Pub Date : 2023-10-11DOI: 10.1142/s0218126624501019
Chen Liang, Mingliang Zhou, Fuqiang Liu, Yi Qin
Object detection occupies a very important position in the fishing operation and autonomous navigation of underwater vehicles. At present, most deep-learning object detection approaches, such as R-CNN, SPPNet, R-FCN, etc., have two stages and are based on anchors. However, the previous methods generally have the problems of weak generalization ability and not high enough computational efficiency due to the generation of anchors. As a well-known one-stage anchor-free method, CenterNet can accelerate the inference speed by omitting the step of generating anchors, whereas it is difficult to extract sufficient global information because of the residual structure at the bottom layer, which leads to low detection precision for the overlapping targets. Dilation convolution makes the kernel obtain a larger reception field and access more information. Multi-branch structure can not only preserve the whole area information, but also efficiently separate foreground and background. By combining the dilation convolution and multi-branch structure, multi-branch dilation convolution is proposed and applied to the Hourglass backbone network in CenterNet, then an improved CenterNet named multi-branch dilation convolution CenterNet (MDC-CenterNet) is built, which has a stronger ability of object detection. The proposed method is successfully utilized for detection of underwater organisms including holothurian, scallop, echinus and starfish, and the comparison result shows that it outperforms the original CenterNet and the classical object detection network. Moreover, with the MS-COCO and PASCAL VOC datasets, a number of comparative experiments are performed for showing the advancement of our method compared to other best methods.
{"title":"Multi-Branch Dilation Convolution CenterNet for Object Detection of Underwater Vehicles","authors":"Chen Liang, Mingliang Zhou, Fuqiang Liu, Yi Qin","doi":"10.1142/s0218126624501019","DOIUrl":"https://doi.org/10.1142/s0218126624501019","url":null,"abstract":"Object detection occupies a very important position in the fishing operation and autonomous navigation of underwater vehicles. At present, most deep-learning object detection approaches, such as R-CNN, SPPNet, R-FCN, etc., have two stages and are based on anchors. However, the previous methods generally have the problems of weak generalization ability and not high enough computational efficiency due to the generation of anchors. As a well-known one-stage anchor-free method, CenterNet can accelerate the inference speed by omitting the step of generating anchors, whereas it is difficult to extract sufficient global information because of the residual structure at the bottom layer, which leads to low detection precision for the overlapping targets. Dilation convolution makes the kernel obtain a larger reception field and access more information. Multi-branch structure can not only preserve the whole area information, but also efficiently separate foreground and background. By combining the dilation convolution and multi-branch structure, multi-branch dilation convolution is proposed and applied to the Hourglass backbone network in CenterNet, then an improved CenterNet named multi-branch dilation convolution CenterNet (MDC-CenterNet) is built, which has a stronger ability of object detection. The proposed method is successfully utilized for detection of underwater organisms including holothurian, scallop, echinus and starfish, and the comparison result shows that it outperforms the original CenterNet and the classical object detection network. Moreover, with the MS-COCO and PASCAL VOC datasets, a number of comparative experiments are performed for showing the advancement of our method compared to other best methods.","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136057946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Micro coal-fired units (MCFU) and combined heat and power plants (CHP) in integrated energy system (IES) will emit a large amount of carbon dioxide when providing loads to customers, which will lead to higher operating costs of IES. To solve this challenge, an optimal dispatch model of power-to-gas (P2G) and methane reactor (MR) considering the reward and punishment costs based on carbon emission trading mechanism is proposed, to reduce carbon emissions of IES and enhance the accommodation of renewable energy (RE). Subsequently, considering the uncertainty of RE, a combination optimization method for MCFU and CHP units is developed based on the Lagrange multiplier method. Finally, considering the mechanism of electricity spot market (ESM), a transaction strategy for IES participating in ESM is proposed to further enhance the accommodation of RE. The effectiveness of the proposed framework is demonstrated through simulations.
