Youjung Ko, Insuk Hong, Hyunsoon Shin, Yoonjoong Kim
{"title":"Construction of a database of emotional speech using emotion sounds from movies and dramas","authors":"Youjung Ko, Insuk Hong, Hyunsoon Shin, Yoonjoong Kim","doi":"10.1109/INFOC.2017.8001672","DOIUrl":"https://doi.org/10.1109/INFOC.2017.8001672","url":null,"abstract":"In this study, an emotional speech database called Hanbat Emotional Database (HEMO) was constructed using movie and drama scenes in which emotion is abundantly expressed by professional actors. HEMO consists of 454 speech samples classified into seven emotion categories such as anger, happiness, sadness, disgust, surprise, fear, and neutral. In order to evaluate the performance of HEMO, consistent experiments were conducted based on HMM (Hidden Markov Model) and GMM (Gaussian Mixture Model) for both HEMO and the Berlin Emotional Speech Database (EMO). HEMO showed better results than EMO with a positive recognition rate of 78.89%.","PeriodicalId":109602,"journal":{"name":"2017 International Conference on Information and Communications (ICIC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124652821","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}
Sunil Kumar, M. G. Kibria, Sajjad Ali, M. Jarwar, I. Chong
{"title":"Smart spaces recommending service provisioning in WoO platform","authors":"Sunil Kumar, M. G. Kibria, Sajjad Ali, M. Jarwar, I. Chong","doi":"10.1109/INFOC.2017.8001686","DOIUrl":"https://doi.org/10.1109/INFOC.2017.8001686","url":null,"abstract":"In ubiquitous IoT environment, recommending services are getting popular in daily livings that depend on user identification, location, activity, situation and preferences. To provide scalable and dynamic solutions for smart spaces service features, Web of Objects facilitates real world object virtualization using semantic ontology. Cognitive functionalities in Web of Objects combines intelligence and analytics to create knowledge-based services and hence results in better service provisioning. This paper discusses the functional architecture of three levels on Web of Objects platform. Finally, a use case scenario for smart spaces has been studied.","PeriodicalId":109602,"journal":{"name":"2017 International Conference on Information and Communications (ICIC)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124780815","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":"A study on the fast system recovery: Selecting the number of surrogate nodes for fast recovery in industrial IoT environment","authors":"Soo-Yeon Lee, Tai M. Chung","doi":"10.1109/INFOC.2017.8001669","DOIUrl":"https://doi.org/10.1109/INFOC.2017.8001669","url":null,"abstract":"This paper is based on the previous research that selects the proper surrogate nodes for fast recovery mechanism in industrial IoT (Internet of Things) Environment which uses a variety of sensors to collect the data and exchange the collected data in real-time for creating added value. We are going to suggest the way that how to decide the number of surrogate node automatically in different deployed industrial IoT Environment so that minimize the system recovery time when the central server likes IoT gateway is in failure. We are going to use the network simulator to measure the recovery time depending on the number of the selected surrogate nodes according to the sub-devices which are connected to the IoT gateway.","PeriodicalId":109602,"journal":{"name":"2017 International Conference on Information and Communications (ICIC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123072384","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}
Q. Hong, N. N. Tuan, T. T. Quang, Dung Nguyen Tien, C. Le
{"title":"Deep spatio-temporal network for accurate person re-identification","authors":"Q. Hong, N. N. Tuan, T. T. Quang, Dung Nguyen Tien, C. Le","doi":"10.1109/INFOC.2017.8001673","DOIUrl":"https://doi.org/10.1109/INFOC.2017.8001673","url":null,"abstract":"Feature extraction is one of two core tasks of a person re-identification besides metric learning. Building an effective feature extractor is the common goal of any research in the field. In this work, we propose a deep spatio-temporal network model which consists of a VGG-16 as a spatial feature extractor and a GRU network as an image sequence descriptor. Two temporal pooling techniques are investigated to produce compact yet discriminative sequence-level representation from a sequence of arbitrary length. To highlight the effectiveness of the final sequence-level feature set, we use a cosine distance metric learning to find an accurate probe-gallery pair. Experimental results on the ilIDS-VID and PRID 2011 dataset show that our method is slightly better on one dataset and significantly better on the other than state-of-the-art ones.","PeriodicalId":109602,"journal":{"name":"2017 International Conference on Information and Communications (ICIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128962031","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}
Minh-Luan Tran, A. Nguyen, Quoc-Dung Nguyen, Tin Huynh
{"title":"A comparison study for job recommendation","authors":"Minh-Luan Tran, A. Nguyen, Quoc-Dung Nguyen, Tin Huynh","doi":"10.1109/INFOC.2017.8001667","DOIUrl":"https://doi.org/10.1109/INFOC.2017.8001667","url":null,"abstract":"Job recommender is a system that automatically returns a ranked list of suitable, prospective jobs for employees. It plays a significant role in connecting employees and employers. In order to choose a suitable algorithm to build the system, a comparison study of popular recommendation methods is conducted and reported in this paper. The experimental data crawled from vietnamworks.com, itviec.com and careerlink.vn. A subset includes 7623 jobs extracted for running experiment. There are totally 59 users who have joint in rating jobs as well as giving feedback to measure performance of different methods. The experimental results demonstrated that content based approach is outperform than other tradictional ones.","PeriodicalId":109602,"journal":{"name":"2017 International Conference on Information and Communications (ICIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128014125","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}