检索结果-内蒙古大学图书馆

Diagnosing Dementia Disorder Detection Using an Improved Eliminate Particle Swarm Optimization (IEPSO) Based on Convolutional Neural Networks

引用

SN computer science 2024年第6期5卷 695页

作者： Duraipandian, Kavitha Ambigapathy, Murugan Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Campus Tamil Nadu Chennai India Department of Data Science and Business Systems SRM Institute of Science and Technology SRM Nagar Tamil Nadu Kattankulathur Chennai India

Dementia is an un-repairable and continuous disease that affects a person's mental health. Symptoms of Dementia may vary from one person to another, there are no effective treatments for detecting Dementia. Machine learning algorithm has proven to be effectively used by many researchers in assisting optimal detection of Dementia. So, this research introduces an improved eliminate particle swarm optimization (IEPSO) based Convolutional Neural Network (IEPSO-CNN) for diagnosing Dementia without causing severe effects effectively. IEPSO is used to find suitable parameters while training the model to improve Dementia detection accuracy. This IEPSO is used for tuning the parameter of the two-level Visual Geometry Group 16 (VGG 16) model. The integration of IEPSO and two hierarchical layers of VGG 16 increases the model's Dementia detection performance. The IEPSO-CNN model performance is evaluated using 6400 Dementia and non-Dementia images. The performance analysis shows that the IEPSO-CNN obtained a maximum accuracy of 99% for detecting the dementia stages. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural network Deep learning Dementia detection Improved eliminate particle swarm optimization VGG 16

来源：评论

学校读者我要写书评

暂无评论

Vibration Damping Analysis for Drilling Process Using MR Fluid-Assisted Worktable

引用

Journal of The Institution of Engineers (India): Series D 2025年第1期106卷 107-114页

作者： Vijaya, A. Kumar, C. Shravan Department of Mechanical Engineering SRM Institute of Science and Technology Tamilnadu Kattankulathur Chennai603203 India

The vibrations produced while machining components is annoying and yields discomfort to the operators. Also, if the vibrations are not damped properly, it reduces the machining performance and produces chatter. Magneto-rheological (MR) fluid is highly employed nowadays in dampers due to its ability of changing its viscosity that enhances damping. In this present work, a magneto-rheological fluid-assisted smart worktable is designed and fabricated to damp the vibrations produced during the drilling process. The worktable is designed in such a way that it can damp the vibrations whenever necessary just by keeping the electromagnet in ON/OFF state, which is almost suitable to use for all machine tools. Finite element method magnetics is used to determine the distribution of magnetic flux density on the worktable numerically for optimizing the electromagnet design in MR fluid-assisted worktable. The vibrations that are produced during drilling operations are acquired through an accelerometer connected to a data acquisition system (DAQ). The experiments are carried based on factorial design of experiments for three factors such as diameter of drill, speed of drill and MR effect at two different levels. The acquired vibration signals are filtered and analyzed in frequency domain and are proved to damp the vibrations efficiently when MR fluid effect is ON state. The recorded vibration signals are filtered and evaluated in the frequency domain, and it is demonstrated that when the MR fluid effect is ON, it effectively dampens vibrations by 71% to 98%. Thus, the new innovative MR fluid-assisted worktable proves to damp the vibrations produced on workpiece during all kind of machining operations. © The Institution of Engineers (India) 2022.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

ELEVATE: An AI-Driven Virtual Companion for Nurturing Mental Health Support for Students 2

ELEVATE: An AI-Driven Virtual Companion for Nurturing Mental...

引用

2nd International Conference on Advances in Computation, Communication and Information technology, ICAICCIT 2024

作者： Angeline, R. Roshini, S. Sajith, Mohammed Aman Shasti, M. Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India CSE with specialization AIML SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (纸本)9798331541217

This study introduces Elevate, an AI-powered virtual companion crafted to support the mental health of students from all walks of life, with a focus on those preparing for high-stakes exams like IIT, NEET, and JEE. Mental health challenges among students are a growing global concern, and in India, limited access to counseling often leaves students to manage stress, anxiety, and depression alone. Elevate bridges this gap by offering free, personalized mental health support using the Gemini AI API. Leveraging advanced natural language processing (NLP), discourse structures, and preprocessed Kaggle datasets, Elevate tailors its guidance to individual needs. Key features include real-time sentiment analysis, motivational support, and customized study plans, fostering resilience and overall well-being. By prioritizing inclusivity, Elevate ensures accessible mental health resources for underserved communities. With robust data privacy measures, it exemplifies how pre-trained AI frameworks can address societal challenges. Elevate empowers students of all ages to thrive academically and emotionally, setting a new standard for AI-driven mental health support in education. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Analysis of Mobile Evidence Using Sentimental Analysis

An Intelligent Analysis of Mobile Evidence Using Sentimental...

