Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256514
J. Klomjit, A. Ngaopitakkul, B. Sreewirote
This paper proposes comparison mother wavelets for fault classification on hybrid transmission line systems. Hybrid system consists of overhead line and underground cable of 115 kV. ATP/EMTP software has been used for generating fault signals. Then it varies location of fault, fault type and angle. Current signals and zero sequence are analyzed by Discrete Wavelet Transform (DWT) in MATLAB software. DWT decomposes high frequency components from fault signals. Coefficient in scale 1 has been decomposed from Mother Wavelets such as Daubechies (db), Symlets (sym), Biorthogonal (bior) and Coiflets (coif). The coefficient for any mother wavelet has same behavior but different value. Design algorithm for fault classification and compare the result. Therefore, comparison of mother wavelet for fault classification is important to provide the high accuracy. Daubechies (db) can give accuracy more than any mother wavelet.
{"title":"Comparison of mother wavelet for classification fault on hybrid transmission line systems","authors":"J. Klomjit, A. Ngaopitakkul, B. Sreewirote","doi":"10.1109/ICAWST.2017.8256514","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256514","url":null,"abstract":"This paper proposes comparison mother wavelets for fault classification on hybrid transmission line systems. Hybrid system consists of overhead line and underground cable of 115 kV. ATP/EMTP software has been used for generating fault signals. Then it varies location of fault, fault type and angle. Current signals and zero sequence are analyzed by Discrete Wavelet Transform (DWT) in MATLAB software. DWT decomposes high frequency components from fault signals. Coefficient in scale 1 has been decomposed from Mother Wavelets such as Daubechies (db), Symlets (sym), Biorthogonal (bior) and Coiflets (coif). The coefficient for any mother wavelet has same behavior but different value. Design algorithm for fault classification and compare the result. Therefore, comparison of mother wavelet for fault classification is important to provide the high accuracy. Daubechies (db) can give accuracy more than any mother wavelet.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"204 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":"131543367","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256516
Kotaro Nakano, B. Chakraborty
Human activity recognition (HAR) from time series sensor data collected by low cost inertial sensors attached to small portable devices like smartphones are increasingly gaining attention in various fields especially for health care, medical, millitary and security applications. The need for efficient time series data analysis for recognition of human activities has enhanced research efforts in this area. For correct recognition of human activities, efficient feature selection from the time series data is important. In this work an approach for dynamic feature extraction from time series human activity data is proposed and classification results with dynamic features and static features are compared. The efficiency of dynamic features over static features are noted by simulation experiments with benchmark data set with different classifiers available in machine learning domain. Experiments are also done with convolutional neural networks(CNN) for activity recognition using extracted dynamic features. It is found that CNN provides better recognition accuracy for dynamic activity recognition with dynamic features compared to conventional classifiers such as multilayer perceptron (MLP), support vector machine(SVM) or k-nearest neighbour(KNN) though it takes higher computational time and memory resources.
