G. P. S. Varma's research while affiliated with Bharati Vidyapeeth Deemed University and other places

Publications (71)

Article
The manual inspections of plant diseases resulted in low accuracy with high time consumption and unable to predict the multiple diseases of plants. To address these difficulties, it is necessary to develop automated systems that are capable of effectively classifying. Therefore, this article presents a customized PDICNet model for plant leaf diseas...
Article
Breast cancer is now the most prominent female cancer in both developing and developed nations, and that it is the largest risk factor for mortality worldwide. Notwithstanding the well-documented declines in breast cancer mortality during the last twenty years, occurrence rates continue to rise, and do so more rapidly in nations where rates were pr...
Article
Full-text available
Recommender systems (RS) are strong tools for addressing the internet networking overload problems by considering past user ratings on multiple items with auxiliary data and suggests the better item to the end user. Traditional collaborative filtering (CF) and content-based methods were identified the interaction or correlation between users and th...
Article
Full-text available
Identifying and controlling diseases present in plants is very necessary and useful to have healthy growth in plants and to get products of good quality. In this paper, we proposed a novel model to detect whether a plant is diseased or healthy. This model was developed with a deep neural network (DNN) that extracts and evaluates features from plant...
Article
Software-Defined Networking disassociates the control plane from data plane. The problem of deciding upon the number and locations of controllers and assigning switches to them has attracted the attention of researchers. Foreseeing the possibility of failure of a controller, a backup controller has to be maintained for each switch so that the switc...
Article
The recommender system (RS) plays the major role in online networks, online shopping, and online services etc. The conventional RSs are suffering with the inaccurate quality of experience to the users, so the improper content is recommending to customers. The content based collaborative filtering (CBCF) method is introduced to solve the issues pres...
Article
Edge infrastructure and Industry 4.0 required services are offered by edge-servers (ESs) with different computation capabilities to run social application's workload based on a leased-price method. The usage of Social Internet of Things (SIoT) applications increases day-to-day, which makes social platforms very popular and simultaneously requires a...
Article
Clustering techniques are used widely in computer vision and pattern recognition. The clustering techniques are found to be efficient with the feature vector of the input image. So, the present paper uses an approach for evaluating the feature vector by using Hough transformation. With the Hough transformation, the present paper mapped the points t...
Article
Software Defined Networking is an evolving network model wherein the control plane is decoupled from data plane. It has become a fascinating problem to decide the number of controllers and their positions, and to allocate switches to them. Each switch must be assigned to a backup controller so that if a controller encounters failure then the switch...
Article
Full-text available
In recent works of computer science, especially in the fields of image processing and pattern recognition techniques with machine learning, considerable focus is given to plant taxonomy which enhances the abilities of people to recognize plant species. This paper presents a method that analyzes color images of leaves using a type of Convolutional N...
Article
Massive internet of things (IoT) framework deployments increase edge devices usage and dependently increase the generation of data. The traditional elastic asset scheduling approach is phenomenally suitable to a single cloud environment. The prognosticative asset demand is not sufficient. The existing methods are neglecting billing mechanisms to sc...
Article
Cloud infrastructure assets are accessed by all hooked heterogeneous network servers and applications to maintain entail reliability towards global subscribers with high performance and low cost is a tedious challenging task. Most of the extant techniques are considered limited constraints like task deadline, which leads Service Level Agreement (SL...
Article
Full-text available
We propose a rule-based multivariate text feature selection method called Feature Relation Network using chi-square (FR NC) that considers semantic information and also leverages the syntactic relationships between n-gram features. FRN is intended to efficiently enable the inclusion of extended sets of heterogeneous n-gram features for enhanced sen...
Article
Full-text available
As the increase of social networking, people started to share information through different kinds of social media. Among all varieties of social media, Twitter is a valuable resource for data mining because of its prevalence and recognition by famous persons. In this paper we present a system which collects Tweets from social networking sites, we'l...
Article
Full-text available
We propose a rule-based multivariate text feature selection method called Feature Relation Network using chi-square (FRNC) that considers semantic information and also leverages the syntactic relationships between n-gram features. FRN is intended to efficiently enable the inclusion of extended sets of heterogeneous n-gram features for enhanced sent...
Article
Full-text available
A latest tera to zeta era has been created during huge volume of data sets, which keep on collected from different social networks, machine to machine devices, google, yahoo, sensors etc. called as big data. Because day by day double the data storage size, data processing power, data availability and digital world data size in zeta bytes. Apache Ha...
