检索结果-内蒙古大学图书馆

5th International Conference on Advanced Research in Computing, ICARC 2025

作者： Viraj, Harsha Wijesekara, Sumuduni Tharuka, Kuluni Fernando, Shenika Jayakody, Anuradha Wijesiri, Pipuni Sri Lanka Institute of Information Technology Dept of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798331530983

Analyzing dairy cattle behavior and anomalies is a critical component of precision livestock farming, allowing farmers to remotely monitor animals for health and behavior. In order to accomplish this task better, the use of IoT technology and machine learning algorithms is more appropriate as per the time. The YOLO (you only look once) object recognition algorithm is more suitable for that, and the use of this algorithm allows these processes to be performed automatically and in real time with high accuracy. YOLO's ability to recognize multiple objects in images or videos makes Yolo ideal for cattle detection and tracking. © 2025 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

SWATI AI : Advancing AI Models from Rule-Based Frameworks to NLP-Driven Prescriptive Analytics to Assist Victims of Domestic Abuse 1

SWATI AI : Advancing AI Models from Rule-Based Frameworks to...

引用

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Awasekar, Dipali Dilip Lobo, L.M.R.J. WIT-Solapur Punyashlok Ahilyadevi Holkar Solapur University Dept. of Computer Science and Engg. Maharashtra Solapur India Walchand Institute of Technology Dept. of Information Technology Maharashtra Solapur India

ISBN: (纸本)9798350355611

SWATI AI (Support and Welfare Assistance through technology Interface) is an AI-driven chatbot designed to assist victims of domestic abuse by providing accessible, non-judgmental, and actionable legal guidance. This paper introduces the LAMP2 (Legal Analytics Model for Prediction and Prescription), the core framework that powers SWATI, progressing through four distinct research phases aimed at enhancing decision-making capabilities for victims of domestic violence under the Protection of Women from Domestic Violence Act, 2005. Phase 0 focuses on the creation of a curated dataset, PROTECT-JC, which compiles judgments from district courts, high courts, and the Supreme Court of India between 2008 and 2024. This dataset, developed in collaboration with legal experts and judicial professionals, serves as the foundation for training models to predict legal outcomes. Phase 1 introduces a rule-based decision framework in LAMP2 1.0, designed to extract and map predefined intents and entities from user inputs. This phase enables the structured documentation of complaints, providing victims with initial guidance based on the legal provisions of the Domestic Violence Act, 2005. The rule-based approach achieved accuracy of 80%, but with limited customization for individual cases. In Phase 2, LAMP2 2.0 leverages supervised machine learning models to predict legal outcomes, such as protection orders, custody orders, and monetary relief. These models, including Random Forest, XGBoost, and Decision Trees, achieved impressive results, with the Random Forest model showing 96.5% accuracy in predicting protection orders. Phase 3 evolves the model further with NLP-driven predictive analytics to process unstructured legal narratives, such as case judgments, transforming them into structured data for improved predictions. Models like Llama and Mixtral demonstrated strong summarization capabilities and show promise in predicting legal results. The integration of NLP and machine learning te

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

High Voltage and High Frequency DC Power Supply with Ultra High Voltage SiC Schottky Barrier Diode Modules

引用

Journal of Japan Institute of Electronics Packaging 2025年第1期28卷 123-131页

作者： Nomura, Yuki Funaki, Tsuyoshi Research Dept. NexFi Technology Inc. 2-1 Yamadaoka Suita-shi Osaka565-0871 Japan Dept. of Electronic and Information Engineering Osaka University 2-1 Yamadaoka Suita-shi Osaka565-0871 Japan

A high-voltage (HV) DC power supply typically consists of an inverter, a transformer and a Cockcroft-Walton (CW) voltage multiplier. High-frequency operation of the inverter can reduce the required capacitance of HV capacitors in the CW circuits, allowing miniaturization of HV DC power supplies. High voltage rectifying diodes used in high frequency CW circuits can reduce switching losses by using SiC Schottky barrier diodes (SBD). In this study, we developed an ultra-high voltage SiC SBD module connected in series. However, an increase in the number of SBD modules connected in series results in increased conduction loss, indicating a limitation in the high-voltage blocking capability. This paper proposes an effective circuit configuration required to improve the efficiency of an HV DC power supply by considering the number of series-connected SBDs in the module along with the number of stages in the CW circuit. © The Japan Institute of Electronics Packaging.

