Pub Date : 2023-09-20DOI: 10.20965/jaciii.2023.p0932
Ziwei Xin, Juan Li, Jie Li, Chang Liu
The rapid implementation of multi-task decoupling in restricted flight areas for unmanned aerial vehicle swarms is crucial to ensure swarm effectiveness. This study introduces a task-switching mechanism in the bio-inspired rule-based (Bio-RB) decision-making algorithm and establishes a mapping relationship from behavioral rules to task modes. A complete decision model is constructed for the cooperative search and package delivery tasks. To further improve the search efficiency of swarms in restricted areas, a boundary-handling strategy based on the combination of path prediction and virtual agents is proposed. The overall scheme is termed the task-driven rule-based (Task-RB) decision-making algorithm. The proposed Task-RB method is evaluated under full-flow simulation. Numerical experiments demonstrate the superior performance of the proposed Task-RB method against the Bio-RB method under different instances.
{"title":"Collaborative Search and Package Delivery Strategy for UAV Swarms Under Area Restrictions","authors":"Ziwei Xin, Juan Li, Jie Li, Chang Liu","doi":"10.20965/jaciii.2023.p0932","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0932","url":null,"abstract":"The rapid implementation of multi-task decoupling in restricted flight areas for unmanned aerial vehicle swarms is crucial to ensure swarm effectiveness. This study introduces a task-switching mechanism in the bio-inspired rule-based (Bio-RB) decision-making algorithm and establishes a mapping relationship from behavioral rules to task modes. A complete decision model is constructed for the cooperative search and package delivery tasks. To further improve the search efficiency of swarms in restricted areas, a boundary-handling strategy based on the combination of path prediction and virtual agents is proposed. The overall scheme is termed the task-driven rule-based (Task-RB) decision-making algorithm. The proposed Task-RB method is evaluated under full-flow simulation. Numerical experiments demonstrate the superior performance of the proposed Task-RB method against the Bio-RB method under different instances.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136264987","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}
Blockchain is a technology that collects data in a blockchain and allows transactions securely and transparently. It is used in many fields. Bibliometric publications examining detailed research trends in blockchain and cryptocurrency are still rare, but one bibliometric report did include research on the topic. The present work is filling in the void that eludes the study of research in the blockchain area. In the current work, we have included a wide range of blockchain and cryptocurrency research efforts to date. This study used the Scopus database to extract 2,045 articles from 2014 to 2021. The goal was to examine blockchain and cryptocurrency growth in volume, trend, global distribution, significant journals, pioneering authors, leading nations, and dominant sectors. This study highlights many aspects of worldwide blockchain and cryptocurrency research by researchers from all over the world. This research also studies how consensus decision-making and its processes are used. This study highlights many aspects of global blockchain and cryptocurrency research. This study also examines their use and consensus methods.
{"title":"Blockchain and Cryptocurrency: A Bibliometric Analysis","authors":"Shaily Jain, Chetan Sharma, Prasenjit Das, Shankar Shambhu, Hsin-Yuan Chen","doi":"10.20965/jaciii.2023.p0822","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0822","url":null,"abstract":"Blockchain is a technology that collects data in a blockchain and allows transactions securely and transparently. It is used in many fields. Bibliometric publications examining detailed research trends in blockchain and cryptocurrency are still rare, but one bibliometric report did include research on the topic. The present work is filling in the void that eludes the study of research in the blockchain area. In the current work, we have included a wide range of blockchain and cryptocurrency research efforts to date. This study used the Scopus database to extract 2,045 articles from 2014 to 2021. The goal was to examine blockchain and cryptocurrency growth in volume, trend, global distribution, significant journals, pioneering authors, leading nations, and dominant sectors. This study highlights many aspects of worldwide blockchain and cryptocurrency research by researchers from all over the world. This research also studies how consensus decision-making and its processes are used. This study highlights many aspects of global blockchain and cryptocurrency research. This study also examines their use and consensus methods.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136263675","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}
In order to improve the universality and security of the data management of the Internet of Things and avoid the single point of failure problem in the traditional management architecture, this paper proposes a massive connection management architecture based on blockchain. The blockchain is reconstructed according to the hierarchical structure of blockchain technology, and with reference to the attribute-based access control mechanism, a data exchange model is designed using gossip mode and TLS networking mode to ensure the safe transmission of data. The peer computer network technology, data signature, and consensus mechanism are used to complete the design of the data exchange network layer and realize the design of the blockchain-based massive connection management architecture, so as to effectively avoid the single point of failure problem in the traditional management architecture and greatly reduce the burden of the management center. The access requests of massive devices in 5G application scenarios were simulated, and the results showed that the blockchain-based access control architecture designed in this article can quickly process received requests, with information leakage below 10%, improving the security and processing performance of data connections, achieving efficient processing and management of large-scale data, and providing reliable guarantees for the development of the Internet era.
