Pub Date : 2022-07-15DOI: 10.1109/icaci55529.2022.9837720
Luan Shi, Xiao Zhang, Xin Xiang, Yu Zhou, Shilong Sun
Recent years have witnessed increasingly more Unmanned Aerial Vehicle (UAV) applications for data collection in the Internet of Things (IoT). Due to the limited energy and service capacity, it is very challenging for a single UAV to accomplish the data collection while guaranteeing the information freshness of IoT devices or sensor nodes (SNs). In practice, different types of UAVs may have different energy capabilities. In this paper, we propose a more practical heterogeneous UAV swarm path planning problem for optimizing the information freshness, in which the division and cooperation among UAVs with different energy capacities have been taken into consideration. The freshness, i.e., age of information (AoI) collected from each SN is characterized by the data uploading time and the time elapsed since the UAV leaves this SN. We successfully present a deep reinforcement learning algorithm based on attention mechanism by end-to-end training to optimize the average age under UAVs’ energy constraints. The simulation results show that our algorithm has fast convergence, high optimization capability and reliability, and can solve the heterogeneous UAV swarm cooperative AoI optimization problem effectively.
{"title":"Age of Information optimization with Heterogeneous UAVs based on Deep Reinforcement Learning","authors":"Luan Shi, Xiao Zhang, Xin Xiang, Yu Zhou, Shilong Sun","doi":"10.1109/icaci55529.2022.9837720","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837720","url":null,"abstract":"Recent years have witnessed increasingly more Unmanned Aerial Vehicle (UAV) applications for data collection in the Internet of Things (IoT). Due to the limited energy and service capacity, it is very challenging for a single UAV to accomplish the data collection while guaranteeing the information freshness of IoT devices or sensor nodes (SNs). In practice, different types of UAVs may have different energy capabilities. In this paper, we propose a more practical heterogeneous UAV swarm path planning problem for optimizing the information freshness, in which the division and cooperation among UAVs with different energy capacities have been taken into consideration. The freshness, i.e., age of information (AoI) collected from each SN is characterized by the data uploading time and the time elapsed since the UAV leaves this SN. We successfully present a deep reinforcement learning algorithm based on attention mechanism by end-to-end training to optimize the average age under UAVs’ energy constraints. The simulation results show that our algorithm has fast convergence, high optimization capability and reliability, and can solve the heterogeneous UAV swarm cooperative AoI optimization problem effectively.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115673838","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 : 2022-07-15DOI: 10.1109/icaci55529.2022.9837620
Huanhuan Tian, Peijun Wang, Shuai Wang
This paper studies the containment problem for complex cyber-physical networks (CCPNs) subject to parameter uncertainties and external disturbances. By using the neural network (NN) approximation theory, a continuous neuro-adaptive containment controller is designed, where the NN adaptive law is used to adjust the NN weights and the other adaptive laws are used to adjust the network coupling strengths. And we prove that the containment error is uniformly ultimately bounded (UUB) if the graph among followers is detailed balanced and for each follower, there exists at least one leader has a directed path to it. As the containment criteria depend only on local information, the achieved containment is fully distributed. A favourable property of the containment controller is chattering free since it is continuous. Finally, the theoretical result is validated by numerical simulation.
