Pub Date : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377396
E. Nepolo, G. Lusilao-Zodi
Due to the exponential growth of cloud computing, data centres have become the pivot for supporting the core infrastructure that propels the cloud computing evolution. Data centres are repositories that house different networking devices that are connected together using communication links to collect, store, process and disseminate data. Data centres prioritise high data availability amongst others. However, data availability is challenged by the unpredictable nature of the network environment, which presents enormous challenges in designing routing protocols that are agile enough to adjust to sudden changes in the network's available capacity. To provide seamless services to users, most modern data centres use Fat-Tree as the de-facto topology due to its multipath diversity, and the Equal-Cost Multi-Path protocol (ECMP) as the primary routing protocol to route data towards alternative paths of equal cost when the primary path is over-utilised. However, the weighted algorithm used to achieve this is inefficient, as its assigns traffic to links based on their link capacities without taking into consideration the capacity already in use on that link. In this paper, we propose the Predictive Equal-Cost Multi-Path protocol that enhances ECMP's weighted load-balancing algorithm by making forwarding decisions based on predicted congestion outlooks. The proposed protocol uses packets dropped to compute the bandwidth utilisation of links and uses the computed figures to identify the least congested links, which is then used to build forwarding tables. The protocol was tested in a Fat-Tree enabled data centre where it proved to perform better when compared to the ECMP weighted algorithm.
{"title":"A Predictive ECMP Routing Protocol for Fat-Tree Enabled Data Centre Networks","authors":"E. Nepolo, G. Lusilao-Zodi","doi":"10.1109/IMCOM51814.2021.9377396","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377396","url":null,"abstract":"Due to the exponential growth of cloud computing, data centres have become the pivot for supporting the core infrastructure that propels the cloud computing evolution. Data centres are repositories that house different networking devices that are connected together using communication links to collect, store, process and disseminate data. Data centres prioritise high data availability amongst others. However, data availability is challenged by the unpredictable nature of the network environment, which presents enormous challenges in designing routing protocols that are agile enough to adjust to sudden changes in the network's available capacity. To provide seamless services to users, most modern data centres use Fat-Tree as the de-facto topology due to its multipath diversity, and the Equal-Cost Multi-Path protocol (ECMP) as the primary routing protocol to route data towards alternative paths of equal cost when the primary path is over-utilised. However, the weighted algorithm used to achieve this is inefficient, as its assigns traffic to links based on their link capacities without taking into consideration the capacity already in use on that link. In this paper, we propose the Predictive Equal-Cost Multi-Path protocol that enhances ECMP's weighted load-balancing algorithm by making forwarding decisions based on predicted congestion outlooks. The proposed protocol uses packets dropped to compute the bandwidth utilisation of links and uses the computed figures to identify the least congested links, which is then used to build forwarding tables. The protocol was tested in a Fat-Tree enabled data centre where it proved to perform better when compared to the ECMP weighted algorithm.","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":"129869614","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/IMCOM51814.2021.9377419
Min Wei, Caiqin Li, Xu Yang
With the development of industry, the consumption of industrial electricity is increasing, reducing the cost of electricity has become an urgent problem to be solved. Meanwhile, remote monitoring of connected devices and the intelligence pushed to the edges of the monitoring devices becomes critical in industrial IoT (IIoT). How to design the energy management mechanism that can respond to the change of electricity price in time is the main problem we are facing at present. This paper proposes an energy management architecture based on edge computing for industrial facility, which introduces edge computing into the factory energy management scenes. Under this architecture, an energy management mechanism based on edge computing is proposed. Finally, the proposed mechanism is tested, and the test shows that the mechanism can reduce the electricity cost of the factory.