{"title":"Massive Data Connection Architecture Design of Web Platform Based on Blockchain","authors":"Hongping Cao, Hongxing Cao, Hongwei Zhou, Yifeng Wu, Siyu Xu","doi":"10.20965/jaciii.2023.p0855","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0855","url":null,"abstract":"In order to improve the universality and security of the data management of the Internet of Things and avoid the single point of failure problem in the traditional management architecture, this paper proposes a massive connection management architecture based on blockchain. The blockchain is reconstructed according to the hierarchical structure of blockchain technology, and with reference to the attribute-based access control mechanism, a data exchange model is designed using gossip mode and TLS networking mode to ensure the safe transmission of data. The peer computer network technology, data signature, and consensus mechanism are used to complete the design of the data exchange network layer and realize the design of the blockchain-based massive connection management architecture, so as to effectively avoid the single point of failure problem in the traditional management architecture and greatly reduce the burden of the management center. The access requests of massive devices in 5G application scenarios were simulated, and the results showed that the blockchain-based access control architecture designed in this article can quickly process received requests, with information leakage below 10%, improving the security and processing performance of data connections, achieving efficient processing and management of large-scale data, and providing reliable guarantees for the development of the Internet era.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136265002","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 : 2023-09-20DOI: 10.20965/jaciii.2023.p0812
Yawei Xu, Wei Wang, Jia Zhou, Zhihua Zhu, Changzheng Yao
To ensure the safe operation of the power system, it is necessary to monitor and manage all kinds of power facilities. Real-time power monitoring can play a role in the early warning of geographical disasters. At the transmission end, the state detection and fault location of transmission lines are related to the normal operation of the power system. The precise time synchronization of the power system can be guaranteed through the satellite positioning time service, so that the time of various power operation actions is consistent. The accuracy can reach several microseconds, which provides a basis for the analysis of power grid operation. In this paper, by installing BeiDou functional modules in power equipment and developing the BeiDou operation platform for the distribution network, the precise management of power timing and positioning is realized by docking with the geographic information systems platform of the power grid. The three-dimensional sphere error probability (SEP) algorithm is selected to evaluate the positioning error data. Based on the three traditional SEP calculation methods, the maximum likelihood estimation algorithm is optimized and improved, which can achieve nanosecond synchronization accuracy. It can also be applied to other precision of synchronization scenarios of the power system to meet the development needs of the future clock system of the power system. Through the simulation of experimental data and comparison with other algorithms, the accuracy is verified and the reliable estimation of parameters is realized. Considering the information loss caused by dimension reduction evaluation, the simulation analysis in this paper is compared with other methods, and the accuracy is significantly improved. The power system positioning and timing module developed in this paper can not only be used in the power system but also has a certain reference and application value for other devices in the same industry that need timing and positioning services.
{"title":"SEP Optimization of Power System Location and Timing Module Based on MLE-KNN Synthesis Algorithm","authors":"Yawei Xu, Wei Wang, Jia Zhou, Zhihua Zhu, Changzheng Yao","doi":"10.20965/jaciii.2023.p0812","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0812","url":null,"abstract":"To ensure the safe operation of the power system, it is necessary to monitor and manage all kinds of power facilities. Real-time power monitoring can play a role in the early warning of geographical disasters. At the transmission end, the state detection and fault location of transmission lines are related to the normal operation of the power system. The precise time synchronization of the power system can be guaranteed through the satellite positioning time service, so that the time of various power operation actions is consistent. The accuracy can reach several microseconds, which provides a basis for the analysis of power grid operation. In this paper, by installing BeiDou functional modules in power equipment and developing the BeiDou operation platform for the distribution network, the precise management of power timing and positioning is realized by docking with the geographic information systems platform of the power grid. The three-dimensional sphere error probability (SEP) algorithm is selected to evaluate the positioning error data. Based on the three traditional SEP calculation methods, the maximum likelihood estimation algorithm is optimized and improved, which can achieve nanosecond synchronization accuracy. It can also be applied to other precision of synchronization scenarios of the power system to meet the development needs of the future clock system of the power system. Through the simulation of experimental data and comparison with other algorithms, the accuracy is verified and the reliable estimation of parameters is realized. Considering the information loss caused by dimension reduction evaluation, the simulation analysis in this paper is compared with other methods, and the accuracy is significantly improved. The power system positioning and timing module developed in this paper can not only be used in the power system but also has a certain reference and application value for other devices in the same industry that need timing and positioning services.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136264238","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}
In this study, the train platform rescheduling problem (TPRP) at a high-speed railway station is analyzed. The adjustments of the train track assignment and train arrival/departure times under train arrival delays are addressed in the TPRP. The problem is formulated as a mixed-integer nonlinear programming model that minimizes the weighted sum of total train delays and rescheduling costs. An improved genetic algorithm (GA) is proposed, and the individual is represented as a platform track assignment and train departure priority, which is a mixed encoding scheme with integers and permutations. The individual is decoded into a feasible schedule comprising the platform track assignment and arrival/departure times of trains using a rule-based method for conflict resolution in the platform tracks and arrival/departure routes. The proposed GA is compared with state-of-the-art evolutionary algorithms. The experimental results confirm the superiority of the GA, which uses the mixed encoding and rule-based decoding, in terms of constraint handling and solution quality.
