检索结果-内蒙古大学图书馆

37th Annual Conference on Legal Knowledge and Information systems, JURIX 2024

作者： Kung, Jo-Chi Chang, Chia-Hui Huang, Huai-Hsuan Chien, Kuo-Chun Dept. of Computer Science & Information Engineering National Central University Taiwan

ISBN: (纸本)9781643685625

This study introduces the Collision Clarification Generator (CCG), a Large Language Model-based system designed to assist in documenting traffic accidents. The CCG comprises three modules: Questioning, Information Extraction, and Accident Sequence Generation, which collectively streamline the process of gathering and structuring accident information. The system employs predefined question templates and a standardized Traffic Accident Record Format (TARF) to ensure comprehensive data collection. Evaluation of the CCG involved both human assessment and LLM-based automatic evaluation. Results showed an F1 score of 0.909 in human evaluation, and scores exceeding 7 out of 10 for accuracy and completeness in LLM-based assessment. These findings demonstrate the CCG’s effectiveness in accurately documenting accident information, potentially facilitating subsequent legal and insurance processes. © 2024 The Authors.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

Classification of Brain Tumor Images using Segmentation and Transfer Learning 5

Classification of Brain Tumor Images using Segmentation and ...

引用

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Bindu, J. Hima Devi, M. Uma Dept. of Computer Science and Engineering Andhra Pradesh Guntur522213 India

ISBN: (纸本)9798350395235

Classifying brain tumors is considered imperative for developing successful treatments. In this regard, binary classification of brain tumor was the major objective of this paper. This work uses a magnetic resonance imaging (MRI) dataset for classification purpose. Due to data paucity, the classifying frameworks in this proposed work tested the transfer learning method for extracting features by utilizing four convolutional neural networks (CNNs) of pre-trained capabilities. This research aimed at decreasing the training time, improving accuracy in classifying images, and preventing overfitting. Instead of considering the same datasets, the study considered segmented images of the original dataset for training. Four segmentation methods were used for creating a new segmented dataset of the original dataset. The authors done segmentation and trained the architecture with few pre-processes for three separate epoch numbers in place for investigating the effect on classification accuracy and time consumption. Additionally, profits were gained from obtaining suitable results within a minimal number of epochs in a constrained time amount. The experimental data proved that the transfer learning method has produced accurate outcomes with a classification accuracy of 96.98%. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Analysis on the Contribution and Economic Feasibility of Pumped Storage Hydropower in Korea Power System Considering the Penetration of Renewable Energy Generation

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第6期72卷 709-716页

作者： Kim, Hyun Joong Oh, Jae Young Yoon, Yong Tae Yoon, Yong Beum Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Dept. KEPCO International Nuclear Graduate School Korea Republic of

The government of South Korea proclaimed Energy Transition 3020 and the details thereupon with the generation mix. According to the Basic Plan for Long-term Electricity, additional Pump Storage Hydropower (PSH) were planned to be installed as measure for the variability from the Renewables. However, despite of the astronomical hard cost required for the PSHs, there has been a lack of assessments on the economic feasibility and effectiveness of the PSHs. According to the simulation, there were total three scenarios with high load variability due to the Renewables. The monitoring factors in each scenario were changes, in the generation cost, generation by fuel type, reserve capability by the PSHs, and emission of product gas. Furthermore, the economic feasibility was assessed from the perspectives of the PSHs. Based on the simulation, it was concluded that the additional PSHs decrease the daily generation cost and the ramping of the thermal generation, the greater reserve capabilities procured. On the other hand, emission of the product gas increases due to greater pumping load on the thermal generation. Moreover, it is economically infeasible for the PSHs to salvage their initial investment cost. Thus, this paper implicates the regulatory improvements for the formulation of the just market environment. Copyright © The Korean Institute of Electrical Engineers.

