Pub Date : 2022-12-01DOI: 10.1109/ACMLC58173.2022.00030
Kanokporn Boonjubut, H. Hasegawa
Bike-sharing schemes have become a popular and environmentally friendly transportation mode. This paper focuses on imbalances caused by problems with insufficient bikes or docking stations in such schemes, which lead to operating costs in terms of total distance due to the need to relocate bikes. Here, a method is proposed, based on cluster analysis, for considering depot location in bike-sharing schemes. The main objective is to reduce operating costs by minimizing the total distance required for relocating bikes. First, a method for predicting demand for bikes is presented. Then, the K-means and WK-means are compared to determine the number and location of depots. The last step is to use this method to compare the total distance required for different depot location options. The results indicate that the proposed method performs well in terms of reducing the total distance required.
{"title":"A Comparison of Clustering Method to Determine Depot Location for a Bike-sharing Operation","authors":"Kanokporn Boonjubut, H. Hasegawa","doi":"10.1109/ACMLC58173.2022.00030","DOIUrl":"https://doi.org/10.1109/ACMLC58173.2022.00030","url":null,"abstract":"Bike-sharing schemes have become a popular and environmentally friendly transportation mode. This paper focuses on imbalances caused by problems with insufficient bikes or docking stations in such schemes, which lead to operating costs in terms of total distance due to the need to relocate bikes. Here, a method is proposed, based on cluster analysis, for considering depot location in bike-sharing schemes. The main objective is to reduce operating costs by minimizing the total distance required for relocating bikes. First, a method for predicting demand for bikes is presented. Then, the K-means and WK-means are compared to determine the number and location of depots. The last step is to use this method to compare the total distance required for different depot location options. The results indicate that the proposed method performs well in terms of reducing the total distance required.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"44 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134087663","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 : 2022-12-01DOI: 10.1109/ACMLC58173.2022.00014
Xiaoshan Zeng
With the increasing frequency of our country’s international communication and the popularization and penetration of mobile Internet into people’s work and life styles in modern society, the level of social informatization has also increased. In order not to be eliminated by this era, people must follow the pace of development of this era, always keep an eye on and receive the latest information from all over the world. Most of these materials are published on the Internet in foreign languages. Therefore, language has become the biggest obstacle for people to obtain information. As machine translation technology is restricted in terms of convenience and cost control, people’s need for machine translation or machine translation technology has become more and more urgent. This paper studies the design of English translation software (ETS) based on machine learning technology (MLT). By introducing MLT into ETS, a new neural machine translation method is proposed, and related experiments are used to test the effectiveness of the translation method. The designed translation software has been evaluated for translation quality. The experimental results show that as the arc length distribution increases, the translation quality (TTQ) decreases. The English translation software designed in this paper is of great importance to the research and development of machine translation.
{"title":"The Design of English Translation Software Based on Machine Learning Technology","authors":"Xiaoshan Zeng","doi":"10.1109/ACMLC58173.2022.00014","DOIUrl":"https://doi.org/10.1109/ACMLC58173.2022.00014","url":null,"abstract":"With the increasing frequency of our country’s international communication and the popularization and penetration of mobile Internet into people’s work and life styles in modern society, the level of social informatization has also increased. In order not to be eliminated by this era, people must follow the pace of development of this era, always keep an eye on and receive the latest information from all over the world. Most of these materials are published on the Internet in foreign languages. Therefore, language has become the biggest obstacle for people to obtain information. As machine translation technology is restricted in terms of convenience and cost control, people’s need for machine translation or machine translation technology has become more and more urgent. This paper studies the design of English translation software (ETS) based on machine learning technology (MLT). By introducing MLT into ETS, a new neural machine translation method is proposed, and related experiments are used to test the effectiveness of the translation method. The designed translation software has been evaluated for translation quality. The experimental results show that as the arc length distribution increases, the translation quality (TTQ) decreases. The English translation software designed in this paper is of great importance to the research and development of machine translation.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131763130","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 : 2022-12-01DOI: 10.1109/ACMLC58173.2022.00024
Vinh Truong
Computational or programmatic advertising is the new way to advertise products and services online and in real-time. In this emerging type of advertising, Natural language processing (NLP) is a powerful tool for intelligently targeting and placing advertisements at the right time and in the right place for the right audience in a very short period. This study systematically reviewed journal articles, book chapters, and conference proceedings for the last ten years to find out what are the uses, approaches, and challenges that the researchers have been recently facing in making use of natural language processing techniques in the domain of advertising. It is found that in the majority of studies, information extraction and sentiment analysis are still the main focus areas. Only a small number of advanced artificial intelligence (AI) techniques, such as deep learning and speech synthesis, are used. In addition, most of the studies are based on traditional forms of advertising (such as search engines, websites, and job listings), excluding the newer forms of mobile and app-based advertising. The ongoing challenge in the current literature is applying natural language processing to automatically target advertisements.