{"title":"Improved Genetic Algorithm for Train Platform Rescheduling Under Train Arrival Delays","authors":"Shuxin Ding, Tao Zhang, Rongsheng Wang, Yanhao Sun, Xiaozhao Zhou, Chen Chen, Zhiming Yuan","doi":"10.20965/jaciii.2023.p0959","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0959","url":null,"abstract":"In this study, the train platform rescheduling problem (TPRP) at a high-speed railway station is analyzed. The adjustments of the train track assignment and train arrival/departure times under train arrival delays are addressed in the TPRP. The problem is formulated as a mixed-integer nonlinear programming model that minimizes the weighted sum of total train delays and rescheduling costs. An improved genetic algorithm (GA) is proposed, and the individual is represented as a platform track assignment and train departure priority, which is a mixed encoding scheme with integers and permutations. The individual is decoded into a feasible schedule comprising the platform track assignment and arrival/departure times of trains using a rule-based method for conflict resolution in the platform tracks and arrival/departure routes. The proposed GA is compared with state-of-the-art evolutionary algorithms. The experimental results confirm the superiority of the GA, which uses the mixed encoding and rule-based decoding, in terms of constraint handling and solution quality.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136264989","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}
A novel method for predicting the thicknesses of plastics based on continuous-wave terahertz (THz) frequency-domain spectroscopy (THz-FDS) is presented in this study. Initially, the target material’s THz refractive index is determined from the phase information provided by the coherent nature of THz-FDS. For thickness prediction, the optimal frequency band with a high signal-to-noise ratio and minor water vapor absorption is chosen first. The optical path along which the THz wave passes through a sample with unknown thickness is extracted from the phase delay information. The physical thickness of the sample is then determined using the calibrated refractive index obtained in the first step. Teflon, a classical plastic material, is utilized to illustrate the proposed process. A remarkable consistency with an overall relative difference of only 0.45% is revealed between the THz-FDS predicted and caliper measured thicknesses. The proposed method is expected to significantly expand the capabilities of THz spectroscopy.
{"title":"Prediction of Thickness for Plastic Products Based on Terahertz Frequency-Domain Spectroscopy","authors":"Tian-yao Zhang, Boyang Li, Zhipeng Ye, Jianfeng Yan, Xiaoyan Zhao, Zhaohui Zhang","doi":"10.20965/jaciii.2023.p0726","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0726","url":null,"abstract":"A novel method for predicting the thicknesses of plastics based on continuous-wave terahertz (THz) frequency-domain spectroscopy (THz-FDS) is presented in this study. Initially, the target material’s THz refractive index is determined from the phase information provided by the coherent nature of THz-FDS. For thickness prediction, the optimal frequency band with a high signal-to-noise ratio and minor water vapor absorption is chosen first. The optical path along which the THz wave passes through a sample with unknown thickness is extracted from the phase delay information. The physical thickness of the sample is then determined using the calibrated refractive index obtained in the first step. Teflon, a classical plastic material, is utilized to illustrate the proposed process. A remarkable consistency with an overall relative difference of only 0.45% is revealed between the THz-FDS predicted and caliper measured thicknesses. The proposed method is expected to significantly expand the capabilities of THz spectroscopy.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"5 1","pages":"726-731"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87513512","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0543
T. Obo, Kunikazu Hamada, Masatoshi Eguchi, N. Kubota
This paper presents a method of pose estimation with camera localization based on a genetic algorithm to derive the joint angle using an inverse kinematics model. In recent years, some open-source libraries for human skeleton tracking that can be implemented on smartphones have been released. Such software can detect joint positions of a skeleton from a 2D camera image; however, the 3D posture cannot be obtained. We therefore propose a method to estimate joint angles by using skeleton data. In the proposed approach, we use a multi-island genetic algorithm to maintain the diversity of the population and design a multi-objective function to improve the robustness. Moreover, structured learning based on topological mapping is implemented in the proposed method to enhance searching efficiency. In an experiment, the proposed method reduced the effect of outliers caused by misdetection. In addition, the structured learning was effective in decreasing the difference between skeleton data and the estimated poses.
