检索结果-内蒙古大学图书馆

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

作者： Sai Srujan Reddy, P. Naveen Raj, B.U. Jose, Nikhil Tom Belwal, Meena Department of Computer Science and Engineering Amrita School of Computing Amrita Viswa Vidhyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Urban traffic congestion is still a major problem that causes delays, collisions, and wasteful use of resources. Conventional fixed-schedule systems, which frequently exacerbate problems at junctions, U-turns, and pedestrian crossings, are insufficient for dynamic traffic situations. The Smart Dynamic Traffic Management System described in this work makes use of servo motors, proximity sensors and ultrasonic sensors, Arduino microcontrollers, and AI-powered cameras. To improve safety and streamline traffic flow, the system prioritizes emergency vehicles, controls U-turns, dynamically modifies traffic signals based on real-time data, and monitors road conditions. Scalability and adaptability for a range of urban scenarios are ensured by the integration of IoT technology and intelligent intercommunication between crossings. A visualization tool based on Pygame was used to simulate and assess the suggested solution. The findings showed that traffic flow had significantly improved, with an average increase in the exit-to-entry ratio of 30.71% for the three roadways. More specifically, traffic on Road A decreased by 15.28%, on Road B decreased by 31.25% and on Road C decreased by 45.61%. The outcomes confirm just how well the system works for reducing traffic and giving priorities to critical traffic situations, such as emergency response and turning. This system uniquely integrates real-time adaptive traffic control algorithms with IoT and machine learning to dynamically prioritize traffic flow and emergency vehicles, overcoming the limitations of existing static systems. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Advanced Financial Sentiment Analysis using FinBERT to Explore Sentiment Dynamics 3

Advanced Financial Sentiment Analysis using FinBERT to Explo...

引用

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

作者： Baghavathi Priya, S. Kumar, Madhav Nitheesh Prakash, J.D. Krithika, N. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9798331527549

This research investigates the incorporation of sophisticated Natural Language Processing (NLP) methods in the intricate field of finance. In particular, it utilizes FinBERT, a tailored language model created to understand the complex subtleties of financial text data, in conjunction with assessments of DistilBERT and Bidirectional Encoder Representations from Transformers (BERT). The main goal is to create a strong preprocessing framework that improves the interpretative ability of models for sentiment classification designed for financial uses while providing an in-depth evaluation of the comparative performance of the models. Through extensive empirical validation, our approach demonstrates that FinBERT outperforms the other models in accurately capturing subtle sentiment variations and financial terminology. The comparative study underlines the compromises between computational efficiency and precision, with DistilBERT providing a streamlined option. This research emphasizes FinBERT’s transformative capabilities in analyzing financial sentiment and simultaneously delivering essential insights into the comparative strengths and weaknesses of other approaches, presenting a comprehensive viewpoint to inform decision-making within the financial sector. Upon comprehensive analysis of the methods used in this paper, it is shown that FinBERT is best at capturing hidden features within the data and able to work well with unseen data also with an average accuracy of 89.6% over all the 3 classes that are present in the dataset. The suggested framework has the potential to greatly improve predictive analytics and risk management approaches, allowing for more informed, precise, and prompt financial decisions in intricate market conditions. © 2025 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Rack Sensor Metrics Odyssey: Analyzing Sensor Behavior with Random Forest and kNN for Strategic Job Allocation Insights

Rack Sensor Metrics Odyssey: Analyzing Sensor Behavior with ...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and Computer science, SCEECS 2025

作者： George, Angelina Beena, B.M. Bengaluru Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science & Engineering India

ISBN: (纸本)9798331529833

Data centers are vital to modern computing but contribute significantly to carbon emissions due to their high energy consumption. To address this, machine learning models can optimize resource allocation by analyzing sensor metrics. In this study, the Random Forest Regressor was chosen for its ability to capture sensor behavior, even showing negative R2 values, aligning with observed patterns. Meanwhile, k-Nearest Neighbors (kNN) emerged as the best model for learning from the same data, despite irregularities, with R2 values ranging between 0.6 and 1. This analysis supports sustainable data center management by enhancing energy efficiency and minimizing environmental impact. Future work will explore the integration of these models into simulation environments. © 2025 IEEE.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Integration of Traffic Shaping with Time-Sensitive Networking for Effective Traffic Management 3

Integration of Traffic Shaping with Time-Sensitive Networkin...

