2020 International Conference on Pervasive Artificial Intelligence (ICPAI)最新文献

Stress Level Classifier: Taiwanese College Table Tennis Athletes’ Electroencephalography Analysis Based on Decision Trees 压力水平分类器:基于决策树的台湾大学生乒乓球运动员脑电图分析

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00019

Pingping Cheng, Meng-Hsiun Tsai, Chung-Hao Hsueh, Sheng Kuang Wu

引用次数: 0

Robot Eye: Automatic Object Detection And Recognition Using Deep Attention Network to Assist Blind People 机器人眼:利用深度注意网络辅助盲人的自动目标检测和识别

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00036

Ervin Yohannes, Paul Lin, Chih-Yang Lin, T. Shih

引用次数: 4

TrackNetV2: Efficient Shuttlecock Tracking Network TrackNetV2:高效的羽毛球跟踪网络

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00023

Nien-En Sun, Yu-Ching Lin, Shao-Ping Chuang, Tzu-Han Hsu, Dung-Ru Yu, Ho-Yi Chung, Tsì-Uí İk

{"title":"TrackNetV2: Efficient Shuttlecock Tracking Network","authors":"Nien-En Sun, Yu-Ching Lin, Shao-Ping Chuang, Tzu-Han Hsu, Dung-Ru Yu, Ho-Yi Chung, Tsì-Uí İk","doi":"10.1109/ICPAI51961.2020.00023","DOIUrl":"https://doi.org/10.1109/ICPAI51961.2020.00023","url":null,"abstract":"TrackNet, a deep learning network, was proposed to track high-speed and tiny objects such as tennis balls and shuttlecocks from videos. To conquer low image quality issues such as blur, afterimage, and short-term occlusion, some number of consecutive images are input together to detect an flying object. In this work, TrackNetV2 is proposed to improve the performance of TrackNet from various aspects, especially processing speed, prediction accuracy, and GPU memory usage. First of all, the processing speed is improved from 2.6 FPS to 31.8 FPS. The performance boost is achieved by reducing the input image size and re-engineering the network from a Multiple-In Single-Out (MISO) design to a Multiple-In Multiple-Out (MIMO) design. Then, to improve the prediction accuracy, a comprehensive dataset from diverse badminton match videos is collected and labeled for training and testing. The dataset consists of 55563 frames from 18 badminton match videos. In addition, the network mechanisms are composed of not only VGG16 and upsampling layers but also U-net. Last, to reduce GPU memory usage, the data structure of the heatmap layer is remodeled from a pixel-wise one-hot encoding 3D array to a real-valued 2D array. To reflect the change of the heatmap representation, the loss function is redesigned from a RMSE-based function to a weighted cross-entropy based function. An overall validation shows that the accuracy, precision and recall of TrackNetV2 respectively reach 96.3%, 97.0% and 98.7% in the training phase and 85.2%, 97.2% and 85.4% in a test on a brand new match. The processing speed of the 3-in and 3-out version TrackNetV2 can reach 31.84 FPS. The dataset and source code of this work are available at https://nol.cs.nctu.edu.tw:234/open-source/TrackNetv2/.","PeriodicalId":330198,"journal":{"name":"2020 International Conference on Pervasive Artificial Intelligence (ICPAI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133675414","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: 17

Bidirectional Perspective with Topic Information for Stance Detection 用于姿态检测的带有主题信息的双向透视

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00009

Sheng-Xuan Lin, Bo-Yi Wu, Tzu-Hsuan Chou, Ying-Jia Lin, Hung-Yu kao

{"title":"Bidirectional Perspective with Topic Information for Stance Detection","authors":"Sheng-Xuan Lin, Bo-Yi Wu, Tzu-Hsuan Chou, Ying-Jia Lin, Hung-Yu kao","doi":"10.1109/ICPAI51961.2020.00009","DOIUrl":"https://doi.org/10.1109/ICPAI51961.2020.00009","url":null,"abstract":"Because of the convenience of the Internet, there are many websites or online news spread misinformation, cause panic and trepidation in society. Automatic fake news detection can classify fake news and help the society to clarify the information is true or false without human checking. Detecting fake news by analyzing the stance is one of the mainstream methods, stance detection has become a new popular research field in recent years. How to accurately detect stance has become the primary goal of detecting fake news. This research aims to detect the news stance accurately, and we propose a method based on a pre-trained BERT language model. Most of the previous work only used the knowledge of single inference direction when classifying the stance, which may lose some important information. Therefore, we propose a bidirectional inference stance detection model, which can leverage bidirectional perspective information to classify the stance more comprehensively. We also define the stance detection task as a hierarchical structure task, and use the hierarchical classification and incorporate the topic information to help the stance classification. Experiment results show that our model can classify the stance more accurately.","PeriodicalId":330198,"journal":{"name":"2020 International Conference on Pervasive Artificial Intelligence (ICPAI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124043605","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

Machine Learning in Empirical Asset Pricing Models 经验资产定价模型中的机器学习

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00030

Huei-Wen Teng, Yu-Hsien Li, S. Chang

引用次数: 0

Optimization of Deep Learning Inference on Edge Devices 边缘设备上深度学习推理的优化

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00056

Endah Kristiani, Chao-Tung Yang, K. L. Phuong Nguyen

引用次数: 6

Using Segmentation to Enhance Frame Prediction in a Multi-Scale Spatial-Temporal Feature Extraction Network 在多尺度时空特征提取网络中使用分割增强帧预测

