检索结果-内蒙古大学图书馆

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

作者： Jagadeesh, M. Sriviknesh Ojha, Kiara Srm Institute of Science & Technology Department of Computing Technologies Tamil Nadu Chennai603203 India

ISBN: (纸本)9798331523923

the increasing incidence of vehicle accidents emphasizes the need for faster and more efficient claims handling, as well as methods for categorizing damage. The proposed system addresses key challenges of traditional methods, such as excessive paperwork, manual data entry, and delayed processing times, by integrating advanced technologies including Optical Character Recognition (OCR), machine learning, and real-time analytics. This study evaluates a model for categorizing auto damage, focusing on dents and glass breaks, and introduces an innovative approach to streamline car insurance claims through Automated Verification. Policyholders can seamlessly initiate claims using mobile devices to capture images of damaged vehicle parts and license plates. OCR technology extracts and verifies textual information from these images and related documents, while Convolutional Neural Networks (CNN) are utilized for real-time object detection, enabling accurate identification and classification of vehicle damage. Additionally, machine learning models enhance the system's capability to differentiate between legitimate and fraudulent claims, thereby reducing operational costs and minimizing risks. This integrated approach significantly accelerates claim resolution, improves operational efficiency, and enhances customer experience. By fostering a responsive, automated, and user-centric ecosystem, this solution sets a new standard for innovation and effectiveness in the car insurance sector. © 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

Assessing Traditional Approaches for Atmospheric Light Estimation in Image Dehazing: Metrics and a Call for Innovation 12th

Assessing Traditional Approaches for Atmospheric Light Estim...

引用

12th International Conference on Recent Trends in computing, ICRTC 2024

作者： Pavethra, M. Uma Devi, M. Department of Computing Technologies SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India

ISBN: (纸本)9789819789450

Atmospheric light (AL) refers to the ambient illumination present in Earth's atmosphere resulting from the scattering, absorption, and reflection of sunlight by air molecules, aerosols, and particulate matter. This light contributes to the overall brightness, coloration, and visibility of the sky and surrounding environment. AL is a key factor in determining how the atmosphere appears at various intervals of the day, influencing things like the color of the sky, the tints of sunrise and sunset, and the visibility of far-off objects. It is a fundamental component in various scientific disciplines, including meteorology, astronomy, image dehazing and environmental science, and is essential for understanding atmospheric dynamics and its impact on human experiences and natural processes. AL plays a momentous role in the process of dehazing, which is the task of recovering clear and visually appealing images from hazy or foggy scenes. Understanding the impact of AL in this context is crucial for developing effective dehazing algorithms and techniques. Traditional methods such as Brightest Pixel Selection (BPS), Dark Channel Prior (DCP), Median Filtering, Gradient-based methods, Color Constancy-based Methods, and Regression based methods are employed to estimate AL to boost the efficacy of Image Dehazing. Though Traditional strategies for estimating AL have been widely used and studied, they may have limitations in terms of robustness, adaptability and accuracy, especially in challenging or dynamic environments. This has spurred the development of more advanced approaches which aim to address these limitations and achieve more accurate and reliable estimates of atmospheric light. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Dehazing Images Using Vision Transformer Algorithm

Dehazing Images Using Vision Transformer Algorithm

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Karthik, Anyapu Reddy, B.Siva Chanikya Ranjani, M. Sandhia, G.K. Srm Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798331509828

Image dehazing is an important task to obtain clear images from blurry vision in low vision individuals. Although traditional methods and deep learning have made progress in this field, there are still challenges, especially in solving the real-life haze problem. This paper studies the application of Vision Transformer architecture, especially the Dehaze Former model, to improve the image dehazing performance. We present a new dataset that provides a comprehensive evaluation of the capabilities of Dehaze Former for difficult haze conditions (and perform function adjustments), and it outperforms existing models using state- of-the-art techniques when measured with new data. We propose several metrics to validate our findings, such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Also a good comparison shows the effectiveness of this model in preserving image details and reducing artifacts. This research contributes to the advancement of image dehazing technology by demonstrating the ability of Vision Transformers to process grassy lawns. The insights gained from this study not only highlight the strengths of the Dehaze Former model, but also pave the way for future explorations into dehazing performance using Transformer-based architectures © 2025 IEEE.

