检索结果-内蒙古大学图书馆

Real-time GB pattern convolution neural network-based brain image classification

AIP Conference Proceedings 2024年第1期3075卷

作者： Amarendra Reddy Panyala M. Baskar Research Scholar Department of Computer Science and Engineering School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu Chennai Tamil Nadu 603 203 India Assistant Professor Department of Information Technology MLR Institute of Technology Hyderabad Telangana 500043 India Associate Professor Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu Chennai Tamil Nadu 603 203 India

Medical image classification has been identified as a critical task in several medical solutions. Brain image classification has been identified as a challenging task that has been approached with different methods. The existing methods use different features like shape, texture, and gray to classify brain images. However, the methods need to improve performance in categorizing the brain image and detecting the presence of tumors. An efficient GB Pattern Convolution Neural Network (GBP-CNN) is presented to handle this issue. The method involves preprocessing the brain image given with Adaptive Feature Distribution Normalizer (AFDN) algorithm. The Grey Canvas Segmentation (GCS) technique was used to segment the normalized image. The feature vector is created by extracting the binary and grayscale patterns from the image that has been segmented. A convolution neural network is trained to recognize the features that were extracted. Two convolution layers in the CNN’s design are used to convolve the image’s features. Additionally, a pooling layer is being incorporated into the network’s design, which reduces the data to a single dimension. The neuron predicts support values for several attributes during the assessment stage. The approach then calculates the Class-Based Fitness value (CBFV) in order to categories the image against various tumour classes. The proposed GBP-CNN algorithm improves the performance of brain image classification with less time complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving On Remote Sensing Data Using Reversible Data Hiding

引用

Journal of Physics: Conference Series 2021年第1期1979卷

作者： K Saravanan K Suganthi R Kalaiselvi B Divya S Dilip Kumar PG Scholar Department of Computer Science and Engineering Arasu Engineering College Kumbakonam Tamilnadu India Assistant Professor

The method of steganography covers message in the cover file and forms a stego file. Imagery needs a method that will boost protection, minimise distortion in the stego file and recover data without failure. There is a need for reducing transmitting time in the age of multimedia and the Internet. The main purpose of this project is to create safe contact between the sender and the recipient through emails and other modes of communication. A reversible data hiding algorithm was proposed in the integer wavelet transformation (IWT) domain to resolve the image distortion problem. This strategy aims to incorporate data into IWT coefficients of higher frequencies. After wavelet coefficients are collected by converting the integer wavelet data into high-frequency subbands HL, LH and HH, the human eyes would have fewer recognisable objects. After data is incorporated in such IWT coefficients, reverse integral wavelet transformation can occur following application. The stegno image was further encrypted by using Elliptic Curve Cryptography (ECC). The process of encryption enhances the image security during data transmission. In our proposed work inverse wavelet transformation (IWT) and Elliptic Curve Cryptography (ECC) algorithms are effectively utilized to achieve highly secure communication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing ELearning platform reviews using Sentimental Evaluation with SVM Classifier

引用

Journal of Physics: Conference Series 2021年第1期1767卷

作者： R Muralidharan T Kanagasabapathy R P Vijai Ganesh Assistant Professor Department of Computer Science and Engineering Dr. Mahalingam College of Engineering and Technology Coimbatore India

In today's scenario, the participation of eLearning courses is rapidly increasing among users, especially during post-pandemic situation. Due to a hike in the need of eLearning, there is a sharp increase in emerging of online courses. Not only the academic people (students and teachers), but others also interested in the online courses, irrespective of their ages. Since numerous eLearning platforms are mushrooming, it is mandatory to follow various standard techniques to evaluate the quality of these courses. It would be more adaptable, if the evaluation techniques are made based on the Course users feedback. These feedback of the users contain more valuable information which helps in constructive decision making. The satisfactions and criticisms of the courses are shared through opinion of the registered user. Due to enormous amount of web reviews available for a course, it is extremely time-consuming and difficult to manually analyze the review and come to a conclusive decision. Reviews contain course feature specific factual information along with the opinion statements which may be positive or negative. The text reviews obtained from most of the webpages of the online courses feedback or comments section, are found to be unstructured and inconclusive. Analyzing and extracting the actual opinion throughout the reviews manually is very difficult. So, an automated technique is needed to evaluate the course based on the features of the courses, which results in attaining a decision. The Aspect based opinion mining is such a methodology which describes the important aspects of each opinion and classify them on their polarity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A System to automate the development of anomaly-based network intrusion detection model

引用

Journal of Physics: Conference Series 2021年第1期2089卷

作者： B Padmaja K Sai Sravan E Krishna Rao Patro G Chandra Sekhar Associate Professor Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad India Student Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad India Assistant Professor Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad India