{"title":"Optimal Scheduling Framework of Integrated Energy System Based on Carbon Emission in Electricity Spot Market","authors":"Xiangyu Cai, Haixin Wang, Jian Dong, Xinyi Lu, Zihao Yang, Shanshan Cheng, Yiming Ma, Junyou Yang, Zhe Chen","doi":"10.1142/s0218126624500968","DOIUrl":"https://doi.org/10.1142/s0218126624500968","url":null,"abstract":"Micro coal-fired units (MCFU) and combined heat and power plants (CHP) in integrated energy system (IES) will emit a large amount of carbon dioxide when providing loads to customers, which will lead to higher operating costs of IES. To solve this challenge, an optimal dispatch model of power-to-gas (P2G) and methane reactor (MR) considering the reward and punishment costs based on carbon emission trading mechanism is proposed, to reduce carbon emissions of IES and enhance the accommodation of renewable energy (RE). Subsequently, considering the uncertainty of RE, a combination optimization method for MCFU and CHP units is developed based on the Lagrange multiplier method. Finally, considering the mechanism of electricity spot market (ESM), a transaction strategy for IES participating in ESM is proposed to further enhance the accommodation of RE. The effectiveness of the proposed framework is demonstrated through simulations.","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136057947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The growth of Internet of Things (IoT)-enabled devices has increased the amount of data created by the distribution network’s periphery nodes, requiring more data transfer capacity. Recent applications’ real-time requirements have strained standard computing paradigms, and data processing has struggled to keep up. Edge computing is employed in this research to detect distribution network faults, allowing for instant sensing and real-time reaction to the control room for faster investigation of distribution problems and power outages, making the system more reliable. Moreover, to overcome the challenges of fault detection, advanced signal processing methods need to be integrated with the Adaboost classifier. An Adaboost-based edge device, suitable for installation on top of a power pole, is proposed in this research as a means of real-time fault detection. To increase throughput, decrease latency and offload network traffic, data collecting, feature extraction and Adaboost-based problem identification are all performed in an integrated edge node. Enhanced detection accuracy (98.67%) and decreased latency (115.2 ms) verify the effectiveness of the suggested approach. In this research, we enhance the classical chirplets transform to create the scaling-basis chirplet transform (SBCT) for time–frequency (TF) analysis. This approach modulates the TF basis around the relevant time function to modify the chirp rate with frequency and time. By carefully selecting the sampling frequency, it is possible to discriminate between short circuit fault and high-impedance fault (HIF) by calculating spectral entropy. The TF representation obtained with the SBCT provides considerably higher energy concentrations, even for signals with numerous components, closely spaced frequencies and heavy background noise.
{"title":"A New Approach to Detect Power Quality Disturbances in Smart Cities Using Scaling-Based Chirplet Transform with Strategically Placed Smart Meters","authors":"Pampa Sinha, Kaushik Paul, Sanchari Deb, Ankit Vidyarthi, Abhishek Singh Kilak, Deepak Gupta","doi":"10.1142/s0218126624500932","DOIUrl":"https://doi.org/10.1142/s0218126624500932","url":null,"abstract":"The growth of Internet of Things (IoT)-enabled devices has increased the amount of data created by the distribution network’s periphery nodes, requiring more data transfer capacity. Recent applications’ real-time requirements have strained standard computing paradigms, and data processing has struggled to keep up. Edge computing is employed in this research to detect distribution network faults, allowing for instant sensing and real-time reaction to the control room for faster investigation of distribution problems and power outages, making the system more reliable. Moreover, to overcome the challenges of fault detection, advanced signal processing methods need to be integrated with the Adaboost classifier. An Adaboost-based edge device, suitable for installation on top of a power pole, is proposed in this research as a means of real-time fault detection. To increase throughput, decrease latency and offload network traffic, data collecting, feature extraction and Adaboost-based problem identification are all performed in an integrated edge node. Enhanced detection accuracy (98.67%) and decreased latency (115.2 ms) verify the effectiveness of the suggested approach. In this research, we enhance the classical chirplets transform to create the scaling-basis chirplet transform (SBCT) for time–frequency (TF) analysis. This approach modulates the TF basis around the relevant time function to modify the chirp rate with frequency and time. By carefully selecting the sampling frequency, it is possible to discriminate between short circuit fault and high-impedance fault (HIF) by calculating spectral entropy. The TF representation obtained with the SBCT provides considerably higher energy concentrations, even for signals with numerous components, closely spaced frequencies and heavy background noise.","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135251910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-06DOI: 10.1142/s0218126624501184