引用

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

作者： Penumada, Archana Reddy Gundapaneni, Divya Jyothi Chennupati, Akshitha Rajagopal, Shinu M. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

Time-Sensitive Networking (TSN) has recently become an important standard to support time-sensitive reliable low-latency data transmission in industrial and real-time applications. This work explores the use of different traffic shaping algorithms, namely, credit-based shaping (CBS) and time-aware shaping (TAS) alongside frame preemption—a TSN instance which gives precedence to high-importance frames by means of lower-priority traffic interruption—to extend TSN’s traffic management capabilities. By controlling data flow and allowing for high priority packets to pass through unimpeded, traffic shaping algorithms serve an essential function in making the network more efficient and reducing congestion rates. The work compares these algorithms in isolation and also in combination over a network model, comprising of four switches and three end users for each switch, using the OMNeT++ simulation environment. This study aims to contribute insights into optimal shaping techniques for TSN, enhancing its suitability for critical network applications. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Maximizing Throughput and Minimizing Latency: Evolutionary Algorithms for Optimizing Wireless Cellular Networks 3

Maximizing Throughput and Minimizing Latency: Evolutionary A...

引用

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

作者： Pechetti, Jyoshitha Yadav, Sneha Tarunya, G. Rajagopal, Shinu M. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

In the rapidly evolving world of wireless cellular network, optimizing key parameters like data throughput and latency is of critical importance for ensuring high quality communication services. The proposed presents a novel approach to multi-objective optimization to enhance overall network performance using Genetic Algorithms (GA), Pareto, and Particle Swarm Optimization (PSO). By employing optimization algorithms, a balance is sought in terms of trade-off of other parameters while maximizing data throughput and minimizing latency. Simulation layers indicate the comparative study further solidifies the efficacy of the value of evolutionary algorithms in optimizing wireless networks to satisfy the growing needs of high speed and less latency services in today’s communication landscape. © 2025 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

complex wavelet transform with progressive network for medical imaging super resolution

引用

Multimedia Tools and Applications 2025年第13期84卷 12061-12079页

作者： Sharma, Ajay Shrivastava, Bhavana P. School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh Sehore466114 India Maulana Azad National Institute of Technology Bhopal India

This research provides a new method of improving the resolution of medical images by employing a correlation filter in conjunction with a progressive dilated convolution network (PDCNCF). In an effort to enhance automatic identification and segmentation, the technique targets problems with blur, noise, and low texture quality in medical images. The model uses a combination of correlation filtering and dilated convolution to increase the receptive field while preserving pixel information, drawing inspiration from deep learning's capacity to preserve perceived quality. DRIVE, CHASEB1, MRI, ultrasound, and histopathological datasets at 2x, 4x, and 8 × upscaling are among the medical datasets and upscaling factors that the model has been tested on. On the histopathological dataset, the model obtains strong PSNR (49.74) and SSIM (0.9860) at 2 × upscaling. The suggested method outperforms current networks and demonstrates greater performance in medical image reconstruction by combining the complicated wavelet transform, correlation filter, and progressive dilated convolution network. This model has promise for improving medical diagnosis and therapy because of its ability to preserve perceptual quality and enhance resolution. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Leveraging EfficientNetB4 Model with Multi-head Attentions for Maize Leaf Disease Detection 2nd

Leveraging EfficientNetB4 Model with Multi-head Attentions ...

