Pub Date : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377438
Tien-Dung Nguyen, D. Le, Nguyen Pham-Van, Hyunseung Choo, T. P. Van
Using unmanned aerial vehicles (UAVs) has been considered as an effective way to collect data from a sensor network spanning over a wide area. Existing schemes usually divide the network into several clusters, and the UAV visits the cluster heads one by one to collect the gathered data. However, they only solved how to efficiently plan the UAV trajectory and neglected the data aggregation time within each cluster. This paper proposes an incremental clustering and scheduling scheme, in which the transmission schedule of sensors is calculated in line with the UAV trajectory and velocity. The cluster head that the UAV visits at a later time will be given more time to collect data from its cluster. As a result, the data aggregation time is significantly shorter.
{"title":"UAV-aided Sensory Data Aggregation: Incremental Clustering and Scheduling Approach","authors":"Tien-Dung Nguyen, D. Le, Nguyen Pham-Van, Hyunseung Choo, T. P. Van","doi":"10.1109/IMCOM51814.2021.9377438","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377438","url":null,"abstract":"Using unmanned aerial vehicles (UAVs) has been considered as an effective way to collect data from a sensor network spanning over a wide area. Existing schemes usually divide the network into several clusters, and the UAV visits the cluster heads one by one to collect the gathered data. However, they only solved how to efficiently plan the UAV trajectory and neglected the data aggregation time within each cluster. This paper proposes an incremental clustering and scheduling scheme, in which the transmission schedule of sensors is calculated in line with the UAV trajectory and velocity. The cluster head that the UAV visits at a later time will be given more time to collect data from its cluster. As a result, the data aggregation time is significantly shorter.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128863451","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377358
San Kim, Eunjung Joo, Jusung Ha, Jaekwang Kim
Data-processing methods have evolved because of the high demand due to the development of information technology. Specifically, data created by individuals are being generated very rapidly through social-media services, and thus, they assume importance in service personalization. Personal data involve very complex relations and various lists. It is difficult to develop a data system for complex relational lists, using the traditional relational-table model. There are several approaches to addressing this limitation in the relational-table model. The graph structure is one such emerging approach. In graph data, each object in the data constitutes a node, and relations between objects constitute links. The graph data structure has been used in commercial products, such as Google Cayley and Amazon Neptune. In this study, we generalize the graph data structure to a topological data structure and demonstrate a method to transform topological data into a sentence structure. We suggest the use of query functions and provide relevant examples.
{"title":"Generalizing and Processing Topological Data using Sentence Data Structure","authors":"San Kim, Eunjung Joo, Jusung Ha, Jaekwang Kim","doi":"10.1109/IMCOM51814.2021.9377358","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377358","url":null,"abstract":"Data-processing methods have evolved because of the high demand due to the development of information technology. Specifically, data created by individuals are being generated very rapidly through social-media services, and thus, they assume importance in service personalization. Personal data involve very complex relations and various lists. It is difficult to develop a data system for complex relational lists, using the traditional relational-table model. There are several approaches to addressing this limitation in the relational-table model. The graph structure is one such emerging approach. In graph data, each object in the data constitutes a node, and relations between objects constitute links. The graph data structure has been used in commercial products, such as Google Cayley and Amazon Neptune. In this study, we generalize the graph data structure to a topological data structure and demonstrate a method to transform topological data into a sentence structure. We suggest the use of query functions and provide relevant examples.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130750227","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377351
An Le Ha, Trinh Van Chien, T. Nguyen, Wan Choi, V. Nguyen
Deep learning has demonstrated the important roles in improving the system performance and reducing computational complexity for 5G-and-beyond networks. In this paper, we propose a new channel estimation method with the assistance of deep learning in order to support the least squares estimation, which is a low-cost method but having relatively high channel estimation errors. This goal is achieved by utilizing a MIMO (multiple-input multiple-output) system with a multi-path channel profile used for simulations in the 5G networks under the severity of Doppler effects. Numerical results demonstrate the superiority of the proposed deep learning-assisted channel estimation method over the other channel estimation methods in previous works in terms of mean square errors.
