检索结果-内蒙古大学图书馆

Fast Hybrid Adaboost Binary Classifier For Brain Tumor Classification

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

作者： S. Jayaprada G. JayaLakshmi L. KanyaKumari Associate Professor Department of Computer Science & Engineering Gudlavalleru Engineering College Gudlavalleru Andhra Pradesh India Assistant Professor Department of Information Technology VR Siddhartha Engineering College Vijayawada Andhra Pradesh India Assistant Professor Department of Information Technology Andhra Loyola Institute of Engineering and Technology Vijayawada Andhra Pradesh India

The brain tumor is a dangerous disease and its characterization is a difficult undertaking for radiologists in light of the heterogeneous idea of the tumor cells. computer-Aided tasks and its implementation of the current models with their frameworks would suffice the design metrics to recognize and relate the different tumors including brain though the process with scanning of the brain would emphasize on MRI. The models with support vector machine-nearest neighbor, naïve bayes analysis are obtained aren't enough to produce the different scenario at each set of layers and its correlation values of the performance observed. We propose a design model with fast Adaboost binary classifier, ensemble approach with fast boosting algorithm with the pre-trained model's dataset to analyze the different problem which proposes a strategy for multiple application scenarios of feature extraction to provide a classification model for different tumors in the brain to improve different performance parametric values for each trained and test sets with the prediction algorithm with each design formulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation of Recycled Coarse Aggregates on Partial Replacement of Cement with Silica Fume

引用

IOP Conference Series: Materials science and engineering 2021年第1期1026卷

作者： S Manivel N Pannirselvam J Rajprasad T.S. Hemanarayanan Assistant Professor Department of Civil Engineering SRM Institute of Science and Technology Potheri Kattankulathur 603203 Chengalpattu District Tamilnadu India. Assosciate Professor Department of Civil Engineering SRM Institute of Science and Technology Potheri Kattankulathur 603203 Chengalpattu District Tamilnadu India. Assistant Professor (Sr.G) Department of Civil Engineering SRM Institute of Science and Technology Potheri Kattankulathur 603203 Chengalpattu District Tamilnadu India. PG Student Department of Civil Engineering SRM Institute of Science and Technology Potheri Kattankulathur 603203 Chengalpattu District Tamilnadu India.

Coarse aggregate utilized majorly in concrete to reach the ultimate quantity in larger proportion. The structural and non-structural elements in the construction utilize majorly the concrete. Due to the mass availability of concrete during the demolition process and hence absorbing the same material to replace the coarse aggregate with recycled aggregate is the emerging field and it is sustainable. The experimental work involving the replacement of coarse aggregates with recycled aggregates and cement with silica fumes to improve the properties of concrete and eliminate the difficulties in construction field paves way for the further researches. The experimental study concentrates in the strength properties of the concrete with recycled aggregates and silica fume and compared with the conventional concrete.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning approach for grading of Diabetic Retinopathy

引用

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

作者： T Aswathi T R Swapna S Padmavathi Student Research Scholar Department of Computer Science Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India. Assistant Professor Department of Computer Science Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India.

There has been a wide interest in applying Deep Learning (DL) algorithms for automated binary and multi class classification of colour fundus images affected with Diabetic Retinopathy (DR). These algorithms have shown high sensitivity and specificity for detecting DR in non-clinical setup. Transfer learning has been successfully tested in many medical imaging applications like skin cancer detection, pulmonary nodule detection, Alzheimer's disease etc. This paper experiments with the different DL architectures such as VGG19, InceptionV3, ResNet50, MobileNet and NASNet for automated DR classification (binary and multi class) on Messidor dataset. The dataset is publicly available, and comprises of 1200 retinal fundus images. The images belong to four different classes of DR namely, normal (class 0), mild (class 1), moderate (class 2) and severe (class 3), graded based on the severity level of DR. In our experiment, we have enhanced the quality of input images by applying algorithms like CLAHE (Contrast Limited Adaptive Histogram Equalisation) algorithm and Powerlaw transformation as pre-processing techniques, which work on the small image patches with high accuracy, contrast limiting and image sharpening. Hyper parameter tuning on pretrained InceptionV3 architecture, resulted in enhancing the accuracy of the model. Both binary and multi class results were analysed considering inter class (one class with another class) accuracies. We achieved an accuracy of 78% between class 0 and class 1, the accuracy between class 0 and class 2 further reduced to 69%, while class 1 and class 2 showed an accuracy of 61%. Moreover, the interclass class accuracy between class 1 and class 3 was 62%, class 2 and class 3 further reduced to 49%. The accuracy further diminished between class 0 and class 3 to 32%. These experiments suggest that the pretrained models provided better results in classifying normal and mild, but they were not that much efficient in classifying moderate-severe and

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secured Communication in Vehicular Adhoc Networks (VANETs) using Blockchain