Zhongqiu Zhang, Jun You, Zhiguo Han
{"title":"3-D Impact Time and Angle Control Guidance Law Based on Sliding Mode without Speed Control","authors":"Zhongqiu Zhang, Jun You, Zhiguo Han","doi":"10.1142/s0218126624501184","DOIUrl":"https://doi.org/10.1142/s0218126624501184","url":null,"abstract":"","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135351285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-06DOI: 10.1142/s0218126624501196
Chen Hao, Du XinGang, Peng ChuNing, Liu Jing
{"title":"Fast Detection Technology of Abnormal Out-of-Tolerance Meters Based on FIT Model Theory","authors":"Chen Hao, Du XinGang, Peng ChuNing, Liu Jing","doi":"10.1142/s0218126624501196","DOIUrl":"https://doi.org/10.1142/s0218126624501196","url":null,"abstract":"","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135350533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-06DOI: 10.1142/s0218126624501007
Jie Zhang, Xinghao Wang, Jinyou Hou, Yan Guo, Qinggang Xie
This paper proposes a new four-dimensional hyper-chaotic system capable of generating multi-wing chaotic attractors by introducing active magnetron memristors, multi-segmented square functions and trigonometric functions. The dynamical properties of this new hyper-chaotic system, such as equilibrium point, dissipation, Lyapunov exponential spectrum, bifurcation diagram and Poincaré cross-section and attraction basin, are analyzed theoretically and simulated numerically, and the complexity of this system with different parameters is analyzed. It is observed that this hyper-chaotic system has periodic, chaotic and hyper-chaotic variations with an infinite number of equilibria and coexisting attractors under different parameter conditions. The circuit simulation was performed using Multisim and the results obtained were consistent with the numerical analysis of the dynamics, and the chaotic circuit system is designed by FPGA to verify the realizability of the system. Finally, an image encryption algorithm is designed in conjunction with the DNA algorithm to enable a new system chaotic sequence for image encryption. The results show that the hyper-chaotic system has rich dynamical behavior and has high-security performance when applied to image encryption with strong chaotic key and plaintext sensitivity and large key space in image encryption.
{"title":"A novel memristor-based multi-vortex hyperchaotic circuit design and its application in image encryption","authors":"Jie Zhang, Xinghao Wang, Jinyou Hou, Yan Guo, Qinggang Xie","doi":"10.1142/s0218126624501007","DOIUrl":"https://doi.org/10.1142/s0218126624501007","url":null,"abstract":"This paper proposes a new four-dimensional hyper-chaotic system capable of generating multi-wing chaotic attractors by introducing active magnetron memristors, multi-segmented square functions and trigonometric functions. The dynamical properties of this new hyper-chaotic system, such as equilibrium point, dissipation, Lyapunov exponential spectrum, bifurcation diagram and Poincaré cross-section and attraction basin, are analyzed theoretically and simulated numerically, and the complexity of this system with different parameters is analyzed. It is observed that this hyper-chaotic system has periodic, chaotic and hyper-chaotic variations with an infinite number of equilibria and coexisting attractors under different parameter conditions. The circuit simulation was performed using Multisim and the results obtained were consistent with the numerical analysis of the dynamics, and the chaotic circuit system is designed by FPGA to verify the realizability of the system. Finally, an image encryption algorithm is designed in conjunction with the DNA algorithm to enable a new system chaotic sequence for image encryption. The results show that the hyper-chaotic system has rich dynamical behavior and has high-security performance when applied to image encryption with strong chaotic key and plaintext sensitivity and large key space in image encryption.","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135302896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-06DOI: 10.1142/s0218126624501202
Yutao Wu, Min Liu
{"title":"Hybrid Deep Learning Model based on Sparse Recurrent Architecture","authors":"Yutao Wu, Min Liu","doi":"10.1142/s0218126624501202","DOIUrl":"https://doi.org/10.1142/s0218126624501202","url":null,"abstract":"","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135350514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-06DOI: 10.1142/s0218126624501214
Yajie Wang, Shaolin Liang
{"title":"A Fast Scenario Transfer Approach for Portrait Styles Through Collaborative Awareness of Convolutional Neural Network and Generative Adversarial Learning","authors":"Yajie Wang, Shaolin Liang","doi":"10.1142/s0218126624501214","DOIUrl":"https://doi.org/10.1142/s0218126624501214","url":null,"abstract":"","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135350518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-04DOI: 10.1142/s0218126624501020
Zhenyu Wang, Juan Xiao, Shuai Zhang, Baoqiang Qi
