Pub Date : 2019-07-01DOI: 10.1109/ICMLC48188.2019.8949202
Yan Liu, Zhengjun Lin, Ying Pan
Perception verbs are the linguistic realization of human perceptual behavior. Based on the physiological stress response mechanism, this study deconstructs each English perception verb into a two-tuple which contains lexical core and lexical tentacle. The lexical core characterizes language features of perception verb and the lexical tentacle carries language information of perception verb. In this way, the process of perception verb cognition is activated by lexical core, along with lexical tentacle spreading. Language information like polysemy and collocation is described by lexical tentacle, more specifically, is described by word chains inside the lexical tentacle. The word chains record the linguistic information of perception verbs. And the numbers of word chains measure the lexical value of perception verbs. According to the lexical value, the perception verbs are ordered as see>feel>hear>smell > taste.
{"title":"Deconstruction of Perception Verbs: Structure and Value","authors":"Yan Liu, Zhengjun Lin, Ying Pan","doi":"10.1109/ICMLC48188.2019.8949202","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949202","url":null,"abstract":"Perception verbs are the linguistic realization of human perceptual behavior. Based on the physiological stress response mechanism, this study deconstructs each English perception verb into a two-tuple which contains lexical core and lexical tentacle. The lexical core characterizes language features of perception verb and the lexical tentacle carries language information of perception verb. In this way, the process of perception verb cognition is activated by lexical core, along with lexical tentacle spreading. Language information like polysemy and collocation is described by lexical tentacle, more specifically, is described by word chains inside the lexical tentacle. The word chains record the linguistic information of perception verbs. And the numbers of word chains measure the lexical value of perception verbs. According to the lexical value, the perception verbs are ordered as see>feel>hear>smell > taste.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133804948","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}
Technology always comes from human nature and life safety is more important than anything. In recent years natural disasters and work safety accidents happened frequently. So we put what have learned into practice. With the technology of IoT, our team has developed the Intelligent and Disaster Prevention Hard Hat, which improve the life safety more than tradition hard hat. Different from traditional Hard Hats, we combine Raspberry 3 and various sensors to transform into an Intelligent and Disaster Prevention Hard Hat, with Global Positioning System and MQ2 toxic gas detection, which is the best to apply in a variety of disaster situations. The main control terminal is built with a Responsive Web Design (RWD), which can change the webpage frame with various devices to provide the best visual effect. With 21 kinds of multi-hazard instant alarms, users can instantly know whether there will be a secondary disaster in near future, and combine voice and face recognition, etc. The Hakka's speech recognition is included for communication between client and backsite center.
技术总是源于人性，生命安全比什么都重要。近年来，自然灾害和生产安全事故频发。所以我们把所学到的付诸实践。我们的团队利用物联网技术，开发了智能防灾安全帽，比传统安全帽更能提高生命安全。与传统安全帽不同的是，我们将树莓3与各种传感器相结合，改造成一顶智能防灾安全帽，具有全球定位系统和MQ2有毒气体检测功能，最适合应用于各种灾害情况。主控终端采用响应式网页设计(Responsive Web Design, RWD)，可以随各种设备改变网页框架，提供最佳的视觉效果。21种多灾种即时报警，用户可即时得知近期是否会有二次灾害，并结合语音和人脸识别等功能。客家语音识别功能用于客户端与后台中心之间的沟通。
{"title":"Intelligent and Disaster Prevention Hard Hat Based on AIOT and Speeches Recognition","authors":"Feng-Long Huang, Zih-Zrong Liao, Tsun-Hong Wang, Qiming Chen, Ting-Hua Wu, Ching-Hsiang Chang","doi":"10.1109/ICMLC48188.2019.8949271","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949271","url":null,"abstract":"Technology always comes from human nature and life safety is more important than anything. In recent years natural disasters and work safety accidents happened frequently. So we put what have learned into practice. With the technology of IoT, our team has developed the Intelligent and Disaster Prevention Hard Hat, which improve the life safety more than tradition hard hat. Different from