Based on the analysis of warship maintenance resources, the optimized task of model of warship maintenance is founded, and the resolution procedure of model with ant colony algorithm is also presented. This method that pheromone update strengthen ants’ ability in searching for better path ensures problems better solved. Finally, the example verifies this method effective.
{"title":"Study on Optimized Dispatching of Warship Equipment Maintenance Task Based on Ant Colony Algorithm","authors":"Yongming Zhang, Chao Mao, Hanqin Li","doi":"10.1145/3446132.3446190","DOIUrl":"https://doi.org/10.1145/3446132.3446190","url":null,"abstract":"Based on the analysis of warship maintenance resources, the optimized task of model of warship maintenance is founded, and the resolution procedure of model with ant colony algorithm is also presented. This method that pheromone update strengthen ants’ ability in searching for better path ensures problems better solved. Finally, the example verifies this method effective.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123111645","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}
M. Wang, Qing Cheng, Jincai Huang, Guangquan Cheng
The epidemic of COVID-19 has swept the world, which has had a very serious impact on the social economy. The stock market, as a barometer of the economy, has also been hit. This paper selects the stock indexes of Britain, Germany and France as the research object to explore the influence of COVID-19 on the stock index. The results show that the European stock market will fluctuate several days before the epidemic, and the volatility of the stock market is an early warning for the outbreak of COVID-19. The specific days of early warning for COVID-19 in stock markets of various countries are not quite the same. In Britain, the number of early warning days is 14 days, and the number of daily new confirmed cases of COVID-19 is strongly related to the country's stock market index. France's early warning days are 7 days, and the number of daily newly diagnosed COVID-19 is weakly related to the country's stock market index. Germany's early warning days are 5 days, and the daily new number of COVID-19 's confirmed cases is strongly related to the country's stock market index.
{"title":"Analysis of the European stock market's advance response time to COVID-19 based on Pearson correlation Coefficient","authors":"M. Wang, Qing Cheng, Jincai Huang, Guangquan Cheng","doi":"10.1145/3446132.3446149","DOIUrl":"https://doi.org/10.1145/3446132.3446149","url":null,"abstract":"The epidemic of COVID-19 has swept the world, which has had a very serious impact on the social economy. The stock market, as a barometer of the economy, has also been hit. This paper selects the stock indexes of Britain, Germany and France as the research object to explore the influence of COVID-19 on the stock index. The results show that the European stock market will fluctuate several days before the epidemic, and the volatility of the stock market is an early warning for the outbreak of COVID-19. The specific days of early warning for COVID-19 in stock markets of various countries are not quite the same. In Britain, the number of early warning days is 14 days, and the number of daily new confirmed cases of COVID-19 is strongly related to the country's stock market index. France's early warning days are 7 days, and the number of daily newly diagnosed COVID-19 is weakly related to the country's stock market index. Germany's early warning days are 5 days, and the daily new number of COVID-19 's confirmed cases is strongly related to the country's stock market index.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132882101","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}
Bank fraud transaction has brought huge losses to consumers and banks, and the original rule-based fraud detection method is not suitable for various new fraud way. According to the fact that bank fraud transaction is a typical unbalanced data classification problem, two neural network models of DNN and LSTM are established, with a new type loss function, Focalloss is used to train and test on the Kaggle's TESTIMON Dataset. As the test results, LSTM-Focalloss's network was able to detect fraud transactions significantly higher than other methods, indicating that this network model is very effective in detecting bank fraud transactions.
