检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Parthipan, S. Senthil Velan, S. Babu, Chitra PG Scholar Department of Computer Science and Engineering SSN College of Engineering Chennai India

Software metric plays a vital role in quantitative assessment of any specific software development methodology and its impact on the maintenance of software. It can also be used to indicate the degree of interdependence among the components by providing valuable feedback about quality attributes such as maintainability, modifiability and understandability. The effort for software maintenance normally has a high correlation with the complexity of its design. Aspect Oriented Software Design is an emerging methodology that provides powerful new techniques to improve the modularity of software from its design. In this paper, evaluation model to capture the symptoms of complexity has been defined consisting of metrics, artifacts and elements of complexity. A tool to automatically capture these metrics across different versions of a case study application, University Automation System has been developed. The values obtained for the proposed metrics are used to infer on the complexity of Java and AspectJ implementations of the case study application. These measurements indicate that AspectJ implementations are less complex compared to the Java implementations and there by positively influencing the maintainability of software. © 2020, CC0.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Survey paper on big data tool analysis

引用

AIP Conference Proceedings 2023年第1期2800卷

作者： Vaishali B. Bhagat V. M. Thakare Sagar Pande Research Scholar PG Department of Computer Science and Engineering Sant Gadge Baba Amravati University Amravati Maharashtra India Professor and Head PG Department of Computer Science and Engineering Sant Gadge Baba Amravati University Amravati Maharashtra India Assistant Professor Intelligent System School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India

In this era of technology, online data is increasing enormously in various forms be it images, videos, texts, sound, etc. Now with increasing data, there arises the issue of storage and that’s the time when Bigdata and its tools come into the picture. To analyze the big data and process it with the available traditional methods, becomes an extremely strenuous task. And to overcome this drawback, there are various big data tools and techniques available. Some of the techniques that are used to analyze big data are the techniques of data mining such as clustering, classification, division, and prediction. The tools that are used in analyzing the big data are MongoDB, NoSQL, HPCC, Apache Storm, Spark, Apache Hadoop, also these tools are used in handling big data. In this paper, analysis of big data tools and techniques has been done with different examples and instances. To understand the tools better, their summaries along with examples are presented.

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

Barcode System for Hotel Food Order with Delivery Robot

引用

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

作者： D. Saravanan E. Racheal Anni Perianayaki R. Pavithra R. Parthiban Associate Professor Department of Computer Science and Engineering IFET College of Engineering Villupuram PG Scholar Department of Computer Science and Engineering IFET College of Engineering Villupuram

Technological development has reached perhaps in each field in the present developing world; our test aspirations to give a move up to administrations in the subject of Restaurants and Hotels, with the guide of making and exhibiting a model of a Wireless Waiter Robot. Robots can make the transporter additional condition benevolent and do it more prominent viably sparing time and diminishing work costs. The method utilized right here has an arrange following automated which guarantees the arranged dinner to the respected clients. A menu is made close by to the clients on their mobile phones when they partner with the Bluetooth affiliation open at the diner, the gala is mentioned by strategies for a cell application. The RF mechanical mastery will information the robot to the important work zone of the purchaser using a coordinated system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Analysis on Crypto-ransomware by using Machine Learning: GandCrab Ransomware

引用

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

作者： S Usharani P Manju Bala M Martina Jose Mary Associate Professor Dept of Computer Science and Engineering IFET college of Engineering Villupuram India. PG Scholar Dept of Computer Science and Engineering IFET college of Engineering Villupuram India.

