2023 IEEE Conference on Artificial Intelligence (CAI)最新文献_第8页

Quantifying Domain Knowledge in Large Language Models 在大型语言模型中量化领域知识

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00091

Sudhashree Sayenju, Ramazan S. Aygun, Bill Franks, Sereres Johnston, George Lee, Hansook Choi, Girish Modgil

{"title":"Quantifying Domain Knowledge in Large Language Models","authors":"Sudhashree Sayenju, Ramazan S. Aygun, Bill Franks, Sereres Johnston, George Lee, Hansook Choi, Girish Modgil","doi":"10.1109/CAI54212.2023.00091","DOIUrl":"https://doi.org/10.1109/CAI54212.2023.00091","url":null,"abstract":"Transformer based Large language models such as BERT, have demonstrated the ability to derive contextual information from the words surrounding it. However, when these models are applied in specific domains such as medicine, insurance, or scientific disciplines, publicly available models trained on general knowledge sources such as Wikipedia, it may not be as effective in inferring the appropriate context compared to domain-specific models trained on specialized corpora. Given the limited availability of training data for specific domains, pre-trained models can be fine-tuned via transfer learning using relatively small domain-specific corpora. However, there is currently no standardized method for quantifying the effectiveness of these domain-specific models in acquiring the necessary domain knowledge. To address this issue, we explore hidden layer embeddings and introduce domain_gain, a measure to quantify the ability of a model to infer the correct context. In this paper, we show how our measure could be utilized to determine whether words with multiple meanings are more likely to be associated with domain-related meanings rather than their colloquial meanings.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132646416","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

Blended Temperature Forecasting Model for Thailand Using Multiple Data Sources 泰国多数据源混合温度预报模型

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/cai54212.2023.00141

Sukrit Jaidee, Walanchaporn Boon-Nontae, Weerayut Srithiam

{"title":"Blended Temperature Forecasting Model for Thailand Using Multiple Data Sources","authors":"Sukrit Jaidee, Walanchaporn Boon-Nontae, Weerayut Srithiam","doi":"10.1109/cai54212.2023.00141","DOIUrl":"https://doi.org/10.1109/cai54212.2023.00141","url":null,"abstract":"With the escalation in the cost of electricity, there has been a noticeable inclination towards the installation of solar photovoltaic (PV) systems in multiple regions across Thailand. The increase in PV installations has led to an electricity demand that fluctuates depending on the prevailing weather conditions, creating challenges in managing and regulating electricity demand. In order to support electricity regulators in managing the fluctuations, it is crucial to implement a solar power forecasting system for individual households. One of the critical variables in forecasting solar power generation, besides solar irradiance, is temperature. This study introduces a temperature prediction system for every geographic location in Thailand at a 10x magnification level, which provided an hourly temperature for each location in the country. The proposed model integrated input data from three open-source platforms, namely Meteostat, Weatherapi, and IBM Weather. Utilizing the capabilities of each input source, the deep learning model was employed. The system, powered by the proposed model, achieved a Mean Squared Error (MSE) of 1.17 °C when compared to the actual data acquired from the Meteorological Department of Thailand.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131287885","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

Structural health monitoring of steel moment frame buildings via sequence-based recurrent neural networks 基于序列递归神经网络的钢弯矩框架结构健康监测

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00154

Khashayar Heydarpour, Doeun Choe, Kyungyong Chung

{"title":"Structural health monitoring of steel moment frame buildings via sequence-based recurrent neural networks","authors":"Khashayar Heydarpour, Doeun Choe, Kyungyong Chung","doi":"10.1109/CAI54212.2023.00154","DOIUrl":"https://doi.org/10.1109/CAI54212.2023.00154","url":null,"abstract":"Signal-based damage detection has gained extensive attention in recent years due to its capability in improving the deficiencies of previous structural health monitoring methods. Deep learning, with high capabilities in feature learning, has emerged as a powerful tool for sequence classification. In this paper, sequence-based deep learning models using long short-term memory (LSTM) and gated recurrent units (GRU) networks are used to detect structural damages and damage locations applied to steel building structures. To propose an appropriate deep-learning method for structural health monitoring, sets of monitoring data from the IASC-ASCE benchmark building were used. The data was collected from 15 sensors to collect accelerations attached to a 4-story steel moment frame building. The data has been properly pre-processed, denoised, sliced, and normalized. K-fold cross-validation validation is performed. The networks are designed using various combinations of recurrent neural networks, such as LSTM and GRU. It is concluded that stacked multilayer bidirectional long short-term memory networks, with an accuracy of 98%, have a superior performance in detecting the presence and location of structural damage.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131304621","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