{"title":"Natural Language Processing in Advertising – A Systematic Literature Review","authors":"Vinh Truong","doi":"10.1109/ACMLC58173.2022.00024","DOIUrl":"https://doi.org/10.1109/ACMLC58173.2022.00024","url":null,"abstract":"Computational or programmatic advertising is the new way to advertise products and services online and in real-time. In this emerging type of advertising, Natural language processing (NLP) is a powerful tool for intelligently targeting and placing advertisements at the right time and in the right place for the right audience in a very short period. This study systematically reviewed journal articles, book chapters, and conference proceedings for the last ten years to find out what are the uses, approaches, and challenges that the researchers have been recently facing in making use of natural language processing techniques in the domain of advertising. It is found that in the majority of studies, information extraction and sentiment analysis are still the main focus areas. Only a small number of advanced artificial intelligence (AI) techniques, such as deep learning and speech synthesis, are used. In addition, most of the studies are based on traditional forms of advertising (such as search engines, websites, and job listings), excluding the newer forms of mobile and app-based advertising. The ongoing challenge in the current literature is applying natural language processing to automatically target advertisements.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127678548","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 : 2022-12-01DOI: 10.1109/ACMLC58173.2022.00020
G. Catedrilla
This project mainly aims to develop a mobile-based application for navigation with real-time obstacle detection to provide fair access to people with visual impairment to some activities, specifically navigating outdoors. It is a navigation mobile application equipped with speech and gesture recognition, to allow the people with visual impairment to access and use the application, and obstacle detection to provide audio prompts to the user, so they will know whenever an object or obstacle is within the frame of the phone camera. The research was structured and accomplished through different scientific and technological process and approach. With the use of Dialog flow, it was possible to create a speech recognition feature for the application, while YOLO algorithm allowed the process of object detection using mobile phone camera, possible. In this research, it was found out that the application was applicable to improving the navigation of the visually impaired, it is ideal that it serves as supplement to the white stick in order to improve their navigation experience. Also, this project would like to emphasize that researches that seeks to help person with disability be considered and conducted by other researchers.
{"title":"Mobile-Based Navigation Assistant for Visually Impaired Person with Real-time Obstacle Detection Using YOLO-based Deep Learning Algorithm","authors":"G. Catedrilla","doi":"10.1109/ACMLC58173.2022.00020","DOIUrl":"https://doi.org/10.1109/ACMLC58173.2022.00020","url":null,"abstract":"This project mainly aims to develop a mobile-based application for navigation with real-time obstacle detection to provide fair access to people with visual impairment to some activities, specifically navigating outdoors. It is a navigation mobile application equipped with speech and gesture recognition, to allow the people with visual impairment to access and use the application, and obstacle detection to provide audio prompts to the user, so they will know whenever an object or obstacle is within the frame of the phone camera. The research was structured and accomplished through different scientific and technological process and approach. With the use of Dialog flow, it was possible to create a speech recognition feature for the application, while YOLO algorithm allowed the process of object detection using mobile phone camera, possible. In this research, it was found out that the application was applicable to improving the navigation of the visually impaired, it is ideal that it serves as supplement to the white stick in order to improve their navigation experience. Also, this project would like to emphasize that researches that seeks to help person with disability be considered and conducted by other researchers.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128387315","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 : 2022-12-01DOI: 10.1109/acmlc58173.2022.00016
Fan Li, Y. Li, Pin Wang, Hong Chen, Wei Wang, Jie Xiao
Age estimation based on machine learning has received lots of attention. Traditional age estimation mechanism focuses age error ignoring the deviation between the estimated age and real age due to disease. Pathological age estimation mechanism used age deviation as the training label to solve the above problem. However, it results in a larger error between the estimated age and real age in the normal control (NC) group. An integrated age estimation mechanism based on Decision-Level fusion of error and deviation orientation model is proposed to solve the problem. Firstly, the traditional age and pathological age estimation mechanisms are weighted together. Then, their optimal weights are obtained by minimizing mean absolute error (MAE). Finally, with the optimal weight, the integrated age estimation mechanism (IAE) is built. Several representative age-related datasets are used for verification. The results show that the proposed age estimation mechanism achieves a good tradeoff effect of age estimation. It not only improves the classification ability of the estimated age, but also reduces the age estimation error of the NC group.
