检索结果-内蒙古大学图书馆

data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： R. Ponnusamy Veeramalai Sankaradass HarshivKrishna M Sre Sandhya K Bharath Sampath Aashika B Dept. of Artificial Intelligence and Data Science Madha Engineering College Chennai Tamil Nadu India Dept. of Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Crime classification using the Indian Penal Code (IPC) is a common task at each police station. It involves complex decision-making related to crimes and respective IPC sections for different cases. The IPC is the foundational criminal code in India, containing a list of all substantive penal laws with definitions and punishments for each offense. Automating the crime classification is helpful due to the complexity and sheer volume of crimes reported daily. This work uses machine learning techniques to automate crime classification based on IPC. To serve this purpose, this paper utilizes the K-Nearest Neighbors algorithm. The proposed system accepts an input crime report and textually corroborates the report to an IPC section. For this intent, the system relies on the bag-of-words technique for identifying sections under IPC by scrutinizing repetition and availability of key terms in the crime to 98% accuracy in classifying crimes. Hence, the automated method is quite effective for mapping crime reports into the corresponding sections of the IPC. Also, because the system can easily be deployed online, it will be easy to integrate with existing workflows at the police stations. So, case filing and management would become more effective. This reduces the amount of manual effort and also brings consistency in classification; for this reason, the tool is of immense value to law enforcement agencies nationwide. The innovation in the paper is the development of a machine learning-based system using the K-Nearest Neighbors (KNN) algorithm to automate the classification of crimes under the Indian Penal Code (IPC) based on textual crime reports.

关键词： Technological innovation Codes Accuracy Machine learning algorithms Automation Law enforcement Machine learning Nearest neighbor methods Classification algorithms System implementation

来源：评论

学校读者我要写书评

暂无评论

Temporal Fusion Transformer -LSTM-based Improved State of Charge Estimation of Li-ion battery for Real Drive Cycle

Temporal Fusion Transformer -LSTM-based Improved State of Ch...

引用

Power, Control and Computing Technologies (ICPC2T), Conference on

作者： Anbumalar Pandian S Shruthi V Dhanush Sriranganayaki Sundarajan P Abishek Sutha Subbian Pappa Natarajan Dept. of Instrumentation Engineering MIT Campus Anna University Chennai India Dept. of Artificial Intelligence and Data science Meenakshi Sundararajan Engineering college Chennai India

ISBN: (数字)9798331530402

ISBN: (纸本)9798331530419

Precise measurement of State of Charge (SoC) in Liion battery is crucial for effective utilization of energy storage system. However, it is challenging with physics-based model due to computation complexity while data-driven model often lacks generalization for unseen data. To improve the robustness of data-driven model, hybrid algorithms are employed. This paper focuses on combining Temporal Fusion Transformer (TFT)Long Short-Term Memory (LSTM) to improve the generalization of state-of charge estimation of unseen drive cycles. By leveraging the attention mechanism feature, temporal feature extraction of TFT along with memory capability of LSTM TFT-LSTM model is developed with optimal hyperparameters using Optuna framework. This model is used to estimate the SoC during the discharging cycle of a Turnigy Graphene Li-Ion Battery ($5000 \mathrm{mAh}, \mathbf{6 5 C}$) for the LA92 drive cycle at an ambient temperature of $40^{\circ} \mathrm{C}$. Additionally, uncertainty analysis is performed against US06 drive cycle. Finally, the performance of TFT-LSTM is compared with LSTM model. The results demonstrate that TFT-LSTM achieves better performance compared to LSTM with Root Mean Square Error (RMSE) of $\mathbf{1. 1 9 6 2}$ for unseen US06 drive cycle. These findings demonstrate the robustness of hybrid TFTLSTM against unseen drive cycle and highlight its potential under realistic conditions with variability.