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00038

Michael Mu-Chien Hsu, Richard Jui-Chun Shyur

引用次数: 0

SlowFast-GCN: A Novel Skeleton-Based Action Recognition Framework SlowFast-GCN:一种新的基于骨架的动作识别框架

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00039

Cheng-Hung Lin, Po-Yung Chou, Cheng-Hsien Lin, Min-Yen Tsai

{"title":"SlowFast-GCN: A Novel Skeleton-Based Action Recognition Framework","authors":"Cheng-Hung Lin, Po-Yung Chou, Cheng-Hsien Lin, Min-Yen Tsai","doi":"10.1109/ICPAI51961.2020.00039","DOIUrl":"https://doi.org/10.1109/ICPAI51961.2020.00039","url":null,"abstract":"Human action recognition plays an important role in video surveillance, human-computer interaction, video understanding, and virtual reality. Different from two-dimensional object recognition, human action recognition is a dynamic object recognition with a time series relationship, and it faces many challenges from complex environments, such as color shift, light and shadow changes, and sampling angles. In order to improve the accuracy of human action recognition, many studies have proposed skeleton-based action recognition methods that are not affected by the background, but the current framework does not have much discussion on the integration of the time dimension.In this paper, we propose a novel SlowFast-GCN framework which combines the advantages of ST-GCN and SlowFastNet with dynamic human skeleton to improve the accuracy of human action recognition. The proposed framework uses two streams, one stream captures fine-grained motion changes, and the other stream captures static semantics. Through these two streams, we can merge the human skeleton features from two different time dimensions. Experimental results show that the proposed framework outperforms to state-of-the-art approaches on the NTU-RGBD dataset.","PeriodicalId":330198,"journal":{"name":"2020 International Conference on Pervasive Artificial Intelligence (ICPAI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132559893","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: 4

Transferring a facial depression model to estimate mood in a natural web browsing task 用面部抑郁模型估计自然网页浏览任务中的情绪

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00017

Giri Basant Raj, J. Morita

{"title":"Transferring a facial depression model to estimate mood in a natural web browsing task","authors":"Giri Basant Raj, J. Morita","doi":"10.1109/ICPAI51961.2020.00017","DOIUrl":"https://doi.org/10.1109/ICPAI51961.2020.00017","url":null,"abstract":"Because people are living in a stressful era, they are prone to common mental health problems, which cause them to experience low mood and loss of interest or pleasure. Although many suffer from depression/low mood, they hesitate to undergo clinical check-ups. Therefore, a systematic and efficient web-based system that automatically detects emotions is necessary. The purpose of this study was to design and develop a system that can automatically detect negative and positive mood states and to investigate the relationship between the depression and mood states of individuals. User’s facial expressions features are detected and analyzed in real-time and after the completion of using the system, the determined emotion is hence provided to the users. A facial depression model constructed from a dataset obtained in a human–agent interaction (HAI) experiment was applied to a general human-computer interaction (HCI) situation to classify negative and positive mood states. The model exhibits the highest accuracy rate for classifying mood states. These findings suggest that faces provide strong evidence of mood induction to depression and guidance to construct the automatic mental health care web-based system to know the preliminary mental state.","PeriodicalId":330198,"journal":{"name":"2020 International Conference on Pervasive Artificial Intelligence (ICPAI)","volume":"993 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133166894","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

Enhancing Stock Trend Prediction Models by Mining Relational Graphs of Stock Prices 利用股价关系图挖掘增强股票走势预测模型

2020 International Conference on Pervasive Artificial Intelligence (ICPAI) Pub Date : 2020-12-01 DOI: 10.1109/ICPAI51961.2020.00028

Hung-Yang Li, V. Tseng, Philip S. Yu

{"title":"Enhancing Stock Trend Prediction Models by Mining Relational Graphs of Stock Prices","authors":"Hung-Yang Li, V. Tseng, Philip S. Yu","doi":"10.1109/ICPAI51961.2020.00028","DOIUrl":"https://doi.org/10.1109/ICPAI51961.2020.00028","url":null,"abstract":"Stock trend prediction has been a subject that attracts lots of attentions from a diverse range of fields recently. Despite the advance by the cooperation with artificial intelligence and finance domains, a large number of works are still limited to the use of technical indicators to capture the principles of a stock price movement while few consider both historical patterns and the relations of its correlated stock. In this work, we propose a novel framework named RGStocknet (Relational Graph Stock Enhancing Network) that can boost performance on an arbitrary time series prediction backbone model. Our approach automatically extracts the relational graph into which the graph embedding model can be easily integrated. Treated as an additional input feature, company embedding from the graph embedding model aims to improve performance without the need for external resources of the knowledge graph. The experiment results show that the three benchmark baseline can benefit from our proposed RGStocknet module in relative performance gain on the S&P500 dataset with 2.97%, 2.48%, and 7.03% on profit-score and with 25.50%, 17.53%, and 12.75% on accuracy respectively. Applied to a real-world trading simulation environment, our approach also outperformed the backbone model and doubled the average return on ResNet over the buy and hold (BH) strategy from 4.42% to 7.38%. Visualization of the generated relational graph and company embedding also shows that the proposed method can capture the hidden dynamics of other correlated stocks and learn representation across the whole stock market. Moreover, the proposed method was shown to carry the potential to incorporate relations with external resources to achieve higher performance further.","PeriodicalId":330198,"journal":{"name":"2020 International Conference on Pervasive Artificial Intelligence (ICPAI)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130313042","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