{"title":"Effect of dynamic feature for human activity recognition using smartphone sensors","authors":"Kotaro Nakano, B. Chakraborty","doi":"10.1109/ICAWST.2017.8256516","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256516","url":null,"abstract":"Human activity recognition (HAR) from time series sensor data collected by low cost inertial sensors attached to small portable devices like smartphones are increasingly gaining attention in various fields especially for health care, medical, millitary and security applications. The need for efficient time series data analysis for recognition of human activities has enhanced research efforts in this area. For correct recognition of human activities, efficient feature selection from the time series data is important. In this work an approach for dynamic feature extraction from time series human activity data is proposed and classification results with dynamic features and static features are compared. The efficiency of dynamic features over static features are noted by simulation experiments with benchmark data set with different classifiers available in machine learning domain. Experiments are also done with convolutional neural networks(CNN) for activity recognition using extracted dynamic features. It is found that CNN provides better recognition accuracy for dynamic activity recognition with dynamic features compared to conventional classifiers such as multilayer perceptron (MLP), support vector machine(SVM) or k-nearest neighbour(KNN) though it takes higher computational time and memory resources.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"20 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":"130907916","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256468
Yi-Chi Tsai, Cheng-Yih Hong
It has been an important task for business and individuals to make financial investments on stock market in order to wisely extend possible income sources. Such investments require precise timely decision and highly awareness of market changes at all time. Many well-known pricing models have already been proposed by different learnt researchers to explain the rationality between stock price and the covalent factors. These models were meant to assist information receivers to adjust their holding of stocks with reasonable pricing strategy and make wise financial decision timely. Since any newly entered information in the market shall be digested and cause stock price movement. By assuming that the stock market possesses sufficient efficiency to adjust stock price to the equilibrium status, a prediction made prior to such movement would be regarded possible. This paper has constructed a GPLAB financial customized prototype system and demonstrated certain accuracy in the forecast of stock price movements in TWSE (Taiwan Stock Exchange). The empirical study reveals that the system possesses a fair prediction ability of stock price movement in a random chosen period and a bear market period. Under certain restrictions that this model may serve as an early stock price changes awareness system. Such awareness may provide investors opportunity to adjust stock holding strategy timely. This study also believes the accuracy of forecast could have been further improved with the assistance of other tools such as deep learning and neuron network. The potential of genetic algorism application in the field of financing decisions could have also been further accomplished in the future.
{"title":"The application of evolutionary approach for stock trend awareness","authors":"Yi-Chi Tsai, Cheng-Yih Hong","doi":"10.1109/ICAWST.2017.8256468","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256468","url":null,"abstract":"It has been an important task for business and individuals to make financial investments on stock market in order to wisely extend possible income sources. Such investments require precise timely decision and highly awareness of market changes at all time. Many well-known pricing models have already been proposed by different learnt researchers to explain the rationality between stock price and the covalent factors. These models were meant to assist information receivers to adjust their holding of stocks with reasonable pricing strategy and make wise financial decision timely. Since any newly entered information in the market shall be digested and cause stock price movement. By assuming that the stock market possesses sufficient efficiency to adjust stock price to the equilibrium status, a prediction made prior to such movement would be regarded possible. This paper has constructed a GPLAB financial customized prototype system and demonstrated certain accuracy in the forecast of stock price movements in TWSE (Taiwan Stock Exchange). The empirical study reveals that the system possesses a fair prediction ability of stock price movement in a random chosen period and a bear market period. Under certain restrictions that this model may serve as an early stock price changes awareness system. Such awareness may provide investors opportunity to adjust stock holding strategy timely. This study also believes the accuracy of forecast could have been further improved with the assistance of other tools such as deep learning and neuron network. The potential of genetic algorism application in the field of financing decisions could have also been further accomplished in the future.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"49 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":"124391889","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256464
F. Chao, Chung-Shun Feng, Boxiu Fanjiang, Chang-Liang Sun
In this study, authors propose the modified design Jigsaw with placed QR code at the back of the card for the elderly with Dementia. Puzzle and App designed to complement each other for Nostalgia-based support of old. Image and text are utilized to trigger previous memory those bring out shared experience from the patient. By using suitable trigger elements and group sharing, one can enhance the memory recall experience. We can divided the procedure of rice dumpling preparation and make in sequential step. First, cards are shuffled, and the elderly are asked to sort these cards to right sequence. QR scanner has modified for unstable hand member. For healthy old, the puzzle for group users provided with transparent display wall and tandem rod. In multiple theme scenarios, the different group of object making steps mixed, the player need select cards that related to a specific group. Then, one need arrange those cards in proper sequence. The qualitative testing results shown elderly enjoy the activities; participants actively talked about experiences. Those recording verified the effectiveness of the proposed method.