关键词： Lithium-ion batteries Adaptation models Uncertainty computational modeling Estimation Drives Transformers Robustness Thin film transistors State of charge

来源：评论

学校读者我要写书评

暂无评论

Can Large Language Models Predict the Outcome of Judicial Decisions?

arXiv

引用

arXiv 2025年

作者： Kmainasi, Mohamed Bayan Shahroor, Ali Ezzat Al-Ghraibah, Amani Computer Science and Engineering Dept. Qatar University Doha Qatar School of Computing and Data Science OUC in partnership with LJMU Doha Qatar Biomedical Engineering Dept. Jordan University of Science and Technology Irbid Jordan

Large Language Models (LLMs) have shown exceptional capabilities in Natural Language Processing (NLP) across diverse domains. However, their application in specialized tasks such as Legal Judgment Prediction (LJP) for low-resource languages like Arabic remains underexplored. In this work, we address this gap by developing an Arabic LJP dataset, collected and preprocessed from Saudi commercial court judgments. We benchmark state-of-the-art open-source LLMs, including LLaMA-3.23B and LLaMA-3.1-8B, under varying configurations such as zero-shot, one-shot, and fine-tuning using LoRA. Additionally, we employed a comprehensive evaluation framework that integrates both quantitative metrics (such as BLEU, ROUGE, and BERT) and qualitative assessments (including Coherence, Legal Language, Clarity, etc.) using an LLM. Our results demonstrate that fine-tuned smaller models achieve comparable performance to larger models in task-specific contexts while offering significant resource efficiency. Furthermore, we investigate the impact of fine-tuning the model on a diverse set of instructions, offering valuable insights into the development of a more human-centric and adaptable LLM. We have made the dataset, code, and models publicly available to provide a solid foundation for future research in Arabic legal NLP1 Copyright © 2025, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Voice AI-Intelligence Based Voice Assistant

Voice AI-Intelligence Based Voice Assistant

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Pooja Garai Aditya Nikam Suyash Kerkar Samruddhi Deshmukh Atharva Mane Suvarna Bhise Dept. of Artificial Intelligence & Data Science Vasantdada Patil College Of Engineering & Visual Arts Mumbai India

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

Voice assistant applications have become integral parts of modern technology ecosystems, offering users convenient and efficient ways to interact with their devices. This paper introduces Voice Ai, a versatile voice assistant application developed using Android Studio and Google's Machine Learning Kit Machine learning(MLKit) for Optical Character Recognition (OCR) functionalities. The app includes features like setting alarms, making calls, opening applications, and conducting question-answer sessions powered by G4F. A comparative analysis between G4F and Google's backend is performed, assessing their performance and user satisfaction during question-answer interactions. Voice Ai simplifies daily tasks and boosts productivity, providing insights for developers, researchers, and end-users interested in AI-based voice assistant applications.

关键词： Measurement Productivity Accuracy Optical character recognition Personal voice assistants Machine learning Internet Time factors Smart phones Bars

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Smart Healthcare Using SDN-Driven Edge Computing

Personalized Federated Learning for Smart Healthcare Using S...

引用

IEEE Southeastcon

作者： Deborsi Basu Ritu Chaudhary Uttam Ghosh Raja Datta G. S. Sanyal School of Telecommunications Indian Institute of Technology Kharagpur India Dept. of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur India Dept. of Computer Science and Data Science School of Applied Computational Sciences MMC TN USA

ISBN: (数字)9798331504847

ISBN: (纸本)9798331504854

The advancement in distributed Federated Learning (FL) techniques is transforming next-generation edge computing, especially in e-Helathcare systems where data integrity and security are critical concerns. Collecting, processing and analyzing such substantial medical data is highly challenging due to their non-identical and versatile nature. Conventional FL approaches often show unsatisfactory and inaccurate results while operating on those data. Traditional FL methods also lack optimal dynamic management mechanisms for edge devices in ehealthcare, which is crucial to ensure that only authorized devices participate in handling any system failures and new registrations. To tackle such important aspects, in this work, we propose a personalized FL technique to handle abrupt label shifts among clients' data. The proposed approach further targets to achieve personalized models for local edge clients. A statistical batch normalization is proposed on customized edge servers, keeping the data specificity intact. To make the proposed system more secure and robust, a Software Defined Network-based (SDN-based) centralized server is used that allows only authorized and efficient edge clients to participate. The proposed comprehensive experiments on two healthcare datasets demonstrate better accuracy than traditional FL methods with enhanced security and privacy.