引用

IOP Conference Series: Materials science and engineering 2021年第1期1022卷

作者： Shivaprasad More Rahul Sonkamble Udaykumar Naik Shraddha Phansalkar Priyanka More Baljit Singh Saini Assistant Professor Department of Computer Science and Engineering Sanjay Ghodawat University Kolhapur Maharashtra India Professor Department of Electronics & Communication KLE Dr. M.S. Sheshgiri College of Engineering & Technology Belagavi Karnataka India Professor Symbiosis Institute of Technology Lavale Pune Research Scholar School of Computer Science and Engineering Lovely Professional University Punjab Professor School of Computer Science and Engineering Lovely Professional University Punjab

In the last decade, the vehicular ad-hoc network (VANET) field is growing drastically. In VANET the communication is the most important aspect through which the data transmission is taking place. Data transmission is maybe related to data in the form of multimedia messages, notifications, announcements, or some warning messages that are involved in VANETs. Data transmission among different vehicles would lead to an exchange of audio-video files in the formed network. These multimedia messages should be transmitted in the fraction of second as this network is built for temporary communication. Vehicles involved in this communication should be trustworthy otherwise other vehicles those who are part of this network would be misguided due to intruder present in the network. To achieve security and integrity in the constituted network, system has proposed the blockchain security environment as a part of this proposed system. Blockchain induces high-end communication in the ad-hoc network. It also enhances the overall security aspect of the constituted network. In this paper, we have proposed blockchain-based security system for vehicular communication that handles this communication securely in a well efficient manner. The performance of the proposed system will be measured based on parameters like end-to-end delay, reliability, and packet delivery ratio.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IOT Based Tool Garbage Management System

引用

Journal of Physics: Conference Series 2021年第1期1916卷

作者： S Sathyabama A Bharath Raaj S S Cibi Saamraat T Girimurugan Assistant Professor Department of Computer Science and Engineering Sri Krishna College of Technology Coimbatore Tamil Nadu India UG Students Department of Computer Science and Engineering Sri Krishna College of Technology Coimbatore Tamil Nadu India

These days, safe and hygiene disposal of waste via dustbins in smart cities needs a centralized and monitored system. This system monitors various bins used for rubbish and garbage collectionextent is also informed inside these garbage bins via centralized online Application. For this the system the bins are fitted specially placed ultrasonic sensors to determine the level and depth of rubbish. It incorporates an AVR based microcontroller, GSM Module, Wi-Fi modem, a buzzer for alert and LCD screen for viewing data. The voltage support is given by a 12V transformer. To determine the display status and the extent to which the rubbish bin is loaded an LCD screen is used. These LCD screens are used inside the rubbish bins. To point out the condition however the web application is designed which is used to monitor the garbage or rubbish bins. The geographical view of rubbish bins can be obtained by the web page and also these web pages indicate the colored rubbish that they can highlight

关键词：

来源：评论

学校读者我要写书评

暂无评论

(CSM2-RA-R2-TI): Cyber Security Maturity Model for Risk Assessment Using Risk Register for Threat Intelligence

引用

Journal of Physics: Conference Series 2021年第1期2040卷

作者： B Lakshmi Prasanna M SaidiReddy Research Scholar Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Hyderabad Telangana India. Assistant Professor Department of Computer Science RBVRR Women's College Hyderabad Telangana India. Associate Professor Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Hyderabad Telangana India.

Because of the growing frequency sophistication, and severity of cyber security attacks, all businesses should ensure that cyber security risk is properly addressed in their enterprise risk management (ERM) programs. Risk Management, agreeing with the NIST Guide 8286 is the arrangement of 'composed exercises to direct and control an association concerning risk'. NISTIR 8286 characterizes a system and framework for hazard the executives. In any case, executing this norm without an in-depth plan can turn into a risk on associations. This paper provides a capability maturity model for risk assessment for threat intelligence using a risk register. This model helps the organization as reference and set clear path to survey risk assessments in accordance with latest threats.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Full Fledged Automated Human Resource Management Software Suite

引用

Journal of Physics: Conference Series 2021年第1期1916卷

作者： M Sri Sivasankaran T Suganya UG Student Department of Computer Science and Engineering Sri Krishna College of Technology Coimbatore Tamilnadu India. Assistant Professor Department of Computer Science and Engineering Sri Krishna College of Technology Coimbatore Tamilnadu India.

