Pub Date : 2014-08-01DOI: 10.1109/IDAM.2014.6912705
Junheung Park, Kyoung-Yun Kim, O. Kwon
For ubiquitous healthcare service delivery, psychological wellness indices have been developed. A psychological wellness index integrates the survey results that measure stress, depression, anger, and fatigue. The current model is based on a multiple regression method and manually constructs a cause and effect model of the psychological wellness. However, this constructed model depends upon the survey responses. The relationship between these survey responses and psychological wellness indices are not linear due to data imbalance. When any data inconsistency exists, the reliability of the model decreases and eventually cost of maintenance on model revision increases. Also, when new variables or data entries are considered, the entire model should be constructed again. This paper examines the feasibility of machine learning algorithms to predict the psychological wellness indices based on the reconstructed responses. In this paper, four machine learning algorithms including multi-layer perceptron, support vector regression, generalized regression neural network, and k nearest neighbor regression, are compared and the experiment results are presented.
{"title":"Comparison of machine learning algorithms to predict psychological wellness indices for ubiquitous healthcare system design","authors":"Junheung Park, Kyoung-Yun Kim, O. Kwon","doi":"10.1109/IDAM.2014.6912705","DOIUrl":"https://doi.org/10.1109/IDAM.2014.6912705","url":null,"abstract":"For ubiquitous healthcare service delivery, psychological wellness indices have been developed. A psychological wellness index integrates the survey results that measure stress, depression, anger, and fatigue. The current model is based on a multiple regression method and manually constructs a cause and effect model of the psychological wellness. However, this constructed model depends upon the survey responses. The relationship between these survey responses and psychological wellness indices are not linear due to data imbalance. When any data inconsistency exists, the reliability of the model decreases and eventually cost of maintenance on model revision increases. Also, when new variables or data entries are considered, the entire model should be constructed again. This paper examines the feasibility of machine learning algorithms to predict the psychological wellness indices based on the reconstructed responses. In this paper, four machine learning algorithms including multi-layer perceptron, support vector regression, generalized regression neural network, and k nearest neighbor regression, are compared and the experiment results are presented.","PeriodicalId":135246,"journal":{"name":"Proceedings of the 2014 International Conference on Innovative Design and Manufacturing (ICIDM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123925516","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 : 2014-08-01DOI: 10.1109/IDAM.2014.6912699
Jie Zhao, Zhiyong Chang
Tolerance design is playing an important role in industry. The wide application of MBD (Model Based Define) technique has expedited the utilization of optimizing tolerance. In this paper, we propose a new approach to optimize tolerance of multiple processes based on MBD technique. The main features include (a) the subordinate relationship between processes model and tolerance information is analyzed and a model chaining them together is established, and (b) a revised Taguchi quality loss function is adopted to reflect the real quality distribution of mass product. A case study shows that this approach could, we believe, improve the steady of processes of product manufacturing, and make the manufacturing more economical.
{"title":"A novel approach to optimize tolerances of multiple processes based on MBD","authors":"Jie Zhao, Zhiyong Chang","doi":"10.1109/IDAM.2014.6912699","DOIUrl":"https://doi.org/10.1109/IDAM.2014.6912699","url":null,"abstract":"Tolerance design is playing an important role in industry. The wide application of MBD (Model Based Define) technique has expedited the utilization of optimizing tolerance. In this paper, we propose a new approach to optimize tolerance of multiple processes based on MBD technique. The main features include (a) the subordinate relationship between processes model and tolerance information is analyzed and a model chaining them together is established, and (b) a revised Taguchi quality loss function is adopted to reflect the real quality distribution of mass product. A case study shows that this approach could, we believe, improve the steady of processes of product manufacturing, and make the manufacturing more economical.","PeriodicalId":135246,"journal":{"name":"Proceedings of the 2014 International Conference on Innovative Design and Manufacturing (ICIDM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121340134","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 : 2014-08-01DOI: 10.1109/IDAM.2014.6912685
Yaoyao Shi, Tao Yu, Youmin Zhang, Xiaodong He, C. Kang
As considering the issues of inefficiency and stress concentration caused by hand-stitched methods in winding processes, the hot-press technology for prepreg tape splicing is proposed. The splicing device and automatic control system are designed as well. After the theoretical analysis of intimate contact and autohesion processes is investigated, the key parameters which mainly affect the quality of splicing processes are determined. They are temperature, pressure, and time, respectively. Moreover, the influence mechanism of these three parameters on splicing quality is examined by experimental tests, based on which the appropriate values are selected to achieve the favorable performance of splicing zone.
{"title":"Research on hot-press splicing technology for composite prepreg tape","authors":"Yaoyao Shi, Tao Yu, Youmin Zhang, Xiaodong He, C. Kang","doi":"10.1109/IDAM.2014.6912685","DOIUrl":"https://doi.org/10.1109/IDAM.2014.6912685","url":null,"abstract":"As considering the issues of inefficiency and stress concentration caused by hand-stitched methods in winding processes, the hot-press technology for prepreg tape splicing is proposed. The splicing device and automatic control system are designed as well. After the theoretical analysis of intimate contact and autohesion processes is investigated, the key parameters which mainly affect the quality of splicing processes are determined. They are temperature, pressure, and time, respectively. Moreover, the influence mechanism of these three parameters on splicing quality is examined by experimental tests, based on which the appropriate values are selected to achieve the favorable performance of splicing zone.","PeriodicalId":135246,"journal":{"name":"Proceedings of the 2014 International Conference on Innovative Design and Manufacturing (ICIDM)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127942789","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：