects and improve the qualification rate of gear products, aiming at the generalization of traditional defect recognition algorithms and the time-consuming of manual features extraction, this paper proposes an improved gear flaw detection algorithm for Faster R-CNN. VGG-2CF network is designed to improve the ability to identify smaller targets. Introducing AM-Softmax loss function is introduced to reduce the intra-class variation and optimize the inter-class difference. Combining with F-measure in machine learning algorithm, an AMF-Softmax loss function is proposed to solve the problem of data imbalance. The experimental results show the …
Survey Of Vision-Based Augmented Reality 3d Registration Technology, Shouming Hou, Han Ji, Yudong Zhang, Ziqiu Zhu
Survey Of Vision-Based Augmented Reality 3d Registration Technology, Shouming Hou, Han Ji, Yudong Zhang, Ziqiu Zhu
Journal of System Simulation
Abstract: Three-dimensional registration technology is one of the core technologies for augmented reality system implementation. In recent years, with the maturity of augmented reality hardware technology and the expansion of application fields, vision-based three-dimensional registration technology has received more attention and development. This paper introduces the basic principles and classification methods of 3D registration technology, focuses on the analysis of the principles and research status of three kinds of visual three-dimensional registration technology based on artificial identification, natural feature points and model.Furthermore, the defects and treatment methods of three visual registration technologies are discussed. The development prospect of visual 3D …
Decision-Making Method For Formulating Spares Reserve Scheme Based On Deep Neural Network, Yunjing Zhang, Guangming Tang, Xiaoyu Xu
Decision-Making Method For Formulating Spares Reserve Scheme Based On Deep Neural Network, Yunjing Zhang, Guangming Tang, Xiaoyu Xu
Journal of System Simulation
Abstract: Spare parts classification is important for spare parts storage and is a key part of spare parts decision-making activities. This paper analyzes the factors affecting the reserve scheme of wartime spares. Then by analyzing the inherent attributes of wartime spares, two methods of spare parts classification are proposed to determine the variety and quantity of wartime spares based on deep neural network: (1) Ranks wartime spares according to their importance. A relatively simple deep neural network is used to analyze every attribute of the wartime spares in turn; (2) Inputs all the attributes of wartime spares into a relatively …
Research On Intelligent Clustering Algorithm For Complex Water Wireless Network Surveillance, Hua Xiang, Hongtao Liang, Zhaoxin Dong, Wang Zhao, Hongjuan Yao, Baohua Li, Bingqing Jiang
Research On Intelligent Clustering Algorithm For Complex Water Wireless Network Surveillance, Hua Xiang, Hongtao Liang, Zhaoxin Dong, Wang Zhao, Hongjuan Yao, Baohua Li, Bingqing Jiang
Journal of System Simulation
Abstract: The clustering of irregular networks will cause load imbalance, which results in the phenomenon of “energy hot zone”. Aiming at the unreasonable topology of irregular network clustering, an intelligent clustering algorithm based on genetic strategy is proposed for the wireless network surveillance of complex water system. An irregular complex water topology model and an energy consumption model are built, and a genetic clustering strategy is designed via the principle of minimum energy consumption. The P matrix coding method is given, which avoids the squared increment of data calculation. Simultaneously, an adaptive genetic operator and a fuzzy modified operator are …
Moving Object Detection Based On Deep Convolutional Neural Network, Yuqiu Lu, Jinyu Sun, Shiwei Ma
Moving Object Detection Based On Deep Convolutional Neural Network, Yuqiu Lu, Jinyu Sun, Shiwei Ma
Journal of System Simulation
Abstract: A deep convolution neural network MONet is designed for the intermittent motion problem in moving objects detection. In the absence of training data sets, a synthetic dataset GoChairs is generated by affine transformation, and on this basis the network training and testing are performed. The results show that the trained MONet can effectively detect the moving objects based on the correspondence between the pixels. The traditional datasets CDnet and I2R are also tested to verify the generalization performance of the network. In addition, MONet is compared qualitatively and quantitatively with classical methods for the intermittent motion problem of …
Urban Functional Area Identification Method Based On Mobile Big Data, Xiao Di, Xiaoyong Zhang, Hu Yang
Urban Functional Area Identification Method Based On Mobile Big Data, Xiao Di, Xiaoyong Zhang, Hu Yang
Journal of System Simulation
Abstract: With the rapid development of urbanization, the function of urban land is constantly evolving. It is of great significance to identify urban functional areas in real time and accurately. In recent years, accompanied by the popularity of smart phones and the rapid development of the Internet, mobile phones have become sensors of human activities. In this paper, a method of urban functional area identification based on time series mobile phone data mining and POI semantics analysis is proposed. The time series feature of remaining mobile phone positioning is extracted facing block scale. And a FCM clustering algorithm based …
3d Shape Deformation Simulation Algorithm Based On Haptics, Binbin Qi, Xuefang Zhu, Lipeng Fan
3d Shape Deformation Simulation Algorithm Based On Haptics, Binbin Qi, Xuefang Zhu, Lipeng Fan
