2017 2nd International Conference on Information Technology (INCIT)最新文献

{"title":"Impersonal smartphone-based activity recognition using the accelerometer sensory data","authors":"Therdsak Dungkaew, J. Suksawatchon, U. Suksawatchon","doi":"10.1109/INCIT.2017.8257856","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257856","url":null,"abstract":"Smartphone-based activity recognition focuses on identifying the current activities of a mobile user by employing the sensory data which are available on smartphones. A lightweight model and less inquiry users for true activities, are necessary for deploying the activity recognition on a mobile platform for identifying activities based on new sensory data in real time. In this paper, we propose a new smartphone-based activity recognition framework for evolving sensory data stream called ISAR. It stands for Impersonal Smartphone-based Activity Recognition. ISAR model is built using annotated sensory data from a panel of user as training data and are applied to the new users. Our new model is an offline and online phase. In offline phase, we propose a new method for finding the threshold value which used to distinguish between dormant activities and energetic activities. Only a set of the energetic activities are used to build a light-weight classifier model. In online phase, we introduce the recognition technique of unannotated streaming sensory data with different activities. The experimental results using real human activity recognition data have conducted and compared with STAR model in terms of the accuracy and time complexity. Our results indicates that ISAR model can perform dramatically better than STAR model. Moreover, ISAR can utilize better than STAR model in real situation, especially across different users and without inquiry users.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125369716","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 linked data approach to planning collaboration amongst local governments in Thailand","authors":"Lerluck Boonlamp","doi":"10.1109/INCIT.2017.8257850","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257850","url":null,"abstract":"This research focuses on developing a new framework for the Sub-district Administrative Organization (SAO) of local government in Thailand. The goal is to publish linked data amongst local governments which allows discovering, accessing and encouraging interoperability. In order to achieve efficient interoperability of information systems, linked data play an important role in relating data. Linked data use semantic web technologies to publish structured data on the web and set links between data. Structure data are encoded as RDF. Furthermore, the data model supports integration of data sources by a linking semantic vocabulary, which is an effective way of exchanging data on the web. We propose a new framework for Thai local government with linked data technology to relate data that was not previously linked to enable exposing, sharing, and connecting pieces of data, information, and knowledge on the semantic web using URLs, RDF, data model and ontology.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126346238","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":"CSDeep: A crushed stone image predictor based on deep learning and intelligently selected features","authors":"Phasit Charoenkwan, Natdanai Homkong","doi":"10.1109/INCIT.2017.8257857","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257857","url":null,"abstract":"In civil construction industry, different types of crushed stone are used as aggregate materials. As the prices of crushed stone depend on their types, the automated system that can examine their type is needed to avoid human mistakes. This study aims to propose a novel method for classifying 5 different classes of crushed-stone images in the dump-body of a truck. Remarkably, 4 classes are defined according to 4 types of crushed stone and the other class is the empty dump-body of a truck. We create a crushed-stone predictor called CSDeep based on a convolution neural network (CNN) and the generic texture-features such as Gabor wavelet, Haralick and Laws. A CNN is a backpropagation neural network with an effective image processing tool, i.e., convolutions. The generic texture features are used to provide additional information that is missed by CNN. The set of 2,500 and 500 images equally sampled from each class are used as training and test data, respectively. The optimal set of generic texture features are chosen by an inheritable biobjective combinatorial genetic algorithm. The proposed CSDeep achieves 89.00% of test accuracy. To the best of our knowledge, CSDeep is the first predictor for crushed-stone images taken by a digital camera. The results show that the combination of generic texture-features and CNN is suggested to enhance the performance of a deep learning model.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134387096","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 scalable and low-cost MQTT broker clustering system","authors":"Pongnapat Jutadhamakorn, Tinnapat Pillavas, V. Visoottiviseth, Ryousei Takano, J. Haga, Dylan Kobayashi","doi":"10.1109/INCIT.2017.8257870","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257870","url":null,"abstract":"This paper aims at building a scalable MQTT broker by combining low-cost board computers like Raspberry Pi and open source broker software. The MQTT broker can be used to exchange messages between devices and devices in term of publish/subscribe for create Internet of Things network. Nowadays people extremely interest in IoT not only in small room or home but expand to the big company which have a huge amount of IoT devices. Thus, we propose a scalable and low cost MQTT broker clustering which can implement easily but have high performance with a load balancer for a single entry point of MQTT messages and balance the message in clustering. We decide to use Raspberry Pi as it have low cost and can run linux OS with Docker and have enough spec for MQTT broker. This paper also shows the performance of the Raspberry Pi cluster and how to visualize the status of a computer cluster on SAGE2 wall.