关键词： Schottky barrier diodes

来源：评论

学校读者我要写书评

暂无评论

Implementing HR Management System with an AI Powered ChatBot 3

Implementing HR Management System with an AI Powered ChatBot

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Susitra, D. Pratheesh, G. Karthiga, J.D. Dhanalakshmi, K. Shamreen Ahamed, B. Sylvia Grace, J. Dept. of Computer Science and Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai600119 India

ISBN: (纸本)9798331527549

Human Resource (HR) management is one important section that increases the success of an organization to handle some important functions like employee data manipulation, attendance tracking, payroll processing, and performance evaluation. With the management of these processes becoming key to the success of small-scale startups, it poses a very big challenge for many of them to be able to manage these processes efficiently and cost efficient. By contrast, the old era of traditional HR systems was based on database driven architectures that are expensive in terms of operational cost, require storage space and complex infrastructural needs. These limitations often make traditional HR systems impossible for a startup that would prefer lightweight, affordable, and scalable solutions. Startups need robust platforms to streamline HR work streams, but often lack with financial resources for building complex database driven systems. In this paper, an AI powered HR management system is developed to simplify employee management processes for small scale startups. In this system. cache memory is used instead of traditional databases, thereby the operational cost of the system will be reduced for storage and retrieval of employee details. Automated Attendance Management enhanced with Face Recognition technology, Payroll Management, Leave Management, Feedback Submission modules are included. It is integrated with an AI powered chatbot, which facilitates a smooth interaction by the employees with query for information, submit leave requests and pull up all payroll information etc. A user-friendly dashboard for a consolidated view of employee profiles, attendance records, leave approvals, and payroll data can be served over an optimized and time efficient HR workflow. This system addresses the needs of the startups such as flexible usage, cost effective operations and improved resource management. © 2025 IEEE.

关键词： AI powered chatbot for Small-scale startups using cache memory attendance management face recognition HR Management System leave management payroll management

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques for the Ransomware Detection: Current Methods and Challenges 1

Artificial Intelligence Techniques for the Ransomware Detect...

引用

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Rakibe, Priya Jawale, Madhuri Computer Engineering Research Centre Sanjivani College of Engineering Kopargaon Savitribai Phule Pune University Pune India Sanjivani College of Engineering Kopargaon Savitribai Phule Pune University Dept. of Information Technology Pune India

ISBN: (纸本)9798350355611

Recently, Artificial Intelligence (AI) Techniques have received significant interest across the different fields for data analysis and decision-making. Ransomware detection using AI has been a challenging research problem for the last decade in hybrid communication systems like blockchainintegrated Internet of Things (IoT) architectures. Ransomware is a form of malicious software that restricts access to a victim's resources by altering system login credentials or encrypting digital data. Consequently, typical approaches used to identify other types of threats are inadequate for recognizing ransomware. Different AI techniques recently have been used for the detection of such threats, but an appropriate level of accuracy and minimum false rate with automation are vital challenges. This study presents a systematic review of the current methods for ransomware detection using different AI techniques. The ransomware detection methods under categories such as rule-based, machine learning-based, and deep learning-based are reviewed in this study. The comparative analysis of these methods is provided quantitatively and qualitatively. As per the recent progress in the domain of ransomware detection, the current research problems are identified and discussed as the outcome of the study. The roadmap for future work is described as the research gap analysis output. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Polymer microgripper controlled by magnetic field 23

Polymer microgripper controlled by magnetic field

引用

23rd Slovak-Czech-Polish Optical Conference on Wave and Quantum Aspects of Contemporary Optics

作者： Goraus, Matej Martincek, Ivan Kacik, Daniel Dept. of Physics University of Zilina Faculty of Electrical Engineering and Information Technology Univerzitna 1 Zilina01026 Slovakia

ISBN: (数字)9781510688094

ISBN: (纸本)9781510688087

In this paper, we present a mechanical microgripper structure at the end of an optical fiber, whose movement is controlled by a magnetic field. The mechanical structure is created using modern 3D laser lithography from the IP-Dip polymer. This technique allows the creation of arbitrary structures, and the flexibility of the polymer enables the formation of various movable and mechanical parts of the structure. Our proposed structure has two jaws, one of which is movable and contains a ferromagnetic microparticle that interacts with the magnetic field to open the microgripper's jaw. Once the magnetic field is removed, the jaws return to their original position. The structure is attached to the end face of the optical fiber with epoxy, allowing it to move in a liquid. This way, we aim to capture microparticles present in the liquid. Since IP-Dip also has excellent optical properties, the proposed structure has the potential to create a multidisciplinary sensor in the future and become part of optomechanical components. © 2025 SPIE.

关键词： Plastic optical fibers

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach for Career Guidance Using Brain mapping Technique and Psychometric Test 1

Machine Learning Approach for Career Guidance Using Brain ma...

