DIVAKAR YADAV

Followers

Following

103

Co-authors

Public Views

Phone: 9313714418
Address: Noida (India)

less

Interests

Uploads

Papers by DIVAKAR YADAV

Online Food Court Payment System using Blockchain Technolgy

2018 5th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), Nov 1, 2018

it is a web and cellular-based app designed commonly for use in the meals & beverage enterpri... more it is a web and cellular-based app designed commonly for use in the meals & beverage enterprise. These apps solve the problems of labour cost in the restaurants and food court resulting in an increase in overall business. It also provides the owner to manage and make changes as per the requirements in the shop. The customer can order their food by accessing the food app through their mobile. The shopkeeper can easily complete the order in time, as there will be a regular check-in for the availability of ingredients. In this paper, we will be representing the overall description and software requirement specification of the entire system designed for use in different food courts. Our apps will provide the restaurant employees to manage their online menu and keep track of all the orders placed by their customers. The customers will be able to access the menu from anywhere so they can order their food and collect it immediately after it is ready. Inside this paper, we have depicted a general model of the framework, layouts of functional and non-functional prerequisites, and a definite portrayal of the UI. Eventually, this idea represents an account of the expansion of the device alongside predicted protection.

Improve the Response Time with Content Mining based Web Page Ranking

2022 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), May 20, 2022

Design of a Novel Incremental Parallel Webcrawler

INFLIBNET, 2010

Download

Image Query Based Search Engine Using Image Content Retrieval

In this paper we put forward a model for a search engine where an image can be uploaded from the ... more In this paper we put forward a model for a search engine where an image can be uploaded from the local database of the user to retrieve information about it from the internet. This is similar to the traditional keyword search used by most of the search engines with the only difference being that here an image is uploaded as

Question answering system for semantic web: a review

International Journal of Advanced Intelligence Paradigms, 2022

An approach for fast compressed text matching and to avoid false matching using WBTC and wavelet tree

ICST Transactions on Scalable Information Systems, Jul 13, 2018

Text matching is a process of finding the frequency of occurrences of text pattern in a corpus. I... more Text matching is a process of finding the frequency of occurrences of text pattern in a corpus. It's very costly to store, process, and retrieve a vast volume of text data. In this paper, we present a method to keep the massive text corpus in lesser memory space by using text compression and to retrieve the results by matching directly on this compressed corpus without decompression using compressed pattern matching (CPM). The proposed approach also helps to minimize the time taken to perform matching without compromising the false matching results. We used word-based tagged coding to perform text compression and Wavelet Trees for representing the compressed text in memory. The proposed Text Matching in Compressed text using Parallel Wavelet Tree (TMC_PWT) method is quite fast in comparison to other existing text matching algorithms that support CPM. In the context of CPM, the proposed method provides a good compression ratio and does not suffer from the problem of false matching.

Download

ctu ure e for Pa ar ra al ll le el l Cra awling g an nd A Al lg go ori it thm fo or r C Ch ha an nge D Dete ecti io on n in W We eb b Pa ag ge es s

A novel simulation-annealing enabled ranking and scaling statistical simulation constrained optimization algorithm for Internet-of-things (IoTs)

