Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City最新文献

{"title":"Carpooling Adoption for Educational trips toward Sustainable Mobility in an Emerging Economy:: A Case Study of Thammasat University, Thailand","authors":"W. Lowe, M. Piantanakulchai","doi":"10.1145/3512576.3512668","DOIUrl":"https://doi.org/10.1145/3512576.3512668","url":null,"abstract":"Carpooling is emerging as a sustainable transport mode because of promising benefits in reducing carbon emissions, traveling costs, traffic congestion, etc. However, encouraging car drivers to offer carpooling services in developing countries is challenging due to no proper studies background. Therefore, this study investigated the determinants of carpooling adoption as drivers (not passengers) toward sustainable mobility in an emerging economy. The study used the primary dataset of 180 observations gathered at Thammasat University, Pathum Thani, Thailand. The sample data were analyzed using Structural Equation Modeling (SEM). The binary carpooling choice (i.e., offering and not offering) was used as the endogenous variable. The incentive attributes (hypothetical), sociodemographic characteristics, travel-related variables, and primary reasons for private car use were considered as the exogenous variables. The highlighted findings identified incentive attributes as potential determinants to incline car drivers to offer carpool rides. Female married and the 18–39-year group were more inclined to adopt carpooling than males, unmarried and the ≥40-year group, respectively. Household car ownership increases the likelihood of carpooling while motorcycle ownership does otherwise. Drivers who use private cars on account of privacy and non-availability of public transport are more inclined to offer carpool rides. Also, the study presented policy implications for carpooling adoption as drivers based on the multivariate statistical analysis. The findings enhanced the direction for carpooling adoption for educational trips toward sustainable mobility.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126271392","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}

{"title":"Multi-angle Dual-task Consistency for Semi-Supervised Medical Image Segmentation","authors":"Jing Li, Jiaqi Pu, Xiaogen Zhou, Haonan Zheng, Qinquan Gao, E. Xue, T. Tong","doi":"10.1145/3512576.3512587","DOIUrl":"https://doi.org/10.1145/3512576.3512587","url":null,"abstract":"Semi-supervised learning has shown its effectiveness in the field of medical image segmentation tasks, since it mitigates the heavy burden of obtaining abundant reliable annotations, which is scarce and time-consuming, by leveraging the available unlabeled data. In this paper, we propose a novel Multi-angle Dual-task Consistency Network (MDC-Net) for semi-supervised medical image segmentation. Particularly, our MDC-Net can be formulated as a model similar to the Mean Teacher with both employing exponential moving average (EMA). The difference is that we utilize one of the networks to augment unlabeled data, thus generating its pseudo labels and exploiting MixUp on both labeled and unlabeled data, whose outputs are then utilized as the inputs of another dual-task network based on region-based shape constraints and boundary-based surface mismatch. Finally, by jointly learning pseudo labels, the segmentation probability map and the signed distance map of the target, our framework not only overcomes the problem of incomplete segmentation caused by noise in pseudo labels, but also enforces geometric constraints and makes the model more robust. Experimental results on the public Left Atrium (LA) database show that our method achieves performance gains by incorporating unlabeled data and outperforms six state-of-the-art semi-supervised segmentation methods.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116971177","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}

{"title":"Skeleton-based Human Action Recognition by the Integration of Euclidean distance","authors":"Yi Gao, Zhaokun Liu, Xinmeng Wu, Guangyuan Wu, Jiahui Zhao, Xiaofan Zhao","doi":"10.1145/3512576.3512585","DOIUrl":"https://doi.org/10.1145/3512576.3512585","url":null,"abstract":"With the growing popularity of somatosensory interaction devices, human action recognition becomes more and more attractive in many application scenarios. Nowadays, it takes a long time for some behavior recognition methods to train a model. To solve the problem, this paper proposes a human skeleton model for human action recognition. The joint coordinates are extracted using OpenPose and the thermodynamic diagram, and then we extract partial features and overall features, as well as Euclidean distances between joints. All the data collected above makes up the motion features of independent video frames. What's more, we leverage Multilayer Perceptron (MLP) classifier to classify all the motion features. On the KTH and ICPR datasets, we test the accuracy of the mode verified by changing several parameters. When the image resolution is 320*240, weight is 12 and stride is 1, the highest accuracy rate of single-person behavior recognition is 0.821. When weight is 10 and stride is 1, the highest accuracy rate of multi-person behavior recognition is 0.812, and the high running speed enables the mode to be real-time.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126243167","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}