引用

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Suryawanshi, Soham Kolhe, Chaitanya More, Pranav Barhate, Jayesh Deshmukh, Rushali Hingmire, Amruta JSPM's Rajarshi Shahu College of Engineering Dept. of Computer Engineering Pune India School of Computer Engineering and Technology PCET's Pimpri Chinchwad University Pune India

ISBN: (纸本)9798350355611

After completing upper secondary education, students all over the world commonly struggle to make the crucial decision of pursuing a decent job path. Many of them lack the maturity and experience required to make sound judgments at the age of 18, leaving them concerned about their future. The challenge of identifying whether they have the necessary skills for their chosen vocation adds to the difficulty of the task. Our answer to this problem is an automated career counselling system based on psychometric tests and brain mapping techniques employing scenario-based testing as an approach using machine learning ideas that supports students in picking the optimal career path according to their interests and skill set. The user will first take the Psychometric test, which will help us analyse the user's intelligence ability, followed by another test using the brain mapping technique to help uncover his personality qualities. Based on these two tests, the ultimate outcome will be evaluated by balancing the results of the psychometric and brain mapping tests and forecasting a viable and relevant career choice, which will be backed by college admission support, a thorough career plan, and opportunities for additional study. © 2025 IEEE.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

MAT2I: Enhancing Perceptual Authenticity in Text-to-Image Synthesis Using Multi-Attribute Generative Adversarial Networks

引用

Journal of Artificial Intelligence Research 2025年 82卷 2453-2469页

作者： Singh, Varsha Singh, Vijai Tiwary, Uma Shanker IT Dept. Indian Institute of Information Technology Allahabad U.P. Prayagraj211015 India CSE Department Inderprastha Engineering College U.P. Ghaziabad201010 India

Generating visuals from text involves deriving visual representations from textual descriptions and transforming them into corresponding visuals. This technique finds vast application in various fields, such as graphic design and image editing. Generative adversarial networks (GANs) are the widely used and better performers for this task. A primary hurdle in this process is producing perceptually authentic visuals. This study introduces a Multi-Attribute Text to Image Synthesis Generative Adversarial Network (MAT2I) to address these challenges. The enhancements encompass attribute-control-net, feature alignment, and perceptual loss. The attribute-control-net is used for the fast and attribute-specific generation to maintain authenticity in perceptuality with adaptability. Feature alignment and perceptual loss motivate the generator to create visuals that closely resemble real visuals based on the accompanying text and to reduce randomness. The effectiveness of the proposed model is gauged on the CUB and COCO datasets. Empirical findings illustrate that this approach generates visuals with greater content diversity, enhanced realism, and improved semantic alignment with provided text descriptions. Furthermore, the proposed method surpasses comparative techniques in terms of inception score, further establishing its competitive performance. ©2025 The Authors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Feature engineering and Sampling Strategies for Enhanced Diabetic Retinopathy Classification 3

Hybrid Feature Engineering and Sampling Strategies for Enhan...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Vanlalnunpuia, C. Lalhmingliana Ambeth Kumar, V.D. Vanlalawmpuia, R. Khiangte, David Lalmuanpuia Kumar Khan, Ajoy Mizoram University Dept. of Computer Engineering Aizawl India Mizoram University Dept. of Information Technology Aizawl India Eye Care Hospital Ophthalmologist Aizawl India

ISBN: (纸本)9798331523893

This study presents a machine learning approach for Diabetic Retinopathy (DR) classification, integrating advanced preprocessing, feature extraction, and adaptive sampling. Preprocessing techniques, including CLAHE, gamma correction, and noise reduction, standardize image quality while preserving anatomical details. Class imbalance is addressed with ADASYN, generating synthetic samples in sparse regions for balanced class representation. Feature extraction focuses on clinical markers like vascular density, microaneurysms, exudates, and texture descriptors such as GLCM and LBP. Recursive Feature Elimination (RFE) refines features for better interpretability and reduced computational load. This binary classification framework achieves 92.91% accuracy on test data and a cross-validated ROC AUC of 0.994, demonstrating the effectiveness of hybrid feature engineering and intelligent sampling in DR detection. © 2025 IEEE.

关键词： Diabetic Retinopathy Fundus Image Image Processing Machine Learning Medical Image Diagnostics

来源：评论

学校读者我要写书评

暂无评论

Assessing the Accuracy of Regression and Classification Models in Air Quality Prediction 5

Assessing the Accuracy of Regression and Classification Mode...

引用

5th IEEE International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Vishwakarma, Harsh Kumar Guru Prasad, M.S. Mittal, Vanshika Mittal, Mudit Naik, PavanKumar Chandrappa, S. Dept. of Computer Science and Engg. Dehradun India School of Computing and Information Technology Reva University Bangalore India Dept. of Computer Science and Engg. Bengaluru India

ISBN: (纸本)9798350356236

This research paper addresses the pressing issue of air quality monitoring and prediction using machine learning algorithms. With a dataset comprising pollutant levels from various states, we employed a comprehensive approach to data analysis, visualization, and preprocessing. The study aimed to predict the Air Quality Index related to key pollutants such as SO2, NO2, RSPM, and SPM. We utilized linear regression, decision tree regression, and random forest regression for prediction tasks and logistic regression, decision tree classification, random forest classification, and k-nearest neighbors for classification tasks. The proposed method was evaluated using different performance matrixes for regression and classification tasks, respectively. The results demonstrated the usefulness of the proposed models in predicting and classifying air quality levels. The proposed model provides a robust framework for air quality management and can be a valuable tool for environmental monitoring and policymaking. © 2025 IEEE.

关键词： Random forests

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：