检索结果-内蒙古大学图书馆

OCCOA for clustering-based intrusion detection system with MLP-rNN architecture

Multimedia Tools and Applications 2025年第11期84卷 8567-8592页

作者： Kagade, ranjeet B. Vijayaraj, N. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Tamilnadu Chennai600 062 India

WSN play a critical role in various applications such as environmental monitoring, surveillance, and healthcare. However, their deployment in open and dynamic environments makes them vulnerable to security threats. IdS are essential for safeguarding WSNs against malicious attacks and ensuring the integrity of data transmission. This research introduces a novel Clustering-based Intrusion detection System (CIdS) tailored for WSNs. The CIdS framework encompasses two primary components: optimal CH selection and intrusion detection within the WSN. Clustering is executed based on specific constraints such as energy, distance, rSSI, delay, and Pdr. The selection of optimal CHs is facilitated by the hybrid optimization approach called OCCOA, which combines Osprey optimization algorithm (OOA) and Coot Optimization Algorithm (COA). Following CH selection, intrusion detection is performed within the WSN using dL strategy. The CIdS employs a Multilayer Perceptron-recurrent Neural Network (MLP-rNN) model to detect intrusions by assessing trust and security. Additionally, the weights of the MLP-rNN model are finely tuned through the OCCOA algorithm for optimal performance. Moreover, the proposed method achieved higher performance by considering the measures, namely accuracy, sensitivity, precision and specificity with the values of 98.25%, 99.96%, 99.37% and 97.52%, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Segmentation of the Corpus Callosum from Brain Magnetic resonance Images Using dual deep Learning Classifiers and Optimized U-Shaped Neural Networks

引用

SN Computer science 2024年第1期5卷 1-18页

作者： Sarma, A. Padmanabha Saranya, G. Department of Biomedical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

Segmentation of the corpus callosum (CC) from Mr images is an important step in neuroimaging analysis for various applications, such as brain morphometry, tractography, and connectivity analysis. This research proposes a deep learning-based model for segmenting CC in T1-weighted midsagittal brain MrIs. The model consists of five major phases, namely, image augmentation, pre-processing, segmentation, feature extraction, and feature selection. The collected raw MrI images are augmented using synthetic minority oversampling technique (SMOTE) and pre-processed using improved Gabor filtering and contrast stretch for contrast enhancement. The region of Interest (rOI) has been identified through optimized U-NETS using a new hybrid optimization model. Shape, texture, and colour features are extracted from the segmented image, from which optimal features are selected through proposed hybrid optimization model. The CC segmentation phase will employ a dual deep-learning classifiers approach, with bidirectional LSTM and convolutional block attention module (CBAM) trained using optimally selected features, and a modified convolutional neural network (M-CNN) to provide final detected outcomes. The proposed model aims to improve the accuracy of CC segmentation in brain MrIs. © The Author(s),.

关键词： Corpus callosum Improved Gabor filtering Modified convolutional neural network (M-CNN) Optimized U-NETS

来源：评论

学校读者我要写书评

暂无评论

Suppression of Harmonics in an Air-Filled dual Triangular Slotted Substrate-Integrated Waveguide-Based C-Band Filter for Satellite Applications

引用

Journal of The Institution of Engineers (India): Series B 2023年第1期104卷 269-275页

作者： Souprayen, Oudaya Coumar Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Chennai India

A compact configuration of dual triangular slotted C-band filter using substrate-integrated waveguide for high-frequency harmonics suppression is presented. The C-band filter with unique dual triangular-shaped structure is used to optimize the performance in terms of harmonic suppression. Triangular slots are defected on top of C-band filter for harmonic suppression. SIW arrangement in the design provides extra control mechanisms to achieve desired response. The filter has very sharp pass band ranged from 3.65 to 8.28 GHz for insertion loss of 1.75 dB and return loss of 34.46 dB. The dimensions of proposed C-band filter are (30 × 25 × 1.6) mm3. A smooth agreement is observed between simulation and measurement results with good harmonic suppression. The proposed filter suppressed higher-order harmonics till 16 GHz at − 20 dB level. © 2022, The Institution of Engineers (India).