Image semantic segmentation technology is one of the core research contents in the field of computer vision. With the improvement of computer performance and the continuous development of deep learning technology, researchers have more and more enthusiasm to study the actual effect and performance of image semantic segmentation. The results of deep semantic segmentation allow computers to have a more detailed and accurate understanding of images, and have a wide range of application needs in the fields of autonomous driving, intelligent security, medical imaging, remote sensing images, etc. However, the existing image semantic segmentation algorithms have the disadvantages of easy discontinuous results and insufficient prediction accuracy. In this paper, we take deep learning-based image semantic segmentation technology as the research object to explore the improvement of the image semantic segmentation algorithm and its application in road scenarios. First, this paper proposes MCU-Net method based on residual fusion and multi-scale contextual information. MCU-Net uses residual fusion module to deepen the network structure and improve the ability of U-Net to acquire deeper features. Then a top-down and bottom-up path is constructed for feature information between different levels, and the spatial and semantic information contained in shallow and deep features in the network is fully utilized by fusing features from different levels. In addition, an enhanced void space pyramid pooling module is added for feature information between the same levels, which enables the output features to have a larger range of semantic information. Second, this paper proposes the DAMCU-Net method based on attention mechanism and edge detection based on MCU-Net. DAMCU-Net extracts global contextual information by the attention mechanism optimization module, while fusing features using dense jump connections to facilitate the network to recover more spatial detail information during upsampling, and uses the FReLU activation function to improve the segmentation capability of the network for complex targets. For the edge information lost in the feature extraction process, the edge detection branch is added to supplement the feature information of the main path by feature fusion to achieve the optimization of the edge information.
{"title":"Semantic Segmentation of Images Based on Multi-Feature Fusion and Convolutional Neural Networks","authors":"Zhenyu Wang, Juan Xiao, Shuai Zhang, Baoqiang Qi","doi":"10.1142/s0218126624501020","DOIUrl":"https://doi.org/10.1142/s0218126624501020","url":null,"abstract":"Image semantic segmentation technology is one of the core research contents in the field of computer vision. With the improvement of computer performance and the continuous development of deep learning technology, researchers have more and more enthusiasm to study the actual effect and performance of image semantic segmentation. The results of deep semantic segmentation allow computers to have a more detailed and accurate understanding of images, and have a wide range of application needs in the fields of autonomous driving, intelligent security, medical imaging, remote sensing images, etc. However, the existing image semantic segmentation algorithms have the disadvantages of easy discontinuous results and insufficient prediction accuracy. In this paper, we take deep learning-based image semantic segmentation technology as the research object to explore the improvement of the image semantic segmentation algorithm and its application in road scenarios. First, this paper proposes MCU-Net method based on residual fusion and multi-scale contextual information. MCU-Net uses residual fusion module to deepen the network structure and improve the ability of U-Net to acquire deeper features. Then a top-down and bottom-up path is constructed for feature information between different levels, and the spatial and semantic information contained in shallow and deep features in the network is fully utilized by fusing features from different levels. In addition, an enhanced void space pyramid pooling module is added for feature information between the same levels, which enables the output features to have a larger range of semantic information. Second, this paper proposes the DAMCU-Net method based on attention mechanism and edge detection based on MCU-Net. DAMCU-Net extracts global contextual information by the attention mechanism optimization module, while fusing features using dense jump connections to facilitate the network to recover more spatial detail information during upsampling, and uses the FReLU activation function to improve the segmentation capability of the network for complex targets. For the edge information lost in the feature extraction process, the edge detection branch is added to supplement the feature information of the main path by feature fusion to achieve the optimization of the edge information.","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135547281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-29DOI: 10.1142/s0218126624501159
Wenbo Xu, Xiaojie Ma, Yi Jin
{"title":"A Modular Mathematical Modeling Method for Smart Design and Manufacturing of Automobile Driving Axles","authors":"Wenbo Xu, Xiaojie Ma, Yi Jin","doi":"10.1142/s0218126624501159","DOIUrl":"https://doi.org/10.1142/s0218126624501159","url":null,"abstract":"","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135247168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","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：