Smart and sustainable built environment, Mar 6, 2020

Purpose -Simulation-based optimization is a decision-making tool for identifying an optimal desig... more Purpose -Simulation-based optimization is a decision-making tool for identifying an optimal design of a system. Here, optimal design means a smart system with sensing, computing and control capabilities with improved efficiency. As compared to testing the physical prototype, computer-based simulation provides much cheaper, faster and lesser time-and resource-consuming solutions. In this work, a comparative analysis of heuristic simulation optimization methods (genetic algorithms, evolutionary strategies, simulated annealing, tabu search and simplex search) is performed. Design/methodology/approach -In this work, a comparative analysis of heuristic simulation optimization methods (genertic algorithms, evolutionary strategies, simulated annealing, tabu search and simplex search) is performed. Further, a novel simulation annealing-based heuristic approach is proposed for critical infrastructure. Findings -A small scale network of 50-100 nodes shows that genetic simulation optimization with multicriteria and multi-dimensional features performs better as compared to other simulation optimization approaches. Further, a minimum of 3.4 percent and maximum of 16.2 percent improvement is observed in faster route identification for small scale Internet-of-things (IoT) networks with simulation optimization constraints integrated model as compared to the traditional method. Originality/value -In this work, simulation optimization techniques are applied for identifying optimized Quality of service (QoS) parameters for critical infrastructure which in turn helps in improving the network performance. In order to identify optimized parameters, Tabu search and ant-inspired heuristic optimization techniques are applied over QoS parameters. These optimized values are compared with every monitoring sensor point in the network. This comparative analysis helps in identifying underperforming and outperforming monitoring points. Further, QoS of these points can be improved by identifying their local optimum values which in turn increases the performance of overall network. In continuation, a simulation model of bus transport is taken for analysis. Bus transport system is a critical infrastructure for Dehradun. In this work, feasibility of electric recharging units alongside roads under different traffic conditions is checked using simulation. The simulation study is performed over five bus routes in a small scale IoT network.

Download

A novel approach to solve exact matching problem using multi-splitting of text patterns

International Journal of Systems Assurance Engineering and Management, Jun 1, 2023

A systematic review on page ranking algorithms

International journal of information technology, Feb 22, 2020

Search engines are very useful tool now a days to fulfill the information need of a user. The per... more

Download

ForensicNet : Modern CNN-based Image Forgery Detection Network

Research Square (Research Square), Jul 9, 2022

The advancements in Image editing techniques produce realisticlooking artificial images with ease... more The advancements in Image editing techniques produce realisticlooking artificial images with ease. These images can easily circumvent the forensic systems making the authentication process more tedious and difficult. To overcome this problem, we introduce a modern convolutional neural network (CNN) named ForensicNet, inspired by the recent developments in computer vision. The three major contributions of our CNNs are inverted bottleneck, separate downsampling layers, and using depth-wise convolutions for mixing information in the spatial dimension. The inverted bottlenecks help improve accuracy and reduce network parameters/FLOPs. The separate downsampling layers help converge the network. The normalization layers also help stabilize training whenever the spatial resolution is changed. The depth-wise convolution is a grouped convolution where the number of groups and channels are the same. The experiments show that ForensicNet outperforms the state-of-the-art methods by a large margin.

Survey and Comparative Study on Statistical Tools for Medical Images

Advanced Science Letters, 2015

ABSTRACT This paper is about a comparative study about Statistical tools available for Medical Im... more ABSTRACT This paper is about a comparative study about Statistical tools available for Medical Images and Neuronal Data. Analyzing Medical images and neuronal data statistically there are many software packages available. The study is done with a comprehensive picture of the Definitions, Statistical Tests Errors, Precision, Variance. According to work flow of the tool and on various statistic Parameters. In this paper we have tried to show Tools available to statistically analyze various Medical modalities like CT Scan, PET, MRI, FMRI and we have shown comparison of specifically most popular software packages R, SPSS, SAS and Matlab.

Incremental Refinement of Page Ranking of Web Pages

International journal of information retrieval research, Jul 1, 2020

Web-basedinformationretrievalsystemscalledsearchengineshavemadethingseasyforinformation seekers,b... more Web-basedinformationretrievalsystemscalledsearchengineshavemadethingseasyforinformation seekers,butstilldonotprovideguaranteesabouttherelevanceoftheinformationprovidedtothe users.Informationretrievalsystemsprovidetheinformationtotheuserbasedoncertainretrieval criteria.DuetothelargesizeoftheWWW,itisverycommonthatalargenumberofdocumentsget identifiedrelatedtoaparticulardomain.Therefore,tohelpuserstowardsfindingthebestmatching documents, a ranking mechanism is employed by the search engine. In this article, an improved architectureforaninformationretrievalsystemisproposed.Theproposedsystemmakesaquerylog foreachuserqueryandstorestheresultsretrievedtotheuserforthatquery.Thesystemalsoprovides relevantresultsbyanalyzingthecontentofthepagesretrievedfortheuserquery.