{"title":"Integrated Age Estimation Mechanism based on Decision-Level Fusion of Error and Deviation Orientation Model","authors":"Fan Li, Y. Li, Pin Wang, Hong Chen, Wei Wang, Jie Xiao","doi":"10.1109/acmlc58173.2022.00016","DOIUrl":"https://doi.org/10.1109/acmlc58173.2022.00016","url":null,"abstract":"Age estimation based on machine learning has received lots of attention. Traditional age estimation mechanism focuses age error ignoring the deviation between the estimated age and real age due to disease. Pathological age estimation mechanism used age deviation as the training label to solve the above problem. However, it results in a larger error between the estimated age and real age in the normal control (NC) group. An integrated age estimation mechanism based on Decision-Level fusion of error and deviation orientation model is proposed to solve the problem. Firstly, the traditional age and pathological age estimation mechanisms are weighted together. Then, their optimal weights are obtained by minimizing mean absolute error (MAE). Finally, with the optimal weight, the integrated age estimation mechanism (IAE) is built. Several representative age-related datasets are used for verification. The results show that the proposed age estimation mechanism achieves a good tradeoff effect of age estimation. It not only improves the classification ability of the estimated age, but also reduces the age estimation error of the NC group.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121917808","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 : 2022-12-01DOI: 10.1109/ACMLC58173.2022.00025
C. Tsai, Po-Jiun Chiang
This study aimed to evaluate consumers’ opinions toward Gogoro electric scooters in Taiwan by using four constructs – green perceived value, green brand image, green trust, and green purchase intention. To simultaneously explore the relationships between these four constructs, an online questionnaire was published, and 214 respondents demonstrated their thoughts on different aspects of Gogoro electric scooters. We found out that most people possess positive thoughts toward Gogoro electric scooters due to environmental concerns, and green brand image influences green perceived value, green trust, and green purchase intention, while green trust also influences green purchase intention.
{"title":"The Relationships among Green Perceived Value, Green Brand Image, Green Trust, and Green Purchase Intention: An Application Concerning Gogoro Electric Scooters in Taiwan","authors":"C. Tsai, Po-Jiun Chiang","doi":"10.1109/ACMLC58173.2022.00025","DOIUrl":"https://doi.org/10.1109/ACMLC58173.2022.00025","url":null,"abstract":"This study aimed to evaluate consumers’ opinions toward Gogoro electric scooters in Taiwan by using four constructs – green perceived value, green brand image, green trust, and green purchase intention. To simultaneously explore the relationships between these four constructs, an online questionnaire was published, and 214 respondents demonstrated their thoughts on different aspects of Gogoro electric scooters. We found out that most people possess positive thoughts toward Gogoro electric scooters due to environmental concerns, and green brand image influences green perceived value, green trust, and green purchase intention, while green trust also influences green purchase intention.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129182478","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 : 2022-12-01DOI: 10.1109/acmlc58173.2022.00003
{"title":"Copyright Page","authors":"","doi":"10.1109/acmlc58173.2022.00003","DOIUrl":"https://doi.org/10.1109/acmlc58173.2022.00003","url":null,"abstract":"","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121094470","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 : 2022-12-01DOI: 10.1109/ACMLC58173.2022.00023
Yijia Zhang
To achieve the target of carbon zero” in 2050, the Australian government advocates the development of renewable energy technology to reduce CO2 emissions. Particularly, wind energy resources are rich in South Australia. With the development of wind farms, it is necessary to predict the energy output for the electricity market. This study compared two different methods for forecasting the wind energy output monthly. The first method is the physical method, using predicting weather data from Medium-Range Weather Forecasts (ECMWF). Another method is RNN-LSTM (Recurrent Neural Network-Long Short-Term Memory) by using Python to predict energy output. The result showed that the physical method can predict the trend of energy output value while RNN-LSTM is not suitable for monthly forecasting. This study proved that the deep learning methods should be utilized in the site that have numerous numbers of data resources. And it is better to use physical methods which consider the atmosphere, local terrain, and wind farm layout for wind farm energy outputs forecasting.