引用

International Conference on Information Security, Privacy, and Digital Forensics, 2022

作者： Jones, G. Maria Santhiya, P. Winster, S. Godfrey Sundar, R. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology and Panimalar Engineering College Chennai India

ISBN: (纸本)9789819950904

Smartphones are compatible and easily accessible compared to computers irrespective of place and time. Smartphones merge with our routine which acts as a medium of communication in several ways such as messaging, voice and video calling, sharing of audio and video contact, and many multimedia contents. We express our emotions through words and these communications can be analyzed by a technique called Natural Language Processing (NLP). Many researchers in the field of text mining and NLP have analyzed the polarity of online product reviews, blogs, social media comments, tweets, and many more. Mobile forensics investigation will be more effective by providing the evidences based on sentimental analysis of the text where the suspected messages contain a negative content of having threats, harassments, text against the community guidelines, and some keywords related to the cases which may be the turning point during the forensics investigation. In this paper, a novel framework called Integrated Mobile Device Forensic Investigation Process (IMDFIP) with inclusion of sentimental analysis techniques in the text which is used to emotionally analyze the texts during the communication process. This framework provides additional information to forensic analysts which will trap the suspect during investigation. The proposed framework of IMDFIP identifies the important terms, emotions, and polarity of the text during the crime. IMDFIP capitulates results compared with the previous models. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

OSL-ABE: an optimal secure and lightweight attribute-based encryption method for blockchain-enabled IoT-based healthcare systems

引用

Neural Computing and Applications 2025年第1期37卷 123-148页

作者： Vinnarasi, A. Preethi Dayana, R. Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur India

A secure IoT system can provide end-to-end encryption, secure communication protocols, mechanisms for access control, and intrusion detection and prevention systems to protect against various cyber threats. This paper presents a novel method to guarantee the secured and privateness of information in healthcare system that is Internet of Things based. This proposed method, called optimal secure and lightweight attribute-based encryption (OSL-ABE), is designed to provide an efficient and effective solution for secure data storage in the blockchain. By leveraging ABE, this method enables fine-grained access control over data, ensuring that only authorized users with specific attributes can access the data. Current ABE systems, including those used in IoT applications, often neglect privacy protection, during the key generation phase which is a significant threat to confidentiality of industrial secrets. Therefore, an optimal key generation method is proposed using modified sandpiper optimization (MSO) algorithm to ensure privacy preservation. In addition, it is incorporated with an enhanced gravitational search (EGS) algorithm in this proposed method to facilitate secure key revocations. It uses a single short broadcast message, which helps to maintain the IoT systems with confidentiality and integrity. Based on the simulation results, NPCR and UACI results exhibit 99.76% and 34%, respectively, and the entropy value is also obtained with a safe value of 8 which can withstand brute force attacks;it is found that the OSL-ABE method provides a comprehensive and effective solution for ensuring data security, preserving privacy, and facilitating secure key revocations in blockchain-enabled IoT-based healthcare systems. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Blockchain and IoT integration for secure short-term and long-term air quality monitoring system using optimized neural network

引用

Environmental science and Pollution Research 2024年第27期31卷 39372-39387页

作者： Chinnappan, Balasubramanian Hakim, Kareemullah Kumar, Neelam Sanjeev Elumalai, Vijayalakshmi Electronics and Instrumentation Engineering B.S.A Crescent Institute of Science and Technology Vandalur Tamil Nadu Chennai600048 India Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Campus Tamil Nadu Chennai600026 India

Accurate air pollution prediction is vital for residents’ well-being. This research introduces a secure air quality monitoring system using neural networks and blockchain for robust analysis, precise predictions, and early pollution detection. Blockchain guarantees data integrity, security, and transparency. Goals include real-time air quality data, secure blockchain recording, and enhanced safety through informed decisions. The research integrates blockchain and IoT for short- and long-term air quality monitoring, utilizing an optimized neural network. IoT sensors collect PM2.5, PM10, CO, NO2, and SO2, processed through noise removal and normalization, with feature extraction using N-tuple contrastive learning. Predictions utilize Graph attention-based deep Residual shrinkage Network and Bidirectional long short Term Memory (GRNBTM) categorized into five levels. An adaptive bowerbird algorithm optimizes parameters, reducing computational complexity. Blockchain integration ensures secure, tamper-proof data storage with a lightweight consensus-based algorithm. The GRNBTM model’s air quality monitoring performance is extensively simulated and analyzed at 30-min, 2-h, 1-day, and 1-month intervals, demonstrating superior performance over existing techniques. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Adaptive whale optimization based clustering method for K- anonymization in social networks

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Sivasankari, K. Maheswari, K. M. Uma Department of CSE SRM Institute of Science and Technology Ramapuram Chennai600089 India Department of computing technologies School of computing College of engineering and technology SRM Institute of science and technology Kattankulathur603203 India

