Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012170
Youcef Moudjib Houari, Haibin Duan, Baochang Zhang, A. Maher
Hyperspectral imaging system (HSI) uniquely captures a full spectrum of the reflected radiance of any object in the spatial domain (real world), where each substance exhibits different spectral signatures that combine quantitative and qualitative information. HSI is becoming an overpowering technology for accurate image classification and recognition, for that end, it is pervading many, and increasing, fields of application. However, the high dimension of the data and the shortage of labeled training samples are two majors hindrance to more amelioration of the performance. In this paper, a novel Cross Spatial-Spectral Convolution Network (CSSCN) framework based on the convolutional neural network (CNN) with GoogleNet and principal component analysis (PCA) is proposed. By transforming each pixel into a new spectral channel contains all the spectral signature, the maximum spectral features are exploited, and a concatenated convolutional neural network with a dynamic learning rate based on GoogleNet architecture is employed to extract deep spatial features. We thoroughly evaluate the effectiveness of our method on several commonly used HSI benchmark data sets. Promising results have been achieved when comparing the proposed CSSCN with the state of the art of HSI classification.
{"title":"Cross Spectral-Spatial Convolutional Network for Hyperspectral Image Classification","authors":"Youcef Moudjib Houari, Haibin Duan, Baochang Zhang, A. Maher","doi":"10.1109/ICICIP47338.2019.9012170","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012170","url":null,"abstract":"Hyperspectral imaging system (HSI) uniquely captures a full spectrum of the reflected radiance of any object in the spatial domain (real world), where each substance exhibits different spectral signatures that combine quantitative and qualitative information. HSI is becoming an overpowering technology for accurate image classification and recognition, for that end, it is pervading many, and increasing, fields of application. However, the high dimension of the data and the shortage of labeled training samples are two majors hindrance to more amelioration of the performance. In this paper, a novel Cross Spatial-Spectral Convolution Network (CSSCN) framework based on the convolutional neural network (CNN) with GoogleNet and principal component analysis (PCA) is proposed. By transforming each pixel into a new spectral channel contains all the spectral signature, the maximum spectral features are exploited, and a concatenated convolutional neural network with a dynamic learning rate based on GoogleNet architecture is employed to extract deep spatial features. We thoroughly evaluate the effectiveness of our method on several commonly used HSI benchmark data sets. Promising results have been achieved when comparing the proposed CSSCN with the state of the art of HSI classification.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114308558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012212
Shunyuan Xiao, Xiaohua Ge, Q. Han, Z. Cao
This paper addresses the problem of two-target tracking over a heterogenous sensor network under deception attacks. To track the corresponding targets, the spatially distributed sensors are classified into two groups, and the sensors in each group are capable of exchanging measurement information only with their neighboring sensors in accordance with some prescribed interaction topologies. In the presence of deception attacks, the measurement received by each sensor suffers deliberate modification and thus the tracking performance of the two targets may be degraded or even disrupted. First, a heterogenous distributed estimation scheme based on the two distinct groups of sensors is developed to deal with the simultaneous effects of the unknown but bounded process noises as well as the physically constrained deception attacks. Second, criteria for designing the desired distributed estimators and the weights of interacting information links among the inter- and intra-group sensors are derived. It is shown that the true states of the two moving targets are guaranteed to be enclosed by two groups of estimate ellipsoidal sets at each time step regardless of process noises and deception attacks. Third, an optimization problem is proposed to minimize the obtained ellipsoids, aiming to provide optimal tracking performance. Finally, an illustrative example is given to demonstrate the effectiveness of the proposed target tracking method.
