Guo-qing Ye, Xiao-tong Wang, Han-chang Wang, Yunping Zhou
Abstract: In view of the difficulty in prediction of wartime consumption of aircraft carrier airborne ammunition, this paper combines the case-based reasoning method with the nearest neighbor method and the analytic hierarchy process, fully excavates the effective information in historical consumption data through reasonable case representation, case retrieval, case revision and case learning, and finally presents a concise, fast and efficient method, and verifies the feasibility of the proposed method through an example verification.
{"title":"Wartime Consumption Prediction of Aircraft Carrier Airborne Ammunition Based on Case-Based Reasoning","authors":"Guo-qing Ye, Xiao-tong Wang, Han-chang Wang, Yunping Zhou","doi":"10.1145/3503047.3503096","DOIUrl":"https://doi.org/10.1145/3503047.3503096","url":null,"abstract":"Abstract: In view of the difficulty in prediction of wartime consumption of aircraft carrier airborne ammunition, this paper combines the case-based reasoning method with the nearest neighbor method and the analytic hierarchy process, fully excavates the effective information in historical consumption data through reasonable case representation, case retrieval, case revision and case learning, and finally presents a concise, fast and efficient method, and verifies the feasibility of the proposed method through an example verification.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"176 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120842507","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}
Estimating time difference of arrival (TDOA) is an essential prerequisite for microphone arrays in many applications such as passive sound source localization and self-calibration. In addition to measurement noise and outliers, time of arrival (TOA) deviations derived from shell-related diffraction propagation also contribute to TDOA measurements when a flush mounting array is used which consists of all sensors flush mounted into the shell. Based on the observation that the TDOAs of two pairs of sensors forming equilong parallel lines (EPLs) are equal regardless of the far-field source direction under the line-of-sight condition, we propose a novel method for flush mounting planar arrays to refine TDOA measurements applying both the linear geometric constraint corresponding to EPLs and the rank-2 algebraic constraint to the measured TDOA matrix build from all TDOA measurements. This method is capable of effectively suppressing measurement noise, TDOA outliers, and diffraction induced TOA deviations simultaneously. A closed-form, analytic solution is presented which is computationally efficient and suitable for real-time applications. Simulated and field experiments demonstrate that the proposed method outperforms the state-of-the-art algorithms if the array shape contains at least one pair of EPLs. Furthermore, explicit performance improvement can be achieved when the number of linearly independent EPLs increases. The proposed method is beneficial to further performance improvement of TDOA-based applications such as sound source localization when flush mounting planar arrays are used.
{"title":"Refinement of TDOA Measurements for Flush Mounting Planar Microphone Arrays Using Low Rank and Linear Geometric Constraints","authors":"Chen Chen, Zhao Zhao, Zhi-yong Xu","doi":"10.1145/3503047.3503107","DOIUrl":"https://doi.org/10.1145/3503047.3503107","url":null,"abstract":"Estimating time difference of arrival (TDOA) is an essential prerequisite for microphone arrays in many applications such as passive sound source localization and self-calibration. In addition to measurement noise and outliers, time of arrival (TOA) deviations derived from shell-related diffraction propagation also contribute to TDOA measurements when a flush mounting array is used which consists of all sensors flush mounted into the shell. Based on the observation that the TDOAs of two pairs of sensors forming equilong parallel lines (EPLs) are equal regardless of the far-field source direction under the line-of-sight condition, we propose a novel method for flush mounting planar arrays to refine TDOA measurements applying both the linear geometric constraint corresponding to EPLs and the rank-2 algebraic constraint to the measured TDOA matrix build from all TDOA measurements. This method is capable of effectively suppressing measurement noise, TDOA outliers, and diffraction induced TOA deviations simultaneously. A closed-form, analytic solution is presented which is computationally efficient and suitable for real-time applications. Simulated and field experiments demonstrate that the proposed method outperforms the state-of-the-art algorithms if the array shape contains at least one pair of EPLs. Furthermore, explicit performance improvement can be achieved when the number of linearly independent EPLs increases. The proposed method is beneficial to further performance improvement of TDOA-based applications such as sound source localization when flush mounting planar arrays are used.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130342459","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}
Unmanned aerial vehicles (UAVs) have been attracting more and more attention in the research and industry field. Aerial search is a common mission and is intrinsically fit for UAVs, e.g. disaster rescue, remote sensing and environmental monitoring. With the improvement of UAV hardware and software, UAVs tend to achieve better autonomy and accomplish more complex tasks. However, current UAV aerial search is usually hardcoded, which limits their adaptability, autonomy and robustness in realistic scenarios. In this paper, we propose to address this problem by leveraging reinforcement learning (RL) and a recent control architecture, behavior trees (BTs). We develop robust and adaptive UAV systems that can automatically conduct multi-phase complex aerial search, including search, communication and refueling. Experimental results in a 3D robot simulator verify the effectiveness and robustness of the proposed approach, which achieves better performance than the baseline.