引用

2nd International Conference on Applied Algorithms, ICAA 2025

作者： Reddiar, Nallamilli Eswar Venkata Vikranth, Pilla Veera Satya Sai Kumar, Teerdhala Siddartha, Thota Rayvanth, N. Singh, Rimjhim Padam Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9783031845420

Smart agriculture mainly stresses the improvements in early plant disease diagnostics, crop classification and management, and effective pest control. Maize being an important staple crop necessitates early and accurate disease detection on its leaves. Hence, this paper proposes a novel Convolutional neural network model based on EfficientNet-B4 model and multi-head attention for the effective classification of maize leaf diseases. The proposed model focuses on early-stage disease patterns with the help of a large amount of data. Compared to other architectures, it attains an outstanding F1-score of 96.75%. The proposed system not only helps farmers to get timely diagnosis but also offers them useful information to mitigate risks and improve production. This study benefits agricultural resilience, food security and farmer’s welfare. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Insect control

来源：评论

学校读者我要写书评

暂无评论

Understanding Graph Neural Networks Models for Healthcare Fraud Detection in Insurance Claims 3

Understanding Graph Neural Networks Models for Healthcare Fr...

引用

3rd International Conference on Intelligent and Innovative Technologies in computing, Electrical and Electronics, IITCEE 2025

作者： Archana Reddy, P. Jyothi, Divya Varshita, Velumury Akshitha, Chennupati Aiswariya Milan, K. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798331515911

This study suggests using graph algorithms to detect healthcare fraud, a serious issue that can lead to significant financial losses and compromise patient care. Health care fraud is a representation of deceitful acts carried out by health providers, patients, or other individuals for the purpose of gaining undue financial profit from the health insurance program. It includes false billing, misrepresentation of diagnosis and procedure, and kickbacks at the expense of substantial financial loss and deterioration of patient care. Our approach models the relationships between patients, healthcare providers, physicians, and procedures as a graph to identify unusual patterns that may indicate fraud. We utilize publicly available tabular datasets, including beneficiary data and claims from inpatient stays and outpatient visits, transforming them into a graph structure to create a unified dataset. The system employs algorithmic analysis and graph construction techniques to identify significant nodes, abnormal clusters, and outliers within the healthcare network. This strategy offers a viable method for reducing healthcare fraud, enhancing the integrity of insurance systems, and ensuring that funds are appropriately allocated to legitimate medical needs. Ultimately, this study aims to decrease the rate of fraud in society. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Predicting Judgement Outcomes from Legal Case File Summaries with Explainable Approach 27th

Predicting Judgement Outcomes from Legal Case File Summaries...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Surisetty, Hima Varshini Gottimukkala, Sarayu Varma Prabhakar, Priyanka Pati, Peeta Basa Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9783031781063

Legal Outcome Prediction (LOP) is the process of predicting the possible outcome of a court case based on the case file. The aim of this work is to assess the performance of four deep learning models namely BERT, LegalBERT, DistilBERT and RoBERTa. These models were trained and tested with complete case files and their summaries. The models were then evaluated using metrics like train-test accuracy, loss plots and F-score. Based on these evaluation metrics, RoBERTa was chosen as the model with the best performance. In order to understand the predictions made by the deep learning models, Local Interpretable Model-Agnostic Explanations (LIME) was used. LIME is an eXplainable AI (XAI) tool that highlights the words in a case file which were used in order to predict the outcome of that case. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Keyframe Extraction Approaches for Intelligent Video Analysis 4

Keyframe Extraction Approaches for Intelligent Video Analysi...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Sabarivasan, N. Thangavel, Senthil Kumar Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

Real-time violence detection is essential for protecting the safety and security of people, especially in college campuses that are dynamic and have crowds. Manual surveillance systems are popular but inefficient as they require human attention all the time and are not capable of quickly identifying and responding to violent *** the exsisting violence detection model takes quite a time for processing the entire video. The proposed model extracts features as keyframes from the video using MobileNet V3 and K-medoids clustering. The redundancy of video data can be avoided and significant violent activities identified by isolating and analyzing critical frames from video data. This enhances the efficiency and responsiveness of surveillance systems. This work primarily contributes a customized violent activities dataset and implementing keyframe extraction algorithm for optimizing the usage of computational resources, and incorporating lightweight algorithms for seamless deployment with existing CCTV networks. The experimental results clearly demonstrate the ability of this approach to detect keyframes, thereby offering a scalable and practical solution. © 2025 IEEE.

关键词： Security systems

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：