{"title":"Two-Target Tracking Over Heterogenous Sensor Networks Under Deception Attacks","authors":"Shunyuan Xiao, Xiaohua Ge, Q. Han, Z. Cao","doi":"10.1109/ICICIP47338.2019.9012212","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012212","url":null,"abstract":"This paper addresses the problem of two-target tracking over a heterogenous sensor network under deception attacks. To track the corresponding targets, the spatially distributed sensors are classified into two groups, and the sensors in each group are capable of exchanging measurement information only with their neighboring sensors in accordance with some prescribed interaction topologies. In the presence of deception attacks, the measurement received by each sensor suffers deliberate modification and thus the tracking performance of the two targets may be degraded or even disrupted. First, a heterogenous distributed estimation scheme based on the two distinct groups of sensors is developed to deal with the simultaneous effects of the unknown but bounded process noises as well as the physically constrained deception attacks. Second, criteria for designing the desired distributed estimators and the weights of interacting information links among the inter- and intra-group sensors are derived. It is shown that the true states of the two moving targets are guaranteed to be enclosed by two groups of estimate ellipsoidal sets at each time step regardless of process noises and deception attacks. Third, an optimization problem is proposed to minimize the obtained ellipsoids, aiming to provide optimal tracking performance. Finally, an illustrative example is given to demonstrate the effectiveness of the proposed target tracking method.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128363175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012192
Huiyan Lu, Ruiqi Liu, Xiujuan Du, Haiqi Liu, Mei Lin, Long Jin, Jiliang Zhang
Neural networks have a wide range of applications in dealing with various online computing problems. This paper mainly retrospects one of the latest recurrent neural network (RNN) models and supplies summarizes on it. Firstly, formulations on the RNN model for dealing with the dynamic underdetermined system of linear equations with double bound constraints on state variables and residual errors are presented. Secondly, simple structures of the RNN model, that is, the neuron-connection architecture of RNN model for handling with the perturbed dynamic underdetermined linear system, as well as the RNN model and the unfolding in time of the computation involved in its forward computation are analyzed. In addition, the whole flowchart on the presented method for establishing the RNN model is also given. Then, experiments on executing the tasks of the UR5 robot when the end-effector tracks a “four-leaf clover” path and a “tricuspid valve” path synthesized by the RNN model are conducted, which show the superiority and accuracy of the presented RNN model.
{"title":"On RNN Models for Solving Dynamic System of Linear Equations","authors":"Huiyan Lu, Ruiqi Liu, Xiujuan Du, Haiqi Liu, Mei Lin, Long Jin, Jiliang Zhang","doi":"10.1109/ICICIP47338.2019.9012192","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012192","url":null,"abstract":"Neural networks have a wide range of applications in dealing with various online computing problems. This paper mainly retrospects one of the latest recurrent neural network (RNN) models and supplies summarizes on it. Firstly, formulations on the RNN model for dealing with the dynamic underdetermined system of linear equations with double bound constraints on state variables and residual errors are presented. Secondly, simple structures of the RNN model, that is, the neuron-connection architecture of RNN model for handling with the perturbed dynamic underdetermined linear system, as well as the RNN model and the unfolding in time of the computation involved in its forward computation are analyzed. In addition, the whole flowchart on the presented method for establishing the RNN model is also given. Then, experiments on executing the tasks of the UR5 robot when the end-effector tracks a “four-leaf clover” path and a “tricuspid valve” path synthesized by the RNN model are conducted, which show the superiority and accuracy of the presented RNN model.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130795944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012205
Sifan Yang, Jiayan Wen, W. Luo, Zonghong Zhu, G. Xie, Jin Tao
In order to reduce the unnecessary consumption of limited resources e.g., network bandwidth, communication cost, and energy of agents, a bipartite consensus problem of first-order multi-agent systems under linear asynchronous decentralized event-triggered control is investigated. According to properties of the connected signed graphs, the bipartite consensus control of a first-order multi-agent systems with the coexistence of cooperative and competitive interactions is designed, so that the multi-agent systems can reach an agreement with an identical magnitude but opposite sign. Due to the drawbacks of unnecessary consumption of communication cost in traditional sampling methods, we consider the event-triggered control bipartite consensus protocol, where both the control protocol and the event-triggered condition are based on local information and sampled states of neighboring agents. Specifically, cutting off continuous communication between agents will reduce energy consumption and communication utilization. The simulation results are given to illustrate the efficiency of the proposed control protocol.