traditional Hard Hats, we combine Raspberry 3 and various sensors to transform into an Intelligent and Disaster Prevention Hard Hat, with Global Positioning System and MQ2 toxic gas detection, which is the best to apply in a variety of disaster situations. The main control terminal is built with a Responsive Web Design (RWD), which can change the webpage frame with various devices to provide the best visual effect. With 21 kinds of multi-hazard instant alarms, users can instantly know whether there will be a secondary disaster in near future, and combine voice and face recognition, etc. The Hakka's speech recognition is included for communication between client and backsite center.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117163966","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}
In person re-identification (ReID) task, the variance between the samples are quite large, and there is no standard sample as a comparison. The current common method is to implement it as a classification task, which can get better results than the classical methods in verification task such as contrastive loss. However, the identification loss used in classification task only seeks the boundary of the classification, the intra-class distance between samples is still large so that it is insufficient for ReID task. In this paper, we consider to overcome these difficulties by proposing a joint loss with an identification loss and constrains of modeling the Euclidean distances between samples and their corresponding eigen data which is constructed by Principal Component Analysis method (PCA), we call it EigenPerson. The entire loss is formed in a linear combination. This work is mainly motivated by the center loss for face recognition problems, of which regularizations are restricted by a simultaneously learned center. We substitute the center with EigenPerson which we constructed offline as an auxiliary training sample. The learned model with our proposed method is evaluated on the benchmark of Market1501 and CUHK03 and achieve comparable results to those methods proposed in the same period.
{"title":"Person Re-Identification via Feature Representation Learning Based on Verification Sample Constrain","authors":"Ruifeng Zhao, Ajian Liu, Yanyan Liang, Haozhi Huang","doi":"10.1109/ICMLC48188.2019.8949262","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949262","url":null,"abstract":"In person re-identification (ReID) task, the variance between the samples are quite large, and there is no standard sample as a comparison. The current common method is to implement it as a classification task, which can get better results than the classical methods in verification task such as contrastive loss. However, the identification loss used in classification task only seeks the boundary of the classification, the intra-class distance between samples is still large so that it is insufficient for ReID task. In this paper, we consider to overcome these difficulties by proposing a joint loss with an identification loss and constrains of modeling the Euclidean distances between samples and their corresponding eigen data which is constructed by Principal Component Analysis method (PCA), we call it EigenPerson. The entire loss is formed in a linear combination. This work is mainly motivated by the center loss for face recognition problems, of which regularizations are restricted by a simultaneously learned center. We substitute the center with EigenPerson which we constructed offline as an auxiliary training sample. The learned model with our proposed method is evaluated on the benchmark of Market1501 and CUHK03 and achieve comparable results to those methods proposed in the same period.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129516160","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 : 2019-07-01DOI: 10.1109/ICMLC48188.2019.8949310
M. Yeh, Hung-Ching Lu, Ti-Hung Chen
This study attempts to improve the forecasting accuracy of rolling grey model by applying Gaussian bare-bones differential evolution (GBDE) to optimize the weight of background value and number of data points used to construct a rolling-GM(1,1). Experimental results on two real time series forecasting problems show that the proposed GBDE-based rolling-GM(l,l) outperforms the traditional rolling-GM(l,l) in terms of fitting accuracy and forecasting accuracy.