{"title":"Traffic Matrix Prediction with Attention-based Recurrent Neural Network","authors":"Maliang Zhang, Yingpeng Sang, Weizheng Li, Chaoxin Cai, Jinghao Huang","doi":"10.1145/3512576.3512594","DOIUrl":"https://doi.org/10.1145/3512576.3512594","url":null,"abstract":"Traffic matrix (TM) shows the traffic volume of a network. Therefore, TM prediction is of great significance for network management. Attention mechanism has been successful in many sub-domains of machine learning, such as computer vision and natural language processing, and it performs particularly well on time series data. In this work, we first introduce attention mechanisms into the traffic matrix prediction field by proposing an attention-based deep learning model for traffic matrix prediction. This model is composed of two parts, encoder and decoder. We use a recurrent neural network (RNN) architecture as the encoder and our decoder has an attention layer and a linear layer. Attention mechanism allows the model to have better memory ability, so the model can concentrate on those important data regardless of distance. We also reduce the time consumption of our model using GPU-based parallel acceleration. Finally, we evaluate the effectiveness of our model on a real world TM dataset, and the results show our implementations on the proposed model perform better than the baseline models.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"411 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114828918","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}

{"title":"Factors Influencing Spatial Deprivation of Urban Public Transit——The Perspective of Public Transit Resource Allocation","authors":"Yuanyuan Zhang, Chengkun Li, Zehui Chen","doi":"10.1145/3512576.3512660","DOIUrl":"https://doi.org/10.1145/3512576.3512660","url":null,"abstract":"Based on the allocation of public transit resources, the study firstly used the cluster analysis algorithm to classify the public transit deprivation level into four levels based on the accessibility of public transit. Then, a multivariate logistic regression model between public transit resource allocation and deprivation level was constructed and reversely tested, indicating that the model's accuracy in predicting the fairness level was as high as 76.52%. By using the model, an empirical study was conducted on the public transit deprivation of the downtown area in Guangzhou City. The results show that the public transit deprivation in Guangzhou is affected by the level of public transit resources, and it increases spatially from the center to the outside in a layer structure, with the northeast of the city presenting severe deprivation. With the decrease of station and line coverage and station service area coverage, the more public transit resources per capita, the lower the degree of public transit deprivation. The U-shaped relationship between the station and line occupancy and station occupancy and the intensity of traffic deprivation indicates that although the increase of both can alleviate traffic deprivation to a certain extent, the over-concentration of public transit resources will reduce its spatial allocation efficiency and lead to a decreased equity. The decreased location quotient within the coverage of 300m and 500m of the stations will aggravate the traffic deprivation.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124438998","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}

{"title":"Technology Management Framework for Smart University System in the Philippines","authors":"M. C. F. Raguro, A. Lagman, Ronaldo Juanatas","doi":"10.1145/3512576.3512642","DOIUrl":"https://doi.org/10.1145/3512576.3512642","url":null,"abstract":"In this study, the Smart University came out of the concept of smart cities by applying the principles of smart cities to the operation of university. The Smart University is a vision where the University, as a platform, provides foundational context data to deliver the university of the future. To deal with this reality, the researcher developed a framework for transforming a traditional university into a Smart University, which is more efficient, effective, and has more involvement from both students and teachers, all working together to accomplish the shared goal of improved learning. To achieve this objective, the researchers propose to develop a Technology Management Framework that will address issues and challenges to be considered in establishing and adopting a Smart University in the Philippines. The study will also measure the level of preparedness on Smart Universities among the students, teachers, university administrators, and IT consultant and practitioners that serve in different government agencies. Finally, the paper will also address adaptability of universities and to measure the Level of Smartness of Universities in Metro Manila. This study adopts a mixed-method approach that combines qualitative and quantitative research approaches. The authors also used the sequential exploratory design method. The researchers applied the Nominal Group Technique to acquire knowledge from the group of experts for the qualitative portion of the study. Cronbach's alpha is used by the authors for the designed survey instruments that are taken from the Nominal group. Cronbach's alpha is a tool used to evaluate the internal consistency, or reliability, of a collection of scale or test items. The researchers used the Friedman non-parametric hypothesis test for the Level of Smartness ranking. The outcome of the survey instrument uncovers the strength and weaknesses based on the Level of Smartness every university participant. The authors concluded that the developed Technology Management Framework for Smart University System in the Philippines is aligned with the literature and the available systems and applications. These standards are clustered in the three pillars and five criteria, which will guide the academic institutions on establishing Smart University. The three pillars are Technology Infrastructure, Educational Pedagogy, and Government Collaboration together with the five major criteria (Learning Environment, Educational Technology, Academic System, Governance, Health Services) and the application of a roadmap will support the success rate of Smart University in the Philippines. This leads to increasing the efficiency and responsiveness of the academic institution, holistic educational system, dynamic & safer academic community, and exceptional student experience.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129875235","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}