{"title":"Distributed event-triggered bipartite consensus for multi-agent systems associated with signed graphs","authors":"Sifan Yang, Jiayan Wen, W. Luo, Zonghong Zhu, G. Xie, Jin Tao","doi":"10.1109/ICICIP47338.2019.9012205","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012205","url":null,"abstract":"In order to reduce the unnecessary consumption of limited resources e.g., network bandwidth, communication cost, and energy of agents, a bipartite consensus problem of first-order multi-agent systems under linear asynchronous decentralized event-triggered control is investigated. According to properties of the connected signed graphs, the bipartite consensus control of a first-order multi-agent systems with the coexistence of cooperative and competitive interactions is designed, so that the multi-agent systems can reach an agreement with an identical magnitude but opposite sign. Due to the drawbacks of unnecessary consumption of communication cost in traditional sampling methods, we consider the event-triggered control bipartite consensus protocol, where both the control protocol and the event-triggered condition are based on local information and sampled states of neighboring agents. Specifically, cutting off continuous communication between agents will reduce energy consumption and communication utilization. The simulation results are given to illustrate the efficiency of the proposed control protocol.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123926833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012176
Haowei Lin, Qiuye Wu, Derong Liu, Bo Zhao, Qinmin Yang
This paper develops a fault tolerant control (FTC) scheme based on adaptive dynamic programming(ADP) employing the particle swarm optimization (PSO) for nonlinear systems with actuator failures. Using the well-known ADP method, the solution of Hamilton-Jacobi-Bellman equation (HJBE) is approximated by constructing a critic neural network (CNN) which is trained by the PSO algorithm. Compared to the existing gradient descent-trained CNN, the PSO-trained CNN has a higher success rate in solving the HJBE. In order to eliminate the impact of the actuator failure, the ADP-based FTC strategy is developed to guarantee the closed-loop system to be ultimately uniformly bounded (UUB). Finally, a simulation example is provided to demonstrate the effectiveness of the developed method.
{"title":"Fault Tolerant Control for Nonlinear Systems Based on Adaptive Dynamic Programming with Particle Swarm Optimization","authors":"Haowei Lin, Qiuye Wu, Derong Liu, Bo Zhao, Qinmin Yang","doi":"10.1109/ICICIP47338.2019.9012176","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012176","url":null,"abstract":"This paper develops a fault tolerant control (FTC) scheme based on adaptive dynamic programming(ADP) employing the particle swarm optimization (PSO) for nonlinear systems with actuator failures. Using the well-known ADP method, the solution of Hamilton-Jacobi-Bellman equation (HJBE) is approximated by constructing a critic neural network (CNN) which is trained by the PSO algorithm. Compared to the existing gradient descent-trained CNN, the PSO-trained CNN has a higher success rate in solving the HJBE. In order to eliminate the impact of the actuator failure, the ADP-based FTC strategy is developed to guarantee the closed-loop system to be ultimately uniformly bounded (UUB). Finally, a simulation example is provided to demonstrate the effectiveness of the developed method.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"s3-14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130068808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012097
Kun Zhang, S. Cong, Jiao Ding, Jiaojiao Zhang, Kezhi Li
In this paper, based on Alternating Direction Multiplier Method (ADMM) and Compressed Sensing (CS), we develop three types of novel convex optimization algorithms for the quantum state estimation and filtering. Considering sparse state disturbance and measurement noise simultaneously, we propose a quantum state filtering algorithm. At the same time, the quantum state estimation algorithms for either sparse state disturbance or measurement noise are proposed, respectively. Contrast with other algorithms in literature, simulation experiments verify that all three algorithms have low computational complexity, fast convergence speed and high estimation accuracy at lower measurement rates.