{"title":"Time Series Forecasting Using Optimized Rolling Grey Model","authors":"M. Yeh, Hung-Ching Lu, Ti-Hung Chen","doi":"10.1109/ICMLC48188.2019.8949310","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949310","url":null,"abstract":"This study attempts to improve the forecasting accuracy of rolling grey model by applying Gaussian bare-bones differential evolution (GBDE) to optimize the weight of background value and number of data points used to construct a rolling-GM(1,1). Experimental results on two real time series forecasting problems show that the proposed GBDE-based rolling-GM(l,l) outperforms the traditional rolling-GM(l,l) in terms of fitting accuracy and forecasting accuracy.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127058241","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 : 2019-07-01DOI: 10.1109/ICMLC48188.2019.8949186
Zhenghan Jiang, Qiangfu Zhao, Yoichi Tomioka
Image-based obstacle avoidance has been studied for decades. One weak point of image-based approaches is that the performance usually depends on the lighting condition. That is, the performance can be very poor in dark environments. In this research, we investigate the possibility of the depth image-based approach for full-time indoor patrolling. As the first step, we consider a 3-class problem. Each depth image is classified as “danger” if some obstacle is too close, as “notice” if the obstacle is close, and as “normal” if there is no obstacle in the vicinity. The label of each depth image is defined based on the RGB image captured at the same time, and an AlexNet, which is a well-trained convolutional neural network, is retrained via transfer learning, and used for classification. In our primary experiment, we collected 102,776 image data in the Research Quadrangle of the University of Aizu. Test results show that the performance of the depth image-based approach is good during both day and night, and in most cases, it is better than the RGB image-based approach. This result can provide new insights when designing more practical full-time patrol robots.
{"title":"Depth Image-Based Obstacle Avoidance for an In-Door Patrol Robot","authors":"Zhenghan Jiang, Qiangfu Zhao, Yoichi Tomioka","doi":"10.1109/ICMLC48188.2019.8949186","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949186","url":null,"abstract":"Image-based obstacle avoidance has been studied for decades. One weak point of image-based approaches is that the performance usually depends on the lighting condition. That is, the performance can be very poor in dark environments. In this research, we investigate the possibility of the depth image-based approach for full-time indoor patrolling. As the first step, we consider a 3-class problem. Each depth image is classified as “danger” if some obstacle is too close, as “notice” if the obstacle is close, and as “normal” if there is no obstacle in the vicinity. The label of each depth image is defined based on the RGB image captured at the same time, and an AlexNet, which is a well-trained convolutional neural network, is retrained via transfer learning, and used for classification. In our primary experiment, we collected 102,776 image data in the Research Quadrangle of the University of Aizu. Test results show that the performance of the depth image-based approach is good during both day and night, and in most cases, it is better than the RGB image-based approach. This result can provide new insights when designing more practical full-time patrol robots.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128767417","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 : 2019-07-01DOI: 10.1109/ICMLC48188.2019.8949162
Chun Yuan Lai, R. Chen, R. Caraka
Predicting stock price has been a challenging project for many researchers, investors, and analysts. Most of them are interested in knowing the stock price trend in the future. To get a precise and winning model is the wish of them. Recently, Neural Network has been a prevalent means for stock prediction. However, there are many ways and different predicting models such as Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). In this paper, we propose a novel idea that average previous five days stock market information (open, high, low, volume, close) as a new value then use this value to predict, and use the predicted value as the average of the stock price information for the next five days. Moreover, we utilize Technical Analysis Indicators to consider whether to buy stocks or continue to hold stocks or sell stocks. We use Foxconn company data collected from Taiwan Stock Exchange for testing with the Neural Network Long Short-Term Memory (LSTM).
{"title":"Prediction Stock Price Based on Different Index Factors Using LSTM","authors":"Chun Yuan Lai, R. Chen, R. Caraka","doi":"10.1109/ICMLC48188.2019.8949162","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949162","url":null,"abstract":"Predicting stock price has been a challenging project for many researchers, investors, and analysts. Most of them are interested in knowing the stock price trend in the future. To get a precise and winning model is the wish of them. Recently, Neural Network has been a prevalent means for stock prediction. However, there are many ways and different predicting models such as Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). In this paper, we propose a novel idea that average previous five days stock market information (open, high, low, volume, close) as a new value then use this value to predict, and use the predicted value as the average of the stock price information for the next five days. Moreover, we utilize Technical Analysis Indicators to consider whether to buy stocks or continue to hold stocks or sell stocks. We use Foxconn company data collected from Taiwan Stock Exchange for testing with the Neural Network Long Short-Term Memory (LSTM).","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125913622","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 : 2019-07-01DOI: 10.1109/ICMLC48188.2019.8949199
You-Chen Zhang, Chung-Hong Lee, Tyng-Yeu Liang, Wei-Che Chung, Kuei-Han Li, Cheng-Chieh Huang, Hong-Jie Dai, Chi-Shin Wu, C. Kuo, Chu-Hsien Su, Horng-Chang Yang
This study aims to extract symptom profiles and functional impairments of major depressive disorder from electronic health records (EHRs). A chart review was conducted by three annotators on 500 discharge notes randomly selected from a medical center in Taiwan to compile annotated corpora for nine depressive symptoms and four types of functional impairment. Named entity recognition techniques including the dictionary-based approach., a conditional random field model, and deep learning approaches were developed for the task of recognizing depressive symptoms and functional impairments from EHRs. The results show that the average micro-F-measures of the supervised learning approaches in extracting depressive symptoms is almost perfect (>0.90) but less accurate for the extraction of functional impairment.