{"title":"Modeling the Mixed Traffic Flow with Cars and Trucks Near the Off-Ramp in Freeway Considering Differences of Leading Vehicles","authors":"Changlin Li, Wei Li, Yifei Tian, X. Dai","doi":"10.1145/3512576.3512670","DOIUrl":"https://doi.org/10.1145/3512576.3512670","url":null,"abstract":"In order to study the influence of truck operation on the traffic flow of highway bottleneck section, a model of mixed traffic flow of highway with different types of trucks was established. The sight height of truck and car drivers is different, and the longitudinal movement of cars is only influenced by the leading vehicle, while when the leading vehicle of the truck is a car, its following behavior is influenced by the double leading vehicle. Considering the difference of the leading vehicle of the car and the truck, different car-following models and lane changing models of the car and the truck are constructed. Numerical simulations were carried out by Matlab to analyze the effects of different types of trucks proportion on traffic congestion, driving speed and capacity in the off-ramp section of the highway. The results are also compared with those generated by the simulation using SUMO. The simulation results show that the increase of the proportion of truckswill aggravate the traffic congestion in the off-ramp section, and reduce the driving speed and capacity.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130206415","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}

{"title":"Traffic Status Identification Based On Clustering Algorithm","authors":"Z. Gong, Congyong Cao, Meng Chen","doi":"10.1145/3512576.3512654","DOIUrl":"https://doi.org/10.1145/3512576.3512654","url":null,"abstract":"In order to accurately identify the traffic state of the expressway, this paper preprocesses the ETC monitoring data of the expressway based on the traffic flow parameters of the expressway. A fuzzy C-means clustering model was established to cluster the traffic volume, time average vehicle speed and time occupancy rate data of specific road sections. In order to avoid outliers becoming cluster centers, the data density (DKC) value was used to improve the model. Taking the traffic volume, time average speed and time occupancy rate of a typical section of Suzhou Ring Expressway as an example, clustering calculation is performed to classify the traffic state of this section.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129192343","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}

{"title":"Investigating the Acceptance Model of Cloud Learning: MOOCs for Sustainability Usage in Higher Education Institutes","authors":"Supparang Ruangvanich, Pallop Piriyasurawong","doi":"10.1145/3512576.3512621","DOIUrl":"https://doi.org/10.1145/3512576.3512621","url":null,"abstract":"∗ This study’s objective was to understand better the psycholog-ical mechanisms underlying long-term participation in massive open online courses (MOOCs). The researchers proposed a research model that includes nine variables: content quality, cloud system quality, collaborative learning, knowledge assessment, perceived ease of use, perceived usefulness, satisfaction, habits, and sustainability usage, all of which have been extensively studied in the relevant literature. The study was undertaken in Thai MOOCs. The literature review was conducted using various online databases for the digital library. According to this study, MOOCs will be success-ful if the above conditions are followed. Furthermore, this research can assist MOOC instructors in improving the student experience in this virtual environment, MOOC providers in maintaining MOOCs, and universities in preparing MOOCs for use in blended classrooms.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"Suppl 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130027500","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}

{"title":"An analysis of Disaster Risk Suggestions using Latent Dirichlet Allocation and Hierarchical Dirichlet Process (Nonparametric LDA)","authors":"Ken Gorro, Glicerio A. Baguia, Moustafa F. Ali","doi":"10.1145/3512576.3512608","DOIUrl":"https://doi.org/10.1145/3512576.3512608","url":null,"abstract":"Qualitative data is part of the things that most social scientists would deal with. In this study, qualitative Disaster Risk Reduction suggestions were analyzed using topic modeling techniques. Latent Dirichlet allocation is one of the topic modeling that was utilized in this study. The ideal number of topic models being generated for LDA is 10 with a score of 530.1495. Hierarchical Dirichlet Process model was also used to get the topic models from the corpus. The HDP model generated 11 topic models with a log-likelihood score of -4.08997. The topic models being generated by the parametric LDA and non-parametric LDA are almost similar. To analyze the result of the topic models, open coding technique was utilized. The following narratives were the focus of the DRR responses: Solid waste management and improve drainage system, Relief and Emergency Plan and Early warning system and Disaster Preparedness.","PeriodicalId":278114,"journal":{"name":"Proceedings of the 2021 9th International Conference on Information Technology: IoT and Smart City","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121147237","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}