Pub Date : 2022-03-25DOI: 10.1109/ICCAE55086.2022.9762449
Jing Zhang, Chao Wang, Xianbo Zhang, Zezhou Li
Time series containing abundant monitoring information can tell how a system is running, and anomaly detection of time series is closely related to the identification of potent fault and implementation of proper measurements. Therefore, accurate anomaly detection is of great significance to system stability. Anomaly detection of time series has been studied for decades, and various approaches have been reported for effective detection. In this paper, we propose a novel deep learning-based model for anomaly detection of time series. The proposed model consists of three parallel pipelines and each pipeline containing a convolutional unit in series connection with an amplified attention mechanism is responsible for both temporal and spatial feature extraction. The parallel design can help the model capture input features in a different perception field and the pipelines can work complementarily for a comprehensive understanding. The proposed model is then evaluated in multiple datasets including univariate and multivariate time series, and the results prove the effectiveness of the proposed compact model. An ablation study is also carried out to demonstrate the promotion of the proposed amplified attention mechanism.
{"title":"Multi-Attention Integrated Convolutional Network for Anomaly Detection of Time Series","authors":"Jing Zhang, Chao Wang, Xianbo Zhang, Zezhou Li","doi":"10.1109/ICCAE55086.2022.9762449","DOIUrl":"https://doi.org/10.1109/ICCAE55086.2022.9762449","url":null,"abstract":"Time series containing abundant monitoring information can tell how a system is running, and anomaly detection of time series is closely related to the identification of potent fault and implementation of proper measurements. Therefore, accurate anomaly detection is of great significance to system stability. Anomaly detection of time series has been studied for decades, and various approaches have been reported for effective detection. In this paper, we propose a novel deep learning-based model for anomaly detection of time series. The proposed model consists of three parallel pipelines and each pipeline containing a convolutional unit in series connection with an amplified attention mechanism is responsible for both temporal and spatial feature extraction. The parallel design can help the model capture input features in a different perception field and the pipelines can work complementarily for a comprehensive understanding. The proposed model is then evaluated in multiple datasets including univariate and multivariate time series, and the results prove the effectiveness of the proposed compact model. An ablation study is also carried out to demonstrate the promotion of the proposed amplified attention mechanism.","PeriodicalId":294641,"journal":{"name":"2022 14th International Conference on Computer and Automation Engineering (ICCAE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133567603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-25DOI: 10.1109/ICCAE55086.2022.9762422
Juan Zhang, Lie Bi, Wen-rong Wu, K. Du
Micro-devices are usually assembled by micro-assembly robot operating multi-manipulators in a narrow assembly space. To ensure assembly accuracy, manipulators are required to assemble multiple parts in parallel. However, in the traditional assembly, in order to prevent the parts from interfering, the movement trajectory of each manipulator must be manually input, which leads to low planning efficiency. In this paper, a multi-body spatial approach algorithm is established based on reinforcement learning methods, and a multi-body collision avoidance control method based on grid method and reinforcement learning is proposed, which realizes the purpose of efficiently generating the running trajectory and improving the planning efficiency on the premise that multi-parts achieve the target pose without interference. In addition, the calibration method of the simulation space coordinate systems and the Cartesian space coordinate systems is proposed, the motion trajectory in simulation space is transformed into the Cartesian space motion trajectory to control manipulators movement. Experimental results verify the effectiveness of the proposed method, and realize intelligent and safe parallel approaching of multi-manipulators.