{"title":"Efficient and Fast Optimization Algorithms for Quantum State Filtering and Estimation","authors":"Kun Zhang, S. Cong, Jiao Ding, Jiaojiao Zhang, Kezhi Li","doi":"10.1109/ICICIP47338.2019.9012097","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012097","url":null,"abstract":"In this paper, based on Alternating Direction Multiplier Method (ADMM) and Compressed Sensing (CS), we develop three types of novel convex optimization algorithms for the quantum state estimation and filtering. Considering sparse state disturbance and measurement noise simultaneously, we propose a quantum state filtering algorithm. At the same time, the quantum state estimation algorithms for either sparse state disturbance or measurement noise are proposed, respectively. Contrast with other algorithms in literature, simulation experiments verify that all three algorithms have low computational complexity, fast convergence speed and high estimation accuracy at lower measurement rates.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121544578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012180
J. Rochac, N. Zhang, Jiang Xiong
This paper presents a Gaussian data augmentation-assisted deep learning using a convolutional neural network (PCA18+GDA100+CNN LSTM) on the analysis of the state-of-the-art infrared backscatter imaging spectroscopy (IBIS) images. Both PCA and data augmentation methods were used to preprocess classification input and predict with a comparable degree of accuracy. Initially, PCA was used to reduce the number of features. We used 18 principal components based of the cumulative variance, which totaled 99.92%. GDA was also used to increase the number of samples. CNN-LSTM (long short-term memory) was then used to perform multiclass classification on the IBIS hyperspectral image. Experiments were conducted and results were collected from the K-fold cross-validation with K=20. They were analyzed with a confusion matrix and the average accuracy is 99%.
{"title":"A Spectral Feature Based CNN Long Short-Term Memory Approach for Classification","authors":"J. Rochac, N. Zhang, Jiang Xiong","doi":"10.1109/ICICIP47338.2019.9012180","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012180","url":null,"abstract":"This paper presents a Gaussian data augmentation-assisted deep learning using a convolutional neural network (PCA18+GDA100+CNN LSTM) on the analysis of the state-of-the-art infrared backscatter imaging spectroscopy (IBIS) images. Both PCA and data augmentation methods were used to preprocess classification input and predict with a comparable degree of accuracy. Initially, PCA was used to reduce the number of features. We used 18 principal components based of the cumulative variance, which totaled 99.92%. GDA was also used to increase the number of samples. CNN-LSTM (long short-term memory) was then used to perform multiclass classification on the IBIS hyperspectral image. Experiments were conducted and results were collected from the K-fold cross-validation with K=20. They were analyzed with a confusion matrix and the average accuracy is 99%.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123282001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sparse coding is invalid to learn parts-based representations when data is corrupted by outliers. In this paper, matrix completion is considered into sparse coding to handle outliers and a novel sparse coding method is proposed to learn a robust subspace. Experiments on the ORL dataset with salt and pepper noise and contiguous occlusion demonstrate that our proposed sparse method is more effective and robust in achieving a robust subspace.
{"title":"Sparse Coding with Outliers","authors":"Xiangguang Dai, Keke Zhang, Wei Zhang, Jiang Xiong, Yuming Feng","doi":"10.1109/ICICIP47338.2019.9012102","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012102","url":null,"abstract":"Sparse coding is invalid to learn parts-based representations when data is corrupted by outliers. In this paper, matrix completion is considered into sparse coding to handle outliers and a novel sparse coding method is proposed to learn a robust subspace. Experiments on the ORL dataset with salt and pepper noise and contiguous occlusion demonstrate that our proposed sparse method is more effective and robust in achieving a robust subspace.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114412085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012187
Yong Lu, Pengcheng Cao, Lijun Xiong, Bo Xu
In the research of intelligent control on the internal combustion engine, especially in the control of fully variable valve timing (FVVT) system, the efficiency of valve tracking control can be improved by accurate control of the valve lift. This paper bases on the valve lift PID controller and integrates the application of fuzzy logic which has an advantage can be shown on the fully variable valve timing. The mathematical model is established by analyzing the working principle of the fully variable valve timing. The PID parameter adjustment and response programs are developed respectively by studying the relationship between fuzzy logic and the controlled actuator. Based on the Delphi method, the fuzzy logic controller (FLC) is designed by selecting the fuzzy membership function and the fuzzy logic rules which will effect status of system. The Simulink model is built, compared with the incremental PID controller, the result is that the fuzzy logic PID controller performance and robustness are better than the incremental PID controller not only the case of steady speed but also the case of changing speed, which can provide an valuable reference for enhancing the efficiency of fully variable valve timing tracking control on the internal combustion engine.