{"title":"Neuro-adaptive Containment of Uncertain Complex Cyber Physical Networks with Directed Topology","authors":"Huanhuan Tian, Peijun Wang, Shuai Wang","doi":"10.1109/icaci55529.2022.9837620","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837620","url":null,"abstract":"This paper studies the containment problem for complex cyber-physical networks (CCPNs) subject to parameter uncertainties and external disturbances. By using the neural network (NN) approximation theory, a continuous neuro-adaptive containment controller is designed, where the NN adaptive law is used to adjust the NN weights and the other adaptive laws are used to adjust the network coupling strengths. And we prove that the containment error is uniformly ultimately bounded (UUB) if the graph among followers is detailed balanced and for each follower, there exists at least one leader has a directed path to it. As the containment criteria depend only on local information, the achieved containment is fully distributed. A favourable property of the containment controller is chattering free since it is continuous. Finally, the theoretical result is validated by numerical simulation.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"44 7-12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123419588","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 : 2022-07-15DOI: 10.1109/icaci55529.2022.9837775
Huan Liu, Jiang Xiong, Nian Zhang, Jing Zhong
In the past few years, due to the strong feature learning capability of deep neural networks, deep cross-modal hashing (DCMHs) has made considerable progress. However, there exist two problems in most DCMHs methods: (1) most extisting DCMHs methods utilize single labels to calculate the semantic similarity of instances, which overlooks the fact that, in the field of cross-modal retrieval, most benchmark datasets as well as practical applications have multiple labels. Therefore, single labels based DCMHs methods cannot accurately calculate the semantic similarity of instances and may decrease the performance of the learned DCMHs models. (2) Most DCMHs models are built on the image-text modalities, nevertheless, as the initial feature space of the text modality is quite sparse, the learned hash projection function based on these sparse features for the text modality is too weak to map the original text into robust hash codes. To solve these two problems, in this paper, we propose a text modality enhanced based deep hashing for multi-label cross-modal retrieval (TMEDH) method. TMEDH firstly defines a multi-label based semantic similarity calculation formula to accurately compute the semantic similarity of cross-modal instances. Secondly, TMEDH introduces a text modality enhanced module to compensate the sparse features of the text modality by fuse the multi-label information into the features of the text. Extensive ablation experiments as well as comparative experiments on two cross-modal retrieval datasets demonstrate that our proposed TMEDH method achieves state-of-the-art performance.
{"title":"Text modality enhanced based deep hashing for multi-label cross-modal retrieval","authors":"Huan Liu, Jiang Xiong, Nian Zhang, Jing Zhong","doi":"10.1109/icaci55529.2022.9837775","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837775","url":null,"abstract":"In the past few years, due to the strong feature learning capability of deep neural networks, deep cross-modal hashing (DCMHs) has made considerable progress. However, there exist two problems in most DCMHs methods: (1) most extisting DCMHs methods utilize single labels to calculate the semantic similarity of instances, which overlooks the fact that, in the field of cross-modal retrieval, most benchmark datasets as well as practical applications have multiple labels. Therefore, single labels based DCMHs methods cannot accurately calculate the semantic similarity of instances and may decrease the performance of the learned DCMHs models. (2) Most DCMHs models are built on the image-text modalities, nevertheless, as the initial feature space of the text modality is quite sparse, the learned hash projection function based on these sparse features for the text modality is too weak to map the original text into robust hash codes. To solve these two problems, in this paper, we propose a text modality enhanced based deep hashing for multi-label cross-modal retrieval (TMEDH) method. TMEDH firstly defines a multi-label based semantic similarity calculation formula to accurately compute the semantic similarity of cross-modal instances. Secondly, TMEDH introduces a text modality enhanced module to compensate the sparse features of the text modality by fuse the multi-label information into the features of the text. Extensive ablation experiments as well as comparative experiments on two cross-modal retrieval datasets demonstrate that our proposed TMEDH method achieves state-of-the-art performance.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115044071","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 : 2022-07-15DOI: 10.1109/icaci55529.2022.9837577
Lin Wu, J. Xiao, Zhe Zhang
DeepLabv3+ has a wide range of applications in autonomous driving, geographic information systems, etc. However, its deployment on the mobile terminal faces a trade-off between model size and accuracy. Consecutive downsampling operations also result in a great loss of detail information. To solve these problems, this paper proposes an improved algorithm based on DeepLabv3+. Firstly, backbone is replaced by MobileNetv2 to reduce the size of the model; Secondly, the improved Atrous Spatial Pyramid Pooling module is proposed to augment the segmentation result while reducing the parameters. The performance is further ameliorated by applying attention mechanism; Finally, through refining decoder module, the proposed network makes up for lost detail information. Experiment shows that the algorithm achieves an mIoU of 73.31% on the validation set of the PASCAL VOC2012 dataset. Compared with typical algorithms, proposed algorithm has a better effect on trade-off between model size and accuracy.
