发布求助
文献互助 智能选刊 最新文献

2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)最新文献

筛选
英文 中文
Deep convolutional neural network classifier for travel patterns using binary sensors 基于二元传感器的深度卷积神经网络旅行模式分类器
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-08 DOI: 10.1109/ICAWST.2017.8256432
Munkhjargal Gochoo, Shing-Hong Liu, Damdinsuren Bayanduuren, Tan-Hsu Tan, Vijayalakshmi Velusamy, Tsung-Yu Liu
{"title":"Deep convolutional neural network classifier for travel patterns using binary sensors","authors":"Munkhjargal Gochoo, Shing-Hong Liu, Damdinsuren Bayanduuren, Tan-Hsu Tan, Vijayalakshmi Velusamy, Tsung-Yu Liu","doi":"10.1109/ICAWST.2017.8256432","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256432","url":null,"abstract":"The early detection of dementia is crucial in independent life style of elderly people. Main intention of this study is to propose device-free non-privacy invasive Deep Convolutional Neural Network classifier (DCNN) for Martino-Saltzman's (MS) travel patterns of elderly people living alone using open dataset collected by binary (passive infrared) sensors. Travel patterns are classified as direct, pacing, lapping, or random according to MS model. MS travel pattern is highly related with person's cognitive state, thus can be used to detect early stage of dementia. The dataset was collected by monitoring a cognitively normal elderly resident by wireless passive infrared sensors for 21 months. First, over 70000 travel episodes are extracted from the dataset and classified by MS travel pattern classifier algorithm for the ground truth. Later, 12000 episodes (3000 for each pattern) were randomly selected from the total episodes to compose training and testing dataset. Finally, DCNN performance was compared with three other classical machine-learning classifiers. The Random Forest and DCNN yielded the best classification accuracies of 94.48% and 97.84%, respectively. Thus, the proposed DCNN classifier can be used to infer dementia through travel pattern matching.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130739338","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}
引用次数: 8
Comparison of arterial stiffness between the dominant and non-dominant hands 优势手与非优势手动脉僵硬度的比较
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256456
Jia-Jung Wang, June-Der Li, Jhen-Yang Syu, Jia-Hao Li, Yu-An Shih, W. Tseng
{"title":"Comparison of arterial stiffness between the dominant and non-dominant hands","authors":"Jia-Jung Wang, June-Der Li, Jhen-Yang Syu, Jia-Hao Li, Yu-An Shih, W. Tseng","doi":"10.1109/ICAWST.2017.8256456","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256456","url":null,"abstract":"The goal of the study was to assess the peripheral arterial stiffness by using pulse wave velocity (PWV) in dominant and non-dominant hands. The study recruited fifty-eight subjects who were separated into Control group (N=29) and Exercise group (N=29). Pressure waves were in brachial and finger arteries were simultaneously measured with author-designed cuff pressure devices. PWV was calculated as the length from the upper arm cuff to finger cuff divided by the propagation time. In the 58 subjects, PWV (471±158 cm/sec) measured from the non-dominant hands was found to be significantly greater than that (444±147 cm/sec) in the dominant hands (p<0.05). Also, in the exercise group (N=29), their dominant hands had significantly smaller PWV (398±126 cm/sec) than non-dominant hands (425±130 cm/sec) (p<0.01). In summary, dominant rather than non-dominant hands have decreased arterial stiffness, mostly due to its frequent usage in daily life.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","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":"117342280","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}
引用次数: 0
Deep learning based personality recognition from Facebook status updates 基于Facebook状态更新的深度学习人格识别
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256484
Jianguo Yu, K. Markov
{"title":"Deep learning based personality recognition from Facebook status updates","authors":"Jianguo Yu, K. Markov","doi":"10.1109/ICAWST.2017.8256484","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256484","url":null,"abstract":"Many approaches have been proposed to automatically infer users personality from their social networks activities. However, the performance of these approaches depends heavily on the data representation. In this work, we apply deep learning methods to automatically learn suitable data representation for the personality recognition task. In our experiments, we used the Facebook status updates data. We investigated several neural network architectures such as fully-connected (FC) networks, convolutional networks (CNN) and recurrent networks (RNN) on the myPersonality shared task and compared them with some shallow learning algorithms. Our experiments showed that CNN with average pooling is better than both the RNN and FC. Convolutional architecturewith average pooling achieved the best results 60.0±6.5%.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"35 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":"125040020","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}