{"title":"A Robust and Learning Approach for Multi-Phase Aerial Search with UAVs","authors":"Zhongxuan Cai, Minglong Li","doi":"10.1145/3503047.3503067","DOIUrl":"https://doi.org/10.1145/3503047.3503067","url":null,"abstract":"Unmanned aerial vehicles (UAVs) have been attracting more and more attention in the research and industry field. Aerial search is a common mission and is intrinsically fit for UAVs, e.g. disaster rescue, remote sensing and environmental monitoring. With the improvement of UAV hardware and software, UAVs tend to achieve better autonomy and accomplish more complex tasks. However, current UAV aerial search is usually hardcoded, which limits their adaptability, autonomy and robustness in realistic scenarios. In this paper, we propose to address this problem by leveraging reinforcement learning (RL) and a recent control architecture, behavior trees (BTs). We develop robust and adaptive UAV systems that can automatically conduct multi-phase complex aerial search, including search, communication and refueling. Experimental results in a 3D robot simulator verify the effectiveness and robustness of the proposed approach, which achieves better performance than the baseline.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"290 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132511855","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}
API protocols play an important role in program verification, testing, evolution and other phases of the software development process. Many approaches have been proposed to mine API protocols automatically from programs. However, few tools are available, especially dynamical API protocol mining tools. In this paper, we present a dynamical API protocol mining tool for Java programs: ProExtor. Our tool mines API protocols in an online mode based on the instrumentation technique of Java agent. For each class, it produces two models: a probabilistic model and a deterministic model. The probabilistic model will be evolved persistently when more application programs are fed for mining. The deterministic model is transformed from the latest probabilistic model, which can be used for program verification, testing, evolution, etc. Both models can be visualized with the software Graphviz. We elaborate design and implementation details of our tool and an application to a real-world program. We believe our work is a good reference for the development of similar tools.
{"title":"ProExtor: Mining API Protocols for Program Vulnerability Detection","authors":"Huijia Ye, Juwei Rao, Yang Shi, Zhihua Li","doi":"10.1145/3503047.3503100","DOIUrl":"https://doi.org/10.1145/3503047.3503100","url":null,"abstract":"API protocols play an important role in program verification, testing, evolution and other phases of the software development process. Many approaches have been proposed to mine API protocols automatically from programs. However, few tools are available, especially dynamical API protocol mining tools. In this paper, we present a dynamical API protocol mining tool for Java programs: ProExtor. Our tool mines API protocols in an online mode based on the instrumentation technique of Java agent. For each class, it produces two models: a probabilistic model and a deterministic model. The probabilistic model will be evolved persistently when more application programs are fed for mining. The deterministic model is transformed from the latest probabilistic model, which can be used for program verification, testing, evolution, etc. Both models can be visualized with the software Graphviz. We elaborate design and implementation details of our tool and an application to a real-world program. We believe our work is a good reference for the development of similar tools.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128771474","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}
The neural network model has been applied to all walks of life. By detecting the internal information of a black-box model, the attacker can obtain potential commercial value of the model. At the same time, understanding the model structure helps the attacker customize the strategy to attack the model. We have improved a model detection method based on input and output pairs to detect the internal information of the trained neural network black-box model. On the one hand, our work proved that adversarial examples are very likely to carry architecture information of the neural network model. On the other hand, we added adversarial examples to the model pre-detection module, and verified the positive effects of adversarial examples on model detection through experiments, which improved the accuracy of the meta-model and reduced the cost of model detection.