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132424095","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":"Enhancing comment Feedback classification using text classifiers with word centrality measures","authors":"Watchreewan Jitsakul, P. Meesad, S. Sodsee","doi":"10.1109/INCIT.2017.8257879","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257879","url":null,"abstract":"This paper presents a novelty of item's feedback classification in e-commerce systems. This proposed work is developed based on a combination between a text classifier and word centrality measures. Herein, the item's feedback means comments written by customers to the purchased items, which are classified into positive or negative comments. In this work, the suitable text classifier is selected from four major types of classification: Rule-based, Tree structure-based, Probability-based, and Learning-based, which are Conjunctive Rule, Random Forest, Bayesian Logistic Regression, and Support Vector Machine, respectively. In this work, the classifiers are used for identifying the feedbacks in the probability distribution value [0, 1]. On the other hand, items' feedbacks are also represented by a graph, which is presenting a relationship among words. As well as, centrality measures are applied to determine each contained word centrality, and finalize to a probability centrality in [0, 1]. Both probability distribution and probability centrality, here, are applied to classify the item's feedback to positive or negative comments. The simulation results showed that the proposed classification method was efficient to classify three benchmark datasets, compared to other existing approaches with an average of classification accuracy 80.9%.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129401978","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":"Review of Ethereum: Smart home case study","authors":"Yu Nandar Aung, T. Tantidham","doi":"10.1109/INCIT.2017.8257877","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257877","url":null,"abstract":"Nowadays, Internet of Things (IoT) plays a vital role in various domains, which are home, agricultural, healthcare, tourism, transportation and education. The more of its development, the more we need to consider about its security and privacy issues. In this paper, we consider smart home system (SHS) as a case study. SHS is an integration of home appliances together with sensors to get automatic operations of heating, lighting, air conditioning, home security, health care systems, etc. Moreover, SHS allows homeowner to monitor and perform appliances functions remotely at any instant time via the Internet. Due to the widespread availability and proliferation of the SHS, attackers can impersonate as a homeowner to steal important data (e.g., vital signs) for doing extortion and life threatening. Therefore, in this paper, we present an approach of private Blockchain implementation for SHS to cope of its privacy and security issues. We review Ethereum Blockchain packages for SHS according to its smart contract features for handling access control policy, data storage and data flow management.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114122816","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":"Clinical research on therapeutic effect of virtual reality technology on Broca Aphasia patients","authors":"Yaowen Zhang, Peirong Chen, Xin Li, G. Wan, Chunqing Xie, Xianjia Yu","doi":"10.1109/INCIT.2017.8257880","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257880","url":null,"abstract":"Objective: To explore the therapeutic effect of virtual reality technology on speech function of Broca Aphasia patients after stroke. Method: Eighteen patients with stroke were enrolled in the Rehabilitation Medicine Department, the Third Affiliated Hospital of Sun Yat-sen University from December 2016 to August 2017. The patients were divided into observation group and control group by random number table. Both groups were trained in speech function. The observation group received regular speech training for 20 minutes per day, Virtual Reality (VR) training for 20 minutes per day; the control group was given conventional speech training 40 minutes per day but the same training content with the observation group. And both groups of patients were treated for 5 days per week lasting for 4 weeks. CRRCAE was used to evaluate the language ability before and after treatment. The Boston Diagnostic Aphasia Examination, BDAE was used to assess the severity of aphasia. Bucco-facial-apraxia and speech apraxia Methods were used to assess the patient's state of bucco facial function and speech function. Result: There was no significant difference (P > 0.5) between the situations of two groups in general data, bucco-facial-apraxia and speech apraxia. Before treatment, the difference in CRRCAE and BDAE between the two groups is also not so big(P > 0.05). After 4 weeks of treatment, the severity of aphasia was improved in both groups (P < 