引用次数: 32
A dynamic industry-related analysis on investment, energy consumption and CO2 emissions 投资、能源消耗和二氧化碳排放的动态行业分析
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256479
Chung-Huang Huang, Cheng-Yih Hong, Jian-Fa Li
{"title":"A dynamic industry-related analysis on investment, energy consumption and CO2 emissions","authors":"Chung-Huang Huang, Cheng-Yih Hong, Jian-Fa Li","doi":"10.1109/ICAWST.2017.8256479","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256479","url":null,"abstract":"In the present study, we employs a dynamic industry-related model to estimate the economic spillover effect and the CO2 emissions from both R&D of government and private equipment investment. The present study attempts to measure (1) the investment multiplier of government R&D and private equipment investment, (2) the difference in the employment creation effect of government R&D and private equipment investment and (3) The CO2 emission of both governmental R&D and private equipment investment, and further to propose the direction of Taiwan's industrial development.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"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":"123769149","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}
引用次数: 0
Performance evaluation of the universal filtered multi-carrier communications under various multipath fading propagation conditions 通用滤波多载波通信在各种多径衰落传播条件下的性能评价
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256502
Hsuan-Fu Wang, Yung-Fa Huang
{"title":"Performance evaluation of the universal filtered multi-carrier communications under various multipath fading propagation conditions","authors":"Hsuan-Fu Wang, Yung-Fa Huang","doi":"10.1109/ICAWST.2017.8256502","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256502","url":null,"abstract":"The Universal filtered multi-carrier (UFMC) which filtering successive sub-bands for supporting sliced spectrum is one of the enabling approaches for the fifth generation (5G) mobile networks. The UFMC system not only provides a flexibility of filtering arbitrary number of subcarriers to diminish out of band (OoB) leakage, but also maintains the orthogonality between subbands and subcarriers inside one sub-band at the same time. The simulation is conducted that utilizing the physical downlink shared channel (PDSCH) processing of the long-term evolution (LTE) system with the UFMC and orthogonal frequency-division multiplexing (OFDM) schemes under various multipath fading propagation conditions.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"92 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":"122941784","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}
引用次数: 3
An efficient algorithm for web service selection based on local selection in large scale 基于局部选择的大规模web服务选择算法
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256443
Sheng Zhang, Incheon Paik
{"title":"An efficient algorithm for web service selection based on local selection in large scale","authors":"Sheng Zhang, Incheon Paik","doi":"10.1109/ICAWST.2017.8256443","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256443","url":null,"abstract":"Nowadays, services are published on the Internet is growing explosively, it causes that it is difficult to select the web services which have the same function to satisfy the users' requirements. (Quality of Service) QoS mainly includes cost, response time, availability, etc. It is also knew to be the most important non-functional standard in service selection. So how to select a best Web service on real-time for large services, it will become very important. Many researchers have adopted various heuristic and meta-heuristic algorithm to solve the problem of web service selection based on QoS. One of the algorithms is the genetic algorithm. But genetic algorithm doesn't have a good adaptability, that means when the number of services which are expected to mutation is so many, it often needs more search space. So in this paper, I will introduce the label method to select “good” services, then by genetic algorithm to get the best services selection.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"2 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":"129859298","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}
引用次数: 2
A user's intention detection method for smart walker 一种用于智能步行机的用户意图检测方法
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256477
Wen-Chang Cheng, Yan-Zhi Wu