{"title":"An Energy Management System with Edge Computing for Industrial Facility","authors":"Min Wei, Caiqin Li, Xu Yang","doi":"10.1109/IMCOM51814.2021.9377419","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377419","url":null,"abstract":"With the development of industry, the consumption of industrial electricity is increasing, reducing the cost of electricity has become an urgent problem to be solved. Meanwhile, remote monitoring of connected devices and the intelligence pushed to the edges of the monitoring devices becomes critical in industrial IoT (IIoT). How to design the energy management mechanism that can respond to the change of electricity price in time is the main problem we are facing at present. This paper proposes an energy management architecture based on edge computing for industrial facility, which introduces edge computing into the factory energy management scenes. Under this architecture, an energy management mechanism based on edge computing is proposed. Finally, the proposed mechanism is tested, and the test shows that the mechanism can reduce the electricity cost of the factory.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"40 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":"114871991","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/IMCOM51814.2021.9377428
Yunseon Jang, C. Son, Hyunseung Choo
In bad weather, artifacts such as rain streaks degrade the image quality. In addition, artifacts in the damaged image obstruct human vision and adversely affect the accuracy of object detection. Hence, single image rain removal is an important issue to improve image quality. However, state-of-the-art methods have limitation that require a lot of training data. This paper proposes a lightweight Deep Extraction Network (DEN), which performs well on image de-raining even with a small training dataset. Particularly, we design a novel Light Residual Block (LRB), which is connected in five cascading layers for extracting a deep local feature. Furthermore, DEN deploys a residual learning for training only artifacts. The experimental results on synthetic and real-world rainy image demonstrate the effectiveness in terms of visual and quantitative performance.
{"title":"Lightweight Deep Extraction Networks for Single Image De-raining","authors":"Yunseon Jang, C. Son, Hyunseung Choo","doi":"10.1109/IMCOM51814.2021.9377428","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377428","url":null,"abstract":"In bad weather, artifacts such as rain streaks degrade the image quality. In addition, artifacts in the damaged image obstruct human vision and adversely affect the accuracy of object detection. Hence, single image rain removal is an important issue to improve image quality. However, state-of-the-art methods have limitation that require a lot of training data. This paper proposes a lightweight Deep Extraction Network (DEN), which performs well on image de-raining even with a small training dataset. Particularly, we design a novel Light Residual Block (LRB), which is connected in five cascading layers for extracting a deep local feature. Furthermore, DEN deploys a residual learning for training only artifacts. The experimental results on synthetic and real-world rainy image demonstrate the effectiveness in terms of visual and quantitative performance.","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":"130094386","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/IMCOM51814.2021.9377424
Yeji Shin, J. Bum, C. Son, Hyunseung Choo
Facial expression synthesis is widely applied to emotion prediction and face recognition for human-computer interaction. This task is challenging because it is difficult to reconstruct realistic and accurate facial expressions. Early deep learning methods focus only on pixel-level manipulation and are not suitable for generating realistic facial expressions. In this paper, we propose a bottleneck-layered conditional generative adversarial networks (BCGAN) for more realistic and accurate facial expression synthesis. BCGAN adopts a bottleneck layer that uses channel-wise concatenation in the generator to train with meaningful features only. In addition, a dense connection that links all bottleneck layers is added to generate an image which preserves the facial details of the original image. Both quantitative and qualitative evaluations were performed using the Radboud Faces Database (RaFD). Experimental results showed that BCGAN had 2% higher classification accuracy (98.7%) on the generated images as well as faster training speed compared to state-of-the-art approach.
