Pub Date : 2021-05-14DOI: 10.1109/ICACI52617.2021.9435896
Z. Hou, Yong Pan, Jiang Xiong, Y. Zeng, Chuanpeng Shen
A compact micro-strip printed antenna with reconfigurable frequency for the intelligent robot is proposed. The antenna is fabricated on FR4epoxy substrate and consists of a main rectangular ring, an additional rectangular resonant band, two elliptical rings and a defected ground structure (DGS). By purposefully controlling two PIN diode switches, three reconfigurable frequencies for Bluetooth, WiMAX (worldwide inter-operability for microwave access), WLAN (wireless local area network) and RFID (radio frequency identification devices) systems are realised. As a traditional monopole, the antenna is omnidirectional and has high gain. Meanwhile, the simulation results are in good agreement with the measured results.
{"title":"A frequency reconfigurable antenna for intelligent mobile robot","authors":"Z. Hou, Yong Pan, Jiang Xiong, Y. Zeng, Chuanpeng Shen","doi":"10.1109/ICACI52617.2021.9435896","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435896","url":null,"abstract":"A compact micro-strip printed antenna with reconfigurable frequency for the intelligent robot is proposed. The antenna is fabricated on FR4epoxy substrate and consists of a main rectangular ring, an additional rectangular resonant band, two elliptical rings and a defected ground structure (DGS). By purposefully controlling two PIN diode switches, three reconfigurable frequencies for Bluetooth, WiMAX (worldwide inter-operability for microwave access), WLAN (wireless local area network) and RFID (radio frequency identification devices) systems are realised. As a traditional monopole, the antenna is omnidirectional and has high gain. Meanwhile, the simulation results are in good agreement with the measured results.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125864757","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 : 2021-05-14DOI: 10.1109/ICACI52617.2021.9435915
Yufeng Diao, Ruping Cen, Fangzheng Xue, Xiaojie Su
This paper presents ORB-SLAM2S, a fast and complete simultaneous localization and mapping (SLAM) system based on ORB-SLAM2 for monocular, stereo, and RGB-D cameras. The system works, ensuring accuracy simultaneously, in real-time on standard central processing units (CPU) at a faster speed in small and large indoor and outdoor environments. The system includes a lightweight front-end which is a sparse optical flow method for non-keyframes to avoid the extraction of keypoints and descriptors that allows for high-speed real-time performance. For keyframes, a feature-based method is used to ensure the accurate trajectory estimation almost the same as ORB-SLAM2. The evaluation of famous public sequences shows that our method achieves almost the same state-of-the-art accuracy as ORB-SLAM2 and faster speed performance which is 3~5 times that of ORB-SLAM2, being in most cases the faster SLAM solution. As proved by experiments, the system provides a fast and lightweight visual SLAM while ensuring accuracy for low-cost mobile devices.
{"title":"ORB-SLAM2S: A Fast ORB-SLAM2 System with Sparse Optical Flow Tracking","authors":"Yufeng Diao, Ruping Cen, Fangzheng Xue, Xiaojie Su","doi":"10.1109/ICACI52617.2021.9435915","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435915","url":null,"abstract":"This paper presents ORB-SLAM2S, a fast and complete simultaneous localization and mapping (SLAM) system based on ORB-SLAM2 for monocular, stereo, and RGB-D cameras. The system works, ensuring accuracy simultaneously, in real-time on standard central processing units (CPU) at a faster speed in small and large indoor and outdoor environments. The system includes a lightweight front-end which is a sparse optical flow method for non-keyframes to avoid the extraction of keypoints and descriptors that allows for high-speed real-time performance. For keyframes, a feature-based method is used to ensure the accurate trajectory estimation almost the same as ORB-SLAM2. The evaluation of famous public sequences shows that our method achieves almost the same state-of-the-art accuracy as ORB-SLAM2 and faster speed performance which is 3~5 times that of ORB-SLAM2, being in most cases the faster SLAM solution. As proved by experiments, the system provides a fast and lightweight visual SLAM while ensuring accuracy for low-cost mobile devices.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124045387","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 : 2021-05-14DOI: 10.1109/ICACI52617.2021.9435907
Weiwei Zhao, Z. Zeng
Adversarial examples cause the deep neural network prediction error, which is a great threat to the deep neural network. How to generate more natural adversarial examples and improve the robustness of deep neural networks has received attention. In this paper, we propose an improved blackbox attack (IBBA) algorithm based on query and perturbation distribution. This algorithm only needs the top-l label of the attacked model to generate the adversarial examples. Based on the existing black-box attacks, we optimize the performance of the algorithm from two aspects: query distribution and perturbation distribution. In the aspect of query distribution, we adopt different strategies for nontargeted attack and targeted attack; in the aspect of perturbation distribution, we choose different low-frequency noise according to the difference between the targeted attack and nontargeted attack. The experimental results on ImageNet show that the proposed algorithm is better than the existing algorithms in low query number, and the targeted attack is better in each specified query number.