{"title":"Design Jigsaw puzzle and app for Nostalgia-based support on elderly with Dementia","authors":"F. Chao, Chung-Shun Feng, Boxiu Fanjiang, Chang-Liang Sun","doi":"10.1109/ICAWST.2017.8256464","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256464","url":null,"abstract":"In this study, authors propose the modified design Jigsaw with placed QR code at the back of the card for the elderly with Dementia. Puzzle and App designed to complement each other for Nostalgia-based support of old. Image and text are utilized to trigger previous memory those bring out shared experience from the patient. By using suitable trigger elements and group sharing, one can enhance the memory recall experience. We can divided the procedure of rice dumpling preparation and make in sequential step. First, cards are shuffled, and the elderly are asked to sort these cards to right sequence. QR scanner has modified for unstable hand member. For healthy old, the puzzle for group users provided with transparent display wall and tandem rod. In multiple theme scenarios, the different group of object making steps mixed, the player need select cards that related to a specific group. Then, one need arrange those cards in proper sequence. The qualitative testing results shown elderly enjoy the activities; participants actively talked about experiences. Those recording verified the effectiveness of the proposed method.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"37 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":"124535414","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256453
Ching-Ming Lai, J. Teh, Yu-Huei Cheng
The objective of this paper is to propose an active ripple filter (ARF) for eliminating the double-line-frequency (DLF) current ripple of a single-phase DC/AC conversion system. The proposed ARF and its control strategies can not only prolong the usage life of battery energy device but also improve the DC/AC system performance. At first, the phenomena of DLF current ripple and the operation principle of the ARF are illustrated. Then, steady-state analysis, small-signal model and control loop design of the ARF circuit architecture are derived. The proposed control system structure includes: (1) a current control loop to provide the excellent ripple cancelling performance on the output of the battery energy device; (2) a voltage control loop for the high-side capacitor voltage of ARF circuit to achieve good steady-state and transient-state responses; (3) a voltage feed-forward control loop for the low-side voltage of ARF circuit to cancel the voltage fluctuation caused by the instability of the battery energy device. Finally, the feasibility of proposed concept can be verified by the system simulation, and the results show that the low DLF current ripple can be achieved.
{"title":"An efficient active ripple filter for use in single-phase DC-AC conversion system","authors":"Ching-Ming Lai, J. Teh, Yu-Huei Cheng","doi":"10.1109/ICAWST.2017.8256453","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256453","url":null,"abstract":"The objective of this paper is to propose an active ripple filter (ARF) for eliminating the double-line-frequency (DLF) current ripple of a single-phase DC/AC conversion system. The proposed ARF and its control strategies can not only prolong the usage life of battery energy device but also improve the DC/AC system performance. At first, the phenomena of DLF current ripple and the operation principle of the ARF are illustrated. Then, steady-state analysis, small-signal model and control loop design of the ARF circuit architecture are derived. The proposed control system structure includes: (1) a current control loop to provide the excellent ripple cancelling performance on the output of the battery energy device; (2) a voltage control loop for the high-side capacitor voltage of ARF circuit to achieve good steady-state and transient-state responses; (3) a voltage feed-forward control loop for the low-side voltage of ARF circuit to cancel the voltage fluctuation caused by the instability of the battery energy device. Finally, the feasibility of proposed concept can be verified by the system simulation, and the results show that the low DLF current ripple can be achieved.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"49 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":"114754411","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256420
R. Oka
In this talk, we focus on recognition of static images, motion images from a video, and speech waves spoken by simultaneously multiple speakers. The necessary size of data for learning depends on algorithms for recognizing patterns. Real world data of static images, motion images, and speech waves includes many kinds of problems to be solved for their recognition. The most important one is the separation of segmentation and recognition in both time and space domains as well as overcoming their non-linear variations of these patterns. The segmentation problem is strongly coupled with the recognition problem. Without segmentation, recognition is impossible and vice versa. We need to create a sophisticated algorithm for decoupling of the two. If the recognition algorithm itself can also solve both the problems of segmentation and overcoming problem of non-linear variations of these patterns in the inside process of recognition, big data is not