{"title":"BCGAN: Facial Expression Synthesis by Bottleneck-Layered Conditional Generative Adversarial Networks","authors":"Yeji Shin, J. Bum, C. Son, Hyunseung Choo","doi":"10.1109/IMCOM51814.2021.9377424","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377424","url":null,"abstract":"Facial expression synthesis is widely applied to emotion prediction and face recognition for human-computer interaction. This task is challenging because it is difficult to reconstruct realistic and accurate facial expressions. Early deep learning methods focus only on pixel-level manipulation and are not suitable for generating realistic facial expressions. In this paper, we propose a bottleneck-layered conditional generative adversarial networks (BCGAN) for more realistic and accurate facial expression synthesis. BCGAN adopts a bottleneck layer that uses channel-wise concatenation in the generator to train with meaningful features only. In addition, a dense connection that links all bottleneck layers is added to generate an image which preserves the facial details of the original image. Both quantitative and qualitative evaluations were performed using the Radboud Faces Database (RaFD). Experimental results showed that BCGAN had 2% higher classification accuracy (98.7%) on the generated images as well as faster training speed compared to state-of-the-art approach.","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":"129468452","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/IMCOM51814.2021.9377388
A. Sharshar, A. Fayez, Yasser Ashraf, W. Gomaa
Recently, the use of the inertia measurement units (IMU), especially the gyroscope and accelerometer sensors, has increased in the human activity recognition (HAR) due to the extensive use of smartwatches and smartphones. In addition to the high quality and efficiency result in by these sensors, they can capture the data of the body dynamic motion as function of time, then the stream of data is analyzed and processed to classify and predict the action being done, the gender, the health status and many other characteristics. Gender and activity recognition have been deeply studied recently, using various ways to recognize either of them through many interfaces, like voice, image, or inertia measurement motion data. All these types of classifications are crucial in many applications such as recommendation systems, speech recognition, sports tracking, security and most importantly in healthcare. In this research, we present two models (hierarchical model and joint distribution model) and compare between two datasets (MoVi and MotionSense), using only two IMU sensors on right and left hand and motion sense dataset using mobile phone, to predict gender with activity and see how every activity reflect on gender, and explore the efficiency on using autocorrelation function as a feature extractor and compare between three classifiers, Random Forest (RF), Support Vector Machine (SVM) and Convolution Neural Network (CNN).
{"title":"Activity With Gender Recognition Using Accelerometer and Gyroscope","authors":"A. Sharshar, A. Fayez, Yasser Ashraf, W. Gomaa","doi":"10.1109/IMCOM51814.2021.9377388","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377388","url":null,"abstract":"Recently, the use of the inertia measurement units (IMU), especially the gyroscope and accelerometer sensors, has increased in the human activity recognition (HAR) due to the extensive use of smartwatches and smartphones. In addition to the high quality and efficiency result in by these sensors, they can capture the data of the body dynamic motion as function of time, then the stream of data is analyzed and processed to classify and predict the action being done, the gender, the health status and many other characteristics. Gender and activity recognition have been deeply studied recently, using various ways to recognize either of them through many interfaces, like voice, image, or inertia measurement motion data. All these types of classifications are crucial in many applications such as recommendation systems, speech recognition, sports tracking, security and most importantly in healthcare. In this research, we present two models (hierarchical model and joint distribution model) and compare between two datasets (MoVi and MotionSense), using only two IMU sensors on right and left hand and motion sense dataset using mobile phone, to predict gender with activity and see how every activity reflect on gender, and explore the efficiency on using autocorrelation function as a feature extractor and compare between three classifiers, Random Forest (RF), Support Vector Machine (SVM) and Convolution Neural Network (CNN).","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"14 2 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":"123341182","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/IMCOM51814.2021.9377323
Jieun Kim, Y. Sah, Hayeon Song
Agreeableness is one of the key personalities expected to a virtual agent as a social interactant, as the agent's primary role is to provide help and assistance. Based on the theoretical background of the Computers-Are-Social-Actors (CASA) paradigm, this study aims to identify factors affecting the perceived agreeableness of virtual agents. Focusing on the reciprocity rule of help and users' need for help, an online experiment was conducted with a 2 (help type: reciprocal vs. unconditional) x 2 (need for help: wanted vs. not wanted) between-subjects design. The findings demonstrated that the agent providing unconditional help, compared to the agent that provided reciprocated help, was perceived to be more socially attractive, while marginally significant results were observed in terms of perceived agreeableness. In addition, the recipient's unwanted help damaged users' perception of the agent's agreeableness and social attraction. Both theoretical and practical implications are discussed.