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

Simulation and implementation of a reconfigurable dual-function pixel

引用

Optoelectronics Letters 2024年第8期20卷 454-459页

作者： Shaher dwik Gurusamy Sasikala Department of Electronics&Communication Engineering School of Electrical&CommunicationVel Tech Rangarajan Dr Sagunthala R&D Institute of Science and TechnologyChennai 600062India

This paper presents the simulation and implementation of a reconfigurable pixel that serves both data acquisition and energy harvesting *** main topic focuses on switching between the two operating modes of the photodiode:photoconductive and photovoltaic *** proposed model can be used to design novel optical sensors with energy harvesting capability,such as position sensitive device(PSd)and complementary metal oxide semiconductor(CMOS)image sensors,which can extend the battery lifetime of the whole optical ***,we can overcome power supply problems like wiring and changing batteries frequently,especially in hard-to-reach places like space(cube satellites)or even underwater wireless optical communication(UWOC).The proposed pixel architecture offers the advantage of a minimalistic design with only four ***,it does come with a drawback in the form of higher noise *** simulation was achieved using MATLAB,and the implementation was performed using the programmable system-on-chip(PSoC)*** results showed that the functionality of the dual-function pixel is correct,and the scheduling of both energy harvesting and signal sensing functions was successfully achieved.

关键词： implementation harvesting function

来源：评论

学校读者我要写书评

暂无评论

Improving the Autonomous Vehicle Vision with Synthetic data using Gen AI 3

Improving the Autonomous Vehicle Vision with Synthetic Data ...

引用

3rd International Conference on Intelligent data Communication technologies and Internet of Things, IdCIoT 2025

作者： Kadiyapu, durga Chandra Mouli Mangali, Venkata Sai Thummuru, Jaideep reddy Sattula, Sriya Annapureddy, Sasivardhan reddy Arunkumar, M.S. Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331527549

This research focuses on addressing the challenges associated with training object detection and segmentation models for autonomous vehicles using real-world data, which is often difficult to collect, limited in diversity, and expensive to annotate. To overcome these limitations, we propose a novel framework for generating synthetic datasets using deep learning techniques and generative AI. Specifically, we utilize the Stable diffusion models to generate synthetic images, and annotate them using a combination of the Segment Anything Model (SAM) and the CVAT tool. The annotations are further refined to produce label files, and the dataset is split into training and validation sets. For evaluation, the YOLOv8 is applied for object detection and segmentation tasks using the synthetic dataset. Additionally, the Salesforce/Blip image-captioning model is integrated to provide descriptive captions for the detected objects. Experimental results demonstrate that synthetic datasets generated by this approach not only provide coverage of complex and rare scenarios but also achieve comparable or superior performance compared to real-world datasets in object detection and segmentation tasks. These findings underscore the potential of synthetic data to serve as a cost-effective and scalable alternative to real-world data for autonomous vehicle training. © 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

Innovative Smart Network Enabled Charging Station for Future Electric Vehicle

引用

Journal of The Institution of Engineers (India): Series B 2024年第1期105卷 147-156页

作者： Paramasivam, Alagumariyappan Vijayalakshmi, Sankaran Swamynathan, Kudiyarasan Mahalingam, N. Gughan, N.M. Department of Biomedical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Electrical Group Bharatiya Nabhikiya Vidyut Nigam Limited Tamilnadu Kalpakkam603102 India School of Mathematics University of Leeds Leeds United Kingdom

renewable energy has become a major resource in the twenty-first century due to the excess usage of oil. The world is being transitioned to develop technology which uses renewable energy as its core element. The common renewable energy includes solar, wind, wave, geothermal. As technology develops, the Electric Vehicle became a demanding factor in the automobile sector. Increase in Electric vehicle production leads to the creation of the charging station. In this paper, a charging station is designed by utilizing the solar energy as a primary source. The primary focus of the charging station is the dC–dC converter which extracts energy from the PV Array. Further, the charging station detects the vehicle using YOLO v3 model and charge its battery. Additionally, the battery energy information in the charging station can be shared between other charging stations. © 2023, The Institution of Engineers (India).