关键词： Dataset Deep Learning Image Dehazing Non-Homogeneous Haze Single Image Restoration Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Optimised EfficientNet for multi-class skin cancer diagnosis: integrating chaotic grey wolf algorithms

引用

Current science 2025年第7期128卷 728-736页

作者： Rama, P. Angayarkanni, V. Theresa, W. Gracy Pandiaraj, A. Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603 203 India Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai600 123 India

The detection of skin cancer holds paramount importance worldwide due to its impact on global health. While deep convolutional neural networks (DCNNs) have shown potential in this domain, current approaches often struggle with fine-grained variability in skin lesion features, imbalanced datasets and inadequate augmentation. The objectives of our study encompass building a model that not only enhances accuracy but also reduces training time and cost, improves dimensionality reduction during classification and segmentation, and is evaluated on larger datasets for robustness. We enhance the learning process using an improved nature-inspired optimisation algorithm tailored specifically for skin cancer classification tasks. This algorithm optimises model parameters to maximise classification accuracy while minimising computational overhead. Our proposed architecture leverages a gold standard dermatological image dataset meticulously curated and validated by experts. This dataset spans eight distinct classes, including actinic keratosis, basal cell carcinoma, melanoma, nevus, and others, ensuring a diverse representation of skin conditions. The balanced class distribution in the training and test sets enables fair evaluation and robustness assessment of our deep learning models. The developed algorithm showcases novelty in its approach, contributing to advancements in early skin cancer detection technologies. This study introduces an optimised deep learning model designed for the early detection of skin cancer, achieving a notable accuracy of 97.48%. Our study aims to contribute significantly to the medical field by providing a reliable and efficient tool for dermatologists and healthcare practitioners to assist in diagnosing skin conditions accurately and promptly, ultimately improving patient outcomes and healthcare efficiency. © (2025), (Indian Academy of sciences). All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Smart Systems for Identifying Brain Tumors with MRI Images using LSTM 6

Smart Systems for Identifying Brain Tumors with MRI Images u...

引用

6th International Conference on Mobile computing and Sustainable Informatics, ICMCSI 2025

作者： Sudhakaran, Pradeep Yeshovardhan, N. Ranga Swamy, T. Department of Computing Technologies SRM Institute of Science and Technology Chengalpattu Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798331522667

The detection and classification of brain tumors are vital components of medical imaging, with timely and accurate diagnoses having profound implications for patient health. This research introduces a novel approach that employs Long Short-Term Memory (LSTM) networks for detecting and classifying brain tumors using imaging data. As a specialized form of Recurrent Neural Networks (RNNs), LSTMs excel at processing sequential data, which is particularly relevant for medical images. The methodology involves processing a series of MRI images through a feature extraction pipeline, with the extracted features subsequently analyzed by the LSTM model for tumor identification. We have trained the model on a dataset consisting of synthetic brain tumors, allowing it to effectively distinguish between false positives and negatives with good accuracy. Experimental findings indicate that the LSTM technique outperforms conventional machine learning algorithms in both detection and classification tasks. The robustness of this system suggests it could serve as a valuable tool for radiologists, providing critical diagnostic support and enhancing patient care. Furthermore, the adaptability of the LSTM model allows for future integration with advanced imaging techniques, potentially broadening its applicability across various medical conditions. By improving diagnostic precision and efficiency, this approach may pave the way for more personalized strategies and good overall patient outcomes. © 2025 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

MANAS: Integrating Advanced AI for Personalized Mental Health Support, Crisis Intervention, and Medical Insights 3

MANAS: Integrating Advanced AI for Personalized Mental Healt...

引用

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

作者： Gayathri, S. Pradeep, Mutyala Sri Siva Sai Lakshmi Vara Prasad, N. School Of Computing Sathyabama Institute Of Science and Technology India

ISBN: (纸本)9798331527549

MANAS (Mental Assistance Network for Alleviating Suffering) is an AI-based system designed to address the pressing challenges in mental health care, including limited access to personalized, timely support and crisis intervention. By leveraging advanced AI techniques such as personality analysis using the Big Five model and emotion recognition through NLP, MANAS offers personalized responses to users’ mental health concerns. It also detects traces of crisis and triggers appropriate interventions, including notifying relevant authorities. The system generates detailed medical reports to aid healthcare professionals in diagnosing and managing mental disorders more effectively. This research demonstrates MANAS's capability to bridge the gap in mental health care with innovative and practical AI-driven solutions. © 2025 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Behavioral-based Meal Optimizer and Personalized Diet Solutions for Teenagers

