发布求助
文献互助 智能选刊 最新文献

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)最新文献

筛选
英文 中文
True or False: Does the Deep Learning Model Learn to Detect Rumors? 真假:深度学习模型能学会检测谣言吗?
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/TAAI54685.2021.00030
Shiwen Ni, Jiawen Li, Hung-Yu kao
{"title":"True or False: Does the Deep Learning Model Learn to Detect Rumors?","authors":"Shiwen Ni, Jiawen Li, Hung-Yu kao","doi":"10.1109/TAAI54685.2021.00030","DOIUrl":"https://doi.org/10.1109/TAAI54685.2021.00030","url":null,"abstract":"It is difficult for humans to distinguish the true and false of rumors, but current deep learning models can surpass humans and achieve excellent accuracy on many rumor datasets. In this paper, we investigate whether deep learning models that seem to perform well actually learn to detect rumors. We evaluate models on their generalization ability to out-of-domain examples by fine-tuning BERT-based models on five real-world datasets and evaluating against all test sets. The experimental results indicate that the generalization ability of the models on other unseen datasets are unsatisfactory, even common-sense rumors cannot be detected. Moreover, we found through experiments that models take shortcuts and learn absurd knowledge when the rumor datasets have serious data pitfalls. This means that simple modifications to the rumor text based on specific rules will lead to inconsistent model predictions. To more realistically evaluate rumor detection models, we proposed a new evaluation method called paired test (PairT), which requires models to correctly predict a pair of test samples at the same time. Furthermore, we make recommendations on how to better create rumor dataset and evaluate rumor detection model at the end of this paper.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122197233","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
FOCM: Faster Octave Convolution Using Mix-scaling FOCM:使用混合缩放更快的八度卷积
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00015
Kuan-Hsian Hsieh, Erh-Chung Chen, Che-Rung Lee
{"title":"FOCM: Faster Octave Convolution Using Mix-scaling","authors":"Kuan-Hsian Hsieh, Erh-Chung Chen, Che-Rung Lee","doi":"10.1109/taai54685.2021.00015","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00015","url":null,"abstract":"Octave convolution that separates the feature maps for different resolutions is an effective method to reduce the spatial redundancy in Convolution Neural Networks (CNN). In this paper, we propose a faster version of octave convolution, FOCM, which can further reduce the computation cost of CNNs. Similar to the octave convolution, FOCM divides the input and output feature maps into the domains of different resolutions, but without explicit information exchange among them. In addition, FOCM utilizes the mix-scaled convolution kernels to learn different sized spatial features. Experiments on various depth ResNet with ImageNet data-set have shown that FOCM can reduce 33.9% to 46.4% operations of the original models, and save 11.1% to 21.7% FLOPS of the models using octave convolutions, with similar top-1 and top-5 accuracy.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115911112","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
Adaptive Ant Colony Optimization with Several Pheromone Updates for Constraint Satisfaction Problems 约束满足问题的若干信息素更新自适应蚁群优化
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00013
Takaaki Toya, Kazunori Mizuno, Shotaro Koike
{"title":"Adaptive Ant Colony Optimization with Several Pheromone Updates for Constraint Satisfaction Problems","authors":"Takaaki Toya, Kazunori Mizuno, Shotaro Koike","doi":"10.1109/taai54685.2021.00013","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00013","url":null,"abstract":"Ant colony optimization, ACO, has been applied to solving constraint satisfaction problems, CSPs., as an effective meta-heuristics. Because most of ACO based algorithms have prepared only the single pheromone update method, however, such algorithms have sometimes been inefficient for CSP instances very hard to solve due to dependence on how pheromone accumulates. In this paper, we propose an ACO based algorithm that can deal with several pheromone update methods. Besides, the proposed method also prepare an adaptive mechanism, in which pheromone update methods suitable to each problem instance to be solved can dynamically be adjusted during the search process. We also demonstrate that the proposed method can be more effective than some ACO based algorithms with the single pheromone update method for large-scale and very hard instances of the graph coloring problem that has been known as one of typical examples of CSPs.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115801449","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
Using digital image and curve regression model to classify air quality 采用数字图像和曲线回归模型对空气质量进行分类