{"title":"Neural Network Model Extraction Based on Adversarial Examples","authors":"Huiwen Fang, Chunhua Wu","doi":"10.1145/3503047.3503085","DOIUrl":"https://doi.org/10.1145/3503047.3503085","url":null,"abstract":"The neural network model has been applied to all walks of life. By detecting the internal information of a black-box model, the attacker can obtain potential commercial value of the model. At the same time, understanding the model structure helps the attacker customize the strategy to attack the model. We have improved a model detection method based on input and output pairs to detect the internal information of the trained neural network black-box model. On the one hand, our work proved that adversarial examples are very likely to carry architecture information of the neural network model. On the other hand, we added adversarial examples to the model pre-detection module, and verified the positive effects of adversarial examples on model detection through experiments, which improved the accuracy of the meta-model and reduced the cost of model detection.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122984184","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}
The Internet-of-Things (IoT) has long become reality and contributes to the digital transformation of many industrial domains. IoT technologies are at the core of industry 4.0 application scenarios, contribute to cyber-physical system implementation, smart connected products and new business models exploiting their potential. There is plenty of work on how to specify, design and implement IoT solutions, but a lot of enterprises struggle to create business value from IoT technology because they have difficulties to define the organizational integration. Methodologies for model-driven engineering (MDE) of IoT solutions should encompass both, organizational and system development and integration, but existing model-based approaches focus on the technical perspective. The paper proposes a modeling approach integrated into enterprise modeling techniques to compensate for this lack. The enterprise modeling language 4EM is extended by adding a method component for IoT modeling. The main contributions of this paper are (a) a summary of the state-of-research in the field, (b) an industrial case for model-based IoT development, and (c) a meta-model and tool support for IoT modelling.
{"title":"Meta-Model and Tool Support for the Organizational Aspects of Internet-of-Things Development Methods: Organizational Aspects of IoT Development Methods","authors":"Benjamin Nast, K. Sandkuhl","doi":"10.1145/3503047.3503077","DOIUrl":"https://doi.org/10.1145/3503047.3503077","url":null,"abstract":"The Internet-of-Things (IoT) has long become reality and contributes to the digital transformation of many industrial domains. IoT technologies are at the core of industry 4.0 application scenarios, contribute to cyber-physical system implementation, smart connected products and new business models exploiting their potential. There is plenty of work on how to specify, design and implement IoT solutions, but a lot of enterprises struggle to create business value from IoT technology because they have difficulties to define the organizational integration. Methodologies for model-driven engineering (MDE) of IoT solutions should encompass both, organizational and system development and integration, but existing model-based approaches focus on the technical perspective. The paper proposes a modeling approach integrated into enterprise modeling techniques to compensate for this lack. The enterprise modeling language 4EM is extended by adding a method component for IoT modeling. The main contributions of this paper are (a) a summary of the state-of-research in the field, (b) an industrial case for model-based IoT development, and (c) a meta-model and tool support for IoT modelling.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122755167","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}
Xiaofei Qu, En Long, Shouye Lv, Pengfei Chen, Guangling Lai, Yuke Yang, Jisheng Du
Given their high detection rates and low false alarm rates, object detection neural networks based on deep learning have been widely used in ship detection. However, the detection in real-world scenario with complex back ground remains a challenge in marine dynamic ship detection, whose performance is limited by the scale of training datasets, where training a model with high-performance usually requires a large number of multi-scale datasets. However, it is difficult to obtain a large-scale dataset in such cases. In addition, R3Det solves the problem that the vertical and horizontal ratio of the object to be detected is large, the objects to be detected are densely arranged, and category asymmetry of objects to be detected have been widely concerned. However, R3Det uses the nearest neighbor interpolation to up-sampling the image, which leads to a blocky effect of the image with a certain probability, which affects the object detection. In order to alleviate these problems, we propose a new model called “Refined Single-Stage Detector with Feature Refinement for Rotating Object based on Scale-match”. The new pre-training strategy of scale match and improved feature pyramid network (IFPN) were introduced. The method not only expands the training data sample set, but also improves the clarity of training pictures, and improves the ship detection rate and reduce the false alarm rate. Experiments with DOTAv1.5 and high-resolution datasets showed that the ship detection rate and false alarm rate are better than baseline methods.