{"title":"Deep Learning-Aided 5G Channel Estimation","authors":"An Le Ha, Trinh Van Chien, T. Nguyen, Wan Choi, V. Nguyen","doi":"10.1109/IMCOM51814.2021.9377351","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377351","url":null,"abstract":"Deep learning has demonstrated the important roles in improving the system performance and reducing computational complexity for 5G-and-beyond networks. In this paper, we propose a new channel estimation method with the assistance of deep learning in order to support the least squares estimation, which is a low-cost method but having relatively high channel estimation errors. This goal is achieved by utilizing a MIMO (multiple-input multiple-output) system with a multi-path channel profile used for simulations in the 5G networks under the severity of Doppler effects. Numerical results demonstrate the superiority of the proposed deep learning-assisted channel estimation method over the other channel estimation methods in previous works in terms of mean square errors.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"35 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132151271","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377406
Mingue Song, Yanggon Kim
Medical image analysis is consistently being researched in the computer vision in that it captures potential symptoms and enables more delicate diagnosis of patients. Based on the development of medical equipment such as optical coherence tomography(OCT) and magnetic resonance imaging(MRI), it is possible to analyze medical data with clearer and higher resolution than before. However, there are still many data that have limitations in manually diagnosis by human. Moreover, identifying the extent of the damaged retinal layer also remains one of the most challenging tasks since the damaged layer not only contains too many invisible layers, but it is too small. Normal OCT data has smooth layers while age-related macular degeneration(AMD) or diabetic macular edema(DME), which are classified as abnormal, has layers that are damaged by bleeding. The precise regional classification is required for the diagnosis and prescription of the damaged layers and a new approach to effectively training an irregular layer of abnormal data is also needed. Hence, this paper proposes an OCT data manipulation method as a preprocessing step to improve training boundaries of regional layers. The preprocessed data were generated by manual range using the proposed method and applied to the encoder-decoder networks, SegNet and Unet. The experiment shows that the preprocessed datasets were trained much faster than the original and the optimized range was also confirmed through comparison the results of preprocessed dataset by each range.
{"title":"Manipulating Retinal OCT data for Image Segmentation based on Encoder-Decoder Network","authors":"Mingue Song, Yanggon Kim","doi":"10.1109/IMCOM51814.2021.9377406","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377406","url":null,"abstract":"Medical image analysis is consistently being researched in the computer vision in that it captures potential symptoms and enables more delicate diagnosis of patients. Based on the development of medical equipment such as optical coherence tomography(OCT) and magnetic resonance imaging(MRI), it is possible to analyze medical data with clearer and higher resolution than before. However, there are still many data that have limitations in manually diagnosis by human. Moreover, identifying the extent of the damaged retinal layer also remains one of the most challenging tasks since the damaged layer not only contains too many invisible layers, but it is too small. Normal OCT data has smooth layers while age-related macular degeneration(AMD) or diabetic macular edema(DME), which are classified as abnormal, has layers that are damaged by bleeding. The precise regional classification is required for the diagnosis and prescription of the damaged layers and a new approach to effectively training an irregular layer of abnormal data is also needed. Hence, this paper proposes an OCT data manipulation method as a preprocessing step to improve training boundaries of regional layers. The preprocessed data were generated by manual range using the proposed method and applied to the encoder-decoder networks, SegNet and Unet. The experiment shows that the preprocessed datasets were trained much faster than the original and the optimized range was also confirmed through comparison the results of preprocessed dataset by each range.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134584936","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377355
Yuriko Takahashi, Shigeto Suzuki, Takuji Yamamoto, Hiroyuki Fukuda, M. Oguchi
In recent years, efforts have been made to reduce the number of servers by virtualizing servers to improve their utilization rate. In this approach, it is necessary to predict and control the CPU utilization of all the virtual servers because the performance of the virtual servers may deteriorate due to the over-committed state in which the servers are allocated more CPUs than their own CPU resources. In this study, we discuss a regression modeling method for time-series data to generate a general-purpose deep-learning prediction model of the CPU utilization of virtual servers. After exploring methods, we confirmed that the number of data used during retraining could be reduced by extracting the time series data by the length required for training and using the data randomly after subdivision.
