检索结果-内蒙古大学图书馆

Garbage Waste Segregation Using Deep Learning Techniques

IOP Conference Series: Materials Science and engineering 2021年第1期1012卷

作者： G Sai Susanth L M Jenila Livingston L G X Agnel Livingston School of Computer Science and Engineering Vellore Institute of Technology Chennai Tamil Nadu India - 600127 Assistant Professor CSE Department St. Xavier's Catholic College of Engineering Chunkankadai Nagercoil Kanyakumari District Tamil Nadu India - 629003

Waste segregation is one of the primary challenges to recycling systems in major cities in our country. In India, 62 million tons of garbage is generated annually. Of this 5.6 million tons of wastes consist of plastic materials. About 60 percent of this is recycled every year. In addition, 11.9 million tons are recycled from 43 million tons of solid waste produced. Though the numbers sound good, a serious problem in the recycling industry is the segregation of waste before recycling or any other waste treatment processes. In India, at present situation waste is not segregated when collected from households. So a lot of workforce and effort are needed to separate this waste. In addition to this people working in this industry are prone to various infections caused due to toxic materials present in the waste. So the idea is to decrease the human intervention and make this waste segregation process more productive. The proposed work is aimed to build an image classifier that identifies the object and detects the type of waste material using Convolutional Neural Network. In this work, four different models of the CNN, such as ResNet50, DenseNet169, VGG16, and AlexNet, trained on ImageNet, are used to extract features from images and feed them into a classifier to make predictions and distinguish a type of waste from its corresponding category. The experimental results showed that the performance of DenseNet169 was significantly greater than all four models and the performance of ResNet50 is closer to DenseNet169.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performing Experimentation with Physics Model to Predict Statistical Weather Condition

引用

Journal of Physics: Conference Series 2020年第1期1712卷

作者： A. Jayanthiladevi V. Nagaraju L. Devi N. Padmavathi P. Sailaja M.S Minu B R Tapas Bapu Professor-Computer Science & Information Science Srinivas University Karnataka India Professor / Department of ECE Rajalakshmi institute of technology Assistant professor in computer application Muthayammal College of arts and science Rasipuram Tamilnadu India Assistant Professor / Department Of Technology Velammal Institute Of Technology Assistant professor Dept of CSE SRM Institute of Science and Technology Ramapuram Campus Professor / Dept of ECE S. A. engineering college

Ice in wind turbines may cause a tremendous reduction in energy conservation. As, ice over turbines are not considered to be a traditional weather prediction data, prediction towards power can leads to higher error. This work anticipates a statistical approach dependent on Niave bayes regression to identify production loss has to be analyzed. It measures input of regional weather condition and various other conditions, and identify power production loss for 48 hours to enhance prediction of next generation energy loss. This can be trained with various prediction measurements and drastically enhances other conventional approaches for longer period. It may diminish absolute production error by ~100kW and it computes its skill with other models. Prediction of weather data is considered to be one of the effectual data for diverse statistical prediction and some calculations are not so absolute. This method can be computational less cost and may be trained again for next prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi Path Routing Technique Based RRP for P2P Network

引用

IOP Conference Series: Materials Science and engineering 2020年第1期994卷

作者： Mary Subaja Christo R. M. Bommi K. Mariyappan Associate Professor Department of Information Science and Engineering Faculty of Engineering Technology Jain University Bangalore India Associate Professor Mechatronics Engineering Department Chennai Institute of Technology Kundratur India Assistant Professor Department of Computer Science and Engineering Jain University Bangalore India

All articles must contain an abstract. Peer to Peer (P2P) network is useful for developing applications and downloading files from the internet. In the existing P2P networks, communication is initiated and supported by peers. Security issues constitute the main challenge in the design of reliable communication techniques for P2P networks. In the past, Rumor Riding Protocol was used in distributed systems for performing coordination and communication. However, the existing Rumor Riding Protocol is used flooding technique to forward the response to the initiator it may leads high network traffic to avid this I have Enhanced Multi path forwarding technique to Rumor Riding Protocol and also enhancement with security features to make them suitable for downloading applications in P2P networks. In this method, it enhances the Rumor Riding Protocol with security features by including a Cryptographic Puzzle, a Challenge Question scheme using trust modeling and an intelligent beta reputation model for secured communication in P2P networks. For this purpose, five new techniques are proposed in this research work, all of which aim at enhancing the security of communication using Rumor Riding Protocol in the P2P networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of high grade and low grade tumors in MR Brain Image using Modified Monkey Search Algorithm