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00049
Yan-Ting Lin, Kuan-Yu Chen, Jiun-Jian Liaw, Jungpil Shin
{"title":"Using digital image and curve regression model to classify air quality","authors":"Yan-Ting Lin, Kuan-Yu Chen, Jiun-Jian Liaw, Jungpil Shin","doi":"10.1109/taai54685.2021.00049","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00049","url":null,"abstract":"Monitoring air quality is an important issue for people's health. The pollutant that has the greatest impact on air quality is PM2.5 concentration. Since PM2.5 concentration is positively correlated with air quality and visibility, the main objective of this study is to use PM2.5 concentration estimation technology to classify the air quality level. The proposed method is based on digital image processing and is a simple and low-cost method of assessing air quality. The image will be extracted with high-frequency information, contrast and entropy as features. Three regression models are used for training to get the relationship with PM2.5 concentration. The air quality level is classified by the estimated concentration of PM2.5. Air quality is divided into 3 levels, allowing the public to directly understand the current level of air pollution. This study uses images taken by two air quality monitoring stations as experimental samples. In addition to images, the collected data also includes PM2.5 concentration, relative humidity and AQI values. The experimental results show that the method proposed in this paper is suitable for classifying the air quality level.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129516274","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
Global Structured Feature Graph Convolutional Network for Skeleton-Based Action Recognition 基于骨架的动作识别的全局结构特征图卷积网络
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00026
Chia-Fen Hsieh, Po-Jen Liao
{"title":"Global Structured Feature Graph Convolutional Network for Skeleton-Based Action Recognition","authors":"Chia-Fen Hsieh, Po-Jen Liao","doi":"10.1109/taai54685.2021.00026","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00026","url":null,"abstract":"With the development of human action recognition technology, deep learning has been applied to still images, and great progress has been made. However, in film action recognition, there is still the issue of using deep learning to improve the recognition rates. When predicting the action of a movie, encountering occlusions, large background changes, or accumulation of some errors in consecutive frames in the movie, resulting in a decrease in the accuracy of action recognition and increase the difficulty of film action recognition. In addition, there is a lack of structural information of bone joints and related research between two different structures. To solve this problem, this paper proposed a joint structure related feature network method using graph convolution network (GCN), which combines multiple convolution kernels of different dimensions to enhance the recognition rate of movie actions. The experimental database was established in the laboratory of Nanyang Technological University, Singapore. The system uses the NTU RGB+D motion recognition data set to evaluate our network. Preliminary experimental results show that our system may improve accuracy and make it more efficient.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116916008","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
A PCA Approach to Estimate the Q-matrix 一种估计q矩阵的PCA方法
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00053
Mengta Chung
{"title":"A PCA Approach to Estimate the Q-matrix","authors":"Mengta Chung","doi":"10.1109/taai54685.2021.00053","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00053","url":null,"abstract":"The primary purpose for this research is to estimate the Q-matrix using an exploratory factor analysis (EFA) of tetrachoric correlations. Results from simulation studies suggest that an EFA of tetrachoric correlations is feasible for estimating the Q-matrix, with recovery rates from different concoctions above 0.920. All analyses in this research are implemented in R.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131983953","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 Needs Analysis of Virtual Exergaming 虚拟游戏的需求分析
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00063
Long-Sheng Chen, Yi-Xun Wu