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Production of polyhydroxybutyrate (PHB), a biodegradable polymer from seaweed biomass using novel bacterial isolates

引用

JOUrNAL OF MOLECULAr STrUCTUrE 2024年 1303卷

作者： raju, Nirmala Nithya Sankaranarayanan, Mugesh Bharathiraja, B. Vel Tech Rangarajan Dr Sagunthala R&D Inst Science Dept Biotechnol Chennai 600062 Tamil Nadu India Vel Tech High Tech Dr Rangarajan Dr Sakunthala Eng Dept Chem Engn Chennai 600062 Tamil Nadu India

Poly-(3-hydroxybutyrate) (PHB), is a partially crystalline polymer naturally synthesized by microorganisms, and the production of PHB has attracted much attention recently due to its exceptional biodegradable and biocompatible nature. By serving as a copolymer and by being a block copolymer, PHB enhances the mechanical properties of the polymer materials. The materials developed using PHB as a block copolymer are used in numerous applications such as polymer aging resistance, controlled drug delivery, cardiovascular engineering, thin film formation, etc. This study focuses on synthesizing PHB from microbial sources as cell factories. From distinct natural sources two novel bacterial isolates, Bacillus pacificus NAA2 (NAA2) and Klebsiella quasipneumonia NAA4 (NAA4) were screened based on their high PHB synthesizing abilities. To improve the PHB levels, a series of process optimization studies were conducted. The process conditions such as different carbon and nitrogen sources, concentrations, pH levels, temperatures, and incubation periods have been explored and optimized. Under optimized conditions, NAA2 produced 2.92 g/L of PHB (79 %) with glycerol and peptone as carbon and nitrogen sources respectively at pH 7.5 and 35 degree celsius at 48 h. The other isolate, NAA4, produced 2.89 g/L of PHB (73 %) from xylose and urea as equivalent carbon and nitrogen sources respectively with the same pH and temperature after 36 h of incubation. In addition, the replacement of conventional carbohydrates (glucose and/ or xylose) with seaweed hydrolysate exhibited almost equivalent levels of PHB 72.7 and 70.7 % of PHB in NAA2 and NAA4 respectively. Fourier Transform Infrared (FTIr) spectroscopy and FE-SEM analysis confirmed the production of a polymer. Though there are several studies reported with other Bacillus sp and Klebsiella sp., this is the only study that used novel strains Bacillus pacificus (NAA2) and Klebsiella quasipneumonia (NAA4) as the microbial cell factories for t

关键词： Polyhydroxybutyrate Block copolymer Biodegradable plastic Thin film Seaweed Process parameters FTIr

来源：评论

学校读者我要写书评

暂无评论

A Novel Blockchain-Assisted deep Learning Model For Secure Edge Intelligence in IoT Networks

引用

Journal of The Institution of Engineers (India): Series C 2024年 1-14页

作者： Sekhar, G. Chandra Aruna, r. Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R & ampD Institute of Science and Technology Tamilnadu Chennai India

The Internet is being connected to billions of mobile and Internet of Things (IoT) devices, generating zillions of Bytes of data at the network edge. This is in addition to developments in mobile computing and the Internet of Things (IoT). In the context of edge computing, applications are placed closer to data sources such as IoT sensors, local edge devices, and edge servers. data are transmitted from edge devices to dedicated computer infrastructures for a range of activities in any edge computing environment. For the reason that data are regularly sent from IoT edge devices to centralized virtualization technologies, it is more vulnerable to security vulnerabilities and complexity measures. Finally, to preserve the privacy of the IoT devices, the performance of the proposed algorithms is evaluated using datasets in a large-scale network prototyped system. According to the data, the suggested strategy is both more effective and secure than the alternatives. © The Institution of Engineers (India) 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Influence of nano AL2O3 on compression ignition engine characteristics fuelled with Mahua biodiesel