Cyber security is the major concern in today's world. Over the past couple of decades, the internet has grown to such an extent that almost every individual living on this planet has the access to the internet today. This can be viewed as one of the major achievements in the human race, but on the flip side of the coin, this gave rise to a lot of security issues for every individual or the company that is accessing the web through the internet. Hackers have become active and are always monitoring the networks to grab every possible opportunity to attack a system and make the best fortune out of its vulnerabilities. To safeguard people's and organization's privacy in this cyberspace, different network intrusion detection systems have been developed to detect the hacker's presence in the networks. These systems fall under signature based and anomaly based intrusion detection systems. This paper deals with using anomaly based intrusion detection technique to develop an automation system to both train and test supervised machine learning models, which is developed to classify real time network traffic as to whether it is malicious or not. Currently the best models by considering both detection success rate and the false positives rate are Artificial Neural Networks(ANN) followed by Support Vector Machines(SVM). In this paper, it is verified that Artificial Neural Network (ANN) based machine learning with wrapper feature selection outperforms support vector machine (SVM) technique while classifying network traffic as harmful or harmless. Initially to evaluate the performance of the system, NSL-KDD dataset is used to train and test the SVM and ANN models and finally classify real time network traffic using these models. This system can be used to carry out model building automatically on the new datasets and also for classifying the behaviour of the provided dataset without having to code.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An empirical research on consumer online buying behaviour during the COVID-19 pandemic

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1055卷

作者： C Jamunadevi S Deepa K T Kalaiselvi R Suguna A Dharshini Assistant Professor Department of Computer Technology-PG Kongu Engineering College Perundurai Erode India Associate Professor Department of Management Studies Erode Sengunthar Engineering College Erode India Assistant Professor Department of Computer Science and Engineering Bannariamman Institute of Technology Sathyamangalam India Student Department of Computer Technology-PG Kongu Engineering College Perundurai Erode India

The extraordinary episode of the 2019 novel Corona-virus named as COVID-19 by the World Health Organization (WHO) has put various governments around the globe in a shaky position. The shortage of health care facilities to bear the COVID-19 has forced the countries to go with the hand of complete or partial lock down. According to the World Health Organization (WHO) report 32.6 million cases has been recorded as on 26 September 2020. Corona-virus have its major influence on consumer buying behaviour which is going to change the consumers' future hopping habits. This article highlights the change in consumer behaviour from physical store to online shopping. The present study was conducted during the month of July- August 2020, where questionnaires' are formed and data collected using Google forms. Analysis of the data is made through Simple percentage method, ANOVA test, Chi square test and ranking method. After analysis it found that the majority holding 21-30 age group of customers prefer shopping while free shipping and their cart behaviour is also analysed for the same.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1055卷

作者： Kusumalatha Karre Y Rama Devi Research Scholar Department of Computer Science and Engineering Osmania University and Assistant Professor Department of Electronics and Computer Engineering Sreenidhi Institute of Science and Technology Hyderabad Professor Department of Computer Science and Engineering Chaitanya Bharathi Institute of Technology Hyderabad

Autism is a mental condition which hinders social and communication skills. It's a lifelong disability which makes the child's day to day life very difficult. But in most of the cases early intervention has helped the children to develop the skills which are needed to the fullest to overcome autism. As early the intervention, better the development of the child. Most of the research has been carried out to detect the autism using various machine learning algorithms which consider autistic diagnostic tools such as ADI-R, ADOS or CARS. Once autism is detected, different areas which need to be developed are considered and recommendations are given to the child. In this paper, a system is proposed which uses multi dimensional data collected from facp, DST and Diet to perform analytics using machine learning and provide recommendations to the child.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning approach for detection of keratoconus

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1055卷

作者： S Shanthi K Nirmaladevi M Pyingkodi K Dharanesh T Gowthaman B Harsavardan Associate Professor Department of Computer Science and Engineering Kongu Engineering College Erode India Assistant Professor Department of Computer Applications Kongu Engineering College Erode India UG Student Department of Computer Science and Engineering Kongu Engineering College Erode India

Keratoconus is a progressive eye disease and it should be detected in early stage, to avert probable refractive surgery that could develop ecstasies. In this the authors proposes a new computer aided diagnosis model based on Support Vector Machine (SVM) learning to detect the early stage of keratoconus using the available topographic, pachymetric and aberrometry parameters of patients with keratoconus, subclinical keratoconus and normal corneas. The proposed SVM produces 91.8% accuracy with 94.2% sensitivity, 97.5% specificity for classification of early keratoconus from normal; 100% accuracy with 100%, 100% of sensitivity and specificity respectively for classification of early keratoconus from subclinical keratoconus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAMS: Smart Agriculture Management System Using Emerging Technologies IoT, AI -A Study