{"title":"Forecasting for Wind Farm Energy Output in South Australia: A Comparative Analysis of Physical Methods and Deep Learning Methods","authors":"Yijia Zhang","doi":"10.1109/ACMLC58173.2022.00023","DOIUrl":"https://doi.org/10.1109/ACMLC58173.2022.00023","url":null,"abstract":"To achieve the target of carbon zero” in 2050, the Australian government advocates the development of renewable energy technology to reduce CO2 emissions. Particularly, wind energy resources are rich in South Australia. With the development of wind farms, it is necessary to predict the energy output for the electricity market. This study compared two different methods for forecasting the wind energy output monthly. The first method is the physical method, using predicting weather data from Medium-Range Weather Forecasts (ECMWF). Another method is RNN-LSTM (Recurrent Neural Network-Long Short-Term Memory) by using Python to predict energy output. The result showed that the physical method can predict the trend of energy output value while RNN-LSTM is not suitable for monthly forecasting. This study proved that the deep learning methods should be utilized in the site that have numerous numbers of data resources. And it is better to use physical methods which consider the atmosphere, local terrain, and wind farm layout for wind farm energy outputs forecasting.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126647010","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 : 2022-12-01DOI: 10.1109/ACMLC58173.2022.00022
Wongsathon Naksuwan, Picha Suwannahitatorn, Chakrit Watcharopas, Pakaket Wattuya
Malaria is a significant global health issue, with 241 million people infected and resulting in 627,000 deaths in 2020, officially reported by the World Health organization (WHO). In addition, during the Covid-19 pandemic, 47,000 people died because of a reluctance to receive treatment. In Thailand, Malaria still spreads in distant communities where restrictions are in place for military deployments due to the high risk of infection. Therefore, the 8,000 or so military personnel who deploy on missions close to the country’s borders are actively monitored by the Armed Forces Research Institute of Medical Sciences (AFRIMS). The lack of medical personnel in these remote settlements, however, slows detection and adversely impacts the health and lives of military soldiers working in these locations. Because of their comparative effectiveness to traditional learning algorithms, deep learning technologies are used as a tool for medical screenings. In this study, the YOLOv3 and the DenseNetl21 are used to diagnose malaria infection using thin film blood smears. The results show that testing on normal slide datasets can distinguish between normal red blood cells and malaria-infected red blood cells in four species, including Falciparum, Vivax, Malariae, and Ovale, with accuracy for infection classification at 98.08%, sensitivity at 98.05%, and specificity at 99.73%. Furthermore, when the hard slide dataset is examined, the infection classification’s accuracy, sensitivity, and specificity are 98.48%, 90%, and 99.24%, respectively. In normal slide datasets, this detection method yields a positive hit rate for malaria-infected red blood cells and normal red blood cells of 98.05% for the former and 92.65% for the latter.
