Pub Date : 2021-08-20DOI: 10.1109/CSAIEE54046.2021.9543210
Liang Li, Min Hu, Fuji Ren, Haijun Xu
Over the years, energy time series forecasting has been widely studied and has played an important role in various fields, such as electric energy forecasting, solar energy forecasting, etc. In energy time series forecasting, it is crucial to building forecasting models for long series in order to obtain accurate forecasting results. Since the use of long series can cause the accuracy of the model to decrease. In this paper, we propose a deep learning model (TCNTA-BiGRU) based on a bi-directional gated cyclic unit (BiGRU) with a temporal attention mechanism to address the problem of accuracy degradation in long sequence tasks. First, in order to capture long-term dependencies, this paper divide the dataset and input it into a temporal convolutional network (TCN) to transform long sequences into multiple short sequences, which not only solves the problem that to cause gradient explosion or disappearance when processing long sequences, but also reduces the spatial complexity. Then, BiGRU is used to learn historical and future information and capture more short-term dependencies. Moreover, in order to enhance the model's ability to focus on data periodicity, a temporal attention mechanism is introduced. Additionally the autoregressive module is used to increase the linear fitting ability of the model. The model proposed in this paper is applied to the Electricity and Solar Energy datasets and the results show a better performance relate to existing deep learning models.
{"title":"Temporal Attention Based TCN-BIGRU Model for Energy Time Series Forecasting","authors":"Liang Li, Min Hu, Fuji Ren, Haijun Xu","doi":"10.1109/CSAIEE54046.2021.9543210","DOIUrl":"https://doi.org/10.1109/CSAIEE54046.2021.9543210","url":null,"abstract":"Over the years, energy time series forecasting has been widely studied and has played an important role in various fields, such as electric energy forecasting, solar energy forecasting, etc. In energy time series forecasting, it is crucial to building forecasting models for long series in order to obtain accurate forecasting results. Since the use of long series can cause the accuracy of the model to decrease. In this paper, we propose a deep learning model (TCNTA-BiGRU) based on a bi-directional gated cyclic unit (BiGRU) with a temporal attention mechanism to address the problem of accuracy degradation in long sequence tasks. First, in order to capture long-term dependencies, this paper divide the dataset and input it into a temporal convolutional network (TCN) to transform long sequences into multiple short sequences, which not only solves the problem that to cause gradient explosion or disappearance when processing long sequences, but also reduces the spatial complexity. Then, BiGRU is used to learn historical and future information and capture more short-term dependencies. Moreover, in order to enhance the model's ability to focus on data periodicity, a temporal attention mechanism is introduced. Additionally the autoregressive module is used to increase the linear fitting ability of the model. The model proposed in this paper is applied to the Electricity and Solar Energy datasets and the results show a better performance relate to existing deep learning models.","PeriodicalId":376014,"journal":{"name":"2021 IEEE International Conference on Computer Science, Artificial Intelligence and Electronic Engineering (CSAIEE)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116228351","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 : 2021-08-20DOI: 10.1109/CSAIEE54046.2021.9543343
Xingchen Xu, Xiao Huang, Jinhui Ma, Xuejianwei Luo
As the destruction of diabetes is significant to the whole world, we want to focus on it and extract useful information from the correlation between symptoms and disease. The dataset obtained from UCI is the fundamental resource for the research. In order to ensure the accuracy of the project conclusions, three different approaches were used to verify each other: literature analysis, data analysis and machine learning. Literature part mainly contains previous work and large quantities of medical research done on diabetes. Data analysis included data preprocessing and visualization so as to unfold the concealed information of the dataset. Machine learning is to use the inspiration from the previous two parts to attain a suitable model for diabetes prediction. The project finally provides knowledge of different symptoms of diabetes and their relation with diabetes. It also elaborates how symptoms can be used to predict disease. Finally, we put forward suggestions for the prevention of diabetes and monitoring of potential disease.
{"title":"Prediction of Diabetes with its Symptoms Based on Machine Learning","authors":"Xingchen Xu, Xiao Huang, Jinhui Ma, Xuejianwei Luo","doi":"10.1109/CSAIEE54046.2021.9543343","DOIUrl":"https://doi.org/10.1109/CSAIEE54046.2021.9543343","url":null,"abstract":"As the destruction of diabetes is significant to the whole world, we want to focus on it and extract useful information from the correlation between symptoms and disease. The dataset obtained from UCI is the fundamental resource for the research. In order to ensure the accuracy of the project conclusions, three different approaches were used to verify each other: literature analysis, data analysis and machine learning. Literature part mainly contains previous work and large quantities of medical research done on diabetes. Data analysis included data preprocessing and visualization so as to unfold the concealed information of the dataset. Machine learning is to use the inspiration from the previous two parts to attain a suitable model for diabetes prediction. The project finally provides knowledge of different symptoms of diabetes and their relation with diabetes. It also elaborates how symptoms can be used to predict disease. Finally, we put forward suggestions for the prevention of diabetes and monitoring of potential disease.","PeriodicalId":376014,"journal":{"name":"2021 IEEE International Conference on Computer Science, Artificial Intelligence and Electronic Engineering (CSAIEE)","volume":"231 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126116437","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 : 2021-08-20DOI: 10.1109/CSAIEE54046.2021.9543308
Zixin Huang
Smart homes, which integrate Internet of Things devices by embedding intelligence into sensors and actuators, data, and services, have grown in popularity over the last decade. This paper aims at examining the advantages and applications of IoT-based Smart Home technologies and took a glance of its future prospects. Based on the data and experiments conducted in recent studies, this paper concluded that IoT could connect home with detecting devices and thus improve the home security and energy efficiency in households. The applications of IoT ease the inconveniences faced by the elderly and the disabled in their lives. This paper is optimistic about the future development of smart home, for it would better assist people's lives with better connectivity.
{"title":"Analysis of IoT-based Smart Home Applications","authors":"Zixin Huang","doi":"10.1109/CSAIEE54046.2021.9543308","DOIUrl":"https://doi.org/10.1109/CSAIEE54046.2021.9543308","url":null,"abstract":"Smart homes, which integrate Internet of Things devices by embedding intelligence into sensors and actuators, data, and services, have grown in popularity over the last decade. This paper aims at examining the advantages and applications of IoT-based Smart Home technologies and took a glance of its future prospects. Based on the data and experiments conducted in recent studies, this paper concluded that IoT could connect home with detecting devices and thus improve the home security and energy efficiency in households. The applications of IoT ease the inconveniences faced by the elderly and the disabled in their lives. This paper is optimistic about the future development of smart home, for it would better assist people's lives with better connectivity.","PeriodicalId":376014,"journal":{"name":"2021 IEEE International Conference on Computer Science, Artificial Intelligence and Electronic Engineering (CSAIEE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115008830","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：