{"title":"Time-Series Data Regression Modeling Method for Efficient Operation of Virtual Environments","authors":"Yuriko Takahashi, Shigeto Suzuki, Takuji Yamamoto, Hiroyuki Fukuda, M. Oguchi","doi":"10.1109/IMCOM51814.2021.9377355","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377355","url":null,"abstract":"In recent years, efforts have been made to reduce the number of servers by virtualizing servers to improve their utilization rate. In this approach, it is necessary to predict and control the CPU utilization of all the virtual servers because the performance of the virtual servers may deteriorate due to the over-committed state in which the servers are allocated more CPUs than their own CPU resources. In this study, we discuss a regression modeling method for time-series data to generate a general-purpose deep-learning prediction model of the CPU utilization of virtual servers. After exploring methods, we confirmed that the number of data used during retraining could be reduced by extracting the time series data by the length required for training and using the data randomly after subdivision.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127218522","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377400
Y. Do, ChangYoung Jo, J. Jeon
Controller area network (CAN) was primarily employed as In-vehicle networks (IVNs). But this protocol has not been employed in industrial fieldbuses owing to its inadequate transmission speed and data rate. However, with the development of CANs with flexible data rates (CAN-FD) and CANopen, there has been increased interest regarding the application of CAN-based systems in industrial sites. Nevertheless, the CAN based protocol has the drawback of being vulnerable to unexpected wire breaking. Therefore, this paper proposes a redundancy method requiring 393ns delay time to address unexpected wire breakage in CAN-based systems.
{"title":"Redundancy method to solve CAN-FD bus line breakage problem","authors":"Y. Do, ChangYoung Jo, J. Jeon","doi":"10.1109/IMCOM51814.2021.9377400","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377400","url":null,"abstract":"Controller area network (CAN) was primarily employed as In-vehicle networks (IVNs). But this protocol has not been employed in industrial fieldbuses owing to its inadequate transmission speed and data rate. However, with the development of CANs with flexible data rates (CAN-FD) and CANopen, there has been increased interest regarding the application of CAN-based systems in industrial sites. Nevertheless, the CAN based protocol has the drawback of being vulnerable to unexpected wire breaking. Therefore, this paper proposes a redundancy method requiring 393ns delay time to address unexpected wire breakage in CAN-based systems.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127400154","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377436
Suriana Ismail, R. Ismail
A dense connection within and a sparse connection between is what is assume right for a definition of community. It has been an existing research aim for most researcher recently in detecting community due to this definition. This paper proposes a new way of group the community is to give priority on the structure of the network for its community, rather than arbitrary addition of members with its only indicator is based on the value of modularity. Experiment and comparison of end result of found community shown a promising outcome. Hence, the new algorithm, MuLAN, is more robust in providing the detection where it forms the basic group of members as its first level of community and the it will check whether the remaining members are also connected with each other which form a strong structure for the community.
{"title":"Dynamic Multi Level Approach for Community Detection","authors":"Suriana Ismail, R. Ismail","doi":"10.1109/IMCOM51814.2021.9377436","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377436","url":null,"abstract":"A dense connection within and a sparse connection between is what is assume right for a definition of community. It has been an existing research aim for most researcher recently in detecting community due to this definition. This paper proposes a new way of group the community is to give priority on the structure of the network for its community, rather than arbitrary addition of members with its only indicator is based on the value of modularity. Experiment and comparison of end result of found community shown a promising outcome. Hence, the new algorithm, MuLAN, is more robust in providing the detection where it forms the basic group of members as its first level of community and the it will check whether the remaining members are also connected with each other which form a strong structure for the community.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125322189","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377433
Jaeeun Shin, Jundong Cho, Sangwon Lee
Color education materials for visually impaired students are still a lot to be developed due to a lack of materials compared to their needs. In fact, the supplementary materials are essential to teachers at special education schools who teach blind students by using other senses instead of eyesight. However, it has been a lack of support to provide teaching materials for the purpose so far. Since visually impaired people have learned the color concept in an abstract and literary way, they have had problems in understanding the color theory itself. The main purpose of this study is to design the Tactile-Color system using tactile symbols and texture to explain the color theory. This assistive material was produced by 2.5D embossed UV print materials for visually impaired education. The color symbols were designed based on associations between colors and shapes to help people perceive tactile information; they are primary colors (i.e., red, yellow, blue) matching with primary shapes (i.e., circle, triangle, square), respectively. Brightness and saturation in color theory designated to the tactile texture of softness and roughness gradient. The audio guide also supplied to enhance the efficiency of art teachers' classes and to assist the self-learning of visually impaired students. The survey and interviews were conducted with 17 special education teachers for the evaluation of the tactile-color materials. The evaluation results indicate that tactile-color materials can be effective to teach color theory to visually impaired students in the classroom. The positive responses from actual users proved the usefulness and understandability of the Tactile-Color system.