{"title":"Improved black-box attack based on query and perturbation distribution","authors":"Weiwei Zhao, Z. Zeng","doi":"10.1109/ICACI52617.2021.9435907","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435907","url":null,"abstract":"Adversarial examples cause the deep neural network prediction error, which is a great threat to the deep neural network. How to generate more natural adversarial examples and improve the robustness of deep neural networks has received attention. In this paper, we propose an improved blackbox attack (IBBA) algorithm based on query and perturbation distribution. This algorithm only needs the top-l label of the attacked model to generate the adversarial examples. Based on the existing black-box attacks, we optimize the performance of the algorithm from two aspects: query distribution and perturbation distribution. In the aspect of query distribution, we adopt different strategies for nontargeted attack and targeted attack; in the aspect of perturbation distribution, we choose different low-frequency noise according to the difference between the targeted attack and nontargeted attack. The experimental results on ImageNet show that the proposed algorithm is better than the existing algorithms in low query number, and the targeted attack is better in each specified query number.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133724799","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 : 2021-05-14DOI: 10.1109/ICACI52617.2021.9435914
Yan Yan, Libing Wu, Yuhan Hu, Zhi-Guo Zhang
This paper devotes to investigating the issue of the fuzzy adaptive event-triggered fault-tolerant control for multi-input and single-output (MISO) nonlinear systems with actuator failures and external disturbances. Based on the backstepping technique and fuzzy logic system (FLS), the fault-tolerant controller and the corresponding adaptive update laws are designed to eliminate the effect of actuator fault. At the same time, the event-triggered mechanism is introduced to reduce the computational load of the control input. The stability analysis shows that the control scheme has great tracking performance ensures the stability of the system. The simulation results further verify the validity of the above theoretical.
{"title":"Fuzzy Event-Triggered Fault-Tolerant Control for a Class of Uncertain Nonlinear Systems","authors":"Yan Yan, Libing Wu, Yuhan Hu, Zhi-Guo Zhang","doi":"10.1109/ICACI52617.2021.9435914","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435914","url":null,"abstract":"This paper devotes to investigating the issue of the fuzzy adaptive event-triggered fault-tolerant control for multi-input and single-output (MISO) nonlinear systems with actuator failures and external disturbances. Based on the backstepping technique and fuzzy logic system (FLS), the fault-tolerant controller and the corresponding adaptive update laws are designed to eliminate the effect of actuator fault. At the same time, the event-triggered mechanism is introduced to reduce the computational load of the control input. The stability analysis shows that the control scheme has great tracking performance ensures the stability of the system. The simulation results further verify the validity of the above theoretical.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131136238","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}
As a novel catering mode, the optimization of takeout delivery scheduling plays an important role in improving efficiency of delivery and the service level of catering enterprises. For the current takeout delivery patterns in China, a delivery scheduling optimization model was proposed with the purpose of minimizing the delivery distance. Moreover, a hybrid meta-heuristic algorithm was developed, with considering the strong robustness of ant colony algorithm (ACO) and excellent convergence ability of genetic algorithm (GA). Results of a series of experiments of a restaurant in Hunnan New District, Shenyang City demonstrate the efficiency of proposed model and the hybrid meta-heuristic algorithm.