Journal of System Simulation
Abstract: Shape deformation is widely used in virtual reality, system simulation, computer animation and other graphics applications. Few people pay attention to introducing haptic interaction into 3D model deformation. We provide a haptic interactive framework by introducing haptic interaction into shape editing field. Based on the above haptic interactive framework, we propose a 3D model deformation simulation algorithm based on haptics. In order to realize the shape deformation, this algorithm needs to involve three parts: grid hierarchical structure, local mass-spring model and the dynamic shape deformation. Experimental results show that this algorithm has good stability and strong robustness, and the …
Intelligent Fire Rescue Based On Internet Of Things And Virtual Reality, Fengting Yan, Zhicai Shi, Qianmin Su, Dong Jing, Jue Chen, Yunyu Shi, Tang Xian
Intelligent Fire Rescue Based On Internet Of Things And Virtual Reality, Fengting Yan, Zhicai Shi, Qianmin Su, Dong Jing, Jue Chen, Yunyu Shi, Tang Xian
Journal of System Simulation
Abstract: The integration of virtual reality, Internet of Things and artificial intelligence can provide intelligent WebVR interaction for fire rescue decision-making. However, it is necessary to solve the problems of data lightweight, real-time data transmission based on the Internet of Things, and visualization of fire scenario data on the web, and to build effective mechanisms and algorithms. This paper proposes an intelligent fire rescue (IVIFR) mechanism based on the integration of Internet of Things and Virtual Reality, gives a virtual intelligent fire rescue (VIFR) algorithm, and constructs a prototype system of intelligent fire rescue. The VIFR algorithm …
Intelligent Manufacturing Plan Management Based On Digital Twins, Yingying Xiao, Wang Mei, Liqin Guo, Xing Chi, Changhui Zhuang
Intelligent Manufacturing Plan Management Based On Digital Twins, Yingying Xiao, Wang Mei, Liqin Guo, Xing Chi, Changhui Zhuang
Journal of System Simulation
Abstract: For the multi-variety and small-batch manufacturing mode, the planning management system cannot be timely automatically adjusted according to uncertain factors. This paper proposes an intelligent manufacturing plan management system based on factory digital twins. The plan management PDCA business process model is established. In addition, the processing logic model and constraints of the periodic static scheduling model and the dynamic emergency scheduling model are proposed. Based on the planning management case of hybrid assembly of two types of aerospace complex products, it is verified that the management model proposed in this paper can support the intelligent dynamic adjustment of …
A Cloud Service Composition Optimization Based On Hnn, Huili Zhang, Zhihe Li
A Cloud Service Composition Optimization Based On Hnn, Huili Zhang, Zhihe Li
Journal of System Simulation
Abstract: With the rapid development of Cloud service application, how to effectively optimize the composition of Cloud services on cloud platform and improve the overall performance of cloud platform system have become an urgent research issue. In order to improve the efficiency of Cloud services, a combined optimization model based on Hopfield neural network is proposed. The problem of Cloud services is modeled. The problem is expressed as Hopfield Neural Network energy model for optimization, and a PSO group algorithm with Cauchy disturbance is designed to improve the Hopfield model. The experimental comparison shows that the method can improve …
Rehabilitation Training System Of Vr-Based Speech Apraxia, Huanhuan Jiao, Zhigeng Pan, Shuchang Xu, Qingshu Yuan
Rehabilitation Training System Of Vr-Based Speech Apraxia, Huanhuan Jiao, Zhigeng Pan, Shuchang Xu, Qingshu Yuan
Journal of System Simulation
Abstract: Aiming at the problem that the enthusiasm of active training in patients with traditional speech apraxia rehabilitation is gradually weakened, a virtual reality-based rehabilitation training system for speech apraxia is designed. The system simulates the 26 monosyllabic pronunciation mouths shapes made by virtual human in Chinese and uses it for the learning module. It is proposed to identify 26 monosyllabic words by using the isolated word speech recognition algorithm, which improves the accuracy of speech recognition. The system includes a training module and a scene module for assisting the patient's pronunciation rehabilitation training. The evaluation results show that …
Modeling And Simulation Of Complex Equipment Health Management System Based On Cloud Computing, Tianrui Zhang, Chuansheng Qu, Baoku Wu, Jianan Xu
Modeling And Simulation Of Complex Equipment Health Management System Based On Cloud Computing, Tianrui Zhang, Chuansheng Qu, Baoku Wu, Jianan Xu
Journal of System Simulation
Abstract: For complex equipment operation safely, the health management problems of complex equipment life cycle is analyzed. In order to realize remote service, complex equipment health management mode based on cloud computing is proposed. Aiming at the accuracy problem in the process of extracting and recognizing complex equipment characteristic data, the feature knowledge acquisition method based on ontology is researched, and the expression and acquisition algorithm of state characteristic knowledge is proposed. A task sequencing algorithm faults based on fuzzy comprehensive evaluation method is proposed, an appropriate task assignment model is selected for scheduling health management technicians. …
