检索结果-内蒙古大学图书馆

Brain tumour detection and classification from MRI images using CNN

AIP Conference Proceedings 2024年第1期3134卷

作者： T. Aby Abahai Thulaseedhar Arjun S. Sabarinath Babu Jerin Associate Professor Department of Computer Science and Engineering Mar Athanasius College of Engineering Kothamangalam Kerala India Department of Computer Science and Engineering Mar Athanasius College of Engineering Kothamangalam Kerala India

This study compares different CNN architectures for identifying and categorizing brain tumors. Brain tumors are mainly of three types which are Glioma, Meningioma and pituitary adenoma. Tumors can appear in a variety of places, and the location of a tumor may reveal information about the type of cells that are responsible for it, aiding in a more accurate diagnosis. Here we will use MRI to identify and classify tumors. The main issues in MRI are illumination which can provide wrong result. To remove this the these images should be processed before training. To enhance the quality of the MRI, many image pre-processing techniques are used, such as histogram equalization, blurring and thresholding. This will help in faster classification. Six different architectures are compared in this study. These are ResNet50, VGG19, InceptionV3, MobileNet, DenseNet and NASNetMobile. By comparing this architectures we can find which one is more faster and accurate. Also maybe some architecture will be better than others for identifying certain type of tumor. That can also be identified from this. The model will be trained at different epoch to validate the result. About 20 percent of images will be used for testing and remaining are used for training. Also a part of this paper deals with calculation of brain tumor volume from MRI. Finding volume of brain tumor at two different period can help us to identify progression rate. The direction in which tumor is progressing is also identified. This will help with treatment of tumor. Volume is obtained from various slices of MRI of same brain at different locations. From each slices area of tumor is identified by segmentation. Segmentation allows us to obtain tumor part from MRI. Area will depend on number of pixels in tumor part. Two slices will be separated by a distance. This distance is multiplied by area of slice to give its volume. Summing up volume of each slice will give the approximate volume of the tumour. The main problem is eac

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bridging the Skill Gap Between Academia and Industry in Punjab: A Case Study 20

Bridging the Skill Gap Between Academia and Industry in Punj...

引用

Proceedings of the 12th International Conference on Education Technology and computers

作者： Gulam B. Mustafa Kadhiravan G Venkatesh Vijay C Malathi S Subburaj S Ashwan Paranthaman UG Scholar at Panimalar Engineering College India Senior Lecturer Computer EngineeringBirmingham City University UK Professor Computer Science Engineering Panimalar Engineering College India Asst. Professor Computer Science Engineering Panimalar Engineering College India Associate Professor Panimalar Medical College Hospital & Research Institute India

ISBN: (纸本)9781450388276

Over the past years, the number of students going abroad for higher studies and settling abroad has increased a lot in northern states of India mainly in Punjab whereas it's significantly less in south India. The purpose of this research is to find the reasons for the brain drain also analyzing the strategies used by south Indian universities so that those ideas can be implemented in Punjab so that the brain drain can be reduced. Using a credits composition analysis for two universities, this study analyzed that the College in Punjab had more credits towards practical and college in South India had more credit composition towards theory. This analysis gave us a result that Panimalar engineering College has found a sweet spot in the composition of credits along with some other factors. Using a comparative analysis of various factors for various south Indian Universities along with Punjab University, we have found out that there are many other factors that also influence's the brain drains along with Industry Institute Relationship. We have found out the methodologies used by south Indian universities to prevent brain drain. This study definitively answers the question regarding reasons for brain drain in Punjab along with the solutions to overcome it. Further Detailed studies are needed along with the implementation of these ideas to develop preventative measures.

关键词： Curriculum Employability Employability skills Higher education Strategies or approaches

来源：评论

学校读者我要写书评

暂无评论

Optimal Dietary Management via Data Analytics, ANN Based Health Insights, and Ecosystem for Continuous Nutrient Analysis

Optimal Dietary Management via Data Analytics, ANN Based Hea...

