Kanokwan Rungsuptaweekoon, V. Visoottiviseth, Ryousei Takano
{"title":"Evaluating the power efficiency of deep learning inference on embedded GPU systems","authors":"Kanokwan Rungsuptaweekoon, V. Visoottiviseth, Ryousei Takano","doi":"10.1109/INCIT.2017.8257866","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257866","url":null,"abstract":"Deep learning inference on embedded systems requires not only high throughput but also low power consumption. To address this challenge, this paper evaluates the power efficiency of image recognition with YOLO, a real-time object detection algorithm, on the latest NVIDIA embedded GPU systems: Jetson TX1 and TX2. For this evaluation, we deployed the Low-Power Image Recognition Challenge (LPIRC) system and integrated YOLO, a power meter, and target hardware into the system. The experimental results show that Jetson TX2 with Max-N mode has the highest throughput; Jetson TX2 with Max-Q mode has the highest power efficiency. These findings indicate it is possible to adjust the trade-off relationship of throughput and power efficiency in Jetson TX2. Therefore, Jetson TX2 has advantages for image recognition on embedded systems more than Jetson TX1 and a PC server with NVIDIA Tesla P40.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"57 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":"116292797","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}
J. Mitrpanont, Jaruwan Phandhu-fung, Nantanut Klubdee, Supanat Ratanalaor, Teeranan Mitrpanont
{"title":"iCare-stress: An integrated mental health software","authors":"J. Mitrpanont, Jaruwan Phandhu-fung, Nantanut Klubdee, Supanat Ratanalaor, Teeranan Mitrpanont","doi":"10.1109/INCIT.2017.8257889","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257889","url":null,"abstract":"Not only the psychiatric problem is complicated but screening and diagnosing processes also consume much time to get better treatment. Currently, there is a scarce number of psychiatrists and tools for helping people to assess and manage their level of anxiety and depression. This research extended our previous work on detecting stress using brainwave and neurofeedback [14] to invent an Integrated Mental Health Software tool for early screening, detection, diagnosis, and early treatment mobile application called “Intelligent Caring System for Stress” or “iCare-Stress”. Based on the expert's recommendation, iCare-Stress uses the set of most efficient and evidence-based screening tools which are General Health Questionnaire (GHQ), Patient Health Questionnaire-4 (PHQ-4), Generalized Anxiety Disorder-7(GAD-7), and Patient Health Questionnaire-9 (PHQ-9). Moreover, the psychoeducation of the basic knowledge of diseases and how to handle them by using Cognitive Behavioral Therapy (CBT) is provided. This work proposed the iCare-Stress system architecture and its prototype. The fundamental usability test has been done by the medical and non-medical testers and the result shows a high satisfactory level from both groups. The ultimate goal of iCare-Stress aims to help people to understand the psychiatric problem early and a timely diagnosis would be done to result in better treatment outcome which will reduce effects to both individual and others.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"26 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":"124183877","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}
Chanoksuda Wongvises, A. Khurat, Doudou Fall, S. Kashihara
{"title":"Fault tree analysis-based risk quantification of smart homes","authors":"Chanoksuda Wongvises, A. Khurat, Doudou Fall, S. Kashihara","doi":"10.1109/INCIT.2017.8257865","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257865","url":null,"abstract":"A smart home is a new enabling innovative appliance domain that is developed from the rapid growth of the Internet of Things. Despite its popularity and evident usefulness for human beings, smart homes have numerous security issues that originate from the heterogeneous, wide-scale and complex structure of the Internet of Things. It is obvious that a risk assessment is needed in order to ensure the security of smart homes. We propose a security risk quantification technique that permits to have a measure of the level of security of a given smart home based on the ‘things’ that it is composed of. Our method is based on Fault Tree Analysis which is the de-facto tool used in mission-critical systems. At first, we generated an exhaustive security tree based on the general architecture of a smart home. Afterwards, we evaluated our proposal in a use case of successful attacks on a light bulb system that functions through the ZigBee protocol. We were able to demonstrate that the risk of a successful attack in that system is very high given the same conditions.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"9 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":"121603723","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 using Python vs Weka on dialysis data analysis","authors":"J. Mitrpanont, Wudhichart Sawangphol, Thanita Vithantirawat, Sinattaya Paengkaew, Prameyuda Suwannasing, Atthapan Daramas, Yi-Cheng Chen","doi":"10.1109/INCIT.2017.8257883","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257883","url":null,"abstract":"Health data has been drastically increasing in capacity and variety. Due to large and complex collection of datasets, it is difficult to process data using traditional data processing techniques. Machine Learning techniques, such as KNN and Naïve Bayes, have been used. Python and Weka are tools that are widely used in the field of data analytics. Therefore, this paper gives the comprehensive comparison between both tools together with some machine learning algorithms on data analytic of Dialysis Dataset. The results show that using Python provides the better performance in term of correct/incorrect instances, precision, and recall.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"64 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":"116927988","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 Isarn dialect HMM-based text-to-speech system","authors":"Pongsathon Janyoi, Pusadee Seresangtakul","doi":"10.1109/INCIT.2017.8257873","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257873","url":null,"abstract":"This paper presents a statistical parametric text-to-speech system for the Isarn language, which is a regional dialect of Thai. The features of speech, which consist of Mel-cepstrum and fundamental frequencies, were modelled by the Hidden Markov Model (HMM). Synthetic speech is generated by converting the input text to context-dependent phonemes. Speech parameters are generated from the trained HMM models, according to the context-dependent phonemes. The parameters produced are then synthesized through a speech vocoder. In order to evaluate the intelligibility and naturalness of the proposed system, we conducted a listening test with 20 native speakers. The results indicated a mean opinion score (MOS) of the proposed system of 3.49. The word error rates (WER) within the unpredictable and predictable sentences of the proposed system were 4.28% and 0.84%, respectively.