{"title":"A Novel Fuzzy Logic Control on the FVVT Lift of Internal Combustion Engine","authors":"Yong Lu, Pengcheng Cao, Lijun Xiong, Bo Xu","doi":"10.1109/ICICIP47338.2019.9012187","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012187","url":null,"abstract":"In the research of intelligent control on the internal combustion engine, especially in the control of fully variable valve timing (FVVT) system, the efficiency of valve tracking control can be improved by accurate control of the valve lift. This paper bases on the valve lift PID controller and integrates the application of fuzzy logic which has an advantage can be shown on the fully variable valve timing. The mathematical model is established by analyzing the working principle of the fully variable valve timing. The PID parameter adjustment and response programs are developed respectively by studying the relationship between fuzzy logic and the controlled actuator. Based on the Delphi method, the fuzzy logic controller (FLC) is designed by selecting the fuzzy membership function and the fuzzy logic rules which will effect status of system. The Simulink model is built, compared with the incremental PID controller, the result is that the fuzzy logic PID controller performance and robustness are better than the incremental PID controller not only the case of steady speed but also the case of changing speed, which can provide an valuable reference for enhancing the efficiency of fully variable valve timing tracking control on the internal combustion engine.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114516426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012198
Thayse Christine da Silva, M. Stemmer
The postural assessment of an individual can be related to the angles generated from the markers of two bone references, at any time during routine movements, such as walking, sitting and standing. Postural evaluation assistance systems are commonly developed from the analysis of the gait. However, in this study an algorithm was developed based on activities of sit-to-stand as these activities are pre-requisite for the other daily activities. Based on this context the objective of this study is to develop an automated algorithm to identify a group of nine anatomical landmarks, using a postural assessment protocol of the sit-to-stand and stand-to-sit activities from a lateral view, allowing the extraction of information necessary for the protocol anytime during the execution of the activity. The proposed algorithm employs digital image processing techniques such as image segmentation and the prediction of the occluded points for identification of anatomical landmarks in patients through reflective markers. The results obtained show that the algorithm has an accuracy of 95.1% for the angular values calculated from the obtained videos. The proposed algorithm assists the physical therapists in achieving a quantitative method for monitoring the evolution of the patient's posture and allows periodic reviews to be made more quickly, accurately and throughout the physiotherapeutic treatment.
{"title":"Automatic Identification and Prediction of Anatomical Points in Monocular Images for Postural Assessment","authors":"Thayse Christine da Silva, M. Stemmer","doi":"10.1109/ICICIP47338.2019.9012198","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012198","url":null,"abstract":"The postural assessment of an individual can be related to the angles generated from the markers of two bone references, at any time during routine movements, such as walking, sitting and standing. Postural evaluation assistance systems are commonly developed from the analysis of the gait. However, in this study an algorithm was developed based on activities of sit-to-stand as these activities are pre-requisite for the other daily activities. Based on this context the objective of this study is to develop an automated algorithm to identify a group of nine anatomical landmarks, using a postural assessment protocol of the sit-to-stand and stand-to-sit activities from a lateral view, allowing the extraction of information necessary for the protocol anytime during the execution of the activity. The proposed algorithm employs digital image processing techniques such as image segmentation and the prediction of the occluded points for identification of anatomical landmarks in patients through reflective markers. The results obtained show that the algorithm has an accuracy of 95.1% for the angular values calculated from the obtained videos. The proposed algorithm assists the physical therapists in achieving a quantitative method for monitoring the evolution of the patient's posture and allows periodic reviews to be made more quickly, accurately and throughout the physiotherapeutic treatment.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121625104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：