IEEE CAI 2023 Vertical Teams IEEE CAI 2023垂直团队

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/cai54212.2023.00008

引用次数: 0

Forecasting IT Industry trends using a Fuzzy Decision Support System 利用模糊决策支持系统预测IT行业趋势

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/cai54212.2023.00086

Dudnyk Oleksii, Sokolovska Zoia, A. Gegov, Farzad Arabikhan

引用次数: 0

A constrained Langevin-adapted Particle Filter for Aircraft Engines’ Health Monitoring 一种用于飞机发动机健康监测的约束langevin自适应粒子滤波

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00087

Dong Quan Vu, Y. Marnissi, S. Razakarivony, M. Nocture

引用次数: 0

Automatic segmentation and evaluation techniques for free flap in reconstruction surgery using deep learning 基于深度学习的游离皮瓣重建手术自动分割与评估技术

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00066

Sang Mee Lee, M. Chung, Zero Kim, K. Lee, Da Eun Kim, Ji Su Kim

{"title":"Automatic segmentation and evaluation techniques for free flap in reconstruction surgery using deep learning","authors":"Sang Mee Lee, M. Chung, Zero Kim, K. Lee, Da Eun Kim, Ji Su Kim","doi":"10.1109/CAI54212.2023.00066","DOIUrl":"https://doi.org/10.1109/CAI54212.2023.00066","url":null,"abstract":"Postoperative free flap monitoring would be crucial to achieve the best outcomes of microsurgical reconstruction, for which meticulous clinical examination has served as the gold standard. Despite its high reliability, requirement of excessive consumption of manpower has been addressed a main drawback. To overcome this issue, this study aimed to develop a novel system for free flap monitoring, which is based on artificial intelligence (AI) using deep learning system. Photographs of postoperative appearance of free flaps were gathered retrospectively from patients who underwent free flap-based reconstruction between 2020 and 2021, and prospectively from those in 2022, and used with dividing into 80%:20% for model training and test. The development process proceeded with categorizing into two parts; flap segmentation model that can identify the flap region in the photographs, and flap status classification model that can evaluate the flap perfusion status based on its color. A total of 2,068 photographs of 433 patients were used. The most reliable model for flap segmentation was developed based on U-Net algorithm, achieving a Dice Coefficient of 0.972. For the flap status classification model, the Support Vector Machine algorithms was adopted, showing an accuracy of 0.926, from which the ratio of red pixels in the flap region was extracted as a quantitative indicator. Our results suggest that this novel AI-based model for flap segmentation and status classification could achieve reliable outcomes. A further upgraded system based on this model may provide optimal flap monitoring, keeping high accuracy and reducing medical staffs’ labor burden.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125286194","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

Improved Contrastive Unpaired Translation for Metal Artifacts Reduction in Nasopharyngeal CT Images 鼻咽CT图像金属伪影减少的改进对比非配对平移

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00152

Yu-Hsing Hsieh, Jia-Da Li, Yao Lee, Chu-Song Chen, LiFu Wu, S. H. Cheng

引用次数: 0

Affective Computing for Social Companion Robots Using Fine-grained Speech Emotion Recognition 基于细粒度语音情感识别的社交伴侣机器人情感计算

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/cai54212.2023.00146

Saransh Ahuja, Amir Shabani

引用次数: 0

Skilled Agricultural Task Delivery by a Digital Twin 数字孪生的熟练农业任务交付

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00159

V. Kaburlasos, C. Lytridis, G. Siavalas, Viktoria Nikoleta Tsakalidou, Christos Tsakmakis, Ioannis Kalathas, T. Pachidis, K. Rantos, K. Kalaboukas

引用次数: 0