检索结果-内蒙古大学图书馆

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Sumeth Yuenyong Norapat Buppodom Koravich Sangkaew Konthee Boonmeeprakob Prachya Boonkwan Jillaphat Jaroenkantasima Pitikorn Khlaisamniang Anuruth Lertpiya Apivadee Piyatumrong Peerawat Rojratchadakorn Thaweewat Rugsujarit Teerapol Saengsukhiran Kriangkrai Saetan Isada Sukprapa Thanachot Thavornmongkol Nucharee Thongthungwong Patteera Triamamornwooth Chanon Utupon Kobkrit Viriyayudhakorn Phoochit Witchutanon Sadit Wongprayon Thepchai Supnithi Department of Computer Engineering Faculty of Engineering Mahidol University National Electronics and Computer Technology Center Pathumthani Thailand Artificial Intelligence Asssociation of Thailand Big Data Institute (Public Organization) Bangkok Department of Electrical Engineering Faculty of Engineering Kasetsart University Looloo Technology Faculty of Engineering Kasetsart University Kasikorn Labs Kasikorn Business Technology Group Faculty of Science King Mongkut’s Institute of Technology Ladkrabang School of Information Computer and Communication Technology Sirindhorn International Institute of Technology Thammasat University Next AI Solutions Department of Biomedical Engineering Faculty of Engineering Mahidol University Department of Computer Science University of Liverpool Department of Mechanical Engineering King Mongkut’s University of Technology North Bangkok Artificial Intelligence Entrepreneur Association of Thailand Department of Computer Engineering Faculty of Engineering Chulalongkorn University

ISBN: (数字)9798331509910

ISBN: (纸本)9798331509927

Large language models (LLMs) play an important role in modern NLP technology as they are versatile for a wide array of NLP tasks. However, constructing an LLM is challenging due to concealed construction pipelines, the lack of cleansed datasets, and hyperparameter settings, making it almost irreproducible. This paper presents an efficient pipeline for constructing an LLM tailored to a low-to-medium-sourced language with a high level of data contamination and tools to cleanse the dataset. Following our pipeline, we constructed OpenThaiGPT, an LLM for Thai, with only open-sourced datasets such as CC100, OSCAR, and mC4, and achieved the state-of-the-art accuracies on our downstream tasks. Here, we disclosed the data statistics and all hyperparameter settings for reproducibility.

关键词： Accuracy Large language models Decontamination Pipelines Data visualization Data models Natural language processing Reproducibility of results Arrays Contamination

来源：评论

学校读者我要写书评

暂无评论

Ripeness Classification of Fresh Oil Palm Using Deep Learning

Ripeness Classification of Fresh Oil Palm Using Deep Learnin...

引用

13th International electrical engineering Congress, iEECON 2025

作者： Srithai, Nathaphat Rittireung, Krittiporn Sungthong, Nongnoot Srisomboon, Kanabadee Lee, Wilaiporn Sa-Ing, Vera King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand Broadcasting and Telecommunications Research and Development Fund for Public Interest Office The National Broadcasting and Telecommunications Commission Bangkok Thailand

ISBN: (纸本)9798331543952

The challenge of accurately ripeness level classifying from fresh oil palm fruit, this research investigated the problems and methods that were used in ripeness level classification. The goal of this research is to present a method for classifying the ripeness levels of oil palm fruits using deep learning techniques applied to image data. This research applies a deep learning model for classifying the ripeness level of fresh oil palm fruit and aiming for real-time application or mobile usage. The proposed model, Yolov9n (nano), adapts principles from convolutional neural networks that was tuned the learning parameters consist of the Adam optimizer, a learning rate of 0.001, and a batch size of 32, result in the most accurate ripeness level classification model. The research demonstrates the Yolov9n (nano) improved model with optimized parameters to achieve the highest accuracy. Training and validation datasets represent precision of 99.4%, recall of 99.6%, mean average precision at 50% (mAP50) of 99.5%, and mAP50-95 of 92.6%. These findings confirm the model's effectiveness in accurately classifying the ripeness level of oil palm fruit from images. The study provides guidance for the practical deep learning implementation of ripeness level classification on fresh oil palm imaging for efficient harvesting by farmers cultivating oil palm. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Road Map of Prompt engineering for ChatGPT in Healthcare: A Perspective Study

A Road Map of Prompt Engineering for ChatGPT in Healthcare: ...