{"title":"Improved Lightweight DeepLabv3+ Algorithm Based on Attention Mechanism","authors":"Lin Wu, J. Xiao, Zhe Zhang","doi":"10.1109/icaci55529.2022.9837577","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837577","url":null,"abstract":"DeepLabv3+ has a wide range of applications in autonomous driving, geographic information systems, etc. However, its deployment on the mobile terminal faces a trade-off between model size and accuracy. Consecutive downsampling operations also result in a great loss of detail information. To solve these problems, this paper proposes an improved algorithm based on DeepLabv3+. Firstly, backbone is replaced by MobileNetv2 to reduce the size of the model; Secondly, the improved Atrous Spatial Pyramid Pooling module is proposed to augment the segmentation result while reducing the parameters. The performance is further ameliorated by applying attention mechanism; Finally, through refining decoder module, the proposed network makes up for lost detail information. Experiment shows that the algorithm achieves an mIoU of 73.31% on the validation set of the PASCAL VOC2012 dataset. Compared with typical algorithms, proposed algorithm has a better effect on trade-off between model size and accuracy.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122302805","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 : 2022-07-15DOI: 10.1109/icaci55529.2022.9837508
Keyi Chen, Hangjun Che, Man-Fai Leung, Yadi Wang
Fuzzy c-means(FCM) has attracted wide attentions on picture segmentation as its fuzzy attribute matches the histogram distribution of a picture. However, the fuzzy c-means for the segmentation of a picture with massy noises is barely investigated. In this paper, an improved superpixel-based fuzzy c-means is proposed to segment a massy noise corrupted picture into more than two classes. Firstly, bilateral filtering is used to reduce the compact of noises and makes the picture smoother. Secondly an adaptive method is proposed to fuse the features of the original picture with filtered features. Thirdly simple linearly iterative clustering(SLIC) is used to detect the edge of the picture to avoid over-segmentation. Finally, the histogram-based fuzzy c-means is used to get the segmentation result. In the experiments, the results show the proposed method achieves a $0.004 sim 0.014$ higher mPA and $0.004 sim 0.06$ higher mIoU than other seven algorithms. Besides the segmentation results also show that the over-segmentation is reduced.
{"title":"An Improved Superpixel-based Fuzzy C-Means Method for Complex Picture Segmentation Tasks","authors":"Keyi Chen, Hangjun Che, Man-Fai Leung, Yadi Wang","doi":"10.1109/icaci55529.2022.9837508","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837508","url":null,"abstract":"Fuzzy c-means(FCM) has attracted wide attentions on picture segmentation as its fuzzy attribute matches the histogram distribution of a picture. However, the fuzzy c-means for the segmentation of a picture with massy noises is barely investigated. In this paper, an improved superpixel-based fuzzy c-means is proposed to segment a massy noise corrupted picture into more than two classes. Firstly, bilateral filtering is used to reduce the compact of noises and makes the picture smoother. Secondly an adaptive method is proposed to fuse the features of the original picture with filtered features. Thirdly simple linearly iterative clustering(SLIC) is used to detect the edge of the picture to avoid over-segmentation. Finally, the histogram-based fuzzy c-means is used to get the segmentation result. In the experiments, the results show the proposed method achieves a $0.004 sim 0.014$ higher mPA and $0.004 sim 0.06$ higher mIoU than other seven algorithms. Besides the segmentation results also show that the over-segmentation is reduced.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114633688","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 : 2022-07-15DOI: 10.1109/icaci55529.2022.9837544
Jinzhan Xie, Wen Wei, Pengcheng Liao, Jiahao Liu
Based on the induction motor vector control system, the active disturbance rejection controller (ADRC) technology is discussed. Based on the insufficient observation accuracy of the traditional nonlinear fal function, a new nonlinear normal distribution function ndfal function is constructed to redesign the ADRC controller, which is applied to the induction motor speed regulator, and the induction motor vector control system based on ndfal-ADRC speed control is designed, and the system is compared with the system based on traditional controller. The simulation results show that the control effect of the system based on ndfal ADRC is obviously better than the traditional control. It greatly improves the speed response speed and steady-state accuracy of the system, and has certain anti-interference performance and feasibility.