{"title":"The Needs Analysis of Virtual Exergaming","authors":"Long-Sheng Chen, Yi-Xun Wu","doi":"10.1109/taai54685.2021.00063","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00063","url":null,"abstract":"Due the maturity of virtual reality (VR) products and related technologies, VR has been widely applied to exergaming. The COVID 19 epidemic also fastens applying VR to fitness and sports. However, as with all innovative products, to ensure that the presented product can be successful, understanding the user's actual or potential needs will be one of the key factors for the success of the product. To ensure we can know the players' needs of VR exergaming, Kano model will be employed in this study. We propose 12 design functions for VR exergames. Through Kano analysis, we can understand how these design elements are categorized in the user's needs. Results of Kano analysis could help VR exergaming manufacturers to enhance game design functions, so that VR sport games can be closer to the needs of users.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131123279","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
Application of Deep Learning for Mushrooms Cultivation 深度学习在蘑菇栽培中的应用
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00055
B. Huang, Ji-Yun Chen, Xinying Lai, Guanting Chen, Ko-Wei Huang
{"title":"Application of Deep Learning for Mushrooms Cultivation","authors":"B. Huang, Ji-Yun Chen, Xinying Lai, Guanting Chen, Ko-Wei Huang","doi":"10.1109/taai54685.2021.00055","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00055","url":null,"abstract":"In this study, we designed and implemented an intelligent system that uses image recognition to determine the status of mushrooms in real time and record the growth process. This system may help improve production efficiency and product quality. It primarily applies YOLOv4 to identify mushroom maturity and the presence of dirt; it also includes an image visual distance recognition algorithm that learns the position of the monitoring lens relative to the mushrooms. The results of the experiment demonstrate that the proposed system can accurately recognize mushroom status and calculate the distance between the lens and mushrooms.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"487 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128057281","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
An Automatic Response System based on Multi-layer Perceptual Neural Network and Web Crawler 基于多层感知神经网络和网络爬虫的自动响应系统
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00054
Yen-Ting Liu, M.-H. Hsih, Chen-Chiung Hsieh
{"title":"An Automatic Response System based on Multi-layer Perceptual Neural Network and Web Crawler","authors":"Yen-Ting Liu, M.-H. Hsih, Chen-Chiung Hsieh","doi":"10.1109/taai54685.2021.00054","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00054","url":null,"abstract":"This study proposed a deep-learning based Chinese natural language processing to effectively combine traditional hard-coded judgment and crawler to predict user intention. This study uses Jieba to do word segmentation and TF-IDF for keyword statistics and feature extraction. A multi-layer perceptual neural network is then used to classify user intention. In order to improve accuracy, fixed judgments and crawlers are added to obtain the latest service news on the official website. Experiments were conducted on the training data set (questions) collected by Facebook Chat, compared with the Chinese classification models of the popular methods. 100 questions and answers were tested, the accuracy reached 80% aboveį This shows that our method is feasible for various applications.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114836417","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
Combination of EEG and Brainwave Mind Lamp to detect the value of Attention, Meditation and Fatigue of a person 结合脑电图和脑波精神灯检测人的注意力、冥想和疲劳的价值
2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00040
Rung-Ching Chen, Ming-Jheng Liou, Christine Dewi
{"title":"Combination of EEG and Brainwave Mind Lamp to detect the value of Attention, Meditation and Fatigue of a person","authors":"Rung-Ching Chen, Ming-Jheng Liou, Christine Dewi","doi":"10.1109/taai54685.2021.00040","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00040","url":null,"abstract":"Electroencephalography (EEG) is a technique to capture the brainwaves, which are generated due to the activities of the human brain on the scale of micro-electrical voltage. Stress is a state of mind which leads to emotional instability leading to number of health issues. It is really effective to listen the corresponding music according to the person's emotional state to release stress. This paper uses brainwave instrument combined with Android Studio to develop mobile phone software and uses Bluetooth transmission to EEG on the phone screen to analyze the emotional effects of various music. We also use the brainwave mind lamp to present the brain of color change of the wave data. The project is to study which type of music can bring to different person soothing effect, and then achieve the effect of emotional control, and also observe the user's emotional control through the brainwave mind lamp.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132029819","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
首页 上一页 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：481959085
Book学术官方微信