{"title":"Reinforcement Learning-Based Parallel Approach Control of Micro-Assembly Manipulators","authors":"Juan Zhang, Lie Bi, Wen-rong Wu, K. Du","doi":"10.1109/ICCAE55086.2022.9762422","DOIUrl":"https://doi.org/10.1109/ICCAE55086.2022.9762422","url":null,"abstract":"Micro-devices are usually assembled by micro-assembly robot operating multi-manipulators in a narrow assembly space. To ensure assembly accuracy, manipulators are required to assemble multiple parts in parallel. However, in the traditional assembly, in order to prevent the parts from interfering, the movement trajectory of each manipulator must be manually input, which leads to low planning efficiency. In this paper, a multi-body spatial approach algorithm is established based on reinforcement learning methods, and a multi-body collision avoidance control method based on grid method and reinforcement learning is proposed, which realizes the purpose of efficiently generating the running trajectory and improving the planning efficiency on the premise that multi-parts achieve the target pose without interference. In addition, the calibration method of the simulation space coordinate systems and the Cartesian space coordinate systems is proposed, the motion trajectory in simulation space is transformed into the Cartesian space motion trajectory to control manipulators movement. Experimental results verify the effectiveness of the proposed method, and realize intelligent and safe parallel approaching of multi-manipulators.","PeriodicalId":294641,"journal":{"name":"2022 14th International Conference on Computer and Automation Engineering (ICCAE)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116288272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-25DOI: 10.1109/ICCAE55086.2022.9762443
Laurence Alec M. Burce, Dionis A. Padilla, John Lawrence M. Nagayo
The advancement of new technologies has provided solutions to various problems our lives. In the Philippines, farming has been a way of living, and farmers tend to do traditional farming, which does not utilize any technology. Wireless sensor networks aim to improve harvest’s quantity and quality and maintain a good environment. Data transmission through wireless sensor networks is highly power depleting. Therefore, power-saving is needed, especially in agricultural lands and hard-to-reach places. The soil quality monitoring system is created using a low-powered wireless sensor network. A power management technique was implemented using the sleep mode feature of the ESP8266. The system has successfully measured the soil qualities, checked if in range, and notified when values are out of range. Additionally, power and energy consumption are compared to a system without power management. The value of the energy saved is around 99.87% which indicates that the system is more efficient.
{"title":"Soil Quality Monitoring System using Low-Powered Wireless Sensor Network","authors":"Laurence Alec M. Burce, Dionis A. Padilla, John Lawrence M. Nagayo","doi":"10.1109/ICCAE55086.2022.9762443","DOIUrl":"https://doi.org/10.1109/ICCAE55086.2022.9762443","url":null,"abstract":"The advancement of new technologies has provided solutions to various problems our lives. In the Philippines, farming has been a way of living, and farmers tend to do traditional farming, which does not utilize any technology. Wireless sensor networks aim to improve harvest’s quantity and quality and maintain a good environment. Data transmission through wireless sensor networks is highly power depleting. Therefore, power-saving is needed, especially in agricultural lands and hard-to-reach places. The soil quality monitoring system is created using a low-powered wireless sensor network. A power management technique was implemented using the sleep mode feature of the ESP8266. The system has successfully measured the soil qualities, checked if in range, and notified when values are out of range. Additionally, power and energy consumption are compared to a system without power management. The value of the energy saved is around 99.87% which indicates that the system is more efficient.","PeriodicalId":294641,"journal":{"name":"2022 14th International Conference on Computer and Automation Engineering (ICCAE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123901515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-25DOI: 10.1109/ICCAE55086.2022.9762435
Christian David D. Yu, J. Villaverde
In this study, the Graph Neural Network is a new deep learning algorithm, just like Convolutional Neural Network. This study aims to classify the ripeness of avocado using Graph Neural Network and its yield and benefit to farmers, consumers, vendors, and other researchers who will use the Graph Neural Network. Avocado Ripeness Classification with Graph Neural Network is a system that must classify the ripeness of avocados, whether they are unripe or ripe. Graph Neural Network uses node classification to classify the avocado by setting labels or classes for the nodes. For the training part, there is no available dataset image of avocado. It needs to manually create an image dataset of avocados by downloading at least 200 avocados per class and a total of 400 photos of avocados taken on Google Image. The study was successfully conducted to classify the avocado ripeness using Graph Neural Network to train and check the avocado ripeness. A total of 400 avocados were used in the study to classify ripeness, and it has an overall accuracy of 97.75% in detecting avocado ripeness.