A detailed analysis of image and video forgery detection techniques

The Visual Computer, Jan 13, 2022

Performance Evaluation of Methods for Mining Frequent Itemsets on Temporal Data

Lecture notes on data engineering and communications technologies, 2020

<scp>ForensicNet</scp> : Modern convolutional neural network‐based image forgery detection network

Journal of Forensic Sciences, Jan 31, 2023

Mathlete: an adaptive assistive technology tool for children with dyscalculia

Disability and Rehabilitation: Assistive Technology, Oct 19, 2022

Assistive Technology for Preliminary Diagnosis of Learning Disability (LD) among Children

2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), 2019

Learning Disability (LD) causes difficulties in areas of behavior and learning and thus managing ... more Learning Disability (LD) causes difficulties in areas of behavior and learning and thus managing it is vital for people suffering from such disabilities. In India, 5-10% of children suffer from one of the learning disabilities. It can be assumed that the number might be high as it could remain undiagnosed in many of them. Also, it not known that how learning disabilities are diagnosed and managed among children. There lie no evidences in Indian Context about how learning disability is managed among children. Hence, a survey was conducted in schools of Delhi to determine what strategies the schools use to diagnose and deal with learning disabilities. The results depicted that the primitive pen-paper methodology was being used for preliminary diagnosis. Therefore, latest technologies such as Assistive Technology can be of a great help in eliminating this primitive approach and thus contribute in a cost-effective way of diagnosis. A conceptual framework using assistive technology is proposed for the diagnosis which would optimize the entire process of diagnosis. Such a model would not only help in the diagnosis of LD but also in promoting the broader functional outcomes of assistive technology.

Student performance prediction for adaptive e-learning systems

E-learning Methodologies: Fundamentals, technologies and applications, 2021

The growth of e-learning systems has changed current learning behavior and tries to present a new... more The growth of e-learning systems has changed current learning behavior and tries to present a new framework for the learners. E-learning platforms have become common and approachable for a vast set of audiences. The COVID-19 pandemic in 2020 has triggered the application of these online learning platforms. The number of e-learning platforms has been increasing rapidly to fulfill the requirement. This chapter tries to estimate the three factors consisting of learner's personality, learning style and knowledge level in order to recommend the content that is best suited to the learner. An ensemble approach to solving this problem has been used, which utilizes a genetic algorithm and KNN to find the content appropriate for the learner.

GLCM Based Feature Extraction and Medical X-RAY Image Classification using Machine Learning Techniques

2019 IEEE Conference on Information and Communication Technology, 2019

The machine learning and artificial intelligence play a vital role to solve the challenging issue... more The machine learning and artificial intelligence play a vital role to solve the challenging issues in Clinical imaging. The machine learning and artificial intelligence ease the daily life of both medical practitioner and patient's. Nowadays, the automatic system is designed with high accuracy to perceive abnormality in bone X-ray images. To achieve high accuracy system has less resource available image pre-processing tools are used to enhance the medical images quality. The image pre-processing involves the process like noise removal and contrast enhancement which provides instantaneous abnormality diagnosis system. The Gray Level Co-occurrence Matrix (GLCM) texture features are widely used in image classification problems. GLCM represents the second-order statistical information of gray levels between neighboring pixels in an image[1]. In the paper, we implemented different machine learning approaches to classify the bone X-ray images of MURA (musculoskeletal radiographs) dataset into fractures and no fracture category. The four different classifiers LBF SVM (Radial Basis Function support vector machine), linear SVM, Logistic Regression and Decision tree are used for abnormality detection. The performance evaluation of the above abnormality detection in X-ray images is performed by using five statistical parameters such as Sensitivity, Specificity, Precision, Accuracy and F1 Score, which shows significant improvement.

DIVAKAR YADAV

Uploads

Papers by DIVAKAR YADAV

Log In