{"title":"Agreeableness of a Virtual Agent: Effects of Reciprocity and Need for Help","authors":"Jieun Kim, Y. Sah, Hayeon Song","doi":"10.1109/IMCOM51814.2021.9377323","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377323","url":null,"abstract":"Agreeableness is one of the key personalities expected to a virtual agent as a social interactant, as the agent's primary role is to provide help and assistance. Based on the theoretical background of the Computers-Are-Social-Actors (CASA) paradigm, this study aims to identify factors affecting the perceived agreeableness of virtual agents. Focusing on the reciprocity rule of help and users' need for help, an online experiment was conducted with a 2 (help type: reciprocal vs. unconditional) x 2 (need for help: wanted vs. not wanted) between-subjects design. The findings demonstrated that the agent providing unconditional help, compared to the agent that provided reciprocated help, was perceived to be more socially attractive, while marginally significant results were observed in terms of perceived agreeableness. In addition, the recipient's unwanted help damaged users' perception of the agent's agreeableness and social attraction. Both theoretical and practical implications are discussed.","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":"123895670","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/IMCOM51814.2021.9377386
Hye-Yeon Yu, Moonhyun Kim
This paper presents an analysis of contemporary methods for event extraction from text narratives and of various event expression formats. It also briefly discusses future directions in narrative understanding and generation using artificial intelligence. The three-step study method for extracting events from text stories, comprising token analysis and part-of-speech tagging, dependent parsing, and standardization work, is analyzed. Expressions created using a tuple format are compared and contrasted with expressions created using the 5W format. Finally, we propose a novel method to organize events in a tuple format, reconstructing compound and complex sentences as simple sentences. Our method identifies and extracts verbs, subject, object, and preposition phrases. It then automatically extracts the multiple events that comprise each sentence.
{"title":"Automatic Event Extraction method for Analyzing Text Narrative Structure","authors":"Hye-Yeon Yu, Moonhyun Kim","doi":"10.1109/IMCOM51814.2021.9377386","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377386","url":null,"abstract":"This paper presents an analysis of contemporary methods for event extraction from text narratives and of various event expression formats. It also briefly discusses future directions in narrative understanding and generation using artificial intelligence. The three-step study method for extracting events from text stories, comprising token analysis and part-of-speech tagging, dependent parsing, and standardization work, is analyzed. Expressions created using a tuple format are compared and contrasted with expressions created using the 5W format. Finally, we propose a novel method to organize events in a tuple format, reconstructing compound and complex sentences as simple sentences. Our method identifies and extracts verbs, subject, object, and preposition phrases. It then automatically extracts the multiple events that comprise each sentence.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"18 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":"127528704","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/IMCOM51814.2021.9377356
Andreas Lindblom, T. Laine, H. S. Rossi
Virtual Reality provides the ability to immerse users in realistic environments, which enables utilization of the technology as an immersive educational tool. This is particularly useful for educational fields that require students to visit certain locations, or that concern hazardous situations and materials. The EIT Raw Materials Project MiReBooks intends to develop novel augmented and virtual reality teaching tools to mining education. Within the project, we developed an interactive multi-user VR environment, named MiReBooks VR, for teaching mining to students by simulating a VR mine and creating learning scenarios in it. In this paper, we briefly described MiReBooks VR, and then focused on determining the capacity of the server running in a head-mounted display by measuring latency. To assess the system's capacity to handle multiple students connected to a class session, client simulation tests of up to 30 simultaneous connections were conducted. The results suggests performance issues with respect to latency affecting all peers that could cause a negative effect to the VR user experience. In addition, the results indicate that the frame rate requirements for VR applications are difficult to maintain in multi-user environments using current off-the-shelf VR equipment. Based on the development experiences and the tests, we provide five lessons learned that can be of interest to software engineers and researchers working on the development of multi-user VR systems.