{"title":"Research on bank fraud transaction detection based on LSTM-Focalloss","authors":"Feiyan Zhan","doi":"10.1145/3446132.3446176","DOIUrl":"https://doi.org/10.1145/3446132.3446176","url":null,"abstract":"Bank fraud transaction has brought huge losses to consumers and banks, and the original rule-based fraud detection method is not suitable for various new fraud way. According to the fact that bank fraud transaction is a typical unbalanced data classification problem, two neural network models of DNN and LSTM are established, with a new type loss function, Focalloss is used to train and test on the Kaggle's TESTIMON Dataset. As the test results, LSTM-Focalloss's network was able to detect fraud transactions significantly higher than other methods, indicating that this network model is very effective in detecting bank fraud transactions.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130170695","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}
Myanmar belongs to the Lolo-Burmese sub-branch of the Tibeto-Burmese branch of the Sino-Tibetan language family and is a tonal language. In the front-end text analysis of speech synthesis, the prosodic structure analysis and unit's boundary prediction are crucial to the naturalness of speech synthesis. In order to improve the naturalness of Myanmar speech synthesis, this paper studies prosodic features and prosodic unit boundary prediction. The size of prosodic units and the duration of syllables before and after their boundaries have been studied in this paper. To realize automatic prosodic unit boundaries labeling, a method of labeling based on the combination of word segmentation text and silence duration is proposed. Based on BiLSTM-CRF model, we also have designed and implemented a method to predict the boundaries of prosodic units from Myanmar text. Finally, the boundary prediction results are applied to the speech synthesis system based on HMM to evaluate its naturalness. The experimental results show that our method of automatic prosodic boundary labeling and prosodic unit boundary prediction can improve the naturalness of speech synthesis.
{"title":"Analysis and Prediction of Myanmar Prosodic Unit Boundary","authors":"Peiying Li, Jian Yang, Feng Chen","doi":"10.1145/3446132.3446396","DOIUrl":"https://doi.org/10.1145/3446132.3446396","url":null,"abstract":"Myanmar belongs to the Lolo-Burmese sub-branch of the Tibeto-Burmese branch of the Sino-Tibetan language family and is a tonal language. In the front-end text analysis of speech synthesis, the prosodic structure analysis and unit's boundary prediction are crucial to the naturalness of speech synthesis. In order to improve the naturalness of Myanmar speech synthesis, this paper studies prosodic features and prosodic unit boundary prediction. The size of prosodic units and the duration of syllables before and after their boundaries have been studied in this paper. To realize automatic prosodic unit boundaries labeling, a method of labeling based on the combination of word segmentation text and silence duration is proposed. Based on BiLSTM-CRF model, we also have designed and implemented a method to predict the boundaries of prosodic units from Myanmar text. Finally, the boundary prediction results are applied to the speech synthesis system based on HMM to evaluate its naturalness. The experimental results show that our method of automatic prosodic boundary labeling and prosodic unit boundary prediction can improve the naturalness of speech synthesis.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"351 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116667203","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 bandwidth and energy of wireless sensor networks (WSNs) are limited, it is not appropriate to use all the sensors for acoustic source positioning and so the need for sensor selection. In the article, an efficient expectation maximization algorithm based on sensor selection (EM-SS) is proposed for acoustic source positioning in the WSNs. The sensor selection solution based on the generalized information gain is introduced to select a subset of sensors which can provide reliable measurements. The information filter only depends on the Boolean decision variables and may make full use of the structure of measurement noise. Fewer sensor nodes are used and mass energy is economized. Simulation results demonstrate the well performance of the EM-SS algorithm in terms of localization accuracy, while only a part of sensors is used, so mass energy is economized and the communication channel is smooth.