The Human Resource Management System is essentially worried about dealing with the Administrator of HUMAN RESOURCE Department in an organization. A Human Resource Management System alludes to the frameworks and cycles at the crossing point between human asset the executives and data innovation. It blends HRM as an order and specifically its essential HR exercises and cycles with the data innovation field, though the programming of information preparing frameworks developed into full-fledged HR SUITE. The fundamental target of this paper is to diminish the exertion of Administrator to keep the day-by-day occasions, for example, participation, projects, works, arrangements, and so forth This paper manages the way toward distinguishing the representatives, recording their participation hourly and ascertaining their successful payable hours or days. This paper FULL fledged HR management suite ought to keep up the records of every single worker and their time spend in to organization, which can be utilized for execution evaluation. In view of that move, expulsion, advancement should be possible.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A reversible data hiding method for image protection

引用

AIP Conference Proceedings 2021年第1期2387卷

作者： S. S. Saranya C. Santhosh M. Santhiya S. Jeevana J. Dhivya A. Vanitha 1Assistant Professor Computer Tehnology UG Kongu Engineering College. Perundurai Tamil Nadu-638060 India 2Assistant Professor Department of Computer Science Engineering Nandha Engineering College Perundurai Tamil Nadu-638052 India 3UG Scholar Computer Tehnology UG Kongu Engineering College Perundurai Tamil Nadu-638060 India

Encryption is the way toward encoding given information that can't be perceived by an unapproved individual. Securing a message or a picture which is partaken in a social stage be the difficult undertaking these days. This paper proposes an account procedure to steganography by means of reversible room before encryption surface mix. Reversible room before encryption surface mix measure explore supplementary unobtrusive side picture that arranges different facet picture with a similar and relative appearance with optional dimensions. This paper networks the Reversible room before encryption surface association cycle with steganography for covering secrete data. Rather than using contemporary cover photo for covering information our figure seal the source surface picture and introduces coded message via pattern of Reversible room before encryption surface association. This licenses us to isolate the secret messages and source surface from a stego designed surface. This philosophy proffers main three focal points. Most importantly, the positioning provide data embedding furthest extended that is contrast to dimensions of surface of the stego picture. Second, a steganalytic compute not apparently to conquer steganography technique. Third, changeable capacity gained from our arrangement gives value, which grants recovery surface of the source. Exploratory results are guaranteed to provide various consignment of introducing curtailment, produce ostensibly viable surface pictures, and also recuperate fount surface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZED TARGET TRACKING USING HEURISTICS BASE DISPENSED ADVERT ORIENTED ALGORITHM

引用

Microprocessors and Microsystems 2021年

作者： S. Alonshia Dr. P. Sumathy Research Scholar Department of Computer Science and Engineering Bharathidasan University Khajamalai campus Tiruchirappalli- 23 Tamilnadu India Assistant Professor Department of Computer Science and Engineering Bharathidasan University Khajamalai campus Tiruchirappalli- 23 Tamilnadu India

A Wireless Sensor Network based Target-Tracking is an emerging and challenging research area among the researchers. The existing problems to track the targets in some selective sensor nodes must be under continuoussurveillance. To overcome the issues in continuous monitoringof sensor nodes can be optimized by this model concentrates on behavior based node selection dictionary creation and recording. In target-tracking, each sensor is adapted in numerous systems, for example, grounds security, reconnaissance, natural surroundings, and medicinal services checking. Data can be transmitted in a specially appointed multi-bounce structure using the web or by a sign to screen fromsensor coverage area or target and can frame a pervasive system for a few internet providers. In this paper, CENS (Consecutive Edge Node Selection) and HBDAO (Heuristics-base Dispensed-Advert-Oriented) techniques proposed to figure out the trusted and Omni boundary detection of nodes that are in the WSN simultaneously verify the active, passive status and behavior history of each node. This proposed techniques showed better results in the experiments on a simulated environment than the existing edge node detection techniques. This model also contributed tracking and maintain the accuracy, throughout management and latency avoidance in efficient manner.

关键词： Target Tracking Energy Efficient Routing Protocol WSN

来源：评论

学校读者我要写书评

暂无评论

Understanding Hadoop Framework Through Single-Node Cluster Installation

Understanding Hadoop Framework Through Single-Node Cluster I...

引用

International Conference on Recent Advances in Energy-efficient Computing and Communication (ICRAECC)

作者： V. G. Anisha Gnana Vincy T. Karthija J. Sunil Assistant Professor Department of Computer Science and Engineering V V College of Engineeing Tisaiyanvilai India Assistant Professor Department of Mechanical Engineering V V College of Engineeing Tisaiyanvilai India

ISBN: (纸本)9781538694831

Hadoop is a Java-based open source programming model that becomes a pillar in recent distributed computing by providing massive storage and multiprocessing of data. Hadoop becomes a simple and easy to implement programming model through the usage of commodity hardware. Hadoop open-source became a foundation for massive parallel processing of big data which includes scientific analytics, e-commerce data and sales planning, and processing enormous volumes of sensor from various sensors. Since Hadoop plays vital role in distributed parallel processing of big data, it is good to know the technical details behind the hadoop framework. This paper focus on detailing the necessary steps for the successful implementation of a Hadoop single-node cluster in a individual computer which provide a foundation for the new hadoop users.

关键词： Big Data Java parallel processing public domain software storage management PARALLEL PROCESSING (computerS) big data open source software Store management Java Java programming language Sensors

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：