关键词： Power markets

来源：评论

学校读者我要写书评

暂无评论

ProctorXam - Online Exam Proctoring Tool 1

ProctorXam - Online Exam Proctoring Tool

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Ashwini, S. Bhuvan Kumar, M.S. Chandra Sai, D. Sathya, V. Atria Institute of Technology Dept. of Computer Science & Engineering Bangalore India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371802

Robust exam monitoring solutions are now essential in light of the most notable Covid-19 outbreak and the increasing inclination towards virtual learning. The automated method for supervising online exams that is suggested in this paper is intended to lessen the difficulties associated with exam cheating. With the assistance of our system's clever face detection algorithms, instructors may efficiently identify suspicious conduct by monitoring students' web activity and camera feed in real-time. Unlike earlier systems, ours provides improved accuracy and functionality, guaranteeing the authenticity of online tests. In light of the difficulties presented by the epidemic, this research attempts to offer a workable option for academic institutions and people wishing to administer fair and secure online exams. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Framework for Personality Prediction for E-Recruitment Using Machine Learning Algorithms 14

A Framework for Personality Prediction for E-Recruitment Usi...

引用

14th International Conference on Cloud Computing, Data Science and engineering, Confluence 2024

作者： Thapa, Lakshyajit Pandey, Aniket Gupta, Deepanshu Deep, Ayush Garg, Rakesh Amity University Dept. of Computer Science and Engineering Uttar Pradesh India

ISBN: (纸本)9798350344837

With rapid advancements in technology, the process of recruitment has evolved from traditional methods to online and automated methods known as e-recruitment. While e-recruitment streamlines the initial screening process, assessing the personality and suitability of candidates continues to remain a challenge. In this paper, we propose a framework for online personality prediction to aid the e-recruitment process. The framework utilizes machine learning algorithms to analyze user data from multiple online sources like resumes, social media profiles, and responses to psychometric tests, and predict their personality type based on established psychological theories. Four popular personality prediction models - Big Five, Myers Briggs, HEXACO, and Enneagram are discussed. State-of-the-art natural language processing and deep learning techniques like BERT are explored for feature extraction from text data. Popular supervised machine learning algorithms like logistic regression, Naive Bayes, k-nearest neighbors, support vector machines, random forest, XGBoost, and LSTM are compared to build predictive models. The proposed framework can help recruiters shortlist candidates better matched to job requirements, leading to increased hiring satisfaction and productivity. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

ResNet-50: The Deep Networks for Automated Breast Cancer Classification using MR Images 2

ResNet-50: The Deep Networks for Automated Breast Cancer Cla...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Das, Tejaswini Nayak, Debasish Swapnesh Kumar Kar, Anindita Jena, Lambodar Swarnkar, Tripti University Dept. of Computer Application FET-ITER Bhubaneswar India University FET-ITER Dept. of Computer Science and Engineering Bhubaneswar India Bhubaneswar India

ISBN: (纸本)9798350370188

One in every four cancer cases in women is breast cancer, which is the most prevalent malignancy in this group globally. In 2020, breast cancer will account for one in every eight new instances of cancer, according to projections of 2.3 million new cases. Breast cancer identification, both early and accurate, is critical to improve patient outcomes and survival rates. Magnetic resonance imaging (MRI) has developed as a valuable method for diagnosing breast cancer. Deep learning algorithms, notably convolutional neural networks (CNNs), have demonstrated exceptional effectiveness in a variety of medical image processing applications, including breast cancer classification. The ResNet-50 architecture has received a lot of interest in this context because of its excellent performance in image recognition tasks. ResNet-50 is a deep residual network that introduces skip connections and residual learning to solve the difficulty of training very deep neural networks. A total number of 1480 cancer MRI samples are collected from the Kaggle database, having two classes, which include healthy and malignant scans. It is observed that our proposed model with the data pre-processing techniques has achieved a classification accuracy of 92.01%. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Smart Parking System for Academic Institutions

Energy Efficient Smart Parking System for Academic Instituti...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Forelli, Ryan Naher, Jannatun Aksu, Sinan Panta, Prabin King, David Lehigh University Dept. of Electrical and Computer Engineering BethlehemPA United States

ISBN: (纸本)9798331504847

With a rise in student enrollment at academic institutions, there is an increasing need to improve and expand campus infrastructure, including dormitories, parking facilities, and other vital amenities. During peak times, such as campus move-in days, finding a parking spot can be a lengthy ordeal, involving searches across multiple lots. Many of these parking areas are frequently full and located at dead ends, making it difficult for drivers to maneuver when no spots are available, thus wasting time, energy, and fuel. Current parking occupancy detection systems face challenges such as high initial costs, as well as environmental and privacy concerns. To address these issues, we developed a proof-of-concept system known as the Vehicle Occupancy System (VOS). This solution is weather-resistant, energy-efficient, and eco-friendly, integrating seamlessly with a mobile application to provide real-time updates on parking availability for academic institutions. The system offers reliable monitoring of vehicle presence while being more cost-effective and energy-efficient than existing market solutions. © 2025 IEEE.