引用

International Conference on Energy, Power and Environment: Towards Sustainable Growth (ICEPE)

作者： Chitra Sabapathy Ranganathan Arshadh Ariff Mohamed Abuthahir Riazulhameed G. Swathi Pavithra M.R S. Senthil C. Srinivasan Associate Vice President Mphasis Corporation Chennai Tamil Nadu India Architect - Data Engineer Blackstraw Technologies Pvt Ltd Chennai Tamil Nadu India Assistant Professor Department of Computer Science and Engineering CMR Technical Campus Hyderabad Telangana India Assistant Professor Department of Management Studies Rajalakshmi School of Business Chennai Tamil Nadu India Assistant Professor Department of Mathematics Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350379297

ISBN: (纸本)9798350379303

This research paper offers a groundbreaking study on precision nutrition, an intelligent Internet of Things ecosystem that aims to transform the control of nutritional intake. The system provides continuous nutritional analysis and individualized health insights due to its integration of cutting-edge sensor technology with data analytics. Real-time monitoring of the food and drinks' nutritional content is made possible by the ecosystem thanks to a network of intelligent wearable devices equipped with spectroscopic and ion-selective sensors. The technology delivers tailored health insights and dietary recommendations by using algorithms for machine learning and an extensive library of nutrients. In this article, the architecture, sensor integration, data processing, and validation procedures of the Internet of Things ecosystem are further detailed. The suggested system is accurate and effective, as shown by the results of extensive validation studies. The findings of this study highlight the potentially game-changing role that the Internet of Things (IoT) ecosystem may play in enabling people to improve their health via educated dietary decisions, contribute to the development of precision nutrition research, and maximize their health results.

关键词： Data analysis Ecosystems Transforms Propulsion Nutrients Real-time systems Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of reduced feature set based ML models for IDS

引用

AIP Conference Proceedings 2023年第1期2773卷

作者： P. A. Jishiya K. P. Swaraj Ajay James M-Tech Student Computer Science and Engineering Govt. Engineering College Thrissur India Associate Professor Computer Science and Engineering Govt. Engineering College Thrissur India Assistant Professor Computer Science and Engineering Govt. Engineering College Thrissur India

Cyber-attacks targeting organisations and individuals are getting worse day by day. With the technological improve-ments, the principles used to launch attacks are also varied. Intrusion Detection System (IDS) is a network solution to detect attacks and anomalies in the network. Leveraging Machine Learning for developing an IDS can make it more powerful. This work aims at evaluating the performance of machine learning models for Intrusion Detection System built based on CART Algorithm, ID3Decision tree algorithm, Random forest algorithm with Convolutional Neural Network. The model is built using KDD Cup99 Dataset. In this work we perform Linear Correlation and Mutual Information feature selection algorithms for ML algorithms and for Convolutional Neural Network algorithm being a deep learning technique feature selection happens automatically. Analysing various parameters including F1-score, ID3 has shown better results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Survey on various DDoS attacks on firewall and study on emerging DoF attacks

引用

AIP Conference Proceedings 2023年第1期2773卷

作者： P. A. Jishiya Ajay James K. P. Swaraj M-Tech Student Computer Science and Engineering Govt. Engineering College Thrissur India Assistant Professor Computer Science and Engineering Govt. Engineering College Thrissur India Associate Professor Computer Science and Engineering Govt. Engineering College Thrissur India

A firewall is a network device that act as a security guard between a trusted network and an untrusted network. Firewall is the first line of defence against malicious traffic. Nowadays, attacking an organisation network for evil intentions has become a common thing. Distributed Denial of Service (DDoS) attack floods network traffic with illegitimate traffic and thereby preventing accessibility to legitimate users. However new type of attacks are being emerged targeting the network devices and their vulnerabilities. Attacker uses specially crafted packets to overload firewall with comparatively lesser effort, known as Denial of Firewalling (DoF) attack. This paper discusses about the attacks targeting the firewall and also about the newly emerged DoF attack. Moreover, a detection model for DDoS attack is also analysed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain effect on E-commerce: A framework for key research areas

Blockchain effect on E-commerce: A framework for key researc...