引用

IOP Conference Series: Materials Science and engineering 2021年第1期1074卷

作者： B. Srinivas Kumar S.G. Santhi K. Kranthi Kumar Research Scholar Department of Computer Science and Engineering Annamalai University. Associate Professor Department of Computer Science and Engineering Annamalai University. Assistant Professor Department of Information Technology Gudlavalleru Engineering College Gudlavalleru

Farming or Agriculture is the science and art of cultivating plants. It is the vital enrichment in the growth of human living. It creates food and the other related things by farming with domestic animals and will enable people to live long and healthy life. There are two agricultural categories, one is traditional Agriculture and the second one is Modern Agriculture. In Traditional Agriculture Farmers had faced many difficulties to Farm, but with the modern Agriculture Farmers can be able to see many improvements in Framing due to the agronomy, use of agricultural chemicals such as pesticides and fertilizers, Plant breeding and technological growth, these enrichments in Farming would yield good crop.(IoT)Internet of Things very often called as a system it can able to connect real physical Things, Implanted sensors, Embedded software's along with different technologies to connect and to transfer data amongst various diverse devices over the Internet. It is the hopeful expertise or technology which gives accurate and most reliable solutions on the way to too many domains. There is an extensive set of wide range of real time applications of IoT devices such as Industrial, Consumer, Commercial, Infrastructure may made IoT is the one of the best Technology to see enhancements in many domains. Solutions which are given by IoT would reduce human efforts in Farming and may provide sound of crop. In this paper a small survey will be presented to see how Internet of Things and its equivalent or other represent technologies AI, Cloud Computing would be useful to provide SMART AGRICULTURE along with Modern agricultural improvements will also be presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of hiring a freelance coder website

引用

AIP Conference Proceedings 2021年第1期2387卷 140039页

作者： C. Jamunadevi Malathi Eswaran B. Renukadevi S. Priya B. Varniha Assistant Professor (SrG) Department of Computer Technology-PG Kongu Engineering College Perundurai Erode Tamil Nadu India Assistant Professor Department of Computer Technology-PG Kongu Engineering College Perundurai Erode Tamil Nadu India Assistant Professor Department of Information Technology Sri Sai Ram Engineering College Chennai Tamil Nadu India Assistant Professor Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai Tamil Nadu India Student Department of Computer Technology-PG Perundurai Kongu Engineering College Erode Tamil Nadu India

The 2019 novel Corona-virus infection spreads very quickly all over the world, many employers have decided to secure themselves as freelancers and to shift to remote work. The current system offers project outsourcing in a manual work. Hiring a Freelance Coder is designed to develop an interface for the organization and the freelancing professionals using responsive web design. This article highlights the project outsourcing through virtual environment there is no need of real physical meet up. The working flow of this website, The Company posts its project requirement to this application by the given category. The freelancer can search and view any project posted on this application and the freelancer can bid the project to outsource from the company. The entire bid details can be verified by the company and can approve the bid. The company can monitor the work status given by the freelancer and ask queries. The internship candidate can view the internship list and they can apply and send a resume. The present study was conducted during the month of December 2020, where questionnaires are formed and data collected using Google forms. Analysis of the data is made through Simple percentage method, Chi square test and ranking method. After analysis it found that the majority holding 31-40 age group of freelancers prefer online freelancing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Future Estimate in Confronting Ransomware

引用

Journal of Physics: Conference Series 2021年第1期1717卷

作者： A. Balachandar S. Abdul Alsowdh K. Arumugam Assistant Professor Department of Computer Science and Engineering IFET College of EngineeringVillupuramIndia UG Scholar Department of Computer Science and Engineering IFET College of Engineering VillupuramIndia

Ransomware might be a one assortment of malignant PC code which is that the quickest spreading malware risk as they focusing on each kind of clients records result in brief or perpetual loss of touchy information issue to ordinary activities, cash misfortunes caused to resuscitate framework documents that partners potential hurt to an association. As a consequences of an essential information's unit encoded on the pc arrange by the programmers which they request the payment to pay a computerized cash style of a bitcoin inside a particular date, if installment isn't done no information are back to unique sort of mystery composing. The proposed framework demonstrates that gathering of bitcoin datasets are accustomed to anticipating the eventual fate of bitcoin rates then examination the ransomware, that investigation are utilized to discover the ransomware extends then the client can shutting the framework doors for keeping away from the trail technique for malware go into the framework. It shows the security measures for the framework from the ransomware prediction.

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：