required for learning. On the other hand, deep learning is requiring big data of segmented samples for storing them in the form of connection weights among nodes of multi-layer. Deep learning is basically based on the segmentation of patterns in both learning and recognition stages. We propose two algorithms of matching. The one is called two-dimensional continuous dynamic programming (2DCDP) for spatial segmentation-free recognition of static images. An expanded version of 2DCDP called incremental two-dimensional continuous dynamic programming (I2DCDP) can carry out time segmentation-free and speaker-independent recognition of a single speech wave spoken by multiple speakers without speech separation. The other one is called time-space continuous dynamic programming (TSCDP) for both time segmentation-free and location-free recognition of complex human/object motions from a video even in the moving background. The two algorithms can solve automatically the decoupling problem of segmentation and recognition. They can also solve the problem for overcoming non-linear variations of static images, motion images and speech waves by through the inside process of recognition algorithms. Therefore, a quite small size of data of static images, motion images and speech waves, respectively, is enough for recognizing actual these real data of wide range. We will show many experimental results for confirming our argument.
{"title":"Keynote speech I: Big data, non-big data, and algorithms for recognizing the real world data","authors":"R. Oka","doi":"10.1109/ICAWST.2017.8256420","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256420","url":null,"abstract":"In this talk, we focus on recognition of static images, motion images from a video, and speech waves spoken by simultaneously multiple speakers. The necessary size of data for learning depends on algorithms for recognizing patterns. Real world data of static images, motion images, and speech waves includes many kinds of problems to be solved for their recognition. The most important one is the separation of segmentation and recognition in both time and space domains as well as overcoming their non-linear variations of these patterns. The segmentation problem is strongly coupled with the recognition problem. Without segmentation, recognition is impossible and vice versa. We need to create a sophisticated algorithm for decoupling of the two. If the recognition algorithm itself can also solve both the problems of segmentation and overcoming problem of non-linear variations of these patterns in the inside process of recognition, big data is not required for learning. On the other hand, deep learning is requiring big data of segmented samples for storing them in the form of connection weights among nodes of multi-layer. Deep learning is basically based on the segmentation of patterns in both learning and recognition stages. We propose two algorithms of matching. The one is called two-dimensional continuous dynamic programming (2DCDP) for spatial segmentation-free recognition of static images. An expanded version of 2DCDP called incremental two-dimensional continuous dynamic programming (I2DCDP) can carry out time segmentation-free and speaker-independent recognition of a single speech wave spoken by multiple speakers without speech separation. The other one is called time-space continuous dynamic programming (TSCDP) for both time segmentation-free and location-free recognition of complex human/object motions from a video even in the moving background. The two algorithms can solve automatically the decoupling problem of segmentation and recognition. They can also solve the problem for overcoming non-linear variations of static images, motion images and speech waves by through the inside process of recognition algorithms. Therefore, a quite small size of data of static images, motion images and speech waves, respectively, is enough for recognizing actual these real data of wide range. We will show many experimental results for confirming our argument.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"153 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":"114524150","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256486
Hsiu-Chia Ko, Jianfang Chang
Recently, due to the social networking sites (SNS) users continue to grow, social commerce has been addressed as an important issue by scholars and practitioners. However, the motivations of social commerce intention are unclear. This study aimed to explore the motivations of social commerce intention based on the perspective of consumer shopping value and the model of goal-directed behavior. Given that social commerce has the feature of social and commercial, this study firstly investigated the influences of social, hedonic, and utilitarian motivations on social and commercial desires, respectively. Then, the impacts of both desires on social commerce intention were examined. This study was conducted by survey method. The results revealed that social and hedonic motivations could arouse SNS users' social desire; whereas utilitarian motivation could evoke SNS users' commercial desire. Both commercial and social desires would lead to social commerce intention. Based on the research findings, this study finally provided some discussions and suggestions for firms and SNS service providers to enhance SNS users' social commerce intention.