Article
Full-text available
There are many technologies are coming-up day-by-day in the present scenario. One of those advancements is the Big Data collections and applications are vividly used to attain the massive data. Likewise, massive amounts cannot be evaluated on an individual computer within a sensible time. Thus, modern technology-based distributed computing approach...
Article
Full-text available
In general, with a limited training data, semi-supervised classifiers like Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM) are applied on Multispectral or hyper spectral satellite images by using only spectral information. Spatial dependency is another major factor in achieving the correctness of pixel labeling. In this paper, a n...
Article
Full-text available
From the ancient years' data, distributing process has reached many areas of computer science with geographic information system. With the enduring increase of existing data, algorithms and data management are to be moved to a new design, which requires a great deal of effort. In the existing AEGIS Frame work, large image data is distributed over t...
Article
Full-text available
The point of this survey is to feature issues in information quality research and to talk about potential research chance to accomplish high information quality inside an association. The survey received deliberate writing audit technique in view of research articles distributed in diaries and gathering procedures. Here built up an audit technique...
Article
Watermarking emerged as versatile technique of hiding confidential or copy right protect information. The image embedded with watermark is often prone to several security vulnerabilities due to several attacks. It is desired to secure the information in the form of watermark by making it immune to these attacks. Several techniques are prevailing wh...
Article
Full-text available
Due to the dynamic updating of real time spatial databases, the preservation of spatial association rules for dynamic database is a vital issue because the updates may not only invalidate some existing rules but also make other rules relevant. Consequently, the dynamic updating of spatial rules was handled by many researchers through the incrementa...
Conference Paper
Full-text available
Classification of Image is conquering a vital role within the field of computer Science. Classification of Image can be distinct as processing techniques that concern quantitative methods to the values in a technology field or remotely sensed scene to set pixels with one and the same digital number values into attribute classes or categories. To cr...
Article
Full-text available
With the extensive application of spatial databases to various fields ranging from remote sensing to geographical information systems, computer cartography, environmental assessment, and planning, discovery of interesting and hidden knowledge in the spatial databases is a considerable chore for classifying and using the spatial data and knowledge b...
Article
Additive noise is a serious problem as it degrades the quality of the image. It is often required to reconstruct the original image by suppressing noise even before it is processed. This procedure is known as image de-noising. Many de-noising techniques have been proposed in the recent past which are unique in their approach to filtering noise. Wav...
Article
Full-text available
Spatial clustering has been widely applied in various applications, especially in remote sensing technology. Clustering the geographical nature of the remote sensing imagery is challenging due to its wide and dense spatial distribution. Renowned clustering algorithms such as k-means and other probabilistic clustering algorithms have been reported i...
Article
Semantic associations are the complex relationships that exist between two entities in an RDF knowledge base. As the complexity and size of ontologies are increasing rapidly, the numbers of semantic associations are becoming increasingly overwhelming between a pair of entities. Hence, ranking of semantic associations is required in order to present...
Article
Sequential pattern mining is an important task in data mining. Sequential pattern mining algorithms developed so far provide better performance for short sequences but these algorithms are inefficient at mining long sequences. To mine long sequences efficiently closed sequential pattern mining was proposed. Closed sequential pattern mining produces...
Article
Full-text available
An overview of state of art in computerized object recognition techniques regarding digital images is revised. Advantages of shape based techniques are discussed. Importance of "Fourier Descriptor" (FD) for the shape based object representation is described. A survey for the available shape signature assignment methods with Fourier descriptors is p...
Article
Progress in shape based object recognition methods involving either the boundary based or region based methods and their relative popularity is presented. Prevalence of boundary in almost of types and their shapes discriminating features are discussed. Limitations to boundary based methods viz. sensitivity to noise and variations are detailed. The...
Conference Paper
Bioengineering, bioinformatics, and other advanced technologies provide crosscutting tools that facilitate research in many disciplines. This paper gives Analysis of Cancer data taken from Microarray profiles.
Conference Paper
Closed sequential pattern mining is an important data mining task because it produces more compact result set and it is more efficient than sequential pattern mining. In general closed sequential patterns are generated from large data sets by applying algorithms like CloSpan and BIDE which require more execution time to compute all the closed seque...
Conference Paper
Full-text available
Spatial data mining becomes more attractive and significant as more spatial data have been built up in spatial databases. Many GIS applications using spatial patterns those are equal to association rules of a business data mining i.e. On Line Transaction Processing (OLTP). Mining the spatial co-location patterns is a significant spatial data mining...