{"title":"Investigating Network Performance of a Multi-user Virtual Reality Environment for Mining Education","authors":"Andreas Lindblom, T. Laine, H. S. Rossi","doi":"10.1109/IMCOM51814.2021.9377356","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377356","url":null,"abstract":"Virtual Reality provides the ability to immerse users in realistic environments, which enables utilization of the technology as an immersive educational tool. This is particularly useful for educational fields that require students to visit certain locations, or that concern hazardous situations and materials. The EIT Raw Materials Project MiReBooks intends to develop novel augmented and virtual reality teaching tools to mining education. Within the project, we developed an interactive multi-user VR environment, named MiReBooks VR, for teaching mining to students by simulating a VR mine and creating learning scenarios in it. In this paper, we briefly described MiReBooks VR, and then focused on determining the capacity of the server running in a head-mounted display by measuring latency. To assess the system's capacity to handle multiple students connected to a class session, client simulation tests of up to 30 simultaneous connections were conducted. The results suggests performance issues with respect to latency affecting all peers that could cause a negative effect to the VR user experience. In addition, the results indicate that the frame rate requirements for VR applications are difficult to maintain in multi-user environments using current off-the-shelf VR equipment. Based on the development experiences and the tests, we provide five lessons learned that can be of interest to software engineers and researchers working on the development of multi-user VR systems.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"7 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":"126711259","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/IMCOM51814.2021.9377421
Kunwoo Bae, Yeonju Jang, Jinyoung Han, A. P. D. Pobil, Eunil Park
Given that the concept of sharing economy is one of the widely-employed economic models in our society, users' satisfaction in sharing services is one of the important academic and industrial research topics for the success of such services. This study collects users' online reviews with ratings from Airbnb, one of the representative sharing services, and investigates effects of the following three components of user experience: users' perceived usability, usefulness, and affection. Our work compares the user experience in Airbnb between the United States and Hong Kong. The results of the multiple linear regression analysis indicate that affection (the United States) and usefulness (Hong Kong) show the greatest effects on the rating on Airbnb. Based on the findings, the implications with limitations are discussed.
{"title":"A quantitative analysis of satisfaction on Airbnb from UX perspectives: The comparison between the United States and Hong Kong","authors":"Kunwoo Bae, Yeonju Jang, Jinyoung Han, A. P. D. Pobil, Eunil Park","doi":"10.1109/IMCOM51814.2021.9377421","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377421","url":null,"abstract":"Given that the concept of sharing economy is one of the widely-employed economic models in our society, users' satisfaction in sharing services is one of the important academic and industrial research topics for the success of such services. This study collects users' online reviews with ratings from Airbnb, one of the representative sharing services, and investigates effects of the following three components of user experience: users' perceived usability, usefulness, and affection. Our work compares the user experience in Airbnb between the United States and Hong Kong. The results of the multiple linear regression analysis indicate that affection (the United States) and usefulness (Hong Kong) show the greatest effects on the rating on Airbnb. Based on the findings, the implications with limitations are discussed.","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":"130087997","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/IMCOM51814.2021.9377409
Donghyun Kim, Jae-Min Cha, Seokju Oh, Jongpil Jeong
Maintenance of production equipment and controlling products quality through data analysis are the main issues of smart factory. During production, detected data for analysis is showing abnormal data more than normal data. Therefore, there is lots of energy consumption for analysis, cost, and saving of data. Edge Device which applied deep learning algorithm is able to solve this problem. In this paper, a framework for data filtering method before data analysis is proposed through Anomaly detection using single board computer (SBC). Using Nvidia Jetson nano and desktop computer to compare and analyze the two virtual environments to determine the framework of optimum anomaly data filtering. AnoGAN is a deep learning model utilized for anomaly detection.
{"title":"AnoGAN-Based Anomaly Filtering for Intelligent Edge Device in Smart Factory","authors":"Donghyun Kim, Jae-Min Cha, Seokju Oh, Jongpil Jeong","doi":"10.1109/IMCOM51814.2021.9377409","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377409","url":null,"abstract":"Maintenance of production equipment and controlling products quality through data analysis are the main issues of smart factory. During production, detected data for analysis is showing abnormal data more than normal data. Therefore, there is lots of energy consumption for analysis, cost, and saving of data. Edge Device which applied deep learning algorithm is able to solve this problem. In this paper, a framework for data filtering method before data analysis is proposed through Anomaly detection using single board computer (SBC). Using Nvidia Jetson nano and desktop computer to compare and analyze the two virtual environments to determine the framework of optimum anomaly data filtering. AnoGAN is a deep learning model utilized for anomaly detection.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"10 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":"129517432","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：