引用

Artificial Intelligence and Smart Communication (AISC), International Conference on

作者： Nethravathi K Jeidy Panduro-Ramirez Anita Gehlot Amit Barve Sanjay C. P R. Ponnusamy Department of BMS Jain University Bangalore India Universidad Tecnológica del Perú Uttaranchal Institute of Technology Uttaranchal University India Department of Associate Professor & HOD Parul University Department of IT& Business Analytics Sri Balaji University Pune (SBUP) Department of Computer Science & Engineering Chennai Institute of Technology

Several business applications and procedures are expected to be significantly disrupted by Blockchain-based technologies, which has significant consequences for ecommerce. In light of the potential blockchain based technology are popularly known as "trust building systems" that can be used in multiple business models and standard guidelines which evolved placed above a white period to achieve believe, serviceability, and enforcement in various domains such as cunsumers related business, business related connections have to be questioned and possibly adjusted. By enabling trustless trade interactions that work without specialized intermediaries or even central authority in the case of permission lessblock chains, Blockchain has the power to change how electronic commerce operates. Furthermore, giving universal access to immutable data across the whole supply chain may significantly alter the information and value exchange between businesses and consumers. The methodology presented in this paper are intended to motivate further study of the potential effects of Blockchain on e-commerce. Technology, law, organizational and quality challenges, as well as consumer difficulties, are the four key categories. This paper demonstrates how Blockchain may affect many Electronic commercial components in these relevant fields.

关键词： Technological innovation Law Biological system modeling Supply chains Trustless services Blockchains Cryptocurrency

来源：评论

学校读者我要写书评

暂无评论

Real-time multi-factor adaptive task scheduling model for improved QoS in cloud environment

引用

AIP Conference Proceedings 2024年第1期3075卷

作者： M. Baskar G. John Samuel Babu Associate Professor Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chengalpattu Tamilnadu 603 203 India. Associate Professor Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana 500043 India.

The task scheduling and data security issue in the cloud is well-studied, and different approaches exist around the problem. Most approaches consider makespan, throughput, delay, and others in task scheduling. The existing methods need better performance in various quality of service metrics as they consider only limited features of task scheduling. To overcome these issues, an efficient multi-factor adaptive task scheduling (MATS) is presented in this article. The method considers the cost, delay, and utilization of various services in selecting a service for task scheduling. According to the factors mentioned above, the method applies MFTS scheduling which approximates the factors toward maximizing the QoS performance. The MFTS algorithm computes Cost Support Measure (CSM), Delay Centric QoS Support Measure (DCQSM), and Utilization Support Measure (USM). Using all these measures, the value of Selection Weight (SW) is measured to support scheduling. Further to maximize data security, the proposed MATS model discovers the routes and estimates Quality Centric Transmission Support (QCTS) to identify an optimal route to support QoS maximization. The MATS scheduling approach achieves higher QoS performance with data security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Facemask detection ontology with GBML as meta classifier

引用

AIP Conference Proceedings 2023年第1期2754卷

作者： B. J. D. Kalyani S. Neelima Kopparthi Praneeth Sai Kopparthi Bhanu Prashanth Associate Professor Department of Computer Science and Engineering Institute of Aeronautical Engineering Dundigal Hyderabad India 500043 Associate Professor Department of Computer Science and Engineering Priyadarshini Institute of Science and Technology for Women Khammam India 507002 Process Executive Wipro Limited Hyderabad India 500032 Vardhaman College of Engineering Hyderabad India 501218

