Pub Date : 2022-11-05DOI: 10.1109/isai-nlp56921.2022.9960258
{"title":"International Joint Conference 2022","authors":"","doi":"10.1109/isai-nlp56921.2022.9960258","DOIUrl":"https://doi.org/10.1109/isai-nlp56921.2022.9960258","url":null,"abstract":"","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128425217","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960243
Chanon Nontarit, T. Kondo, Warakorn Khamkaew, Jaroenmit Woradet, Jessada Karnjana
The shrimp agriculturists monitor shrimp growth by observing the size of shrimps in the feeding tray with the naked eye. This approach is time-consuming and needs experienced workers. This study proposes an automatic approach for estimating shrimp size using images. A mask region-based convolutional neural network with ResNeXt was trained to detect shrimps in an image. The detection model achieved an overall precision of 74.45%, recall of 72.20%, Fl score of 73.31 %, and AP of 69.04%. The two unique methods were proposed for estimating shrimp size. The first method achieved a mean absolute error of 0.30 cm and a mean absolute percentage error of 3.97%. The second method achieved a mean absolute error of 0.35 cm and a mean absolute percentage error of 4.59%. The proposed system achieved an automatic shrimp size estimation from the image and provided helpful information for agriculturists.
{"title":"Shrimp-growth Estimation Based on ResNeXt for an Automatic Feeding-tray Lifting System Used in Shrimp Farming","authors":"Chanon Nontarit, T. Kondo, Warakorn Khamkaew, Jaroenmit Woradet, Jessada Karnjana","doi":"10.1109/iSAI-NLP56921.2022.9960243","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960243","url":null,"abstract":"The shrimp agriculturists monitor shrimp growth by observing the size of shrimps in the feeding tray with the naked eye. This approach is time-consuming and needs experienced workers. This study proposes an automatic approach for estimating shrimp size using images. A mask region-based convolutional neural network with ResNeXt was trained to detect shrimps in an image. The detection model achieved an overall precision of 74.45%, recall of 72.20%, Fl score of 73.31 %, and AP of 69.04%. The two unique methods were proposed for estimating shrimp size. The first method achieved a mean absolute error of 0.30 cm and a mean absolute percentage error of 3.97%. The second method achieved a mean absolute error of 0.35 cm and a mean absolute percentage error of 4.59%. The proposed system achieved an automatic shrimp size estimation from the image and provided helpful information for agriculturists.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128197532","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960248
Jiranuwat Piriyasupakij, Ratchada Prasitphan
The encroachment of wild elephants in farming areas and villagers' habitats has caused conflicts among communities resulting to violence in preventing and driving elephants out of the area. The organizers have seen the impact of this problem and aims to solve it by designing and building a prototype Quadcopter that can survey and detect these wild elephants to warn villages and prevent further damage. The model takes crisp image of the detected wild elephants at a distance of 1M to 80% and alerts the forest technicians via the application. The test results showed that there were problems in the controls for it requires GPS signal. In the future, improvements and fixes in various parts shall be made to further develop innovative approaches that solve real-world problems.
{"title":"Design and Construct Quadcopter to Detect Wild Elephant to Alert","authors":"Jiranuwat Piriyasupakij, Ratchada Prasitphan","doi":"10.1109/iSAI-NLP56921.2022.9960248","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960248","url":null,"abstract":"The encroachment of wild elephants in farming areas and villagers' habitats has caused conflicts among communities resulting to violence in preventing and driving elephants out of the area. The organizers have seen the impact of this problem and aims to solve it by designing and building a prototype Quadcopter that can survey and detect these wild elephants to warn villages and prevent further damage. The model takes crisp image of the detected wild elephants at a distance of 1M to 80% and alerts the forest technicians via the application. The test results showed that there were problems in the controls for it requires GPS signal. In the future, improvements and fixes in various parts shall be made to further develop innovative approaches that solve real-world problems.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126649816","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960263
Dhanon Leenoi, Alongkorn Alongkornchai, Akkharawoot Takhom, P. Boonkwan, Thenchai Sunnithi
WordNet is a crucial language resource associated with artificial intelligence activities, for instance, constructing building models for advancement of computational linguistics and natural language processing, or representing statistical insights through knowledge graphs that emulate cognition and human understanding. Thai WordNet has been developed in many approaches, e.g., a merge approach in gold standard, and semi-auto construction with a bilingual dictionary. However, existing Thai WordNet is not easy to find words fit with the definition of synsets; and cover cultural gaps between the different languages of which needed to be aware. This paper presents a methodology of Translation Equivalence in order to construct Thai language resource, called LST22 Thai WordNet.