{"title":"Depressive Symptoms and Functional Impairments Extraction From Electronic Health Records","authors":"You-Chen Zhang, Chung-Hong Lee, Tyng-Yeu Liang, Wei-Che Chung, Kuei-Han Li, Cheng-Chieh Huang, Hong-Jie Dai, Chi-Shin Wu, C. Kuo, Chu-Hsien Su, Horng-Chang Yang","doi":"10.1109/ICMLC48188.2019.8949199","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949199","url":null,"abstract":"This study aims to extract symptom profiles and functional impairments of major depressive disorder from electronic health records (EHRs). A chart review was conducted by three annotators on 500 discharge notes randomly selected from a medical center in Taiwan to compile annotated corpora for nine depressive symptoms and four types of functional impairment. Named entity recognition techniques including the dictionary-based approach., a conditional random field model, and deep learning approaches were developed for the task of recognizing depressive symptoms and functional impairments from EHRs. The results show that the average micro-F-measures of the supervised learning approaches in extracting depressive symptoms is almost perfect (>0.90) but less accurate for the extraction of functional impairment.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127776514","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}
Histogram of oriented gradients (HOG) is a highly important feature representation in computer vision for many applications such as objection detection. The HOG computes local histograms of oriented gradients of pixel luminance on a dense grid of uniformly spaced cells and normalized to be a feature vector. Its computational complexity is high, and its implementation on edge computing and embedded devices is challenging. This paper proposes a hardware software codesign strategy to redesign the HOG algorithm. Pipelining and hardware acceleration by FPGA are applied in the design to the performance improvement of HOG. The design is implemented on a heterogeneous computing platform and with high level synthesis techniques exploiting C-code to accelerate the design of hardware circuits. Our results of full HD images achieve 500 times speed-up compared with software implementation.
定向梯度直方图(Histogram of oriented gradients, HOG)是计算机视觉中一个非常重要的特征表示方法，可用于目标检测等领域。HOG在均匀间隔的密集网格上计算像素亮度方向梯度的局部直方图，并归一化为特征向量。它的计算复杂度很高，并且在边缘计算和嵌入式设备上的实现具有挑战性。本文提出了一种软硬件协同设计策略来重新设计HOG算法。在设计中采用流水线技术和FPGA硬件加速技术来提高HOG的性能。该设计在异构计算平台上实现，采用高级综合技术，利用c代码加速硬件电路的设计。与软件实现相比，我们的全高清图像的速度提高了500倍。
{"title":"Hardware-Software Codesign of Histogram of Oriented Gradients on Heterogeneous Computing Platform","authors":"Yuan-Kai Wang, Hung-Yu Chen, Kuan-Yu Chen, Shih-Yu Huang","doi":"10.1109/ICMLC48188.2019.8949276","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949276","url":null,"abstract":"Histogram of oriented gradients (HOG) is a highly important feature representation in computer vision for many applications such as objection detection. The HOG computes local histograms of oriented gradients of pixel luminance on a dense grid of uniformly spaced cells and normalized to be a feature vector. Its computational complexity is high, and its implementation on edge computing and embedded devices is challenging. This paper proposes a hardware software codesign strategy to redesign the HOG algorithm. Pipelining and hardware acceleration by FPGA are applied in the design to the performance improvement of HOG. The design is implemented on a heterogeneous computing platform and with high level synthesis techniques exploiting C-code to accelerate the design of hardware circuits. Our results of full HD images achieve 500 times speed-up compared with software implementation.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134349804","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 : 2019-07-01DOI: 10.1109/ICMLC48188.2019.8949319
K. Wong, Yi-Chung Chen, Tzu-Chang Lee, Shengmin Wang
This paper presents a head motion detection and recognition study using a smart helmet for motorcycle rider which can potential be used for the analysis of behavior of motorcycle riders. The smart helmet is a full face motorcycle helmet integrated with an intelligent system embedded an Inertial Measurement Unit (IMU) sensor. In the analysis, the motions and the corresponding signals are assessed with the video footage with a data acquisition and visualization platform. We introduce a feature extraction methodology to extract the most discriminant features from the signal data, and the head motion recognition problem is formulated as a machine-learning based classification model. Experiment results show that gyroscope sensor data is more useful than accelerometer sensor data for head motion recognition and the classification accuracy for different head motions ranges from 95.9% to 99.1%.