{"title":"Human Pose Estimation with Multi-Camera Localization Using Multi-Objective Optimization Based on Topological Structured Learning","authors":"T. Obo, Kunikazu Hamada, Masatoshi Eguchi, N. Kubota","doi":"10.20965/jaciii.2023.p0543","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0543","url":null,"abstract":"This paper presents a method of pose estimation with camera localization based on a genetic algorithm to derive the joint angle using an inverse kinematics model. In recent years, some open-source libraries for human skeleton tracking that can be implemented on smartphones have been released. Such software can detect joint positions of a skeleton from a 2D camera image; however, the 3D posture cannot be obtained. We therefore propose a method to estimate joint angles by using skeleton data. In the proposed approach, we use a multi-island genetic algorithm to maintain the diversity of the population and design a multi-objective function to improve the robustness. Moreover, structured learning based on topological mapping is implemented in the proposed method to enhance searching efficiency. In an experiment, the proposed method reduced the effect of outliers caused by misdetection. In addition, the structured learning was effective in decreasing the difference between skeleton data and the estimated poses.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"359 1","pages":"543-553"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76393860","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0561
Zhi Ma, Lei Zhao, Longsheng Wei
Human parsing is one of the basic tasks in the field of computer vision. It aims at assigning pixel-level semantic labels to each human body part. Single human parsing requires further associating semantic parts with each instance. Aiming at the problem that it is difficult to distinguish the body parts with similar local features, this paper proposes a single human parsing method based on the visual attention mechanism. The proposed algorithm integrates advanced semantic features, global context information, and edge information to obtain accurate results of single human parsing resolution. The proposed algorithm is validated on standard look into part (LIP) dataset, and the results prove the effectiveness of the proposed algorithm.
{"title":"Single Human Parsing Based on Visual Attention and Feature Enhancement","authors":"Zhi Ma, Lei Zhao, Longsheng Wei","doi":"10.20965/jaciii.2023.p0561","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0561","url":null,"abstract":"Human parsing is one of the basic tasks in the field of computer vision. It aims at assigning pixel-level semantic labels to each human body part. Single human parsing requires further associating semantic parts with each instance. Aiming at the problem that it is difficult to distinguish the body parts with similar local features, this paper proposes a single human parsing method based on the visual attention mechanism. The proposed algorithm integrates advanced semantic features, global context information, and edge information to obtain accurate results of single human parsing resolution. The proposed algorithm is validated on standard look into part (LIP) dataset, and the results prove the effectiveness of the proposed algorithm.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"33 1","pages":"561-566"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78831594","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0585
Yuanfeng Huang, Sheng Du, Jie Hu, W. Pedrycz, Min Wu
The operating conditions influence the stability and consumption of a blast furnace. Recognizing these conditions makes changing the burden distribution parameters more efficient. The cooling stave temperature (CST) is a crucial state parameter that indicates the conditions of the process. Owing to the high data volume of the CST and the lack of methods for recognizing the stability of the slag crust, it is difficult for operators to recognize the conditions accurately according to the CST during the ironmaking process. Thus, in this study, a condition recognition method with information granulation for burden distribution in a blast furnace was presented. First, information granulation was employed to reduce the volume of the CST data and present it in a granular form. Then, considering the lack of a method for calculating the similarity of CST information granules, a novel fuzzy similarity calculation method was devised to calculate the membership grades of information granules belonging to different standard granules. Finally, the conditions were recognized according to the membership values. Experimental results based on industrial data demonstrated that the proposed method can be used to recognizes the conditions in the blast furnace.