{"title":"Ship Detection Method based on Scale Matched R3Det","authors":"Xiaofei Qu, En Long, Shouye Lv, Pengfei Chen, Guangling Lai, Yuke Yang, Jisheng Du","doi":"10.1145/3503047.3503068","DOIUrl":"https://doi.org/10.1145/3503047.3503068","url":null,"abstract":"Given their high detection rates and low false alarm rates, object detection neural networks based on deep learning have been widely used in ship detection. However, the detection in real-world scenario with complex back ground remains a challenge in marine dynamic ship detection, whose performance is limited by the scale of training datasets, where training a model with high-performance usually requires a large number of multi-scale datasets. However, it is difficult to obtain a large-scale dataset in such cases. In addition, R3Det solves the problem that the vertical and horizontal ratio of the object to be detected is large, the objects to be detected are densely arranged, and category asymmetry of objects to be detected have been widely concerned. However, R3Det uses the nearest neighbor interpolation to up-sampling the image, which leads to a blocky effect of the image with a certain probability, which affects the object detection. In order to alleviate these problems, we propose a new model called “Refined Single-Stage Detector with Feature Refinement for Rotating Object based on Scale-match”. The new pre-training strategy of scale match and improved feature pyramid network (IFPN) were introduced. The method not only expands the training data sample set, but also improves the clarity of training pictures, and improves the ship detection rate and reduce the false alarm rate. Experiments with DOTAv1.5 and high-resolution datasets showed that the ship detection rate and false alarm rate are better than baseline methods.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132464201","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}
Since the leveling system is a nonlinear multi-variable coupling system, it is difficult for the traditional control methods to achieve good control effect in the automatic leveling system. Therefore, this paper takes the four-legged structure platform as the research object and proposes the compound leveling method of the highest point stationary method combined with the inverse system decoupling control method as the leveling method. The mechatronic integration simulation model of the platform and the leg system is established by MATLAB/Simulink. On this basis, the platform is controlled by classical PID controller, classical multi-variable PID neural network controller and improved PID neural network decoupling controller. Simulation results show that the optimized PID neural network controller not only avoids jitter, false leg, overshoot and other problems, but also greatly reduces the leveling time and improves the leveling performance of the platform.
{"title":"Research on automatic leveling Control based on improved PID Neural Network","authors":"Chusi Huang, Jiandong Li","doi":"10.1145/3503047.3503125","DOIUrl":"https://doi.org/10.1145/3503047.3503125","url":null,"abstract":"Since the leveling system is a nonlinear multi-variable coupling system, it is difficult for the traditional control methods to achieve good control effect in the automatic leveling system. Therefore, this paper takes the four-legged structure platform as the research object and proposes the compound leveling method of the highest point stationary method combined with the inverse system decoupling control method as the leveling method. The mechatronic integration simulation model of the platform and the leg system is established by MATLAB/Simulink. On this basis, the platform is controlled by classical PID controller, classical multi-variable PID neural network controller and improved PID neural network decoupling controller. Simulation results show that the optimized PID neural network controller not only avoids jitter, false leg, overshoot and other problems, but also greatly reduces the leveling time and improves the leveling performance of the platform.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128361399","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}
Cell tracking is a challenging task in computer vision because of dramatic changes of cell morphology, unregular movement pattern, and complex physiological phenomena such as mitosis and apoptosis. In recent years, cell image processing benefits a lot from the rapid development of deep learning: cell detection, segmentation, classification, especially tracking. In this paper, we propose a multiple cell tracking framework based-on multi-feature fusion. First, we propose an improved cell detection algorithm, which can detect cell mitosis and cell centroid with higher efficiency and accuracy. Second, we design a tracking framework based on the fusion of deep appearance feature and deep motion feature. Experimental results show that our proposed tracking method outperforms most traditional method and some state-of-the-art methods.