Article
Full-text available
Data mining is has three major components Clustering or Classification, Association Rules and Sequence Analysis. The clustering techniques analyze a set of data and generate a set of grouping rules that can be used to classify future data. The mining tool automatically identifies the clusters, by studying the pattern in the training data. Once the...
Article
Full-text available
Data mining is has three major components Clustering or Classification, Association Rules and Sequence Analysis. The clustering techniques analyze a set of data and generate a set of grouping rules that can be used to classify future data. The mining tool automatically identifies the clusters, by studying the pattern in the training data. Once the...
Article
Full-text available
Sentiment analysis can be very useful for business if employed correctly. In this article, I will attempt to demystify the process, provide context, and offer some concrete examples of how businesses can utilize it. In this paper we present a system which collects Tweets from social networking sites, we'll be able to do analysis using machine learn...
Article
Full-text available
Collocation is a derivation of several typematic features of spatial objects”. A general mathematical definition can be given to the collocation as just a variable therefore possessing more than one quality that belongs to a spatial object. However, the spatial object is a finite set of features, except that the features change when there is a majo...
Article
Full-text available
The main objective of the research paper is to prove the effectiveness of Analyzing social media data. Twitter is a valuable resource for data mining because of its prevalence and recognition by famous persons. In this paper we present a system which collects Tweets from social networking sites, we'll be able to do analysis using machine learning t...
Chapter
Gene prediction has been an interesting area of research in Bioinformatics. Many of the recent gene identification methods adopt different approaches which are more robust when dealing with uncertainty and ambiguity. In this paper details of Artificial Neural Networks and using them in study and analysis of Biological data are discussed. The types...
Article
Full-text available
Spatial data mining becomes more interesting and important as more spatial data have been accumulated in spatial databases. Spatial patterns are of great importance in many GIS applications that yield equal to association rules of a business i.e. On Line Transaction Processing (OLTP). Mining the spatial co-location patterns is an important spatial...
Article
Full-text available
The internet is rich in directional text (i.e., text containing opinions and emotions). World Wide Web provides volumes of text-based data about consumer preferences, stored in online review websites, web forums, blogs, etc. Sentiment analysis is a technique to classify people's opinions in product reviews, blogs or social networks and has emerged...
Conference Paper
Software project management is the art and science of planning and leading software projects. It is a sub-discipline of project management in which software projects are planned, implemented, monitored and controlled. Software Project managed based on models (Example Waterfall Model, Incremental Build Model, etc,). Software Project contains differe...
Conference Paper
A management Information System (MIS) provides information that is needed to manage organizations efficiently and effectively. Management information systems are not only computer systems-these systems encompass three primary components: technology, people (individuals, groups or clusters, or organizations), and data/information for decision making...
Conference Paper
Full-text available
Information Systems enable us to capture up to date effects due to disaster. It has been widely recognized that spatial data analysis capabilities have not kept up with the need for analyzing the increasingly large volumes of geographic data of various themes that are currently being collected and archived. Our analysis is on disaster management th...
Conference Paper
Full-text available
The goal of data mining is to discover nuggets. Spatial data mining discovers collocation rules. Especially in spatial data mining, when spatial data is relatively represented with time series, a Spatio-Temporal significance is inferred. In this context the collocation rule that is a quintessence for the spatial data, obtains changes to its size an...
Article
Full-text available
In Internet, Multimedia and Image Databases image searching is a necessity. Content-Based Image Retrieval (CBIR) is an approach for image retrieval. With User interaction included in CBIR with Relevance Feedback (RF) techniques, the results are obtained by giving more number of iterative feedbacks for large databases is not an efficient method for...
Article
Full-text available
Semantic based Image retrieval is an emerging research area and is currently the mainstay in variety of applications or domains. In recent times, there exists a lot of gap between the high level semantics and low level features. The process of Features extraction is Application-specific or options are limited. In this paper, we propose a new Modifi...
Article
Full-text available
Information Systems enable us to capture up to date effects due to disaster. It has been widely recognized that spatial data analysis capabilities have not kept up with the need for analyzing the increasingly large volumes of geographic data of various themes that are currently being collected and archived. Our analysis is on disaster management th...
Conference Paper
The internet is rich in directional text (i.e., text containing opinions and emotions). World Wide Web provides volumes of text-based data about consumer preferences, stored in online review websites, web forums, blogs, etc. Sentiment analysis is a technique to classify people's opinions in product reviews, blogs or social networks has emerged as a...