引用

34th Medical Informatics Europe Conference, MIE 2024

作者： Abhari, Shahabeddin Fatahi, Somayeh Saragadam, Ashish Chumachenko, Dmytro Pelegrini Morita, Plinio School of Public Health Sciences University of Waterloo WaterlooON Canada Department of Computer Science University of Saskatchewan SaskatoonSK Canada Department of Mathematical Modelling and Artificial Intelligence National Aerospace University "Kharkiv Aviation Institute" Kharkiv Ukraine Department of Systems Design Engineering University of Waterloo WaterlooON Canada Research Institute for Aging University of Waterloo WaterlooON Canada Centre for Digital Therapeutics Techna Institute University Health Network TorontoON Canada Institute of Health Policy Management and Evaluation Dalla Lana School of Public Health University of Toronto TorontoON Canada

ISBN: (纸本)9781643685335

Generative AI models, such as ChatGPT, have significantly impacted healthcare through the strategic use of prompts to enhance precision, relevance, and ethical standards. This perspective explores the application of prompt engineering to tailor outputs specifically for healthcare stakeholders: patients, providers, policymakers, and researchers. A nine-stage process for prompt engineering in healthcare is proposed, encompassing identifying applications, understanding stakeholder needs, designing tailored prompts, iterative testing and refinement, ethical considerations, collaborative feedback, documentation, training, and continuous updates. A literature review focused on "Generative AI" or "ChatGPT," prompts, and healthcare informed this study, identifying key prompts through qualitative analysis and expert input. This systematic approach ensures that AI-generated prompts align with stakeholder requirements, offering valuable insights into symptoms, treatments, and prevention, thereby supporting informed decision-making among patients. © 2024 The Authors.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-Coupled Electrocoagulation Based Azo Dye Fading Rate Prediction Using Deep Neural Networks

Ultrasound-Coupled Electrocoagulation Based Azo Dye Fading R...

引用

International KES Conference on Human Centred Intelligent Systems, KES HCIS 2023

作者： Akoulih, Meryem Tigani, Smail Wakrim, Asmaa Chehri, Abdellah Saadane, Rachid Ghachtouli, Sanae El IME Lab Faculty of Science Hassan 2 University Casablanca20250 Morocco AAIR Lab Digital Engineering and Artificial Intelligence Systems High Private School Casablanca20100 Morocco Electrical Engineering Department SIRC-LaGeS Hassania School of Public Labors Casablanca20250 Morocco Department of Mathematics and Computer Science Royal Military College KingstonONK7K 7B4 Canada

ISBN: (纸本)9789819934232

This research paper presents a deep learning based predictive model for predicting the azo dye fading rate during electrocoagulation coupled with ultrasound. Electrocoagulation is a commonly used method for the treatment of wastewater contaminated with azo dyes, but the efficiency of this process can be improved by incorporating ultrasound. The proposed deep learning model is trained on a dataset of electrocoagulation experiments with varying parameters such as current density, pH, and treatment time, as well as the presence or absence of ultrasound. The model is able to accurately predict the azo dye removal rate for new sets of electrocoagulation parameters, providing a valuable tool for optimizing the treatment process. The model’s performance is evaluated using standard metrics, and the results demonstrate its effectiveness in predicting azo dye removal rate. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Azo dyes

来源：评论

学校读者我要写书评

暂无评论

Learning on Forecasting HIV Epidemic Based on Individuals’ Contact Networks

Learning on Forecasting HIV Epidemic Based on Individuals’ ...

引用

17th International Joint Conference on Biomedical engineering Systems and Technologies, BIOSTEC 2024

作者： Sun, Chaoyue Liu, Yiyang Parisi, Christina Fisk-Hoffman, Rebecca Salemi, Marco Fang, Ruogu Danforth, Brandi Prosperi, Mattia Marini, Simone Department of Electrical and Computer Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States Department of Epidemiology College of Public Health and Health Professions and College of Medicine University of Florida GainesvilleFL United States Department of Pathology Immunology and Laboratory Medicine College of Medicine University of Florida GainesvilleFL United States J. Crayton Pruitt Family Department of Biomedical Engineering Herbert Wertheim College of Engineering University of Florida GainesvilleFL United States Center for Cognitive Aging and Memory McKnight Brain Institute University of Florida GainesvilleFL United States Florida Department of Health 4025 Esplanade Way TallahasseeFL United States Emerging Pathogens Institute University of Florida GainesvilleFL United States