引用

IOP Conference Series: Materials Science and engineering 2020年第1期993卷

作者： Saravanan Alagarsamy T. Abitha S. Ajitha S. Sangeetha Vishnuvarthanan Govindaraj Assistant Professor Department of Computer Science and Engineering Kalasalingam Academy of Research and Education India Under Graduate Scholar Department of Computer Science and Engineering Kalasalingam Academy of Research and Education India Associate Professor Department of Biomedical Engineering Kalasalingam Academy of Research and Education India

Detection of tumors present in the Magnetic Resonance brain image is a challenging task in the research field of medical imaging processing. The tumors with distinguished boundaries are difficult to find in the MR brain images, while performing the manual segmentation process. There is a necessity of an automated segmentation technique for performing better segmentation in terms of tumors with distinguished boundaries. The automated modified monkey search technique is used to find the optimized cluster position, and a random search operation is performed is locate all the pixels present in the image and then finally the location of the tumor region is exactly segmented/predicted by using the suggested monkey search algorithm. The suggested technique will support the radiologist for finding the tumors with distinguishing boundaries and accuracy of prediction of tumors is also improved lot with this approach. Based on the early prediction of tumors, diagnosing procedures will save the lives of many human beings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure Multiparty computation enabled E-Healthcare system with Homomorphic encryption

引用

IOP Conference Series: Materials Science and engineering 2020年第2期981卷

作者： A Vijaya Kumar Mogalapalli Sai Sujith Kosuri Tarun Sai Galla Rajesh Devulapalli Jagannadha Sriram Yashwanth Assistant Professor Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India Student Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India

With the spread of Covid–19 pandemic it is difficult for many patients to physically visit the Hospitals and get treatment. The Improved technology enable such patients to contact the concern doctors and get diagnosis information online. The security of the sensitive data of the Patients is vulnerable when the information is shared across the network. To address this, we are proposing a novel approach with the Privacy ensured self-care health management schema using Secure Multiparty computation (MPC). Through this approach the patient can share the sensitive data to the Hospital server through the online mode, the data will be shared in the encrypted format which will be matched with the existing data at the Hospital records and the best relevant match based on the smart Index of disease. The privacy preserving is key aspect in this model as the data is shared in the sensitive mode so the Homomorphic Encryption (HE) approach is used to perform computations on the Patient's sensitive data in the encrypted mode and ensure the confidentiality from Intruders to access the information. This model also proposes a novel approach which can overcome many security threats. The patient's data will be shared and used in a more secured manner so the patients specifically the elder who are not advised to visit the public places in this pandemic can also receive better treatment through online.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Public Cloud Security for E-Voting System on IoT Environment

引用

IOP Conference Series: Materials Science and engineering 2020年第4期981卷

作者： A Vijaya Kumar Gabbita Viswa Sarvani Dama Satya Assistant Professor Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India Student Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India

Digital Technology is inevitable for better life of the people. Voting by people plays the vital role in democracy as the leaders will be elected by it. IoT helps many edge devices to interact with a Cloud for storage and computation of the Voting results. The major concern for the Voter is whether the vote casted by him is tamperproof or not. Though Cloud offerings are started a decade ago still information security in the cloud is always a concern. This paper focuses on creating a tamperproof framework to ensure the data Integrity. It proposes a novel approach where the user can cast the vote from any of the electronic devices with a unique ID allotted to him, a two-step authentication can be applied like OTP to ensure the security. The votes from these edge devices will be sent to the untrusted third party public cloud for computation, the votes will be saved in the encrypted format. The computation will be done on encrypted data. The Block chain based workflow ensures that the votes which are shared in the encrypted format will not be tampered to ensure trust and Integrity to the proposed model. The model also can be extended to many public shared e-models like E-Auction and healthcare systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mathematical model for implementing Non Linear Time Series Forecasting using Deep Learning

引用

IOP Conference Series: Materials Science and engineering 2020年第2期981卷

作者： Imran Qureshi Burhanuddin Mohammad Mohammed Abdul Habeeb Mohammed Ali Shaik Lecturer IT Department University of Technology and Applied Science-AlMusanna Oman Assistant Professor Department of Computer Science & Engineering SR University Warangal Telangana India