关键词： data privacy Federated learning data integrity Medical services Servers Security Software defined networking Next generation networking Batch normalization Edge computing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multimodal Transformers for Medical Image Captioning: Enhancing Automated Descriptions via AI Systems

Optimizing Multimodal Transformers for Medical Image Caption...

引用

International Image Processing, Applications and Systems Conference (IPAS)

作者： Mithila Arman Md. Khurshid Jahan Ahmed Faizul Haque Dhrubo Md. Mahfuzur Rhaman Sumaya Binte Zilani Choya Din Mohammad Dohan Md. Ashiq Ul Islam Sajid Md. Golam Rabiul Alam Dept. of CSE BRAC University Dhaka Bangladesh Dept. of ECE North South University Dhaka Bangladesh Dept. of Computational Data Science George Mason University Fairfax Virginia USA Dept. of CSE American International University-Bangladesh Dhaka Bangladesh

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

In contemporary diagnostic workflows, medical image captioning has emerged as a pivotal advancement, combining deep learning methodologies and transformer architectures to enhance accuracy and efficiency in medical interpretations. This paper proposes the optimization of multimodal transformers for automated medical image captioning, focusing on integrating Vision Transformers (ViT) and Bidirectional Auto-Regressive Transformers (BART) with novel variations such as Swin Transformers and GPT-2. We use a robust multimodal AI framework to explore how these architectures synergize to generate coherent and diagnostically relevant captions for radiological images. We assess the performance of multiple transformer models by employing the ROCO dataset, containing paired X-ray images and expert-generated reports. Our findings demonstrate that the ViT + BART combination yields the most stable and accurate captions, minimizing training and validation loss. In contrast, DEiT + MBART displayed instability, highlighting the need for further hyperparameter tuning. Through this comparative analysis, we underscore the critical role of transformer-based models in reducing the cognitive load on medical professionals, enhancing diagnostic accuracy, and promoting real-time, automated medical image interpretation.

关键词： Deep learning Training Computer vision Accuracy Transformers Real-time systems Artificial intelligence Medical diagnostic imaging X-ray imaging Tuning

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity for Industrial IoT: A Review on Vulnerabilities and Attacks

Cybersecurity for Industrial IoT: A Review on Vulnerabilitie...

引用

International Conference on Electronics, Materials engineering and Nano-Technology (IEMENTech)

作者： Reetu Kumari Sunil Kumar Amandeep Kamlesh Dutta Aparna Kumari Dept. of Computer Science & Engineering Guru Jambheshwar University of Science and Technology Hisar (Haryana) India Dept. of AI & Data Science Guru Jambheshwar University of Science and Technology Hisar Haryana India Dept. of Computer Science & Engineering National Institute of Technology Hamirpur Himachal Pardesh India Dept. of Computer Science & Engineering Institute of Technology Nirma University Ahmedabad Gujarat India

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

Internet has evolved from a network of connecting people to a network of connecting things, leading to a more complex and sophisticated network of Industrial Things, known as Industrial IoT (IIoT) today. This evolution has revolutionized the traditional Industrial system into real-time smarter systems that enhanced overall efficiency and productivity. Despite its benefits, the interconnected nature of IIoT, expanded the attack surface, exposing the systems to new crucial and complex cybersecurity threats. Several real time attacks on various industries as mentioned in this paper and the increasing cybersecurity cost over the years, clearly states the need of robust security solutions. To deeply understand the cybersecurity aspect, we provided a comprehensive study of attacks and vulnerabilities in this paper. In this paper, we did a indept. study of various IIoT related severe attacks and aspects related to these attacks, like vulnerabilities, impacts, potential solutions etc. We also provided future research directions to help the research community, to work upon and develop more robust and efficient cybersecurity solutions.