{"title":"Scheduling Optimization on Takeout Delivery Based on Hybrid Meta-heuristic Algorithm","authors":"Wen Sheng, Qianqian Shao, Hengxing Tong, Jianfeng Peng","doi":"10.1109/ICACI52617.2021.9435873","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435873","url":null,"abstract":"As a novel catering mode, the optimization of takeout delivery scheduling plays an important role in improving efficiency of delivery and the service level of catering enterprises. For the current takeout delivery patterns in China, a delivery scheduling optimization model was proposed with the purpose of minimizing the delivery distance. Moreover, a hybrid meta-heuristic algorithm was developed, with considering the strong robustness of ant colony algorithm (ACO) and excellent convergence ability of genetic algorithm (GA). Results of a series of experiments of a restaurant in Hunnan New District, Shenyang City demonstrate the efficiency of proposed model and the hybrid meta-heuristic algorithm.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133630939","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 : 2021-05-14DOI: 10.1109/ICACI52617.2021.9435864
Dinghuang Zhang, Carrie M. Toptan, Gongyue Zhang, Shuiwen Zhao, Dalin Zhou, Honghai Liu
Flexibility and adaptability described in individuals with Autism Spectrum Disorders (ASD) refer to Stereotypical Motor Movements (SMM) and social interaction deficits, both of which are important symptoms of ASD. Inspired by the most recent psychological research by Jonge-Hoekstra, this paper aims to distinguish hand movement with two quantitative metrics extracted by the mid-layer of a supervised convolutional gesture recognition network, named diversity and complexity. Particularly, diversity indicates adaptability and complexity indicates flexibility. The utilisation of both metrics shows great potential for hand movement analysis with a particular emphasis on ASD intervention.
{"title":"Diversity and Complexity of Hand Movement for Autism Spectrum Disorder Intervention","authors":"Dinghuang Zhang, Carrie M. Toptan, Gongyue Zhang, Shuiwen Zhao, Dalin Zhou, Honghai Liu","doi":"10.1109/ICACI52617.2021.9435864","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435864","url":null,"abstract":"Flexibility and adaptability described in individuals with Autism Spectrum Disorders (ASD) refer to Stereotypical Motor Movements (SMM) and social interaction deficits, both of which are important symptoms of ASD. Inspired by the most recent psychological research by Jonge-Hoekstra, this paper aims to distinguish hand movement with two quantitative metrics extracted by the mid-layer of a supervised convolutional gesture recognition network, named diversity and complexity. Particularly, diversity indicates adaptability and complexity indicates flexibility. The utilisation of both metrics shows great potential for hand movement analysis with a particular emphasis on ASD intervention.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115419975","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 : 2021-05-14DOI: 10.1109/ICACI52617.2021.9435894
Ming-Jian Sun, Zhe Huang, Chengan Guo
Alzheimer’s disease (AD) is an irreversible neurodegenerative disease and, at present, once it has been diagnosed, there is no effective curative treatment. Accurate and early diagnosis of Alzheimer’s disease is crucial for improving the condition of patients since effective preventive measures can be taken in advance to delay the onset time of the disease. Fluorodeoxyglucose positron emission tomography (FDG-PET) is an effective biomarker of the symptom of AD’s, and has been used as medical imaging data for diagnosing AD’s. Mild cognitive impairment (MCI) is regarded as an early symptom of AD’s, and it has been shown that MCI also has a certain biomedical correlation with FDG-PET. In this paper, we explore how to use 3D FDG-PET images to realize the effective recognition of MCI’s, and thus achieve the early prediction of AD’s. This problem is then taken as the classification of three categories of FDG-PET images, including MCI, AD and NC (normal controls). In order to get better classification performance, a novel network model is proposed in the paper based on 3D convolution neural networks (CNN) and support vector machines (SVM) by utilizing both the excellent abilities of CNN in feature extraction and SVM in classification. In order to make full use of the optimal property of SVM in solving binary classification problems, the three-category classification problem is divided into three binary classifications, each binary classification being realized with a CNN+SVM network. Then the outputs of the three CNN+SVM networks are fused into a final three-category classification result. An end-to-end learning algorithm is developed to train the CNN+SVM networks and a decision fusion strategy is exploited to realize the fusion of the outputs of three CNN+SVM networks. Experimental results obtained in the work with comparative analyses confirm the effectiveness of the proposed method.