{"title":"Head Motion Recognition Using a Smart Helmet for Motorcycle Riders","authors":"K. Wong, Yi-Chung Chen, Tzu-Chang Lee, Shengmin Wang","doi":"10.1109/ICMLC48188.2019.8949319","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949319","url":null,"abstract":"This paper presents a head motion detection and recognition study using a smart helmet for motorcycle rider which can potential be used for the analysis of behavior of motorcycle riders. The smart helmet is a full face motorcycle helmet integrated with an intelligent system embedded an Inertial Measurement Unit (IMU) sensor. In the analysis, the motions and the corresponding signals are assessed with the video footage with a data acquisition and visualization platform. We introduce a feature extraction methodology to extract the most discriminant features from the signal data, and the head motion recognition problem is formulated as a machine-learning based classification model. Experiment results show that gyroscope sensor data is more useful than accelerometer sensor data for head motion recognition and the classification accuracy for different head motions ranges from 95.9% to 99.1%.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134359833","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 : 2019-07-01DOI: 10.1109/ICMLC48188.2019.8949311
Chih-Hung Wu
Although learning style is an important issue in STEM (Science, Technology, Engineering, and Mathematics), most of previous studies adopted questionnaire instrument to identify learning style. Therefore, this study proposes a concept framework of using artificial neural networks to identify students' learning styles based on the learning portfolio data in our designed education balance game with the Felder-Silverman learning style model (FSLSM). An education balance game is designed to train student's physical balance knowledge and collect their learning portfolio data. These portfolio data is input variables in support vector machine to identify students' learning style.
虽然学习风格是STEM (Science, Technology, Engineering, and Mathematics，科学、技术、工程和数学)中的一个重要问题，但以往的研究大多采用问卷调查的方法来识别学习风格。因此，本研究提出了一个概念框架，基于我们设计的费尔德-西尔弗曼学习风格模型(FSLSM)的教育平衡博弈中的学习组合数据，使用人工神经网络识别学生的学习风格。教育平衡游戏旨在培养学生的身体平衡知识，并收集他们的学习档案数据。这些组合数据是支持向量机的输入变量，用于识别学生的学习风格。
{"title":"A Concept Framework of Using Education Game With Artificial Neural Network Techniques to Identify Learning Styles","authors":"Chih-Hung Wu","doi":"10.1109/ICMLC48188.2019.8949311","DOIUrl":"https://doi.org/10.1109/ICMLC48188.2019.8949311","url":null,"abstract":"Although learning style is an important issue in STEM (Science, Technology, Engineering, and Mathematics), most of previous studies adopted questionnaire instrument to identify learning style. Therefore, this study proposes a concept framework of using artificial neural networks to identify students' learning styles based on the learning portfolio data in our designed education balance game with the Felder-Silverman learning style model (FSLSM). An education balance game is designed to train student's physical balance knowledge and collect their learning portfolio data. These portfolio data is input variables in support vector machine to identify students' learning style.","PeriodicalId":221349,"journal":{"name":"2019 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134515898","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：