Research On Eye Location And Head State Detection Based On Integrated Learning, Yingnian Wu, Mengjia He, Xiang Wei
Research On Eye Location And Head State Detection Based On Integrated Learning, Yingnian Wu, Mengjia He, Xiang Wei
Journal of System Simulation
Abstract: For real-time detection of eye location problem, a real-time detection system of human eye based on Viola Jones algorithm is designed. Through the MATLAB, the real-time reading and positioning of the detected human eye pictures are controlled by the external or webcam. Through side view, top view, and upward view, it is shown that the human eye real-time positioning system has good detection effect and robustness. In view of the poor classification effect of small data sets on the head state, the random forest algorithm is used to classify the pitching Angle and yaw Angle by HOG-LBP fusion feature …
A Temporal Action Detection Algorithm Based On Spatio-Temporal Feature Pyramid Network, Liu Wang, Jinyu Sun, Shiwei Ma
A Temporal Action Detection Algorithm Based On Spatio-Temporal Feature Pyramid Network, Liu Wang, Jinyu Sun, Shiwei Ma
Journal of System Simulation
Abstract: In view of the discontinuity of motion timing detection in the frame-level prediction network structure, a novel algorithm based on spatio-temporal feature pyramid network (ST-FPN) is proposed. In the frame-level action prediction, several 3D convolution-de-convolution (CDC) networks are used to sample spatial feature down to 1 dimension and sample temporal feature up to corresponding proposal level. Then the prediction scores of different CDC networks are fused by non-maximum suppression (NMS). The softmax classifier is used to classify frame-level actions, and then temporal action detection is obtained. The experimental results on dataset THUMOS14 show that the proposed algorithm improves the …
Agent Based Modeling And Simulation Analysis Of Low-Orbit Early-Warning Satellites, Liu Wen, Xiaolu Wang, Hongsheng Wang, Zhang Heng, Changqing Wang
Agent Based Modeling And Simulation Analysis Of Low-Orbit Early-Warning Satellites, Liu Wen, Xiaolu Wang, Hongsheng Wang, Zhang Heng, Changqing Wang
Journal of System Simulation
Abstract: Low-Orbit Early-Warning Satellite has accurate midcourse ballistic missile tracking and surveillance capability. The paper takes Space Tracking and Surveillance System’s function and construction as the research subject. System model is constructed based on Agent method. The possible constellation configurations of STSS are analyzed considering the coverage performance,and the detection capability of ballistic missile target is simulated and analyzed. Simulation analysis of target detection is carried out. The result shows that STSS can effectively detect a certain number of targets, but detecting capability is affected severely by solar illumination.
Simulation Of Vehicle Startup Delay At Green Light And Its Direct And Chain-Reaction Impact On Traffic Flow, Longxi Luo, Lijun Xie, Jianping Wu, Xu Ming
Simulation Of Vehicle Startup Delay At Green Light And Its Direct And Chain-Reaction Impact On Traffic Flow, Longxi Luo, Lijun Xie, Jianping Wu, Xu Ming
Journal of System Simulation
Abstract: In current traffic simulations, it is implicitly assumed vehicles are driven by ideal drivers. Therefore, simulated vehicles make the most reasonable decisions such as moving out immediately when traffic lights turn green, resulting in a gap between simulations and real traffics. Research shows that drivers, including those who follow the rules, show a delay in starting-up their vehicles at the green light. The vehicle startup delay (SUD) is even more significant for drivers by things such as cell phones during waiting. However, the SUD has rarely been considered in simulations. The SUD is simulated to study its impacts on …
Microscopic Simulation Based Evaluation Of Congestion Pricing For Beijing Urban Area, Jingchen Dai, Ruimin Li
Microscopic Simulation Based Evaluation Of Congestion Pricing For Beijing Urban Area, Jingchen Dai, Ruimin Li
Journal of System Simulation
Abstract: In order to study the potential effect of congestion charging policy in large-scale road network, a micro-simulation platform Paramics is used to establish a simulation model within Beijing fourth ring road. On this basis, multiple congestion pricing scenarios are assessed in consideration of charging zones size, charging rate, and travel mode shift. When the travel mode shift is put aside, the analysis shows that selecting a larger charging zone is more effective on reducing vehicle kilometers of travel and may increase the total charge revenue. However, congestion pricing appears no potential to significantly affect the average speed of …
Research On Nondestructive Blood Glucose Cloud Detection System Based On Improved Deep Regression Network, Mengjia He, Yingnian Wu, Yang Rui
Research On Nondestructive Blood Glucose Cloud Detection System Based On Improved Deep Regression Network, Mengjia He, Yingnian Wu, Yang Rui
Journal of System Simulation
Abstract: Invasive blood glucose measurement has a strong sense of discomfort and risk of infection, so the study of non-invasive blood glucose has a strong practical significance. At present, the optical method is not convenient for practical use, and the energy conservation method requires strict requirements. In view of the above problems, infrared thermography is used to detect blood glucose. After acquiring infrared thermal images of face figure, we extract the gray feature and reduce its dimension. In order to speed up the training and prevent over fitting, depth regression network is improved to model the infrared thermal image gray …