The usage of online social networks (OSNs) has been significantly swelling over the years. Data from SNs has been shared publicly for the purpose of deeper understanding user behaviour and data mining tasks. However, securing individual identification from the publicly published data is the primary issue in sharing social network databases. K-anonymization is a well-known technique for preventing individual identification of publically available datasets. According to this method, each record in the anonymized dataset must be identical to at least k-1 other records in terms of a set of privacy-related attributes. Although anonymizing the original dataset to meet the k-anonymity criteria is straightforward, the anonymized dataset must maintain as much information from the original dataset as possible. Recently, clustering methods have been used to apply K-anonymization to the social dataset successfully. This paper applies a swarm-based clustering technique, called adaptive whale optimization algorithm (AWOA) for clustering social data. The WOA algorithm replicates humpback whale behavior and employs fewer internal parameters to support a better balance of exploitation and exploration. The method is tested on three publicly available data sets: Yelp and Facebook dataset. The experimental findings show that the proposed method attained the minimum information loss of 11% for Yelp dataset and 10% for facebook dataset. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

An intrusion detection system using ranked feature bagging

引用

International Journal of Information technology (Singapore) 2024年第2期16卷 1213-1219页

作者： Azhagiri, M. Rajesh, A. Karthik, S. Raja, K. Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering Jain University Bangalore India Department of IT College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India

An Intrusion Detection System monitors the network for any malicious attacks. It is an ideal tool for protecting extensive business networks from any kind of attack. In this paper, an Intrusion Detection System using Bagging and ranked features has been proposed. The sample datasets for training the ensemble of classifiers in the bagging approach are obtained by generating subsets of the features ranked according to their importance in the classification process. OneR algorithm has been used to rank the features. The decision tree has been used as the base classifier in the bagging approach. The proposed system was able to predict attacks with an accuracy of 99.71% with a minimal number of features and outperformed other similar approaches discussed in the literature. © The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s);author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

关键词： Bagging CIC-IDS 2017 dataset Decision tree Ensemble Feature selection Intrusion detection system OneR feature selection

来源：评论

学校读者我要写书评

暂无评论

Experimental thermal performance of deionized water and iron oxide nanofluid for cold thermal storage

引用

Environmental science and Pollution Research 2024年第17期31卷 26330-26339页

作者： Chandrasekaran, Ponnusamy Premnath, Doss Cheralathan, Marimuthu Senthil, Ramalingam Department of Mechanical Engineering SRM Institute of Science and Technology Kattankulathur Chennai603203 India

Phase change materials enhance the thermal comfort of buildings by utilizing stored thermal energy. In large air-conditioning systems, ice storage plays a crucial role in managing peak power loads. This experimental study explores the freezing characteristics of deionized water containing suspended iron oxide nanoparticles in spherical containers for cold storage. The synthesized nanofluid phase change material (NFPCM) was investigated for its freezing behavior under surrounding fluid temperatures of − 2 °C and − 6 °C. The uniformity in charging of NFPCM is the unique feature prevalent in the first quarter of the charging, with 50% mass frozen observed. An increased surface heat flux of 200% was achieved using NFPCM at Tsurr = -6 °C. The chiller operational time is optimally reduced by 75% by considering twice the container design’s phase change materials. Adding iron oxide nanoparticles and partial charging is suitable for uniform heat transfer for the shorter freezing duration in cooling applications. The novelty of the present study is that the proposed NFPCM nearly nullifies the subcooling effects of deionized water without using nucleating agents. This NFPCM appreciably enhances power competence, yielding large-scale air-conditioning systems’ desired economic impact and sustainability. The reported results align with Sustainable Development Goals (7—Affordable and Clean Energy and 13—Climate Action). © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Thermal energy

来源：评论

学校读者我要写书评

暂无评论

Improved UNET Architecture for Effective COVID-19 Severity Prediction from Pulmonary CT Images 1

Improved UNET Architecture for Effective COVID-19 Severity P...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Ramla, M. Jasmine, R. Anita Ramesh, M. Bai, Femilda Josephin Joseph Shobana SRM Institute of Science and Technology Department of Computer Applications Chennai India SRM Institute of Science and Technology Department of Data Science and Business Systems Chennai India SRM Institute of Science and Technology Department of Computer Science Chennai India Istinye University Department of Computer Engineering Istanbul Turkey

ISBN: (纸本)9798350376517

COVID-19, is one of the deadliest pandemic hit globally crises in the recent years, continues to persist with emerging variants of concern. Due to the virus's high transmissibility, rapid and precise detection of COVID-19 is crucial for timely medical intervention. This research presents an advanced deep transfer learning approach for quantifying the severity of COVID-19 infection from CT lung images. Using computer vision techniques, lung regions were extracted from CT scans through semantic segmentation using SegNet. An enhanced U-Net architecture, integrated with the Atrous Spatial Pyramid Pooling (ASPP) technique, was employed to semantically segment the infected regions of the lungs. Based on the segmented infection areas, the severity of the infection was classified into mild, moderate, and severe. The proposed framework, which incorporates lung extraction followed by Ground-Glass Opacity (GGO) segmentation, achieves the segmentation accuracy of 96% and a prediction accuracy of 98.9%. © 2024 IEEE.

关键词： COVID-19

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：