关键词： Industries Productivity Reviews Prevention and mitigation Intrusion detection Interconnected systems Real-time systems Internet Computer security Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

The Utilization of Google Cloud in the Healthcare Industry

The Utilization of Google Cloud in the Healthcare Industry

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Rishikesh Kapse Palash Gourshettiwar Dept. of Artificial Intelligence and Data Science Faculty of Engineering and Technology DMIHER (DU) Sawangi(M) Wardha Maharashtra Dept. of Computer Science And Medical Engineering Faculty of Engineering and Technology DMIHER (DU) Sawangi(M) Wardha Maharashtra

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

This essay's primary focus is on Google Cloud's use in healthcare and how it affects data management, teamwork, and cost-effectiveness. With a focus on Google Cloud, which improves the processing, storing, and accessibility of medical data, the study examines the trends, advantages, and persistent challenges that come with the increasing usage of cloud computing technology. These consist of remote patient monitoring, “artificial intelligence,” and “machine learning” applications in diagnostics, diagnostics, and personalized medicine. data privacy, security issues, and concerns with the HIPAA incident are among the problems that are discussed along with all the significant elements that could facilitate the cloud migration of healthcare.

关键词： Industries Cloud computing data privacy Technological innovation Medical services Machine learning Teamwork Security Predictive analytics Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Fire Hazard: Integrating Environmental Factors with Machine Learning

Predictive Modeling of Fire Hazard: Integrating Environmenta...

引用

International Conference on Electrical, Computer and Communication engineering (ECCE)

作者： Tanjim Taharat Aurpa Samiha Maisha Jeba Khaza Minhaz Bin Monib Maherun Nessa Ela Md Shoaib Ahmed Md Musfique Anwar Dept. of Data Science and Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Gazipur Bangladesh Dept. of Computer Science and Engineering International University of Business Agriculture and Technology Bangladesh Boise State University Boise Idaho USA Dept. of Computer Science and Engineering Jahangirnagar University Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

In today’s fast-paced world, where technology is advancing rapidly, the tragic loss of lives due to fire accidents is not only heart-wrenching but also poses a significant risk to public safety. Early prediction of such risks can play a crucial role in educating people about fire hazards, enabling them to be better prepared in case they find themselves in such unfortunate circumstances. Our study employed various machine learning (ML) techniques and evaluated their effectiveness by analyzing different factors. These factors are derived from the diverse living conditions in Bangladesh and were gathered through surveys. To refine and identify the critical features for classification, we utilized feature selection methods like ANOVA-f and the chi-square test. Our approaches have achieved a success rate of up to 97.98%.

关键词： Surveys Accuracy Feature extraction Hazards Encoding Vectors Public security Bayes methods Analysis of variance Random forests

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuning of SVM Using Metaheuristics: An Empirical Analysis

Hyperparameter Tuning of SVM Using Metaheuristics: An Empiri...

引用

Wireless Africa Conference (WAC)

作者： Sunday O. Oladejo Lateef A. Akinyemi Stephen O. Ekwe Taiwo G. Omomule Oluwaseyi P. Babalola School for Data Science and Computational Thinking Stellenbosch University South Africa Centre for Augmented Intelligence and Data Science University of South Africa South Africa Dept. of Electrical Electronic and Comp. Engineering Cape Peninsula University of Technology South Africa Dept of Mathematics and Statistics University of Guelph Ontario Canada

ISBN: (数字)9798331517588

ISBN: (纸本)9798331517595

The Support Vector Machine (SVM) performance is highly dependent on the selection of optimal hyperparameterse Conventional optimisation methods, including grid search, gradient descent, randomized search, and various experimental approaches, have been extensively utilized in the literature to identify optimal hyperparameters. This paper provides an empirical analysis of SVM's hyperparameter tuning by use of metaheuristics. We compare 11 widely known metaheuristics, such as the Genetic Algorithm (GA), Ant Colony Optimisation (ACO), Particle Swarm Optimisation (PSO), and Differential Evolution (DE), and employ three common datasets, namely Iris, Breast Cancer Wisconsin, and MNIST, due to their unique characteristics. Empirical analysis takes into account factors including cross-validation, number of agents, noise, and mis-labelled data insertion, with emphasis on performance metrics such as accuracy, number of support vectors, and computational time. Our findings reveal that the PSO outperforms other metaheuristics, followed by the DE and ACO. In addition, we conclude that the ACO has the least computational time.

关键词： Support vector machines Wireless communication Accuracy Reviews Metaheuristics Optimization methods Vectors Particle swarm optimization Tuning Genetic 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：