{"title":"Automatic Diagnosis of Alzheimer’s Disease and Mild Cognitive Impairment Based on CNN+SVM Networks with End-to-end Training","authors":"Ming-Jian Sun, Zhe Huang, Chengan Guo","doi":"10.1109/ICACI52617.2021.9435894","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435894","url":null,"abstract":"Alzheimer’s disease (AD) is an irreversible neurodegenerative disease and, at present, once it has been diagnosed, there is no effective curative treatment. Accurate and early diagnosis of Alzheimer’s disease is crucial for improving the condition of patients since effective preventive measures can be taken in advance to delay the onset time of the disease. Fluorodeoxyglucose positron emission tomography (FDG-PET) is an effective biomarker of the symptom of AD’s, and has been used as medical imaging data for diagnosing AD’s. Mild cognitive impairment (MCI) is regarded as an early symptom of AD’s, and it has been shown that MCI also has a certain biomedical correlation with FDG-PET. In this paper, we explore how to use 3D FDG-PET images to realize the effective recognition of MCI’s, and thus achieve the early prediction of AD’s. This problem is then taken as the classification of three categories of FDG-PET images, including MCI, AD and NC (normal controls). In order to get better classification performance, a novel network model is proposed in the paper based on 3D convolution neural networks (CNN) and support vector machines (SVM) by utilizing both the excellent abilities of CNN in feature extraction and SVM in classification. In order to make full use of the optimal property of SVM in solving binary classification problems, the three-category classification problem is divided into three binary classifications, each binary classification being realized with a CNN+SVM network. Then the outputs of the three CNN+SVM networks are fused into a final three-category classification result. An end-to-end learning algorithm is developed to train the CNN+SVM networks and a decision fusion strategy is exploited to realize the fusion of the outputs of three CNN+SVM networks. Experimental results obtained in the work with comparative analyses confirm the effectiveness of the proposed method.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129359814","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 : 2021-05-14DOI: 10.1109/ICACI52617.2021.9435872
Dongfang Fan, Zhihong Jin, Kai Luo
In order to accurately predict the macroscopic material flow, aiming at the limitations of the existing medium and long-term macro material flow forecasting models, we propose a multi-objective variable weight combination prediction mode (MOVWCP) based on the parallel cell coordinates system Adaptive Multi-Objective Particle Swarm optimizer algorithm (pccsAMOPSO) to analyze and predict macro material flows. In order to improve the stability of MOVWCP, the concept of error entropy is proposed, at the same time, MOVWCP uses mean absolute percentage error (MAPE) and error entropy to build the objective functions. An intelligent heuristic algorithm based on pccsAMOPSO is designed to solve the Pareto front of variable weights during the fitting period and the variable weight Pareto solution was selected by using the sensitivity difference. A series of numerical experimental results verify the superiority of MOVWCP and its algorithm.
{"title":"Multi-objective Variable Weight Combination Forecasting Model Based on pccsAMOPSO","authors":"Dongfang Fan, Zhihong Jin, Kai Luo","doi":"10.1109/ICACI52617.2021.9435872","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435872","url":null,"abstract":"In order to accurately predict the macroscopic material flow, aiming at the limitations of the existing medium and long-term macro material flow forecasting models, we propose a multi-objective variable weight combination prediction mode (MOVWCP) based on the parallel cell coordinates system Adaptive Multi-Objective Particle Swarm optimizer algorithm (pccsAMOPSO) to analyze and predict macro material flows. In order to improve the stability of MOVWCP, the concept of error entropy is proposed, at the same time, MOVWCP uses mean absolute percentage error (MAPE) and error entropy to build the objective functions. An intelligent heuristic algorithm based on pccsAMOPSO is designed to solve the Pareto front of variable weights during the fitting period and the variable weight Pareto solution was selected by using the sensitivity difference. A series of numerical experimental results verify the superiority of MOVWCP and its algorithm.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127441112","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 : 2021-05-14DOI: 10.1109/ICACI52617.2021.9435878
Juanjuan Liu, Likui Wang
It is shown in [20] that the HPMFD is an efficient method to deal with fuzzy system. In this paper, we extend this method to fuzzy systems with time invariant delay. The matrices in the Lyapunov-Krasovskii functional are designed as HPMFD and the time derivative are also analyzed by applying a switching method. In the end, an example is presented to compare with other method and less conservative results can be obtained by increasing the degree of HPMFD matrices.
{"title":"Improved result for fuzzy systems with time invariant delay","authors":"Juanjuan Liu, Likui Wang","doi":"10.1109/ICACI52617.2021.9435878","DOIUrl":"https://doi.org/10.1109/ICACI52617.2021.9435878","url":null,"abstract":"It is shown in [20] that the HPMFD is an efficient method to deal with fuzzy system. In this paper, we extend this method to fuzzy systems with time invariant delay. The matrices in the Lyapunov-Krasovskii functional are designed as HPMFD and the time derivative are also analyzed by applying a switching method. In the end, an example is presented to compare with other method and less conservative results can be obtained by increasing the degree of HPMFD matrices.","PeriodicalId":382483,"journal":{"name":"2021 13th International Conference on Advanced Computational Intelligence (ICACI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130834840","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：