{"title":"Design of ADRC Controller for Induction Motor Based on Improved fal Function","authors":"Jinzhan Xie, Wen Wei, Pengcheng Liao, Jiahao Liu","doi":"10.1109/icaci55529.2022.9837544","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837544","url":null,"abstract":"Based on the induction motor vector control system, the active disturbance rejection controller (ADRC) technology is discussed. Based on the insufficient observation accuracy of the traditional nonlinear fal function, a new nonlinear normal distribution function ndfal function is constructed to redesign the ADRC controller, which is applied to the induction motor speed regulator, and the induction motor vector control system based on ndfal-ADRC speed control is designed, and the system is compared with the system based on traditional controller. The simulation results show that the control effect of the system based on ndfal ADRC is obviously better than the traditional control. It greatly improves the speed response speed and steady-state accuracy of the system, and has certain anti-interference performance and feasibility.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121657744","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}
This short paper addresses the synchronization problem for a class of complex networks with time delays. In the model studied in this paper, the coupling of nodes is nonlinear, because many network nodes, the dynamic characteristics of complex, if only rely on the network itself, it is difficult to achieve synchronization. Aiming at this kind of complex network with time delay, we control some nodes of the network through pinning control, so that the state of the whole network nodes can achieve synchronization. In addition, we give the sufficient conditions for the synchronization of complex networks with time delays, and use Lyapunov function and inequality principle to carry out theoretical analysis. Finally, an example is presented to illustrate the effectiveness of the theoretical results.
{"title":"On Pinning Synchronization of an Array of Nonlinearly Coupled Dynamical Network With Time Delay","authors":"Wudai Liao, Haoran Chen, Jinhuan Chen, YaoHua Yang, Jingyu Wang, Heng Jia","doi":"10.1109/icaci55529.2022.9837612","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837612","url":null,"abstract":"This short paper addresses the synchronization problem for a class of complex networks with time delays. In the model studied in this paper, the coupling of nodes is nonlinear, because many network nodes, the dynamic characteristics of complex, if only rely on the network itself, it is difficult to achieve synchronization. Aiming at this kind of complex network with time delay, we control some nodes of the network through pinning control, so that the state of the whole network nodes can achieve synchronization. In addition, we give the sufficient conditions for the synchronization of complex networks with time delays, and use Lyapunov function and inequality principle to carry out theoretical analysis. Finally, an example is presented to illustrate the effectiveness of the theoretical results.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128156478","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 : 2022-07-15DOI: 10.1109/icaci55529.2022.9837526
Yang Liu, Guodong Zhang
In this paper, fixed-time projective synchronization (FXTPS) of discontinuous fuzzy inertial neural networks (FINNs) is explored. A class of FINNs with discrete and bounded distributed time-varying delays is proposed. Based on this model, a non-reduced approach is utilized to design an effective feedback control scheme. And sufficient conditions for FXTPS are established. Finally, a numerical example is used to verify the validity of the theoretical results obtained.