A ransomware is a unique class of malware which has gotten extremely famous in digital crooks to corkscrew cash. It categorizes the client confines by accessing their machines (PCs, cell phones and IoT gadgets) unless the payoff is paid. Consistently, security specialists report numerous types of ransomware assaults, including ransomware families. User's data will be collected at the time of dynamic process. The collected data will be in crypto ransomware type from that we can extract features like IP address, file length, URL. We will do dynamic analyse of the presently data with the antecedent data. Using machine learning algorithm (by combining Random Forest, Gradient Tree Boosting and Support Vector machine algorithm) we can classify the data as benign or ransomware. The achievement rate of classification using machine learning algorithm is 98.45% with false rate *** proposed achievement rate will be compared among linear regression, navie Bayes and adaboost algorithm. Gandcrab ransomware-Version, algorithm is to be identified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-learning ai framework for skin lesion image segmentation and classification

arXiv

引用

arXiv 2020年

作者： Kamalakannan, Anandhanarayanan Ganesan, Shiva Shankar Rajamanickam, Govindaraj Department of Cyber Physical Systems Central Electronics Engineering Research Institute CSIR Madras Complex Taramani Chennai India PG Scholar Dept. of Computer Science University of Bridgeport 126 Park Ave Bridgeport United States

Image segmentation and classification are the two main fundamental steps in pattern recognition. To perform medical image segmentation or classification with deep learning models, it requires training on large image dataset with annotation. The dermoscopy images (ISIC archive) considered for this work does not have ground truth information for lesion segmentation. Performing manual labelling on this dataset is time-consuming. To overcome this issue, self-learning annotation scheme was proposed in the two-stage deep learning algorithm. The two-stage deep learning algorithm consists of U-Net segmentation model with the annotation scheme and CNN classifier model. The annotation scheme uses a K-means clustering algorithm along with merging conditions to achieve initial labelling information for training the U-Net model. The classifier models namely ResNet-50 and LeNet-5 were trained and tested on the image dataset without segmentation for comparison and with the U-Net segmentation for implementing the proposed self-learning Artificial Intelligence (AI) framework. The classification results of the proposed AI framework achieved training accuracy of 93.8% and testing accuracy of 82.42% when compared with the two classifier models directly trained on the input images. Copyright © 2020, The Authors. All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach for Indian sign language gestures classification with different backgrounds

引用

Journal of Physics: Conference Series 2021年第1期1950卷

作者： R. Dhiman G. Joshi C. Rama Krishna PG Scholar Department of Computer Science & Engineering NITTTR Chandigarh INDIA. Assistant Professor Department of Electronics & Communication Engineering UIET Panjab University Chandigarh INDIA Professor & Head Department of Computer Science & Engineering NITTTR Chandigarh INDIA.

The sign language recognition system recently has drawn the attention of various researchers as there is no universal sign language, moreover, it consists of many patterns and postures. Many methods for extracting features and classifying sign language have been proposed in the literature, most of them are based on machine learning techniques. In this article, a deep learning method has been adopted by designing a Convolution Neural Network (CNN) model to extract the sign language features where for classification softmax layer is used. All alphabets in simple as well as complex backgrounds have been considered, where data is collected from 100 subjects in different lighting conditions. The effect of various optimization techniques (Adam, Sgdm, RMSProp), activation functions (ReLU and Leaky ReLU) for generalization ability is also observed. The proposed approach has succeeded in attaining the testing accuracy of 99.10%, 92.69%, and 95.95% on the Indian sign language dataset with simple, complex backgrounds and on a mixed background scenarios, respectively. The model is also tested on NUS dataset-I, NUS dataset-II, their combination, and achieved the accuracy of 100%, 95.95%, and 97.22% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cost-Efficient Proof-of-Stake-Voting Based Auditable Blockchain e-Voting System

引用

IOP Conference Series: Materials science and engineering 2021年第1期1099卷

作者： Trishie Sharma C Rama Krishna Arshdeep Bahga PG Scholar Computer Science Engineering Department National Institute of Technical Teachers Training and Research Chandigarh India Professor Computer Science Engineering Department National Institute of Technical Teachers Training and Research Chandigarh India Director Cloudemy Technology Labs Chandigarh India