{"title":"Exploring the motivations of social commerce: A perspective of consumer shopping value","authors":"Hsiu-Chia Ko, Jianfang Chang","doi":"10.1109/ICAWST.2017.8256486","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256486","url":null,"abstract":"Recently, due to the social networking sites (SNS) users continue to grow, social commerce has been addressed as an important issue by scholars and practitioners. However, the motivations of social commerce intention are unclear. This study aimed to explore the motivations of social commerce intention based on the perspective of consumer shopping value and the model of goal-directed behavior. Given that social commerce has the feature of social and commercial, this study firstly investigated the influences of social, hedonic, and utilitarian motivations on social and commercial desires, respectively. Then, the impacts of both desires on social commerce intention were examined. This study was conducted by survey method. The results revealed that social and hedonic motivations could arouse SNS users' social desire; whereas utilitarian motivation could evoke SNS users' commercial desire. Both commercial and social desires would lead to social commerce intention. Based on the research findings, this study finally provided some discussions and suggestions for firms and SNS service providers to enhance SNS users' social commerce intention.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"56 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":"121941595","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256437
Xiaodan Zhou, Ling-Hsiu Chen, R. Chen
In recent years, with the rapid development of technology, Chinese traditional exam-oriented education cannot meet people's need and the social demand for talent. Many native universities face the challenges of education reformation with the emergence of MOOCs, flipped classroom, blended learning, collaborative learning etc. This study surveyed 113 undergraduate students, majoring in international finance management, in order to investigate their mental readiness regarding flipped blended learning classroom combined with collaborative learning by teaching. After the introduction of the flipped blended learning methodology, the survey was implemented in three classrooms that were taught by the same instructor. SPSS 24 software and AMOS 24 software were adopted for data analysis. Through factor analysis, the mental readiness for flipped blended learning consists of four factors: student attitude, motivation for learning, self-efficacy and group efficacy. Examination of the scale led to satisfactory results in terms of reliability, validity, and its predictive power for student mental readiness for flipped blended learning. Summarizing, the scale can help teachers understand student mental situation and improve the development of pedagogical reformation.
{"title":"Measuring student mental readiness for flipped blended learning: Scale development and validation","authors":"Xiaodan Zhou, Ling-Hsiu Chen, R. Chen","doi":"10.1109/ICAWST.2017.8256437","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256437","url":null,"abstract":"In recent years, with the rapid development of technology, Chinese traditional exam-oriented education cannot meet people's need and the social demand for talent. Many native universities face the challenges of education reformation with the emergence of MOOCs, flipped classroom, blended learning, collaborative learning etc. This study surveyed 113 undergraduate students, majoring in international finance management, in order to investigate their mental readiness regarding flipped blended learning classroom combined with collaborative learning by teaching. After the introduction of the flipped blended learning methodology, the survey was implemented in three classrooms that were taught by the same instructor. SPSS 24 software and AMOS 24 software were adopted for data analysis. Through factor analysis, the mental readiness for flipped blended learning consists of four factors: student attitude, motivation for learning, self-efficacy and group efficacy. Examination of the scale led to satisfactory results in terms of reliability, validity, and its predictive power for student mental readiness for flipped blended learning. Summarizing, the scale can help teachers understand student mental situation and improve the development of pedagogical reformation.","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":"129109892","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256518
Jingjing Tong, Shuang Liu, Yufeng Ke, Bin Gu, Feng He, B. Wan, Dong Ming
Emotions are ubiquitous components of everyday life, as they influence behavior to a large extent. And Emotion recognition is one of the most important and necessary parts in the field of emotion research. Its accuracy relies heavily on the ability to generate representative features. However, this is a very challenging problem. In this study, EEG nonlinear features, power spectrum entropy and correlation dimension, were extracted to differentiate emotions. International Affective Picture System (IAPS) pictures with different valence but similar arousal level were used to induce the emotions with 8 valence levels. The results showed that the valence levels were positively correlated with these two features, especially in the frontal lobe. Based on the two features, SVM gave an average accuracy of 82.22%. Analyzing the nonlinear features of EEGs is an efficient way to classify emotions.