Behavioral-based Meal Optimizer and Personalized Diet Soluti...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Dwivedi, Saumya Babu, Maazin Hayath Deepa, R. Niranjana, G. Rajmohan, R. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Tamil Nadu Chengalpattu603203 India

ISBN: (纸本)9798331509828

Behavioral-Based Meal Optimizer is a Dietary Recommendation System that is aimed at creating customized meal plan based on a demographic information (Age, Gender, Geographic Location, Meal Preferences, Allergies) and Behavioral information (Mood, Stress level etc.). Most existing recommendation algorithms for meals are based on the static users' preferences, rather than behavioral dynamic factors that affect the meals. In this regard, our project seeks to overcome this limitation through using a machine learning algorithm and a Flask web application to offer customized meal suggestions in real time. For enhanced accuracy, we also built an ensemble model with Random Forest, XGBoost on big data preprocessing and KNN algorithms. The ensemble model integrates signup questionnaire data as the demographic inputs and the behavioral inputs that are obtained at the user's every login to estimate the current state of the user for the best appropriate meal recommendation. Our approach of data acquisition involves data pre-processing, converting categorical data into numerical data and feature extraction for meaningful inputs for the model. This approach enables incorporating contextual information into the system and offers better and more flexible meal plans. The accuracy, precision, recall, and F1-score values obtained from the test data are high when using the ensemble model compared to the single models-based on cross-validation and number of patterns captured in the data. By incorporating demographic as well as behavioral aspects into the meal planning the system attempts to assist in the satisfaction of both physiological as well as psychological needs of users. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Safe Spaces Analysis for Mental Health 12th

Safe Spaces Analysis for Mental Health

引用

12th International Conference on Recent Trends in computing, ICRTC 2024

作者： Kelawala, Harsh Shah, Zeal Selvaraj, P. Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur 603203 India

ISBN: (纸本)9789819789450

Mental health is a paramount concern in contemporary urban environments, necessitating comprehensive approaches to understanding its determinants and formulating effective interventions. This research project adopts a multifaceted methodology to explore the factors influencing mental well-being in urban areas, specifically focusing on cities within Gujarat. By integrating Geographic Information Systems (GIS) technology and predictive modeling techniques, we analyze various socio-environmental factors spanning air quality, noise pollution, green space availability, educational attainment, population density, income levels, and employability. At the same time, the GIS approach encompasses all major cities across India, the Random Forest algorithm is tailored specifically to the cities of Gujarat, reflecting the unique socio-geographical context of the region. Through rigorous data analysis and visualization, we identify spatial patterns and correlations, enabling the identification of areas most vulnerable to mental health challenges and prioritizing targeted interventions. This work presents our research's methodology, findings, and implications, offering valuable insights for policymakers and stakeholders striving to cultivate safe and supportive urban environments conducive to optimal mental health outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Lithium-Ion Battery Inspection System for EVs 3rd

Lithium-Ion Battery Inspection System for EVs

引用

3rd International Conference on Intelligent Systems and Sustainable computing, ICISSC 2023

作者： Haswanth, Kairam Ram Malladi, Jyothi Swaroop Prabhu, S. Nagendra Dinesh, G. Department of Computational Intelligence School of Computing SRM Institute of Science and Technology KTR Chennai India Lovely Professional University Punjab Phagwara India

ISBN: (纸本)9789819783540

With the increase in the speed of development, there has been a dire need to make the development as efficient as possible. Also, the increased depletion of gasoline resources has forced automobile industries to switch to electric vehicles [1]. However, the switch is not so easy as the batteries used in the electric vehicles are not as good at times giving rise to dying down, wearing out, and even fire breakout without any prior intimation. In this paper, we are trying to solve that problem for electric vehicles and make a detailed study of the automated methods to check for the lithium-ion batteries that are widely used in the vehicles. In this paper, we will be discussing the implementation of machine learning in the domain and solving the problem of EV batteries [2] and helping to generate a smart system to check for the health and the state of charge of the lithium-ion batteries. With the use of machine learning algorithms like XG-Boost, Random Forest classifier, time series analysis algorithms and Deep learning algorithms like RCNN and deep LSTM provide an ensembled result output for the same. The accuracy of the projected module is expected to be much more than the existing systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Petroleum deposits

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

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：