{"title":"A Construction of Thai WordNet through Translation Equivalence","authors":"Dhanon Leenoi, Alongkorn Alongkornchai, Akkharawoot Takhom, P. Boonkwan, Thenchai Sunnithi","doi":"10.1109/iSAI-NLP56921.2022.9960263","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960263","url":null,"abstract":"WordNet is a crucial language resource associated with artificial intelligence activities, for instance, constructing building models for advancement of computational linguistics and natural language processing, or representing statistical insights through knowledge graphs that emulate cognition and human understanding. Thai WordNet has been developed in many approaches, e.g., a merge approach in gold standard, and semi-auto construction with a bilingual dictionary. However, existing Thai WordNet is not easy to find words fit with the definition of synsets; and cover cultural gaps between the different languages of which needed to be aware. This paper presents a methodology of Translation Equivalence in order to construct Thai language resource, called LST22 Thai WordNet.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122996651","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960260
Apichat Chaweewanchon, Rujira Chaysiri
Portfolio optimization is one of the most intriguing topics in the field of finance. The purpose is to maximize return while minimizing risk. In this paper, we investigate the experimental performance of the classical Markowitz portfolio optimization with and without rebalancing based on the minimum risk in terms of portfolio return, portfolio risk, and Sharpe ratio, and compare the results to the experiments with transaction cost. The importance of this work stems from the fact that, while the MV model is extensively utilized, its use in the Thai stock market is limited. This analysis uses the historical close prices of 50 stocks from the Stock Exchange of Thailand 50 Index (SET50) between January 2018 and December 2021. The experiment showed that a portfolio with a rebalancing approach outperforms a portfolio without a rebalancing strategy.
{"title":"Portfolio Optimization and Rebalancing with Transaction Cost: A Case Study in the Stock Exchange of Thailand","authors":"Apichat Chaweewanchon, Rujira Chaysiri","doi":"10.1109/iSAI-NLP56921.2022.9960260","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960260","url":null,"abstract":"Portfolio optimization is one of the most intriguing topics in the field of finance. The purpose is to maximize return while minimizing risk. In this paper, we investigate the experimental performance of the classical Markowitz portfolio optimization with and without rebalancing based on the minimum risk in terms of portfolio return, portfolio risk, and Sharpe ratio, and compare the results to the experiments with transaction cost. The importance of this work stems from the fact that, while the MV model is extensively utilized, its use in the Thai stock market is limited. This analysis uses the historical close prices of 50 stocks from the Stock Exchange of Thailand 50 Index (SET50) between January 2018 and December 2021. The experiment showed that a portfolio with a rebalancing approach outperforms a portfolio without a rebalancing strategy.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134406342","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 : 2022-11-05DOI: 10.1109/isai-nlp56921.2022.9960253
{"title":"ISAI-NLP-AIOT 2022 Technical Oral Sessions","authors":"","doi":"10.1109/isai-nlp56921.2022.9960253","DOIUrl":"https://doi.org/10.1109/isai-nlp56921.2022.9960253","url":null,"abstract":"","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126763876","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960272
Wirot Treemongkolchok, P. Punyabukkana, Dittaya Wanvarie, Ploy N. Pratanwanich
Screening tests like the Montreal Cognitive Assessment (MoCA) can help diagnose mild cognitive impairment (MCI). MoCA comprises subtests that span various cognitive domains. Numerous researchers attempt to detect MCI by employing speech-related features such as acoustic, linguistic, and prosodic features. However, the features can distinguish patients with MCI from healthy people but do not describe each patient's specific cognitive domain impairment. This study focuses on Digit Backward Span (DBS) and Digit Forward Span (DFS), subtests related to the cognitive attention domain in MoCA. We develop a model and identify the most relevant speech features for the domain from a recorded voice from these subtests in the Thai MoCA. We rank features by their importance and found that using a subset of important features has higher predictive power than using the entire feature set in impairment in the attention domain. The most important features in both tests are the median duration of voice and the duration of voice.
{"title":"An Analysis of Acoustic Features for Attention Score in Thai MoCA Assessment","authors":"Wirot Treemongkolchok, P. Punyabukkana, Dittaya Wanvarie, Ploy N. Pratanwanich","doi":"10.1109/iSAI-NLP56921.2022.9960272","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960272","url":null,"abstract":"Screening tests like the Montreal Cognitive Assessment (MoCA) can help diagnose mild cognitive impairment (MCI). MoCA comprises subtests that span various cognitive domains. Numerous researchers attempt to detect MCI by employing speech-related features such as acoustic, linguistic, and prosodic features. However, the features can distinguish patients with MCI from healthy people but do not describe each patient's specific cognitive domain impairment. This study focuses on Digit Backward Span (DBS) and Digit Forward Span (DFS), subtests related to the cognitive attention domain in MoCA. We develop a model and identify the most relevant speech features for the domain from a recorded voice from these subtests in the Thai MoCA. We rank features by their importance and found that using a subset of important features has higher predictive power than using the entire feature set in impairment in the attention domain. The most important features in both tests are the median duration of voice and the duration of voice.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"328 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115965757","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}
Forex is an attractive choice for investors who admire any making profit challenges in the fluctuating market. But on the other hand, it means investors can lose money at the same time. Many investors look for ways to reduce the risks by finding price movement prediction tools. Therefore, this paper proposes the Stacking Machine Learning Models to predict the future price direction to help investors to decide and plan strategies. We experimented with comparing baseline models to evaluate the accuracy performance. In addition, we improve the accuracy performance using Technical Analysis and Fibonacci Retracements to gain an accuracy of 90%.
