2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)最新文献_第3页

Ammonia Gas Detection Based on CNN with Heatmap and Transfer Learning 基于CNN热图和迁移学习的氨气检测

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00016

Kun-Wei Lin, Renhong Wang, I. Liu, Shun-Hao Hu

{"title":"Ammonia Gas Detection Based on CNN with Heatmap and Transfer Learning","authors":"Kun-Wei Lin, Renhong Wang, I. Liu, Shun-Hao Hu","doi":"10.1109/taai54685.2021.00016","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00016","url":null,"abstract":"In this paper, a new gas detection method based on artificial intelligence was proposed. First, the sensory data of ammonia gas is converted into a heatmap, and the changing state of ammonia gas concentration is analyzed with the improved neural network of transfer learning. Second, from the qualified candidate heatmaps, the rising turning point that represents the ammonia adsorption sensing can be found. Based on the above process, the state of ammonia leakage will be clearly presented. By accurately detecting and finding the rising turning point, the leak ammonia concentration can be known, and then a gas prediction system can be established. The dataset used in this study comes from the sensing data obtained by the ammonia sensor in this study under different operational temperatures and different ammonia concentrations condition. Experimentally, the best operating temperature of the ammonia sensor in this study is 190°C. At this temperature, the sensitivity of 1000 ppm NH3/air reaches 15239%. In addition, the lowest detecting concentration of ammonia is 20 ppb NH3/air. This studied ammonia sensor has the advantages of small size, low cost, wide sensing concentration (20 ppb~1000 ppm NH3/air) and wide operating temperature (25~225°C), and super high ammonia sensitivity. Summary, the studied sensor has excellent ammonia sensing characteristics, and can perform detection and prediction in real time.","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":"129779843","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

Data Collection Framework on Menus satisfying both Preferences and Nutritional Balance 满足偏好和营养平衡的菜单数据收集框架

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00038

Yoko Nishihara, Takumi Ohata, Ryosuke Yamanishi

{"title":"Data Collection Framework on Menus satisfying both Preferences and Nutritional Balance","authors":"Yoko Nishihara, Takumi Ohata, Ryosuke Yamanishi","doi":"10.1109/taai54685.2021.00038","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00038","url":null,"abstract":"Having meals with nutritional balanced is an excellent choice to live in healthy and long. However, people may avoid meals with nutritional balanced if they are not matched with their preferences even though they know well the importance of nutritional balance. Meals that satisfy both preferences and nutritional balance should be recommended. This paper proposes a data collection framework on menus satisfying both preferences and nutritional balance. The proposed framework asks a user to think up a menu that consists of several meals while considering both preferences and nutritional balance. The menu is evaluated in its nutritional balance and given a score. The score is relatively compared with the previous scores, and a face mark which is the feedback to the user is decided. If a score is improved even if slightly, a smiley face mark is shown. In contrast, if a score is worsened significantly, a crying face mark is shown. In other cases, a normal face mark is shown to the user. The user can learn characteristics of the menus with nutritional balanced by referring to the feedback. The framework collects data on menus that satisfy both preferences and nutritional balance. The authors conducted evaluation experiments. Experimental results showed that the proposed framework could collect data on menus satisfying both preferences and nutritional balance without tough labor.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"37 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":"128588072","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

More than Extracting "Important" Sentences: the Application of PEGASUS 不仅仅是提取“重要”句子:PEGASUS的应用

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00032

Ting-Hao Yang, Ching-Ching Lu, Wen-Lian Hsu

引用次数: 0

PAPR Reduction of OFDM Signals Using Partial Transmit Sequences with Modified Phase Generation Mechanism 改进相位产生机制的部分发射序列OFDM信号PAPR降低

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00058

Ming Li, Hsinying Liang

{"title":"PAPR Reduction of OFDM Signals Using Partial Transmit Sequences with Modified Phase Generation Mechanism","authors":"Ming Li, Hsinying Liang","doi":"10.1109/taai54685.2021.00058","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00058","url":null,"abstract":"This paper proposes a modified threshold selection partial transmit sequence (M-TS-PTS) technology, which is mainly used to reduce the peak-to-average power ratio (PAPR) of an orthogonal frequency division multiplexing (OFDM) system. The phase generation mechanism of the TS-PTS technology mainly divides the complex phase value used to disturb the input signal into two parts, the real part value and the Imaginary part value, and establishes a threshold value to determine the number of candidate signals. The transmitted signal is obtained by selecting the signal with the smallest PAPR from these candidate signals. Although the TS-PTS technology can reduce the amount of calculations required by the traditional PTS technology, how to improve the performance of the TS-PTS technology to reduce the PAPR is one of the popular research topics. This paper is mainly based on the architecture of TS-PTS technology to study an improved phase generation mechanism and threshold. The simulation results show that the recommended method not only retains the advantages of TS-PTS technology, but has better performance in reducing PAPR than the two technologies of TS-PTS and traditional PTS.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"12 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":"127124314","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 Clustering-Based Gauss Chaotic Mapping Particle Swarm Optimization for Auto Labeling in Human Activity Recognition 基于聚类的高斯混沌映射粒子群算法在人体活动识别中的自动标记