{"title":"Avocado Ripeness Classification Using Graph Neural Network","authors":"Christian David D. Yu, J. Villaverde","doi":"10.1109/ICCAE55086.2022.9762435","DOIUrl":"https://doi.org/10.1109/ICCAE55086.2022.9762435","url":null,"abstract":"In this study, the Graph Neural Network is a new deep learning algorithm, just like Convolutional Neural Network. This study aims to classify the ripeness of avocado using Graph Neural Network and its yield and benefit to farmers, consumers, vendors, and other researchers who will use the Graph Neural Network. Avocado Ripeness Classification with Graph Neural Network is a system that must classify the ripeness of avocados, whether they are unripe or ripe. Graph Neural Network uses node classification to classify the avocado by setting labels or classes for the nodes. For the training part, there is no available dataset image of avocado. It needs to manually create an image dataset of avocados by downloading at least 200 avocados per class and a total of 400 photos of avocados taken on Google Image. The study was successfully conducted to classify the avocado ripeness using Graph Neural Network to train and check the avocado ripeness. A total of 400 avocados were used in the study to classify ripeness, and it has an overall accuracy of 97.75% in detecting avocado ripeness.","PeriodicalId":294641,"journal":{"name":"2022 14th International Conference on Computer and Automation Engineering (ICCAE)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123000747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-25DOI: 10.1109/ICCAE55086.2022.9762434
John Patrick O. Gabriel, Mary Kris R. Cabunilas, J. Villaverde
Cantaloupe has been widely served as a delicacy food to be enjoyed, while it provides essential proteins a fruit usually provides for the human body. However, cantaloupe is one kind of fruit that can have different states mainly unripe, ripe, or overripe while having its physical looks retained. The objective of this paper is to determine the current status of the fruit without the need of breaking open the fruit with the help of the MQ3 sensor. As the fruit generates ethanol, the odor that comes from it can be used as a source of information to determine its ripeness. Using the MQ3 sensor, Arduino, and Fuzzy Logic with Mathlab, the researchers will attempt to determine the fruit’s ripeness without having to break open the fruit. It has been observed that the cantaloupe releases enough ethanol to be detected by the electronic nose. It can be confirmed that the cantaloupe, given enough time, can have its ripeness detected by the MQ3 sensor.
{"title":"Cantaloupe Ripeness Detection Using Electronic Nose","authors":"John Patrick O. Gabriel, Mary Kris R. Cabunilas, J. Villaverde","doi":"10.1109/ICCAE55086.2022.9762434","DOIUrl":"https://doi.org/10.1109/ICCAE55086.2022.9762434","url":null,"abstract":"Cantaloupe has been widely served as a delicacy food to be enjoyed, while it provides essential proteins a fruit usually provides for the human body. However, cantaloupe is one kind of fruit that can have different states mainly unripe, ripe, or overripe while having its physical looks retained. The objective of this paper is to determine the current status of the fruit without the need of breaking open the fruit with the help of the MQ3 sensor. As the fruit generates ethanol, the odor that comes from it can be used as a source of information to determine its ripeness. Using the MQ3 sensor, Arduino, and Fuzzy Logic with Mathlab, the researchers will attempt to determine the fruit’s ripeness without having to break open the fruit. It has been observed that the cantaloupe releases enough ethanol to be detected by the electronic nose. It can be confirmed that the cantaloupe, given enough time, can have its ripeness detected by the MQ3 sensor.","PeriodicalId":294641,"journal":{"name":"2022 14th International Conference on Computer and Automation Engineering (ICCAE)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128094542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-25DOI: 10.1109/ICCAE55086.2022.9762451
Chenyun Liu, Shun Ding, Liang Ye, Xingyu Chen, Wenhao Zhu
Common cache elimination strategies are to improve the hit ratio of files in specific scenarios. In real scenarios, different users' behaviours often show great differences, and a general cache replacement strategy cannot comprehensively achieve good performance. Considering these problems, this paper designs a cache replacement strategy based on user behaviour analysis for file systems (LFU-UB). First, a log analysis module is built to clean the user's access record information and mine association rules, and then the association parameters are transmitted to the computing model. Then several small files with the lowest priority are selected through the cache replacement module. Finally, resources with the lowest priority are replaced by new resources. The effectiveness of LFU-UB strategy is proved by comparison experiments in the storage environment of massive small files; It has a higher hit ratio than the general cache strategy and can effectively reduce the cache load.