World Health Organization (WHO) recommend usage of mask as an operative prevention to avoid spread of Covid 19. Various reports present that wearing face masks top virus transmission and reduces the risk of transmission. This paper focus on cloud-based AI methodology for the detection of face mask. A mask detection data base with two categories of information includes with mask and without mask images that are stored in cloud data Centre via webcam. The proposed work uses Full Convolution Neural Network (FCNN) and Gradient Boost Machine Learning (GBML) model for classification and detection mask. This paper focus on the objective of to recognize whether the person on image or video stream is wearing a mask or not and not wear properly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADVANCED ATTACK MITIGATION IN IOT GATEWAY PROTOCOLS

引用

computers & Security 2025年 157卷

作者： K. Praveen Kumar Dr. N. Suresh Kumar Assistant Professor Department of Information Technology Kakatiya Institute of Technology and Science Warangal (KITSW) Telangana India Research Scholar Department of Computer Science and Engineering GITAM University Visakhapatnam Andhra Pradesh India Associate Professor Department of Computer Science Engineering GITAM Institute of Technology GITAM (Deemed to be University) Visakhapatnam India

With the increasing number of users on the internet, numerous cyberattacks are becoming more and more common. Proper detection of these attacks by Intrusion Detection Systems (IDS) is extremely important, particularly for IoT networks. Deep learning methods have proved to be very promising for enhancing IDS performance. This paper presents an end-to-end system for attack detection and prevention in IoT networks with the use of data augmentation, preprocessing, feature extraction, and deep machine learning algorithms. The class imbalance is resolved using the Enhanced Synthetic Minority Over-Sampling Technique (ESMOTE), and preprocessing operations normalize and clean the data for improved model performance. Feature extraction involves statistical features and Shannon entropy-based features, which are fused and sent through a feature selection process. A new 2D-LICM hyper-chaotic map combined with Walrus Optimization (2D-LICMHy-CM_WO) is used to enhance feature selection through enhanced search diversity, convergence rate, and eliminating redundancy. The Dense Convolutional Spatial Attention-based Enhanced Bi-GRU (DCSAtten_EBi-GRU) effectively extracts attack pattern dependencies for precise detection, and an Enhanced Double Deep Q-Learning Network (DoubleDQN) offers dynamic adaptive real-time countermeasures. Experimental findings prove that the proposed solution can obtain a 99.6% detection accuracy with an F1-score of 0.98 and outperforms current IDS models in false positive rate and detection time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic Powered Fuzzy Algorithm for IoT-Monitored Four Switch Induction Motor Drive

Photovoltaic Powered Fuzzy Algorithm for IoT-Monitored Four ...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： S. Jayaprakash T. Kanthimathi N. Rathika P. Sathyanathan C. Srinivasan Associate Professor School of Electrical and Electronics Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Department of Mechanical Engineering Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh India Department of Electrical and Electronics Engineering Mahendra Institute of Technology Tiruchengode Tamil Nadu India Department of Electrical and Electronics Engineering VelTech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

There has been a lot of focus on the potential benefits to the industry of combining Renewable Energy Sources (RES) with Internet of Things (IoT) technology. The conventional motor-driven control system often uses traditional power sources and has poor continuous tracking capabilities, which limits its energy economy and control accuracy. This research introduces a unique method for enhanced energy efficiency and control by integrating a fuzzy algorithm, a photovoltaic (PV) power source, IoT-monitored four-switch induction motor (IM) drive. A fuzzy algorithm is used to improve the motor drive system. According to input factors like torque, load conditions and speed, the fuzzy logic controller (FLC) modifies the motor driving settings. Because of the adaptive properties of the fuzzy algorithm, the IM may be controlled effectively, improving system performance. Additionally, the IoT monitoring feature allows for remote control and real-time data collecting, improving system performance and issue detection. MATLAB/Simulink is employed to demonstrate the obtained results of the developed system. The results of this research may be used in a variety of fields, including robots, electric cars, and industrial automation powered by renewable energy.

关键词：

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：