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"17 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":"126762992","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 cloud technology adoption in Australian organisations","authors":"Prasanna Balaaooriya, S. Wibowo, Marilyn A. Wells","doi":"10.1109/INCIT.2017.8257858","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257858","url":null,"abstract":"The purpose of this paper is to investigate the relevant factors including security, perceived usefulness, and perceived ease of use affect employee's behavioral and adoption intentions of Cloud technology in organisations. This study was carried out using the quantitative research methodology based on a survey distributed to information technology (IT) professionals in Australia. The survey questionnaire was developed based 6 hypotheses and 13 indicator variables. Around 220 valid responses were received and analyzed by adopting a two-tier approach consisting of (1) confirmatory factor analysis to confirm the reliability and validity of the latent variables, and (2) analysis of the structural model to confirm or reject the hypothesis. The finding of this study indicates that the hypotheses that have been developed are valid and can be adopted in an organisation. This study has found that cyber attacks and Cloud reliability factors are insignificant and have no affects in the Cloud adoption. Furthermore, this study suggests that approximately 37 % of other factors which are not covered in this study need to be considered during its adoption.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"248 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":"115790083","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":"Transfer learning based quantitative assessment model of upper limb movement ability for stroke survivors","authors":"Lei Yu, Jiping Wang, Liquan Guo, Qing Zhang, Peng Li, Yuanyuan Li, Xianjia Yu, Yanyan Huang, Zhengyu Wu","doi":"10.1109/INCIT.2017.8257874","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257874","url":null,"abstract":"Stroke survivors often suffer from movement disability. The accurate assessment of their movement function is an important part of rehabilitation therapy and is the premise of making individualized movement prescriptions. Many previous studies have shown that inertial measurement unit (IMU), which contains accelerometer, gyroscope, and magnetometer, etc., can be used to quantitatively assess the movement function of stroke survivors. However, the assessment results can be influenced by sensor placement. To solve this problem, this paper proposed a novel method which combines random forest and transfer learning algorithm. The experimental results showed that by using the proposed method, the traditional quantitative assessment models established at one sensor placement can be easily transferred to adapt to other sensor placements. In other words, a quantitative assessment model that is free of sensor placement can be achieved.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"25 9-10 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":"127183154","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":"Fair payoff distribution in multiagent systems under Pareto optimality","authors":"Thananchai Khamket, Chattrakul Sombattheera","doi":"10.1109/INCIT.2017.8257861","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257861","url":null,"abstract":"This research proposes a set of algorithms to compute fair payoff distribution among agents in service composition domain based on their contribution. In our system, intelligent agents, representing service providers, negotiate among themselves and form composite services to satisfy multiple-objective requirements. The quality of service for each objective is measured in term of degree of satisfaction. The overall quality of service is achieved by maximizing requesters satisfaction on all objectives according to Pareto optimality. We then deploy Shapley Value concept for fair payoff distribution among agents based on their contributions to the requesters optimal satisfaction. Since the computational complexity for Shapley Value is exponential, we are interested in investigating how well the algorithms for computing payoff perform. We found that on a typical computer, the algorithm can cope with around 20 agents with reasonable computational time.","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":"127973461","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":"Energy efficient greedy forwarding method over MANET based on three-hop information","authors":"Bumrungwong Punsapach, P. Phoummavong, H. Ishii","doi":"10.1109/INCIT.2017.8257855","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257855","url":null,"abstract":"This paper proposes a method that can reduce the energy consumption of battery-driven nodes over MANET by modifying location aided greedy forwarding protocol based on considering information of three-hop away nodes. Our approach determines the suitable path to make sure the path will consume as low energy as it can be. Our algorithm can switch relay nodes by considering the number of hops that are located between source and destination to fulfill the minimum energy consumption and prolong network lifetime. We compare our approach with existing algorithms through computer simulation and analysis. The simulation results show that our approach can achieve lower energy.","PeriodicalId":405827,"journal":{"name":"2017 2nd International Conference on Information Technology (INCIT)","volume":"14 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":"126764607","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":"Extracting significant features based on candlestick patterns using unsupervised approach","authors":"Seksan Sangsawad, C. Fung","doi":"10.1109/INCIT.2017.8257862","DOIUrl":"https://doi.org/10.1109/INCIT.2017.8257862","url":null,"abstract":"This paper proposes algorithms for the extraction of features from candlestick patterns for technical analysis of share indices. The significant features consist of: the direction of candlestick, the gap between CLOSE and OPEN price of two candlesticks, the body level of current and previous candlesticks, and the length of the candlesticks. K-Means clustering approach is applied for solving the unclearly defined length of Upper Shadow, Body and Lower Shadow. The Thai SET index OHLC data from 1990 to 2017 are used as the experimental dataset. The results show the similarity between the candlestick chart from raw data and decoding data, which is applied by the proposed algorithms. The output result from the approach can be used as the input to other machine learning methods such as Artificial Neuron Networks, Reinforcement Learning, or Content Based Image Retrieval (CBIR).","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":"129688226","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}