{"title":"Acoustic Source Positioning based on Sensor Selection in Wireless Sensor Network","authors":"Y. Feng, Guohua Hu, Lei Hong","doi":"10.1145/3446132.3446419","DOIUrl":"https://doi.org/10.1145/3446132.3446419","url":null,"abstract":"Since the bandwidth and energy of wireless sensor networks (WSNs) are limited, it is not appropriate to use all the sensors for acoustic source positioning and so the need for sensor selection. In the article, an efficient expectation maximization algorithm based on sensor selection (EM-SS) is proposed for acoustic source positioning in the WSNs. The sensor selection solution based on the generalized information gain is introduced to select a subset of sensors which can provide reliable measurements. The information filter only depends on the Boolean decision variables and may make full use of the structure of measurement noise. Fewer sensor nodes are used and mass energy is economized. Simulation results demonstrate the well performance of the EM-SS algorithm in terms of localization accuracy, while only a part of sensors is used, so mass energy is economized and the communication channel is smooth.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134620633","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}
Bingzhe Wei, Xiangchu Feng, Kun Wang, Bing-xia Gao
The multi-focus image fusion is a crucial embranchment of image processing, which can obtain better fused consequence from multiple source images. CNN(convolutional neural network)-based and SR(sparse representation)-based image fusion are emerging algorithms in the last decade, and have comprehensive used. So as to gain fused image with more precise and abundant information, this paper proposes a novel multi-focus image fusion method combining CNN and SR. The prevalent SR methods determine the sparse representation vectors after fusion according to ‘max-L1’ rule. But the weighted norm can more accurately reflect the information contained in the source images. Therefore, we choose fused image patches on the basis of the weighted L1-norm, and the weights are got by CNN. Experimental results demonstrate that the proposed method outperforms the existing state-of-the-art methods in terms of both visual perception and objective evaluation metrics.
{"title":"The multi-focus image fusion method based on CNN and SR","authors":"Bingzhe Wei, Xiangchu Feng, Kun Wang, Bing-xia Gao","doi":"10.1145/3446132.3446182","DOIUrl":"https://doi.org/10.1145/3446132.3446182","url":null,"abstract":"The multi-focus image fusion is a crucial embranchment of image processing, which can obtain better fused consequence from multiple source images. CNN(convolutional neural network)-based and SR(sparse representation)-based image fusion are emerging algorithms in the last decade, and have comprehensive used. So as to gain fused image with more precise and abundant information, this paper proposes a novel multi-focus image fusion method combining CNN and SR. The prevalent SR methods determine the sparse representation vectors after fusion according to ‘max-L1’ rule. But the weighted norm can more accurately reflect the information contained in the source images. Therefore, we choose fused image patches on the basis of the weighted L1-norm, and the weights are got by CNN. Experimental results demonstrate that the proposed method outperforms the existing state-of-the-art methods in terms of both visual perception and objective evaluation metrics.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121687126","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}
Cloud platform logs record platform runtime information and are important data for cloud platform anomaly detection. Due to the complex log format and rich semantic information, simple statistical analysis methods cannot fully capture log information. And the cloud platform architecture is constantly being updated, log statements are constantly evolving, and new abnormal logs may appear. In addition, most of the existing methods only perform anomaly detection on log templates, and the information is relatively one-sided, which limits the types of anomalies they can detect. Aiming at the problems that most of the current methods will not be able to diagnose or misjudge the unknown log status and miss the abnormality, this paper proposes an anomaly detection method LogNL based on (Natural Language Processing, NLP) and LSTM (Long Short Term Memory, LSTM). LogNL first uses automatic analysis methods to extract log templates and parameters, uses TF-IDF (Term Frequency–Inverse Document Frequency, TF-IDF) to obtain template feature representations, and then constructs parameter value vectors for logs of different templates, and finally uses LSTM network-based construction of pattern anomaly detection models and parameter value anomaly detection models to achieve cloud Platform log anomaly detection. Experiments on two real cloud platform log data sets show that LogNL has higher accuracy than existing supervised learning methods and unsupervised learning methods.