{"title":"EEG-based emotion recognition using nonlinear feature","authors":"Jingjing Tong, Shuang Liu, Yufeng Ke, Bin Gu, Feng He, B. Wan, Dong Ming","doi":"10.1109/ICAWST.2017.8256518","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256518","url":null,"abstract":"Emotions are ubiquitous components of everyday life, as they influence behavior to a large extent. And Emotion recognition is one of the most important and necessary parts in the field of emotion research. Its accuracy relies heavily on the ability to generate representative features. However, this is a very challenging problem. In this study, EEG nonlinear features, power spectrum entropy and correlation dimension, were extracted to differentiate emotions. International Affective Picture System (IAPS) pictures with different valence but similar arousal level were used to induce the emotions with 8 valence levels. The results showed that the valence levels were positively correlated with these two features, especially in the frontal lobe. Based on the two features, SVM gave an average accuracy of 82.22%. Analyzing the nonlinear features of EEGs is an efficient way to classify emotions.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"50 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":"130949485","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}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256429
P. Prameswari, Zulkarnain, I. Surjandari, Enrico Laoh
In this modern era, online hotel reviews have a big role considering the hotel is one of the aspects in determining the competitiveness in the tourist area, but its implementation is still rare. Regarding the government's plan to increase tourist arrivals to Indonesia, this research utilized text mining towards online hotel reviews to find useful knowledge in building the hospitality sector as an integral part of the tourism industry. Text classification technique was used to obtain sentiment information contained in review sentences through sentiment analysis, as well as clustering technique as a part of text summarization to find representative sentences that are able to describe the entire contents of the review. The main contribution of this research is to combine two techniques in text mining that have never been done before, namely the sentiment analysis and text summarization. Experiments with hotel reviews in Labuan Bajo and Bali generated surprising outcomes, where the accuracy of classification model reaches 78% and the Davies-Bouldin Index (DBI) of clustering algorithm strikes 0.071. The output of this research is expected to describe the condition of the hotel in the tourist area with a different level of tourism development so that it can contribute to improving the quality of the hotel industry as well as supporting the tourism industry in Indonesia.
{"title":"Mining online reviews in Indonesia's priority tourist destinations using sentiment analysis and text summarization approach","authors":"P. Prameswari, Zulkarnain, I. Surjandari, Enrico Laoh","doi":"10.1109/ICAWST.2017.8256429","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256429","url":null,"abstract":"In this modern era, online hotel reviews have a big role considering the hotel is one of the aspects in determining the competitiveness in the tourist area, but its implementation is still rare. Regarding the government's plan to increase tourist arrivals to Indonesia, this research utilized text mining towards online hotel reviews to find useful knowledge in building the hospitality sector as an integral part of the tourism industry. Text classification technique was used to obtain sentiment information contained in review sentences through sentiment analysis, as well as clustering technique as a part of text summarization to find representative sentences that are able to describe the entire contents of the review. The main contribution of this research is to combine two techniques in text mining that have never been done before, namely the sentiment analysis and text summarization. Experiments with hotel reviews in Labuan Bajo and Bali generated surprising outcomes, where the accuracy of classification model reaches 78% and the Davies-Bouldin Index (DBI) of clustering algorithm strikes 0.071. The output of this research is expected to describe the condition of the hotel in the tourist area with a different level of tourism development so that it can contribute to improving the quality of the hotel industry as well as supporting the tourism industry in Indonesia.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"21 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":"126258473","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：