{"title":"A user's intention detection method for smart walker","authors":"Wen-Chang Cheng, Yan-Zhi Wu","doi":"10.1109/ICAWST.2017.8256477","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256477","url":null,"abstract":"To assist home care for the elderly, we've finished a smart walker in previous study, with the features including destination track navigation, obstacle detection, self-positioning, follow-up, and wireless inductive charging. In this study, we further finish the user's intention detection function on the smart walker to control the smart walker. We install 3 pressure sensors on both sides of smart walker handles respectively to extract the user's force application, which are taken as input signal. Through AdaBoost classifier, it finishes input signal recognition and controls of the smart walker moving forward/backward directly. The user doesn't need to press the switch or click on the panel, but apply force on the handle directly, which makes the operation easier. The experiment validates that the accuracy can achieve higher than 98%, which can simplify the operation effectively and achieve the practical purpose.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","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":"128747536","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}
引用次数: 7
Hardware implementation of double basis multiplier using TMVP approach over GF (2m) 双基乘法器在GF (2m)上的TMVP硬件实现
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256506
Shu-Xia Dong, Jeng-Shyang Pan, Chun-Sheng Yang, Chiou-Yng Lee
{"title":"Hardware implementation of double basis multiplier using TMVP approach over GF (2m)","authors":"Shu-Xia Dong, Jeng-Shyang Pan, Chun-Sheng Yang, Chiou-Yng Lee","doi":"10.1109/ICAWST.2017.8256506","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256506","url":null,"abstract":"Finite field multiplication plays a important roles in the applications of elliptic curve cryptography. In this paper, we use PB and modified polynomial basis(MPB) define a double basis multiplication, where MPB is transformed by PB when F(x) = xm + xn + 1, n ≥. m/2 We find that the double multiplication can transformed into Toeplitz matrix vector produc-t(TMVP). To reduce time and space complexities, we recursively use two-way TMVP approach calculate the product of double basis multiplication. We respectively implement shifted addition algorithm and TMVP approach in hardware chip FPGA Kintex7-xc7k325T. The proposed structure can obtain significantly lower area-delay product.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","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":"129803495","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}
引用次数: 1
Embedding of MRC in TM to increase the security for IoT technologies 在TM中嵌入MRC，提高物联网技术的安全性
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256445
J. Chen, Deng Chuang
{"title":"Embedding of MRC in TM to increase the security for IoT technologies","authors":"J. Chen, Deng Chuang","doi":"10.1109/ICAWST.2017.8256445","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256445","url":null,"abstract":"Recently, the IoT (internet of things) still does not have global policies and standards to govern the interaction and the development of applications. There are huge of security issues relevant to the application layer of IoT becoming very urgent. On the other hand, it is important for addressing the development of security algorithm to protect the IoT system from malicious attack. The service requesters must pay attention to the data how will be used, who and when to apply, even they must have tools to control what data want to be disclosed. In this article, a fusion diversity scheme adopting MRC (maximum ratio combining) scheme with TM (trust management) security algorithm is proposed. In MRC stage, specified parameters first extracted and before combined with the control information they weighted by one estimation value. The fused information forward to the upper layer of IoT technologies in succession after the combination is completed. The simulation results from experiments deployed with physical assessment show that the security has more reliability after the MRC scheme fused into the TM procedure.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"54 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":"129841520","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}
引用次数: 1
The large-signal SFG model of DC-DC buck-boost converters DC-DC降压升压变换器的大信号SFG模型
2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) Pub Date : 2017-11-01 DOI: 10.1109/ICAWST.2017.8256501
Li-Chun Liao, Kuo-Wei Chien
{"title":"The large-signal SFG model of DC-DC buck-boost converters","authors":"Li-Chun Liao, Kuo-Wei Chien","doi":"10.1109/ICAWST.2017.8256501","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256501","url":null,"abstract":"This paper introduced the switching flow-graph (SFG) modeling technique for DC-DC switching converters. Based on the concept of virtual switching functions, the large-signal SFG models of DC-DC switching converters can be developed easily without complex mathematics. In this study, the large-signal SFG model of a basic buck-boost converter was implemented to explain the modeling procedure. By establishing the large-signal SFG model in MATLAB/SIMULINK, the circuit's dynamic behavior can be easily observed. In comparison with the experimental results and PSPICE simulation results, it demonstrates the SFG model can reveal some characteristics of buck-boost converters.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"255 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":"133931374","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}
引用次数: 0
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信