云平台日志记录了平台运行信息，是云平台异常检测的重要数据。由于日志格式复杂，语义信息丰富，简单的统计分析方法无法完全捕获日志信息。并且云平台架构在不断更新，日志语句也在不断演变，可能会出现新的异常日志。此外，现有的方法大多只对日志模板进行异常检测，信息比较片面，限制了检测到的异常类型。针对目前大多数方法无法对未知日志状态进行诊断或误判而遗漏异常的问题，本文提出了一种基于自然语言处理(NLP)和LSTM(长短期记忆，LSTM)的异常检测方法logl。logl首先利用自动分析方法提取日志模板和参数，利用TF-IDF (Term Frequency - inverse Document Frequency, TF-IDF)获得模板特征表示，然后对不同模板的日志构建参数值向量，最后利用基于LSTM网络构建模式异常检测模型和参数值异常检测模型，实现云平台日志异常检测。在两个真实云平台日志数据集上的实验表明，与现有的有监督学习方法和无监督学习方法相比，logl具有更高的准确率。
{"title":"An Approach to Cloud Platform Log Anomaly Detection Based on Natural Language Processing and LSTM","authors":"Bei Zhu, Jing Li, Rongbin Gu, Liang-liang Wang","doi":"10.1145/3446132.3446415","DOIUrl":"https://doi.org/10.1145/3446132.3446415","url":null,"abstract":"Cloud platform logs record platform runtime information and are important data for cloud platform anomaly detection. Due to the complex log format and rich semantic information, simple statistical analysis methods cannot fully capture log information. And the cloud platform architecture is constantly being updated, log statements are constantly evolving, and new abnormal logs may appear. In addition, most of the existing methods only perform anomaly detection on log templates, and the information is relatively one-sided, which limits the types of anomalies they can detect. Aiming at the problems that most of the current methods will not be able to diagnose or misjudge the unknown log status and miss the abnormality, this paper proposes an anomaly detection method LogNL based on (Natural Language Processing, NLP) and LSTM (Long Short Term Memory, LSTM). LogNL first uses automatic analysis methods to extract log templates and parameters, uses TF-IDF (Term Frequency–Inverse Document Frequency, TF-IDF) to obtain template feature representations, and then constructs parameter value vectors for logs of different templates, and finally uses LSTM network-based construction of pattern anomaly detection models and parameter value anomaly detection models to achieve cloud Platform log anomaly detection. Experiments on two real cloud platform log data sets show that LogNL has higher accuracy than existing supervised learning methods and unsupervised learning methods.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122195228","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 view of the current situation that the recognition rate of digital signal modulation recognition method is unsatisfactory at low Signal-to-Noise Ratio(SNR), a recognition method based on high-order cumulants and wavelet transform is proposed to realize the automatic modulation recognition of 8 kinds of digital signals such as 2ASK, 4ASK, 8ASK, 2PSK, 4PSK, 8PSK, 16QAM and 32QAM. Based on the high-order cumulants principle and wavelet transform theory, the characteristic parameters f1∼f5 are constructed by the elaborate analysis of the characteristic extraction of these signals. Through simulation experiments, the characteristic parameter changes of different types of modulation signals at different SNR are obtained, and design the classifier of Back Propagation (BP) neural network to classify the signals. The simulation results show that this method can improve the average correct recognition rates of 8 digital modulation signals reaching up to above 97% when the SNR is higher than 0dB, which greatly improves the signal recognition performance at low SNR.
{"title":"Digital signal modulation recognition method based on high-order cumulants and wavelet transform","authors":"Anyi Wang, Peiru Liu","doi":"10.1145/3446132.3446423","DOIUrl":"https://doi.org/10.1145/3446132.3446423","url":null,"abstract":"In view of the current situation that the recognition rate of digital signal modulation recognition method is unsatisfactory at low Signal-to-Noise Ratio(SNR), a recognition method based on high-order cumulants and wavelet transform is proposed to realize the automatic modulation recognition of 8 kinds of digital signals such as 2ASK, 4ASK, 8ASK, 2PSK, 4PSK, 8PSK, 16QAM and 32QAM. Based on the high-order cumulants principle and wavelet transform theory, the characteristic parameters f1∼f5 are constructed by the elaborate analysis of the characteristic extraction of these signals. Through simulation experiments, the characteristic parameter changes of different types of modulation signals at different SNR are obtained, and design the classifier of Back Propagation (BP) neural network to classify the signals. The simulation results show that this method can improve the average correct recognition rates of 8 digital modulation signals reaching up to above 97% when the SNR is higher than 0dB, which greatly improves the signal recognition performance at low SNR.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124813062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a multi-autonomous robot grasping system using a novel deep convolution neural network to perform real-time robotic sorting tasks. The system is composed by a color camera, a sorting line and two robotic arms with grippers. A deep convolution neural network is modified to estimate the position and orientation of the targets in the images and output the corresponding image features of the targets. A task assignment system is considered to transmit visual information about the detected targets to robotic arms for grasping, and continue to track the targets until they are no longer visible to the camera. This paper describes how to efficiently distribute sorting tasks without missing or repeating. We then propose an efficiently and semi-automatic method to expand the published dataset for training. Preliminary experiments were performed to evaluate our robot system and the results had confirmed its effectiveness.