{"title":"Deep Learning for Detecting Malaria Parasites of Infected Red Blood Cells in Thin Blood Smear Images","authors":"Wongsathon Naksuwan, Picha Suwannahitatorn, Chakrit Watcharopas, Pakaket Wattuya","doi":"10.1109/ACMLC58173.2022.00022","DOIUrl":"https://doi.org/10.1109/ACMLC58173.2022.00022","url":null,"abstract":"Malaria is a significant global health issue, with 241 million people infected and resulting in 627,000 deaths in 2020, officially reported by the World Health organization (WHO). In addition, during the Covid-19 pandemic, 47,000 people died because of a reluctance to receive treatment. In Thailand, Malaria still spreads in distant communities where restrictions are in place for military deployments due to the high risk of infection. Therefore, the 8,000 or so military personnel who deploy on missions close to the country’s borders are actively monitored by the Armed Forces Research Institute of Medical Sciences (AFRIMS). The lack of medical personnel in these remote settlements, however, slows detection and adversely impacts the health and lives of military soldiers working in these locations. Because of their comparative effectiveness to traditional learning algorithms, deep learning technologies are used as a tool for medical screenings. In this study, the YOLOv3 and the DenseNetl21 are used to diagnose malaria infection using thin film blood smears. The results show that testing on normal slide datasets can distinguish between normal red blood cells and malaria-infected red blood cells in four species, including Falciparum, Vivax, Malariae, and Ovale, with accuracy for infection classification at 98.08%, sensitivity at 98.05%, and specificity at 99.73%. Furthermore, when the hard slide dataset is examined, the infection classification’s accuracy, sensitivity, and specificity are 98.48%, 90%, and 99.24%, respectively. In normal slide datasets, this detection method yields a positive hit rate for malaria-infected red blood cells and normal red blood cells of 98.05% for the former and 92.65% for the latter.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130466757","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 : 2022-12-01DOI: 10.1109/acmlc58173.2022.00010
Qin Zou, Nan Li, Baowei Xu, Xintong Li
As a reference value, the occupancy guides the building Automation System (BAS) operation, which can significantly reduce energy consumption. However, the occupancy counts of commercials fluctuate dynamically with time, and how to gain the occupancy clusters and accurately predict the occupancy counts has yet to be well solved. To solve the above problems, this research proposes a prediction method for the occupancy counts of commercial buildings based on the integration of Wi-Fi connection counts data, categories of weekdays and holidays, outdoor climate data sets, and the combination of K-Means and decision tree algorithm. First, the K-means algorithm was used to cluster to obtain the representative occupancy daily clusters. Subsequently, the decision tree algorithm recognizes the clusters’ generation rules and constructs the prediction model. The validation experiments were conducted in a commercial building in Chongqing, China. The results showed that the prediction model had an accuracy of 95.24%, with better robustness than independent data sources. The prediction results can provide a practical reference for formulating BAS’s operation control and commercial operation scheme in the low carbon emission reduction environment.
{"title":"A Method of Predicting Occupancy in Commercial Building Based on Machine Learning","authors":"Qin Zou, Nan Li, Baowei Xu, Xintong Li","doi":"10.1109/acmlc58173.2022.00010","DOIUrl":"https://doi.org/10.1109/acmlc58173.2022.00010","url":null,"abstract":"As a reference value, the occupancy guides the building Automation System (BAS) operation, which can significantly reduce energy consumption. However, the occupancy counts of commercials fluctuate dynamically with time, and how to gain the occupancy clusters and accurately predict the occupancy counts has yet to be well solved. To solve the above problems, this research proposes a prediction method for the occupancy counts of commercial buildings based on the integration of Wi-Fi connection counts data, categories of weekdays and holidays, outdoor climate data sets, and the combination of K-Means and decision tree algorithm. First, the K-means algorithm was used to cluster to obtain the representative occupancy daily clusters. Subsequently, the decision tree algorithm recognizes the clusters’ generation rules and constructs the prediction model. The validation experiments were conducted in a commercial building in Chongqing, China. The results showed that the prediction model had an accuracy of 95.24%, with better robustness than independent data sources. The prediction results can provide a practical reference for formulating BAS’s operation control and commercial operation scheme in the low carbon emission reduction environment.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131075651","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：