{"title":"Cache Replacement Strategy Based on User Behaviour Analysis for a Massive Small File Storage System","authors":"Chenyun Liu, Shun Ding, Liang Ye, Xingyu Chen, Wenhao Zhu","doi":"10.1109/ICCAE55086.2022.9762451","DOIUrl":"https://doi.org/10.1109/ICCAE55086.2022.9762451","url":null,"abstract":"Common cache elimination strategies are to improve the hit ratio of files in specific scenarios. In real scenarios, different users' behaviours often show great differences, and a general cache replacement strategy cannot comprehensively achieve good performance. Considering these problems, this paper designs a cache replacement strategy based on user behaviour analysis for file systems (LFU-UB). First, a log analysis module is built to clean the user's access record information and mine association rules, and then the association parameters are transmitted to the computing model. Then several small files with the lowest priority are selected through the cache replacement module. Finally, resources with the lowest priority are replaced by new resources. The effectiveness of LFU-UB strategy is proved by comparison experiments in the storage environment of massive small files; It has a higher hit ratio than the general cache strategy and can effectively reduce the cache load.","PeriodicalId":294641,"journal":{"name":"2022 14th International Conference on Computer and Automation Engineering (ICCAE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128790386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-25DOI: 10.1109/ICCAE55086.2022.9762437
Fan Yang, M. Kefalas, M. Koch, Anna V. Kononova, Yanan Qiao, T.H.W. Bäck
Earthquake prediction, which is a key issue that has long existed among seismologists, is of high scientific importance. An earthquake prediction model can output the time of earthquake occurrence in advance using machine learning methods, which is receiving increasing attention. Earthquake prediction involves a large variety of data mining steps, which requires a large amount of time for processing data and model development. Thus, an efficient and accurate prediction method is needed. Aiming to solve this problem, we propose Auto-REP, an automated machine learning-based regression model. Our contribution of Auto-REP is using laboratory seismic data to develop a regression pipeline in an automated manner, and eventually obtain the prediction results of laboratory earthquake occurrence. The automated pipeline consists of feature extraction, feature selection, modelling algorithm and optimization. With this approach we extract features from each of the earthquake channels which results in a massive feature space. The hyperparameters of the model are optimized by a Bayesian technique as part of the automated approach. The experimental results shows that the MAE and MSE of our model in the training and testing datasets are 1.48, 1.51 and 1.52, 1.59. The results demonstrate that our Auto-REP method can predict laboratory earthquakes efficiently and accurately.
{"title":"Auto-REP: An Automated Regression Pipeline Approach for High-efficiency Earthquake Prediction Using LANL Data","authors":"Fan Yang, M. Kefalas, M. Koch, Anna V. Kononova, Yanan Qiao, T.H.W. Bäck","doi":"10.1109/ICCAE55086.2022.9762437","DOIUrl":"https://doi.org/10.1109/ICCAE55086.2022.9762437","url":null,"abstract":"Earthquake prediction, which is a key issue that has long existed among seismologists, is of high scientific importance. An earthquake prediction model can output the time of earthquake occurrence in advance using machine learning methods, which is receiving increasing attention. Earthquake prediction involves a large variety of data mining steps, which requires a large amount of time for processing data and model development. Thus, an efficient and accurate prediction method is needed. Aiming to solve this problem, we propose Auto-REP, an automated machine learning-based regression model. Our contribution of Auto-REP is using laboratory seismic data to develop a regression pipeline in an automated manner, and eventually obtain the prediction results of laboratory earthquake occurrence. The automated pipeline consists of feature extraction, feature selection, modelling algorithm and optimization. With this approach we extract features from each of the earthquake channels which results in a massive feature space. The hyperparameters of the model are optimized by a Bayesian technique as part of the automated approach. The experimental results shows that the MAE and MSE of our model in the training and testing datasets are 1.48, 1.51 and 1.52, 1.59. The results demonstrate that our Auto-REP method can predict laboratory earthquakes efficiently and accurately.","PeriodicalId":294641,"journal":{"name":"2022 14th International Conference on Computer and Automation Engineering (ICCAE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120967601","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：