{"title":"Multi-autonomous Robot Sorting System Using Deep Convolution Neural Network","authors":"Zhihong Chen, Yao Wang, Yanbo Wang, Junqin Lin, Binyan Liang, Yafang Zhang","doi":"10.1145/3446132.3446140","DOIUrl":"https://doi.org/10.1145/3446132.3446140","url":null,"abstract":"This paper presents a multi-autonomous robot grasping system using a novel deep convolution neural network to perform real-time robotic sorting tasks. The system is composed by a color camera, a sorting line and two robotic arms with grippers. A deep convolution neural network is modified to estimate the position and orientation of the targets in the images and output the corresponding image features of the targets. A task assignment system is considered to transmit visual information about the detected targets to robotic arms for grasping, and continue to track the targets until they are no longer visible to the camera. This paper describes how to efficiently distribute sorting tasks without missing or repeating. We then propose an efficiently and semi-automatic method to expand the published dataset for training. Preliminary experiments were performed to evaluate our robot system and the results had confirmed its effectiveness.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"7899 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127635394","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}
Xiaohui Yan, Cuiying Wen, Yan Ye, Zhicong Zhang, Shuai Li
Bacterial foraging optimization (BFO) algorithm has been widely applied to various optimization problems. However, BFO often suffers from premature convergence and lacking of population information exchanging. To overcome these shortcomings, a relative position-based bacterial foraging optimization (RPBFO) is proposed. The three-layer circulation structure is replaced by a single-layer circulation structure in this algorithm. The relative position-based updating method is used to replace the absolute position-based updating method in the chemotactic operation. The reproduction step of BFO is eliminated. And the escape strategy is employed in the elimination-dispersal operation. Then the optimization results of the RPBFO algorithm are tested on 11 benchmark functions. The results show that the optimization ability of the RPBFO algorithm is significantly better than the original BFO and GA algorithms. On most benchmark functions, it also shows a better performance in convergence speed and accuracy than the PSO algorithm.
{"title":"A Relative Position-based Bacterial Foraging Optimization for Numerical Optimization","authors":"Xiaohui Yan, Cuiying Wen, Yan Ye, Zhicong Zhang, Shuai Li","doi":"10.1145/3446132.3446154","DOIUrl":"https://doi.org/10.1145/3446132.3446154","url":null,"abstract":"Bacterial foraging optimization (BFO) algorithm has been widely applied to various optimization problems. However, BFO often suffers from premature convergence and lacking of population information exchanging. To overcome these shortcomings, a relative position-based bacterial foraging optimization (RPBFO) is proposed. The three-layer circulation structure is replaced by a single-layer circulation structure in this algorithm. The relative position-based updating method is used to replace the absolute position-based updating method in the chemotactic operation. The reproduction step of BFO is eliminated. And the escape strategy is employed in the elimination-dispersal operation. Then the optimization results of the RPBFO algorithm are tested on 11 benchmark functions. The results show that the optimization ability of the RPBFO algorithm is significantly better than the original BFO and GA algorithms. On most benchmark functions, it also shows a better performance in convergence speed and accuracy than the PSO algorithm.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126398956","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：