关键词： Garages (parking)

来源：评论

学校读者我要写书评

暂无评论

A Likelihood Ratio Test of Genetic Relationship among Languages

A Likelihood Ratio Test of Genetic Relationship among Langua...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Akavarapu, V.S.D.S. Mahesh Bhattacharya, Arnab Dept. of Computer Science and Engineering Indian Institute of Technology Kanpur India

ISBN: (纸本)9798891761148

Lexical resemblances among a group of languages indicate that the languages could be genetically related, i.e., they could have descended from a common ancestral language. However, such resemblances can arise by chance and, hence, need not always imply an underlying genetic relationship. Many tests of significance based on permutation of wordlists and word similarity measures appeared in the past to determine the statistical significance of such relationships. We demonstrate that although existing tests may work well for bilateral comparisons, i.e., on pairs of languages, they are either infeasible by design or are prone to yield false positives when applied to groups of languages or language families. To this end, inspired by molecular phylogenetics, we propose a likelihood ratio test to determine if given languages are related based on the proportion of invariant character sites in the aligned wordlists applied during tree inference. Further, we evaluate some language families and show that the proposed test solves the problem of false positives. Finally, we demonstrate that the test supports the existence of macro language families such as Nostratic and Macro-Mayan. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Parametric Model Order Reduction for Large-Scale Circuit Models using Extended Krylov Subspace 20

Efficient Parametric Model Order Reduction for Large-Scale C...

引用

20th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design, SMACD 2024

作者： Chatzigeorgiou, Chrysostomos Floros, George Chatzigeorgiou, Dimitrios Evmorfopoulos, Nestor Stamoulis, George University of Thessaly Dept. of Electrical & Computer Engineering Volos38334 Greece

ISBN: (纸本)9798350351927

The arising packing density of Very Large-Scale Integrated (VLSI) circuit models is subject to parameter variations due to temperature, geometry, process, and operating conditions. As a result, parameter Model Order Reduction (MOR) is motivated by such practical problems to compute the reduced-order model once and then re-simulate the low-order model with just updating the parameters. In this paper, we present a parametric Moment Matching (MM) MOR method, which employs the Extended Krylov Subspace (EKS) to efficiently extract accurate reduced-order models. The proposed method can handle large scale (linear) circuits and generate the corresponding reduced order models in parametric format. Experimental results on the industrial IBM power grid benchmarks prove the effectiveness of the proposed methods. © 2024 IEEE.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Methods in Climate Data Extraction and Forecasting

Comparative Analysis of Machine Learning Methods in Climate ...

引用

2025 International Conference on Emerging Technologies for Intelligent systems, ETIS 2025

作者： Khajgiwale, Parth Ajit Naveen, Atul Jethani, Nishtha Shitole, Ajitkumar International Institute of Information Technology Dept. of Computer Engineering Hinjewadi Pune India

ISBN: (纸本)9798331507541

Climate forecasting plays a critical role in understanding and mitigating the impacts of climate change. Advances in machine learning (ML) have significantly enhanced the accuracy of climate projections, particularly when dealing with large and complex datasets derived from regional climate models (RCMs) and global climate models (GCMs). This study investigates the application of various ML techniques for predicting precipitation based on temperature data extracted from climate datasets. We evaluate a range of regression models, including linear models and advanced ensemble methods such as Gradient Boosting and XGBoost, along with deep learning approaches like Convolutional Neural Networks (CNNs). Through a rigorous evaluation of these models, we focus on their performance as measured by Mean Squared Error (MSE) to identify the most effective techniques for capturing the intricate relationships within climate data. By analyzing existing studies and performance metrics, we aim to provide insights into the capabilities and limitations of these ML models in improving climate predictions. Furthermore, this research highlights the need for incorporating additional climate variables and optimizing model configurations to enhance predictive accuracy in climate forecasting. © 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

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：