In this paper we propose a novel algorithm for implementing the mathematical model using the Non Linear Time Series Forecasting using the methods of deep learning which has to avoid noise and tends to transforms the space to next level in a iterative manner by swapping the down-trend to up-trend or up-trend to down-trend based on the iterative set values by computing the transformations. The proposed model must handle huge dimensional data which is in a dynamic nature of proposed model and then we need to compare the results attained from the proposed model with the complex ARIMA model and identified various trial and error methods for predicting the future price without guidance. For obtaining the results we used the petroleum dataset of India and attained the results which prove that our proposed mathematical model is far better than the famous ARIMA model while handling non linear time series applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WITHDRAWN: An efficient food quality analysis model (EFQAM) using the internet of things (IoT) technologies

引用

Microprocessors and Microsystems 2021年

作者： Neeba EA D. Tamilarasi S. Sasikala Resmi R. Nair K.S. Uma Department of Information Technology Rajagiri School of Engineering & Technology Rajagiri Valley Kakkanad Kochi – 682039 Kerala India Department of Electronics and Communication Engineering MVJ college of Engineering Whitefield Bangalore India Department of Computer Science and Engineering Velammal College of Engineering and Technology Viraganoor Madurai-625 009 Tamil Nadu India Department of Electronics and Communication Engineering Easwari Engineering College Ramapuram Chennai-600089 Tamil Nadu India Assistant Professor Department of Electronics Engineering Pillai College of Engineering New Panvel Navi Mumbai Maharashtra 410206 India

This article has been withdrawn: please see Elsevier Policy on Article Withdrawal ( https://***/about/our-business/policies/article-withdrawal ). This article has been withdrawn at the request of the Editor in Chief. Subsequent to acceptance of this special issue paper by the responsible Guest Editor Vimal Shanmuganathan, the integrity and rigor of the peer-review process was investigated and confirmed to fall beneath the high standards expected by Microprocessors & Microsystems. There are also indications that much of the Special Issue includes unoriginal and heavily paraphrased content. Due to a configuration error in the editorial system, unfortunately the Editor in Chief did not receive these papers for approval as per the journal's standard workflow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review on various authentication schemes and attacks on connected vehicles

引用

IOP Conference Series: Materials Science and engineering 2020年第1期993卷

作者： M. S. Bennet Praba J S Femilda Josephin Assistant Professor Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India. Associate Professor Department of Software Engineering SRM Institute of Science and Technology Kattankulathur Chennai – 603 203 India.

Connected cars are comfortable to drivers. But it also threat to humans. Connected vehicles share data like street safety, traffic analysis, road administration information like café, hospital, etc utilizing intruded on web availability and it is time delicate. Connected vehicles allow drivers and passengers to connect to the outside world while on the road. Security is the primary challenge for automakers and other stakeholders, because connected vehicles rely on wireless and cellular communication interfaces. Information should be protected from intruders. The communications between connected vehicles should be a trusted one. Safety is the primary focus of connected cars and the intruders should be identified and the intruders and falsified nodes can be identified by authentication schemes. In VANET vehicles react as indicated by the data got from the opposite end, so it is very vital that the data spreading in the framework is valid and produced by a genuine client. But there are many pitfalls in various authentication schemes. Privacy of the connected vehicles should be while sharing information and also information shared between connected vehicles should be an authenticated one. So still it a major challenge in connected vehicles due to the special characteristics like mobility, time sensitive, etc. This survey discussed the various authentication schemes and the various attacks related to that. Based on the survey, future directions of the secured trusted communications of connected vehicles have been discussed. The aim of this survey is to identify secured authentication techniques for a trusted communication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new approach to identify similar users based on customer reviews

引用

IOP Conference Series: Materials Science and engineering 2020年第1期804卷

作者： Dimple Chehal Parul Gupta Payal Gulati Research Scholar Department of Computer Engineering J.C. Bose University of Science and Technology YMCA Faridabad Assistant Professor Department of Computer Engineering J.C. Bose University of Science and Technology YMCA Faridabad

Recommender System suggests items of interest to users based on their preferences. These preferences are gauged through various sources such as purchase history, ratings, reviews and browsing behaviour. Collaborative filtering and content based filtering are the two widely used techniques that help in generating recommendations to the target user(s) by identifying similar users to target user or similar items to items of interest. Through this paper a new method to identify similar users based on the similarity of reviews has been proposed.

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：