0.05). Except computing ability, listening comprehension, repetition, expression, readout, reading, transcription, depiction and dictation were all improved (P < 0.01). And in noun repetition(P = 0.03), sentence repetition (P = 0.01), noun expression(P < 0.01), verb expression (P = 0.02), sentence expression (P < 0.01), comic expression (P = 0.01), enumeration (P = 0.03), verb readout(P = 0.04), verb reading(P < 0.01), sentence reading (P = 0.04), noun transcription (P = 0.02), sentence transcription (P = 0.048), verb depiction (P = 0.01) and so on, language ability of the observation group is significantly better than the control group. Conclusion: Virtual reality technology combined with speech function training can improve the language ability of patients with Broca Aphasia, and its improvement is better than the simple speech function training.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134456721","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":"Pinch simulation with haptic feedback for stroke rehabilitation: A pilot study","authors":"Pin-Hua Chiu, Si-Huei Lee, S. Yeh","doi":"10.1109/INCIT.2017.8257885","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257885","url":null,"abstract":"Stroke is a leading cause of long-term disability, and virtual reality (VR)-based stroke rehabilitation has been shown to be effective for increasing the motivation and functional performance of stroke patients. Although many patients regain most reach and grasp capabilities in their upper extremity function, recovery of the pinch skill remains incomplete for the majority of patients. In this study, an innovative VR-based pinch skill training and strengthening system using haptics simulation was developed for the long-term recovery of upper extremity motor function post stroke. Two subject tests were conducted. The first was a healthy subject test conducted with 30 participants to verify the system design and functionality, specifically emphasizing difficulty levels and behavior phases. The second was a pilot test conducted on two stroke patients to examine the feasibility and therapeutic effects of the proposed system. Upon completion of the pilot test, the results of clinical assessment showed that both participants were improved. Using synchronized kinematic and kinetic data, the participants' behavior time-history was reconstructed for behavior interpretation and motor activity analysis. Finally, user acceptance of the technology was high, indicating that the participants intended to continue using the proposed system for rehabilitation.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"51 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134536498","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 method of rehabilitation training for finger pair movement based on multi — Leap motions","authors":"Xiongyi Wei, Yanyan Huang, Zhengyu Wu, Chong Tang","doi":"10.1109/INCIT.2017.8257886","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257886","url":null,"abstract":"This Finger Pair Movement (FPM) is the key indicator for Stroke recovery. This paper presents a multi-Leap Motion-based training method for Finger Pair Movement (FPM) rehabilitation. This method first uses 3 Leap Motions to obtain the hand movement information and uses the Iterative Closest Points Algorithm (ICP) to register finger movements precisely from different angles, which could avoid the traditional obscured problem from the single angle. Then use the Self-Organizing Maps algorithm (SOM) to map the required 9 Finger Pair Movements. ICP algorithm obtains 3D point cloud from multiLeap Motions and completes data registration, which outputs high integrity three-dimensional spatial information of the hand joint skeleton. Using the SOM algorithm can solve the problem of obtaining data containing too much noise. The proposed method has been employed in clinical trials. The experimental results show that the proposed method has high efficiency, high error tolerance, and good performance.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121805239","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 comparative study of ensemble back-propagation neural network for the regression problems","authors":"Jesada Kajornrit, Piyanuch Chaipornkaew","doi":"10.1109/INCIT.2017.8257853","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257853","url":null,"abstract":"This paper proposes a comparative analysis of the ensemble back-propagation neural network for the regression tasks. The ensemble technique is objectively used to improve the accuracy of single back-propagation neural network. Such technique alleviates uncertain generalization of the trained network due to its random initial weight and bias values and noisy data. This comparison includes linear regression, back-propagation neural networks, support vector machine, k-nearest neighbor, ensemble voting and bagging techniques. Seven benchmark regression datasets were used for evaluation. The experimental results indicated that the voting and bagging ensemble techniques provided considerable improvement. In addition, continued from the previous work, this paper also applied ensemble techniques to predict monthly rainfall time series data and compared to the back-propagation neural network optimized by the genetic algorithm. The results showed that voting and bagging ensemble techniques as well as genetic algorithm outstandingly improved the performance of single back-propagation neural network.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124027895","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}