In recent years, blockchain-based systems have emerged powerfully and led to the development of several new and improved applications in terms of increased security, trust, accountability and reliability. One important trust-based application is electronic voting system which still lacks in providing good throughput while also reducing the costs in voting given the deployment of state-of-the-art technologies. So, there is a need to imply an efficient consensus protocol to impart cost-efficiency as well as better performance of a blockchain-based electronic voting system. This paper focuses on boosting up the cost-efficiency in the voting process, while also being auditable, thus, strengthening the trust of voters on the government and lessening the overall costs incurred in voting. In this paper, Proof-of-Stake-Voting is used as consensus protocol which is observed to give a throughput of 4-5K transactions per second. Then its performance is compared with the other existing consensus protocols such as Proof-of-Work and Proof-of-Authority in terms of gas consumption, gas cost, and throughput. It has been shown through the results that there is a significant difference in the total gas cost, with Proof-of-Stake-Voting protocol consuming 3.1 x 10−7 Ethers (ETH), as compared to the Proof-of-Work, taking 5.42536 x 10−4 ETH and Proof-of-Authority protocols taking 2.49759 x 10−4 ETH.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LRFM model for customer purchase behaviour using K-Means algorithm

引用

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

作者： C Jamunadevi S Tamil Selvan M Govindarajan C Saravanan B R Janaki Raman Assistant Professor Department of CT-PG Kongu Engineering College Perundurai Erode India Assistant Professor Department of Computer Science and Engineering Erode Sengunthar Engineering College Erode India Associate Professor Department of Computer Applications Velalar College of Engineering and Technology Erode India Assistant Professor Department of Information Technology Velalar College of Engineering and Technology Erode India UG Scholar Department of Computer Technology-PG Kongu Engineering College Perundurai Erode India

The COVID-19 pandemics have a major collision on every aspect of life, including how people shop for their requirements. As the pandemic has reshaped life as we know, it's also initiated many trends – but the biggest of these trends may be online shopping. The shift toward online shopping was happening before the pandemic, but according to new statistics from IBM, the COIVD-19 has accelerated consumers shift toward online shopping by 5 years. The chief idea of the article is to inspect if the situation is approaching people to purchase things online and the continuation of shopping things online even after the end of pandemic. The information for the article has been gathered by circulating the survey on social networks. The questionnaire is comprised of 12 different questions, and 615 people responded to it. This work is based on LRFM (Length, Recency, Frequency, and Monetary) replica and separation of data based on the questionnaire using K-Means algorithm. Silhouette analysis helps to decide the extent of division among clusters. The results of the survey has a termination that people are fond of purchasing products online through the lockdown and people too agreed that the rate of online shopping will increase in the future when this pandemic is over.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Android security: State of art and challenges

引用

AIP Conference Proceedings 2021年第1期2387卷

作者： R. Thamilselvan K. Tamil Selvi C. Mahalakshmi N. Sanjeev Yogesh Bala 1Professor Department of Master of Computer Application Kongu Engineering College Erode Tamil Nadu India - 638060 2Assistant Professor Department of Computer Science and Engineering Kongu Engineering College Erode Tamil Nadu India - 638060 3PG Scholar Department of Master of Computer Application Kongu Engineering College Erode Tamil Nadu India - 638060

Now-a-days Android devices are rapidly increasing as per user's need and very helpful to fulfil personal and professional need. Also, these devices are quickly turning into a genuine danger because of the various malwares and security issues and threats present in them. In this paper, different proposals of security mechanisms and techniques are reviewed, which are used to ensure the security of these devices along with the latest state of art. It also discovers different kinds of security mechanisms that include authorization related issues, which are a continuous wonder in Android applications. Consent related issues that can often times wait inside an application for an all-inclusive timeframe, which can be as high as quite a while, prior to being fixed. With the collected information, security mechanisms are evaluated to find the effectiveness of methods for forestalling and identifying portable malwares and threats. Also analyzed, the motivating forces that cause benign android hobbyists to distribute root exploits and overviewed the accuracy and accessibility measures of those techniques.

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：