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00052

Bo-Yan Lin, Che-Nan Kuo, Yu-Da Lin

引用次数: 0

Applying Discriminant Analysis and LVQ Neural Network to an Empirical Study of Corporate Social Responsibility on Taiwanese Electronics Companies 运用判别分析和LVQ神经网络对台湾电子企业社会责任的实证研究

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00043

Hsio-Yi Lin

{"title":"Applying Discriminant Analysis and LVQ Neural Network to an Empirical Study of Corporate Social Responsibility on Taiwanese Electronics Companies","authors":"Hsio-Yi Lin","doi":"10.1109/taai54685.2021.00043","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00043","url":null,"abstract":"In recent years, the issue of corporate social responsibility has gradually been valued, some literatures have pointed out that financial performance and corporate social responsibility have a positive relationship, which makes investors and the public have positive views of general companies’ corporate social responsibility activities. Based on the evaluation of Taiwan’s \"CommonWealth Magazine\" from 2007 to 2017 which issued the Corporate Social Responsibility Award shortlist, this study selected the listed Taiwanese electronics companies for both awarded and un-awarded as the empirical samples for clustering. The corporate financial performance ratios and the corporate governance are used as input variables. According to the empirical results, most of the Taiwanese electronics companies that have been shortlisted for CSR indicators can be correctly identified and clustered. The empirical information can provide investors and shareholders a reference of investment. and encourage investors to actively invest and stabilize their psychology when investing.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"32 3 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":"134573593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance of C-V2X Communications for High Density Traffic Highway Scenarios 高密度交通公路场景下C-V2X通信性能研究

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00050

Teguh Indra Bayu, Yung-Fa Huang, Jeang-Kuo Chen

引用次数: 1

Music Genre Classification Based on Visualized Spectrogram 基于可视化谱图的音乐类型分类

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00048

Yu-Huei Cheng, Pang-Ching Chang, Che-Nan Kuo

引用次数: 0

A Fast Algorithm for Deriving Frequent Itemsets 频繁项集的快速生成算法

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00047

Cheng-Wei Wu, Yun-Wei Lin, Ming Chen, Jiashu Cheng

{"title":"A Fast Algorithm for Deriving Frequent Itemsets","authors":"Cheng-Wei Wu, Yun-Wei Lin, Ming Chen, Jiashu Cheng","doi":"10.1109/taai54685.2021.00047","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00047","url":null,"abstract":"When mining frequent itemsets (abbr. FIs) from dense datasets, too many itemsets are generated and results in the mining task from a large amount of execution time and high memory consumption. Frequent closed itemset (abbr. FCI) is a lossless and concise representation of FIs. Mining FCIs can not only greatly reduce the execution time and memory consumption, but also retain the complete information all of FI. Although many studies have proposed different mining FCI algorithms, but they have less developed methods that can effectively derive all FIs from FCIs. Form this point of view, this study proposes a novel efficient algorithm named DFI-List for efficiently deriving FIS from FCIs. The algorithm adopts the methodology of depth-first-search and divide-and-conquer to derive all FIs from FCIs. DFI-List efficiently derives all the FIs with vertical index structure called Cid List and uses SC Table to quickly find the support count of the derived FI. Experimental results show that the execution speed and memory consumption of the proposed algorithm with the proposed strategy is better than of the state-of-art algorithm.","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":"128283237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning real-time detection and correction system for stroke rehabilitation posture 脑卒中康复姿态的深度学习实时检测与校正系统

2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI) Pub Date : 2021-11-01 DOI: 10.1109/taai54685.2021.00056

Yen-Chiu Chen, Chia-Jou Yang

{"title":"Deep learning real-time detection and correction system for stroke rehabilitation posture","authors":"Yen-Chiu Chen, Chia-Jou Yang","doi":"10.1109/taai54685.2021.00056","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00056","url":null,"abstract":"Cerebrovascular diseases are becoming younger, and rehabilitation treatment becomes the importance of future recovery. Some rural areas have limited medical re-sources or people living in more remote mountainous areas have certain difficulties to receive treatment in hospitals. To solve this problem to build a set of OpenPose based human posture recognition algorithms to apply to stroke rehabilitation, to process the action of the characters in the image. Use the frame extraction algorithm of motion capture data to obtain the key frames of the character's movement, so as to analyze the details of the human movement .Then identify the body movements, carry out the stroke rehabilitation OpenPose human body model training, and use the Law of Cosines to calculate the angles of 3 points in BODY25, so as to analyze the details of the body movements to identify the body movements and provide the correct posture to guide the rehabilitation patients to the posture angle Rehabilitation.The experimental results show that the test subjects have a correct rate of posture and movement of 53.3% before using the system and 97% after using the system, and an improvement rate of 43.7%.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"26 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":"130451759","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