{"title":"Fixed-time Projective Synchronization For Discontinuous Fuzzy Inertial Neural Networks Via Non-reduced Method","authors":"Yang Liu, Guodong Zhang","doi":"10.1109/icaci55529.2022.9837526","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837526","url":null,"abstract":"In this paper, fixed-time projective synchronization (FXTPS) of discontinuous fuzzy inertial neural networks (FINNs) is explored. A class of FINNs with discrete and bounded distributed time-varying delays is proposed. Based on this model, a non-reduced approach is utilized to design an effective feedback control scheme. And sufficient conditions for FXTPS are established. Finally, a numerical example is used to verify the validity of the theoretical results obtained.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127573993","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 : 2022-07-15DOI: 10.1109/icaci55529.2022.9837622
Jiaxin Li, Xuan Rao, Songyi Xiao, Bo Zhao, Derong Liu
Channel pruning is an effective way for neural networks compression. However, traditional pruning methods based on rules and regularization usually depend on expert knowledge. Moreover, reinforcement learning and evolutionary algorithms-based pruning methods have low pruning efficiency and are time consuming. In this paper, an efficient pruning method named Pruner to Predictor (P2P) is developed. The pruner which consists of differentiable structural parameters generates a continuous representation of the neural network structure. The predictor which is constructed by neural networks predicts the performance of networks with different structures. As a result, the predictor maps the relationship between the network structure and the performance. Therefore, the gradient descent method is leveraged to optimize the pruner in an end to end manner, which achieves an effective and efficient neural network pruning. Experimental results on CIFAR10 and ImageNet show that the present P2P outperforms many previous state-of-the-art methods.
信道修剪是神经网络压缩的有效方法。然而，传统的基于规则和正则化的剪枝方法往往依赖于专家知识。此外，基于强化学习和进化算法的剪枝方法剪枝效率低且耗时长。本文提出了一种高效的剪枝方法——剪枝到预测器(Pruner to Predictor, P2P)。由可微结构参数组成的剪枝器生成神经网络结构的连续表示。由神经网络构造的预测器预测不同结构网络的性能。因此，预测器映射了网络结构和性能之间的关系。因此，利用梯度下降法对剪枝器进行端到端优化，实现了高效有效的神经网络剪枝。在CIFAR10和ImageNet上的实验结果表明，本文提出的P2P算法优于许多先前最先进的方法。
{"title":"Pruner to Predictor: An Efficient Pruning Method for Neural Networks Compression","authors":"Jiaxin Li, Xuan Rao, Songyi Xiao, Bo Zhao, Derong Liu","doi":"10.1109/icaci55529.2022.9837622","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837622","url":null,"abstract":"Channel pruning is an effective way for neural networks compression. However, traditional pruning methods based on rules and regularization usually depend on expert knowledge. Moreover, reinforcement learning and evolutionary algorithms-based pruning methods have low pruning efficiency and are time consuming. In this paper, an efficient pruning method named Pruner to Predictor (P2P) is developed. The pruner which consists of differentiable structural parameters generates a continuous representation of the neural network structure. The predictor which is constructed by neural networks predicts the performance of networks with different structures. As a result, the predictor maps the relationship between the network structure and the performance. Therefore, the gradient descent method is leveraged to optimize the pruner in an end to end manner, which achieves an effective and efficient neural network pruning. Experimental results on CIFAR10 and ImageNet show that the present P2P outperforms many previous state-of-the-art methods.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133319280","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 : 2022-07-15DOI: 10.1109/icaci55529.2022.9837560
Moxuan Guo, Song Zhu
This work explores state estimation considering Memristive Neural Networks (MNNs) with time-varying delays and bounded disturbances. Some sufficient conditions for algebraic criteria are derived from achieving exponential stability. Establishing two kinds of observers defined by two matrix multiplications, Hadamard product and matmul product, we obtain the estimation of state solutions such that the error system stability. Finally, the availability of the results is verified via a numerical simulation.
{"title":"State Estimation for Memristive Neural Networks with Observer","authors":"Moxuan Guo, Song Zhu","doi":"10.1109/icaci55529.2022.9837560","DOIUrl":"https://doi.org/10.1109/icaci55529.2022.9837560","url":null,"abstract":"This work explores state estimation considering Memristive Neural Networks (MNNs) with time-varying delays and bounded disturbances. Some sufficient conditions for algebraic criteria are derived from achieving exponential stability. Establishing two kinds of observers defined by two matrix multiplications, Hadamard product and matmul product, we obtain the estimation of state solutions such that the error system stability. Finally, the availability of the results is verified via a numerical simulation.","PeriodicalId":412347,"journal":{"name":"2022 14th International Conference on Advanced Computational Intelligence (ICACI)","volume":"829 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133684388","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：