Improving the diagnosis of HIV is a fundamental objective of the Ending the HIV Epidemic initiative, as it represents the initial step toward treatment and achieving undetectable status, thereby reducing transmission. To attain these objectives effectively, it is crucial to identify the groups most susceptible to HIV, allowing interventions to be tailored to their specific needs. In this study, we developed a predictive model designed to assess individual HIV risk within a high-risk contact network – predicting treatment or at-risk – leveraging surveillance data collected through routine HIV case interviews in Florida. Unique to our analysis, we explored the incorporation of behavioral network information with Graph Neural Networks to enhance the predictive capacity for identifying individuals within the treatment or intervention categories, when compared to models that mainly consider conventional HIV risk factors. Our deployed Graph Isomorphism Network achieved 77.3% and 73.2% balanced accuracy in inductive and trans ductive learning scenarios respectively, outperforming the traditional prediction algorithms that do not leverage the network structure. We then usedour model to further investigate the importance of demographic and behavioral factors in the HIV risk prediction process. Our findings provide valuable insights for healthcare practitioners and policymakers in their efforts to combat HIV infection. © 2024 by SCITEPRESS – Science and Technology publications, Lda.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

From Lab to Field: Real-World Evaluation of an AI-Driven Smart Video Solution to Enhance Community Safety

arXiv

引用

arXiv 2023年

作者： Yao, Shanle Ardabili, Babak Rahimi Pazho, Armin Danesh Noghre, Ghazal Alinezhad Neff, Christopher Bourque, Lauren Tabkhi, Hamed Department of Electrical and Computer Engineering University of North Carolina at Charlotte United States Public Policy Program University of North Carolina at Charlotte 9201 University City Blvd CharlotteNC28223 United States

This article adopts and evaluates an AI-enabled Smart Video Solution (SVS) designed to enhance safety in the real world. The system integrates with existing infrastructure camera networks, leveraging recent advancements in AI for easy adoption. Prioritizing privacy and ethical standards, pose based data is used for downstream AI tasks such as anomaly detection. Cloud-based infrastructure and mobile app are deployed, enabling real-time alerts within communities. The SVS employs innovative data representation and visualization techniques, such as the Occupancy Indicator, Statistical Anomaly Detection, Bird’s Eye View, and Heatmaps, to understand pedestrian behaviors and enhance public safety. Evaluation of the SVS demonstrates its capacity to convert complex computer vision outputs into actionable insights for stakeholders, community partners, law enforcement, urban planners, and social scientists. This article presents a comprehensive real-world deployment and evaluation of the SVS, implemented in a community college environment across 16 cameras. The system integrates AI-driven visual processing, supported by statistical analysis, database management, cloud communication, and user notifications. Additionally, the article evaluates the end-to-end latency from the moment an AI algorithm detects anomalous behavior in real-time at the camera level to the time stakeholders receive a notification. The results demonstrate the system’s robustness, effectively managing 16 CCTV cameras with a consistent throughput of 16.5 frames per second (FPS) over a 21-hour period and an average end-to-end latency of 26.76 seconds between anomaly detection and alert issuance. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Constrained Regularization by Denoising with Automatic Parameter Selection

arXiv

引用

arXiv 2023年

作者： Cascarano, Pasquale Benfenati, Alessandro Kamilov, Ulugbek S. Xu, Xiaojian the Department of the Arts University of Bologna Bologna40123 Italy the Department of Environmental Science and Policy University of Milan Milan20133 Italy the Department of Computer Science & Engineering Department of Electrical & System Engineering Washington University in St. Louis St. LouisMO63130 United States the Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States

Regularization by Denoising (RED) is a well-known method for solving image restoration problems by using learned image denoisers as priors. Since the regularization parameter in the traditional RED does not have any physical interpretation, it does not provide an approach for automatic parameter selection. This letter addresses this issue by introducing the Constrained Regularization by Denoising (CRED) method that reformulates RED as a constrained optimization problem where the regularization parameter corresponds directly to the amount of noise in the measurements. The solution to the constrained problem is solved by designing an efficient method based on alternating direction method of multipliers (ADMM). Our experiments show that CRED outperforms the competing methods in terms of stability and robustness, while also achieving competitive performances in terms of image quality. © 2023, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

FixCyprus: Crowdsourcing Smartphone Imagery Data For Managing Road Safety Hazards

FixCyprus: Crowdsourcing Smartphone Imagery Data For Managin...