引用

Materials Today: Proceedings 2023年 72卷 2238-2244页

作者： Backiyaraj, A. Parthasarathy, M. Murugu Nachippan, N. Senthilkumar, P.B. Kumaran, T. Department of Mechatronics Engineering Agni College of Technology Thalambur Chennai 600130 India Department of Automobile Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai 600062 India Department of Aeronautical Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai 600062 India

Growing energy demand and rising emissions have prompted testing on alternative energy sources for IC engine applications. Alternative energies are commonly extracted from biomass waste, algae and plant seeds. Many environmental difficulties develop as a result of the use of petroleum products in IC engines. As a result, adapting an alternative fuel to an existing engine may necessitate some design changes in order to achieve greater or nearly equal performance of conventional fuels. The primary objective of this experiment is to increase the efficiency of the engine and reduce the concentration of HC, CO2 and NOx. The experimental investigation was assessed in a single cylinder, compression ignition engine fuelled with mahua biodiesel and its diesel blends with AL2O3 nano additive. The engine was analysed with different test fuels such as diesel, 10 % mahua biodiesel + 90 % diesel (B10), 20 % mahua biodiesel + 80 % diesel (B20), 70 % diesel (B30) at different load conditions. From the tested fuel, 20 % mahua biodiesel + 80 % diesel (B20) showed reasonable performance and tail pipe emission compared to other biodiesel blends. The preparation of nano blended biodiesel was based on 80 % of diesel, 20 % of mahua biodiesel and 10, 25, 50 ppm of nano AL2O3. The 50 ppm of nano AL2O3 blended biodiesel shows better thermal efficiency and reduced emissions due to presence of nanoparticle in the blends which enhance the fuel atomization characteristics. BTE of 50 ppm of nano AL2O3 blended biodiesel increased 6.05 %, when compared with the diesel. The emission of HC, CO, NOx, and Smoke by 50 ppm of nano AL2O3 blended biodiesel was reduced by 19.52 %, 29.81 %, 14.48 %, and 23.35 %, respectively when correlated to base fuel. On whole, it was concluded that nano AL2O3 blended mahua biodiesel found to be a better alternative energy for unmodified existing CI engine. © 2022

关键词： Aluminum oxide

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Tomato Leaf diseases in relation to Soil Nutrition data 2nd

Comparative Analysis of Tomato Leaf Diseases in Relation to ...

引用

2nd International Conference on Innovations in data Analytics, ICIdA 2023

作者： Gurujukota, ramesh babu Gokuldhev, M. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India

ISBN: (纸本)9789819749270

This study presents a comparative analysis of various tomato leaf diseases in soil nutrition data, specifically focusing on phosphorus, nitrogen, potassium, pH values, temperature, and humidity. The research aims to identify the correlation between these soil parameters and the prevalence of specific leaf diseases in tomato plants. The study employs an efficient algorithm for preprocessing the noise data, which is crucial in ensuring the accuracy and reliability of the re-results. This algorithm is designed to filter out irrelevant or erroneous data, thereby enhancing the quality of the input data for further analysis. The research also explores different classification algorithms for preprocessing data, including decision Trees, random Forests, Support Vector Machines, and Neural Networks. These algorithms are evaluated based on their efficiency in handling large datasets, their ability to deal with noise and outliers, and their performance in terms of speed and accuracy. The findings of this study are expected to provide valuable insights into the relationship between soil nutrition and tomato leaf diseases. This could potentially lead to the development of more effective disease prevention and management strategies in tomato cultivation. Furthermore, comparing different classification algorithms could contribute to advancing data preprocessing techniques in agricultural research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： data accuracy

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：