{"title":"Condition Recognition Method with Information Granulation for Burden Distribution in Blast Furnace","authors":"Yuanfeng Huang, Sheng Du, Jie Hu, W. Pedrycz, Min Wu","doi":"10.20965/jaciii.2023.p0585","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0585","url":null,"abstract":"The operating conditions influence the stability and consumption of a blast furnace. Recognizing these conditions makes changing the burden distribution parameters more efficient. The cooling stave temperature (CST) is a crucial state parameter that indicates the conditions of the process. Owing to the high data volume of the CST and the lack of methods for recognizing the stability of the slag crust, it is difficult for operators to recognize the conditions accurately according to the CST during the ironmaking process. Thus, in this study, a condition recognition method with information granulation for burden distribution in a blast furnace was presented. First, information granulation was employed to reduce the volume of the CST data and present it in a granular form. Then, considering the lack of a method for calculating the similarity of CST information granules, a novel fuzzy similarity calculation method was devised to calculate the membership grades of information granules belonging to different standard granules. Finally, the conditions were recognized according to the membership values. Experimental results based on industrial data demonstrated that the proposed method can be used to recognizes the conditions in the blast furnace.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"18 1","pages":"585-593"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86153507","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 : 2023-07-20DOI: 10.20965/jaciii.2023.p0710
Chinonso Paschal Udeh, Luefeng Chen, Sheng Du, Min Li, Min Wu
In the quest for human-robot interaction (HRI), leading to the development of emotion recognition, learning, and analysis capabilities, robotics plays a significant role in human perception, attention, decision-making, and social communication. However, the accurate recognition of emotions in HRI remains a challenge. This is due to the coexistence of multiple sources of information in utilizing multimodal facial expressions and head poses as multiple convolutional neural networks (CNN) and deep learning are combined. This research analyzes and improves the robustness of emotion recognition, and proposes a novel approach that optimizes traditional deep neural networks that fall into poor local optima when optimizing the weightings of the deep neural network using standard methods. The proposed approach adaptively finds the better weightings of the network, resulting in a hybrid genetic algorithm with stochastic gradient descent (HGASGD). This hybrid algorithm combines the inherent, implicit parallelism of the genetic algorithm with the better global optimization of stochastic gradient descent (SGD). An experiment shows the effectiveness of our proposed approach in providing complete emotion recognition through a combination of multimodal data, CNNs, and HGASGD, indicating that it represents a powerful tool in achieving interactions between humans and robotics. To validate and test the effectiveness of our proposed approach through experiments, the performance and reliability of our approach and two variants of HGASGD FER are compared using a large dataset of facial images. Our approach integrates multimodal information from facial expressions and head poses, enabling the system to recognize emotions better. The results show that CNN-HGASGD outperforms CNNs-SGD and other existing state-of-the-art methods in terms of FER.
{"title":"Multimodal Facial Emotion Recognition Using Improved Convolution Neural Networks Model","authors":"Chinonso Paschal Udeh, Luefeng Chen, Sheng Du, Min Li, Min Wu","doi":"10.20965/jaciii.2023.p0710","DOIUrl":"https://doi.org/10.20965/jaciii.2023.p0710","url":null,"abstract":"In the quest for human-robot interaction (HRI), leading to the development of emotion recognition, learning, and analysis capabilities, robotics plays a significant role in human perception, attention, decision-making, and social communication. However, the accurate recognition of emotions in HRI remains a challenge. This is due to the coexistence of multiple sources of information in utilizing multimodal facial expressions and head poses as multiple convolutional neural networks (CNN) and deep learning are combined. This research analyzes and improves the robustness of emotion recognition, and proposes a novel approach that optimizes traditional deep neural networks that fall into poor local optima when optimizing the weightings of the deep neural network using standard methods. The proposed approach adaptively finds the better weightings of the network, resulting in a hybrid genetic algorithm with stochastic gradient descent (HGASGD). This hybrid algorithm combines the inherent, implicit parallelism of the genetic algorithm with the better global optimization of stochastic gradient descent (SGD). An experiment shows the effectiveness of our proposed approach in providing complete emotion recognition through a combination of multimodal data, CNNs, and HGASGD, indicating that it represents a powerful tool in achieving interactions between humans and robotics. To validate and test the effectiveness of our proposed approach through experiments, the performance and reliability of our approach and two variants of HGASGD FER are compared using a large dataset of facial images. Our approach integrates multimodal information from facial expressions and head poses, enabling the system to recognize emotions better. The results show that CNN-HGASGD outperforms CNNs-SGD and other existing state-of-the-art methods in terms of FER.","PeriodicalId":45921,"journal":{"name":"Journal of Advanced Computational Intelligence and Intelligent Informatics","volume":"22 1","pages":"710-719"},"PeriodicalIF":0.7,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83497227","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：