引用

International Conference on Mobile Data Management

作者： Georgios Christou Andreas Georgiou Christos Laoudias Aristotelis Savva Christos G. Panayiotou KIOS Center of Excellence University of Cyprus Cyprus Public Works Department Ministry of Transport Communications and Works Cyprus Department of Electrical and Computer Engineering University of Cyprus Cyprus

In this demonstration paper, we present FixCyprus, which is a cost-effective crowdsourcing service for road transportation authorities in Cyprus to gather information and manage defects and incidents on the road network and surrounding infrastructure (e.g., pavements, lighting, drinking water pipes, etc.). The production service, which includes a lightweight and user-friendly mobile application for sharing image-annotated incident reports, is already operating nationwide for six months providing significant budget savings by reducing field inspections and the use of expensive equipment. We will demonstrate FixCyprus using two modes: i) Interactive mode, where attendees will be able to create and submit their own dummy incident reports and see the end-to-end processing flow in a test environment and ii) Trace-driven mode, where attendees will be able to visualize a large number of synthetic reports, see the workload for manually managing them, and explore enhancements that are underway for automating some of the underlying tasks using machine learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Neural Networks Based Needle Detection for Medical Retinal Surgery

arXiv

引用

arXiv 2023年

作者： Xu, Jidong Yu, Jinglun Yao, Jianing Zhang, Rendong Department of Electrical and Computer Engineering Johns Hopkins University Baltimore United States Department of Biostatistics Johns Hopkins Bloomberg School of Public Health Baltimore United States

In recent years, deep learning technology has developed rapidly, and the application of deep neural networks in the medical image processing field has become the focus of the spotlight. This paper aims to achieve needle position detection in medical retinal surgery by adopting the target detection algorithm based on YOLOv5 as the basic deep neural network model. The state-of-the-art needle detection approaches for medical surgery mainly focus on needle structure segmentation. Instead of the needle segmentation, the proposed method in this paper contains the angle examination during the needle detection process. This approach also adopts a novel classification method based on the different positions of the needle to improve the model. The experiments demonstrate that the proposed network can accurately detect the needle position and measure the needle angle. The performance test of the proposed method achieves 4.80 for the average Euclidean distance between the detected tip position and the actual tip position. It also obtains an average error of 0.85 degrees for the tip angle across all test sets. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Empowering Healthcare with AI: Brain Tumor Detection Using MRI and Multiple Algorithms

Empowering Healthcare with AI: Brain Tumor Detection Using M...

引用

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Micheal Olaolu Arowolo Williams Oluwatobiloba Ajayi Prisca Olawoye Oluwatomilola Babajide Happiness Eric Aigbogun Mukhtar Damola Salawu Marion Olubunmi Adebiyi Ayodele Adebiyi Department of Electrical Engineering and Computer Science University of Missouri Columbia USA Department of Computer Science Landmark University Omu-Aran Nigeria Department of Public Health Western Illinois University USA Stowers Institute for Medical Research Kansas City MO USA Department of Computer Science Kwara State University Malete Nigeria

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

Artificial intelligence (AI) has revolutionized neuroimaging, especially in the identification of brain cancers, by giving patients greater control and providing highly accurate diagnostic imaging. utilizing MRI data, this study investigates the feasibility of AI-driven brain tumor diagnosis utilizing methods including K-nearest neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Naive Bayes (NB). Careful data preprocessing allowed us to access Kaggle's brain MRI datasets labeled with cancer information, which allowed us to obtain accurate results. While Naive Bayes achieved 60% accuracy and 84% sensitivity, SVM achieved 82% sensitivity and 62% accuracy. Enhanced sensitivity and precision, in addition to 63% accuracy, were shared by Decision Tree and KNN. These findings suggest that AI could be helpful in the multi-method detection strategy that is essential for the correct diagnosis of brain tumors. This study provides clinicians with flexible diagnostic tools powered by artificial intelligence, opening a new chapter in the fight against neurological disorders and for better patient outcomes. The combination of artificial intelligence with magnetic resonance imaging (MRI) holds great promise for the better early detection and treatment planning of brain cancers. As AI keeps changing the healthcare landscape, these studies show how AI can revolutionize diagnostics and the fight against neurological illnesses.

关键词： Support vector machines Accuracy Sensitivity Magnetic resonance imaging Brain cancer Nearest neighbor methods Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：