{"title":"Forex Price Movement Prediction Using Stacking Machine Learning Models","authors":"Thanapol Kurujitkosol, Akkharawoot Takhom, Sasiporn Usanavasin","doi":"10.1109/iSAI-NLP56921.2022.9960245","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960245","url":null,"abstract":"Forex is an attractive choice for investors who admire any making profit challenges in the fluctuating market. But on the other hand, it means investors can lose money at the same time. Many investors look for ways to reduce the risks by finding price movement prediction tools. Therefore, this paper proposes the Stacking Machine Learning Models to predict the future price direction to help investors to decide and plan strategies. We experimented with comparing baseline models to evaluate the accuracy performance. In addition, we improve the accuracy performance using Technical Analysis and Fibonacci Retracements to gain an accuracy of 90%.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131774143","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 : 2022-11-05DOI: 10.1109/iSAI-NLP56921.2022.9960268
Visarut Trairattanapa, Sasin Phimsiri, Chaitat Utintu, Riu Cherdchusakulcha, Teepakorn Tosawadi, Ek Thamwiwatthana, Suchat Tungjitnob, Peemapol Tangamonsiri, A. Takutruea, Apirat Keomeesuan, Tanapoom Jitnaknan, V. Suttichaya
With the development of robotic technology, au-tonomous robots have been extended to production industries to substitute manual tasks like routine operations. In the general manufacturer, analog gauges are the most commonly utilized and required operators for manual reading. Accordingly, an analog gauge reading can be considered a fundamental feature for the operator robots to be fully automated for inspection purposes. This paper presents the methods for reading multiple analog gauges automatically using a camera. The processing pipeline consists of two main stages: 1) gauge detector for extracting individual gauges and 2) gauge reader for estimating gauge values. For gauge detectors, we propose three different YOLOvS architecture sizes. The gauge readers are mainly categorized into computer-vision approach (CV), and deep learning regression approaches. The deep learning approaches consist of two CNN-based backbones, ResNetSO and EfficientNetV2BO, and one transformer-based SwinTransformer. Finally, we introduce the feasibility of the combination of each gauge detector and reader. As a result, the YOLOv5m detector with EfficientNetV2BO CNN backbone reader theoretically achieves the best performance but is not practical for industrial applications. In contrast, we introduce the YOLOv5m detector with the CV method as the most robust multiple gauge reader. As a result, it reaches the comparative performances to the EfficientNetV2BO backbone and is more compatible with robotic applications.
{"title":"Real-time Multiple Analog Gauges Reader for an Autonomous Robot Application","authors":"Visarut Trairattanapa, Sasin Phimsiri, Chaitat Utintu, Riu Cherdchusakulcha, Teepakorn Tosawadi, Ek Thamwiwatthana, Suchat Tungjitnob, Peemapol Tangamonsiri, A. Takutruea, Apirat Keomeesuan, Tanapoom Jitnaknan, V. Suttichaya","doi":"10.1109/iSAI-NLP56921.2022.9960268","DOIUrl":"https://doi.org/10.1109/iSAI-NLP56921.2022.9960268","url":null,"abstract":"With the development of robotic technology, au-tonomous robots have been extended to production industries to substitute manual tasks like routine operations. In the general manufacturer, analog gauges are the most commonly utilized and required operators for manual reading. Accordingly, an analog gauge reading can be considered a fundamental feature for the operator robots to be fully automated for inspection purposes. This paper presents the methods for reading multiple analog gauges automatically using a camera. The processing pipeline consists of two main stages: 1) gauge detector for extracting individual gauges and 2) gauge reader for estimating gauge values. For gauge detectors, we propose three different YOLOvS architecture sizes. The gauge readers are mainly categorized into computer-vision approach (CV), and deep learning regression approaches. The deep learning approaches consist of two CNN-based backbones, ResNetSO and EfficientNetV2BO, and one transformer-based SwinTransformer. Finally, we introduce the feasibility of the combination of each gauge detector and reader. As a result, the YOLOv5m detector with EfficientNetV2BO CNN backbone reader theoretically achieves the best performance but is not practical for industrial applications. In contrast, we introduce the YOLOv5m detector with the CV method as the most robust multiple gauge reader. As a result, it reaches the comparative performances to the EfficientNetV2BO backbone and is more compatible with robotic applications.","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"70 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120929117","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 : 2022-11-05DOI: 10.1109/isai-nlp56921.2022.9960282
{"title":"iSAI-NLP-AIoT Organizing Committee","authors":"","doi":"10.1109/isai-nlp56921.2022.9960282","DOIUrl":"https://doi.org/10.1109/isai-nlp56921.2022.9960282","url":null,"abstract":"","PeriodicalId":399019,"journal":{"name":"2022 17th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125923542","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：