{"title":"Tactile-Color System for Accessibility of Color Education: 2.5D UV Printed Supplementary Material for Visually Impaired Students","authors":"Jaeeun Shin, Jundong Cho, Sangwon Lee","doi":"10.1109/IMCOM51814.2021.9377433","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377433","url":null,"abstract":"Color education materials for visually impaired students are still a lot to be developed due to a lack of materials compared to their needs. In fact, the supplementary materials are essential to teachers at special education schools who teach blind students by using other senses instead of eyesight. However, it has been a lack of support to provide teaching materials for the purpose so far. Since visually impaired people have learned the color concept in an abstract and literary way, they have had problems in understanding the color theory itself. The main purpose of this study is to design the Tactile-Color system using tactile symbols and texture to explain the color theory. This assistive material was produced by 2.5D embossed UV print materials for visually impaired education. The color symbols were designed based on associations between colors and shapes to help people perceive tactile information; they are primary colors (i.e., red, yellow, blue) matching with primary shapes (i.e., circle, triangle, square), respectively. Brightness and saturation in color theory designated to the tactile texture of softness and roughness gradient. The audio guide also supplied to enhance the efficiency of art teachers' classes and to assist the self-learning of visually impaired students. The survey and interviews were conducted with 17 special education teachers for the evaluation of the tactile-color materials. The evaluation results indicate that tactile-color materials can be effective to teach color theory to visually impaired students in the classroom. The positive responses from actual users proved the usefulness and understandability of the Tactile-Color system.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126725086","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377353
C. MacKay, Teng-Sheng Moh
A picture is worth a thousand words, or if you want it labeled, it's worth about ten cents per bounding box. Data is the fuel that powers modern technologies run by AI engines. High quality data is important to produce accurate machine learning models. Acquiring high quality labeled data however, can be expensive and time consuming. For small companies, academic researchers, or hobbyists, gathering large datasets that are not already publicly available is challenging. This research paper will describe the ability to generate labeled image data synthetically which can be used in supervised learning for object detection. This paper describes a system using 3D modeling software in conjunction with Generative Adversarial Networks and image augmentation that can create a diverse dataset of images containing objects with bounding boxes and labels. The result of this effort is an accurate object detector in an environment of aerial surveillance with no cost to the end user.
{"title":"Learning for Free: Object Detectors Trained on Synthetic Data","authors":"C. MacKay, Teng-Sheng Moh","doi":"10.1109/IMCOM51814.2021.9377353","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377353","url":null,"abstract":"A picture is worth a thousand words, or if you want it labeled, it's worth about ten cents per bounding box. Data is the fuel that powers modern technologies run by AI engines. High quality data is important to produce accurate machine learning models. Acquiring high quality labeled data however, can be expensive and time consuming. For small companies, academic researchers, or hobbyists, gathering large datasets that are not already publicly available is challenging. This research paper will describe the ability to generate labeled image data synthetically which can be used in supervised learning for object detection. This paper describes a system using 3D modeling software in conjunction with Generative Adversarial Networks and image augmentation that can create a diverse dataset of images containing objects with bounding boxes and labels. The result of this effort is an accurate object detector in an environment of aerial surveillance with no cost to the end user.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123420696","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377391
Nurmalitasari, Zalizah Awang Long, Mohammad Faizuddin Mohd Noor
Reducing dimensional data is an essential step before data analysis in Predictive Learning Analytics (PLA) for student dropouts. It was reducing dimensions in the study using the CATPCA method. CATPCA has advantages in reducing data dimensions on measurement variables of various levels such as nominal, ordinal, and numerical, which may not have a linear correlation between one variable and another, such as variables related to the PLA data processing. This study's results are five factors that store important information about the input variables, namely social and economic, academic program, institutional, academic performance, and personal. The conclusions of this study will be beneficial for further research in the PLA process
{"title":"Reduction of Data Dimensions in The PLA Process","authors":"Nurmalitasari, Zalizah Awang Long, Mohammad Faizuddin Mohd Noor","doi":"10.1109/IMCOM51814.2021.9377391","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377391","url":null,"abstract":"Reducing dimensional data is an essential step before data analysis in Predictive Learning Analytics (PLA) for student dropouts. It was reducing dimensions in the study using the CATPCA method. CATPCA has advantages in reducing data dimensions on measurement variables of various levels such as nominal, ordinal, and numerical, which may not have a linear correlation between one variable and another, such as variables related to the PLA data processing. This study's results are five factors that store important information about the input variables, namely social and economic, academic program, institutional, academic performance, and personal. The conclusions of this study will be beneficial for further research in the PLA process","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121573199","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：