{"title":"Cell Tracking based on Multi-frame Detection and Feature Fusion","authors":"Wanli Yang, Huawei Li, Fei Wang, Dianle Zhou","doi":"10.1145/3503047.3503098","DOIUrl":"https://doi.org/10.1145/3503047.3503098","url":null,"abstract":"Cell tracking is a challenging task in computer vision because of dramatic changes of cell morphology, unregular movement pattern, and complex physiological phenomena such as mitosis and apoptosis. In recent years, cell image processing benefits a lot from the rapid development of deep learning: cell detection, segmentation, classification, especially tracking. In this paper, we propose a multiple cell tracking framework based-on multi-feature fusion. First, we propose an improved cell detection algorithm, which can detect cell mitosis and cell centroid with higher efficiency and accuracy. Second, we design a tracking framework based on the fusion of deep appearance feature and deep motion feature. Experimental results show that our proposed tracking method outperforms most traditional method and some state-of-the-art methods.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114850597","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 further improve the population diversity of the immune cloning algorithm when optimizing high-dimensional objects, and to improve the algorithm's global optimization ability and search efficiency, an immune cloning optimization algorithm based on antibody similarity screening and steady-state adjustment (ICASA) is proposed. By screening, that is, removing highly similar antibodies in the antibody population, the probability of the algorithm searching for the optimal solution is improved, and the repeated solution of similar antibodies is avoided. The antibody population is adjusted based on themedian property, and is injected with a high-quality vaccine realized by the median, which makes the antibody population evenly diffuse in the solution space to generate global antibody solutions. Finally, the convergence of the algorithm is proved by Markov chain theory. The test results of six groups of high-dimensional functions show that, compared with genetic algorithm (GA), immune cloning algorithm (ICA) and immune genetic algorithm (IGA), the proposed algorithm achieves 100% optimization, and the minimum convergence algebra, average convergence algebra and iterative algebra standard deviation are reduced by an average of 13.3%, 5.3%, and 29.3%, respectively, which verifies the algorithm's strong optimization ability, fast convergence and good stability.
{"title":"Immune Cloning Optimization Algorithm Based on Antibody Similarity Screening and Steady-State Adjustment","authors":"Su-lan Liu, Lijia Tao, Chaohun Liu, Yunqiang Gao, Hongwei Sun, Mingxin Yuan","doi":"10.1145/3503047.3503113","DOIUrl":"https://doi.org/10.1145/3503047.3503113","url":null,"abstract":"In order to further improve the population diversity of the immune cloning algorithm when optimizing high-dimensional objects, and to improve the algorithm's global optimization ability and search efficiency, an immune cloning optimization algorithm based on antibody similarity screening and steady-state adjustment (ICASA) is proposed. By screening, that is, removing highly similar antibodies in the antibody population, the probability of the algorithm searching for the optimal solution is improved, and the repeated solution of similar antibodies is avoided. The antibody population is adjusted based on themedian property, and is injected with a high-quality vaccine realized by the median, which makes the antibody population evenly diffuse in the solution space to generate global antibody solutions. Finally, the convergence of the algorithm is proved by Markov chain theory. The test results of six groups of high-dimensional functions show that, compared with genetic algorithm (GA), immune cloning algorithm (ICA) and immune genetic algorithm (IGA), the proposed algorithm achieves 100% optimization, and the minimum convergence algebra, average convergence algebra and iterative algebra standard deviation are reduced by an average of 13.3%, 5.3%, and 29.3%, respectively, which verifies the algorithm's strong optimization ability, fast convergence and good stability.","PeriodicalId":190604,"journal":{"name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","volume":"335 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116908640","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：