Article
Full-text available
The internet is rich in directional text (i.e., text containing opinions and emotions). World Wide Web provides volumes of text-based data about consumer preferences, stored in online review websites, web forums, blogs, etc. Sentiment analysis is a technique to classify people's opinions in product reviews, blogs or social networks has emerged as a...
Article
Full-text available
Social networking sites are increasing rapidly in this global world where communication plays a major role. There is drastic increase in the usage of social networking sites among all age groups. This can be used for business development, reviews about various social activities and acceptance of any new ideas by means of Sentiment Analysis. Thus fo...
Article
Full-text available
In recent years, we became witnesses of a large number of websites that enable users to contribute, modify, and grade the content. Users have an opportunity to express their personal opinion about specific topics. The examples of such web sites include blogs, forums, product review sites, and social networks. Micro-blogs are a challenging new sourc...
Conference Paper
In this paper, we developed an efficient approach for the automated analysis of microarray images. The proposed approach consists of three steps: pre-processing, gridding and segmentation. Initially, the microarray images are preprocessed by hill climbing algorithm and gridding is applied to accurately identify the location of each spot while extra...
Article
Microarrays are novel and dominant techniques that are beingmade use in the analysis of the expression level of DNA, withpharmacology, medical diagnosis, environmental engineering,and biological sciences being its current applications. Studies onmicroarray have shown that image processing techniques canconsiderably influence the precision of microa...
Conference Paper
Full-text available
WebCrawler is the comprehensive full-text search engine for the WorldWide Web. Its invention and subsequent evolution helped the Web " s growth by creating a new way of navigating hypertext. WebCrawler assists users in their Web navigation by automating the task of link traversal, creating a searchable index of the web and fulfilling searchers " qu...
Article
Microarrays are novel and dominant techniques that are being made use in the analysis of the expression level of DNA, with pharmacology, medical diagnosis, environmental engineering, and biological sciences being its current applications. Studies on microarray have shown that image processing techniques can considerably influence the precision of m...
Article
Full-text available
In this paper, the proposed approach consists of mainly three important steps: preprocessing, gridding and segmentation of micro array images. Initially, the microarray image is preprocessed using filtering and morphological operators and it is given for gridding to fit a grid on the images using hill-climbing algorithm. Subsequently, the segmentat...

Citations

... A DRL technique is employed to formulate service optimization issues by designing an optimal task offloading policy (TOP). A Vehicle-to-Vehicle (V2V) system has been created to enhance the service reliability with the deployment of DRL policies [35,36]. ...
... When it comes to parallel approaches in general, we can mention early contributions focused on the information gain using MapReduce jobs executed on Hadoop clusters [22], the open-source distributed machine learning library MLib [23], other more recent methods and techniques in Apache Spark [24] and Mahout [25]. In addition, it is worth including other new approaches that focus, in particular, on computing Pearson's correlation coefficients, such as ForkJoinPcc [26]. ...
... The authors of [1] proposed an optimization solution for the controller placement problem (CPP) called SA failure foresight capacitated controller placement problem (SA-FFCCPP). The authors of [2] proposed and implemented a greedy heuristic annealing simulation algorithm to solve the CPP. ...
... The performance metrics of accuracy, precision and sensitivity achieved were 98, 93 and 85%, respectively. Moreover, Reddy et al. [48] proposed an optimized CNN model consisting of four convolutional layers, followed by two fully connected layers and a softmax layer. Their suggested CNN model was focused on the color images of leaves. ...
... These features describe each sample in the image in detail, so it has rich spatial and spectral information [2], but it also greatly increases the difficulty of feature selection and mining. Hyperspectral images is widely used in various fields, including marine remote sensing [19], desert vegetation [3, 17, 21], urban area division [31] and other fields [10,13,15]. The recent rapid development of deep learning [7,25] and data analysis [18] has accelerated the classification and recognition efficiency of hyperspectral data, and also improved the classification accuracy. ...
... Two different users can choose different words to describe the image characteristics that results in irrelevant retrieval results. To get rid of all these issues of existing systems content based image retrieval (CBIR) has been developed [2]. In content based method images are searched using visual contents like color, texture, shape and spatial information in the image. ...
... Machine learning is one of the very effective methods by which Big Data can be processed, visualized, and interpreted [17], [18]. In this study, for the execution of our model, we relied on the Spark framework since spark is capable of performing large processing tasks quickly and allows the distribution of tasks over several computers for processing [19]. ...
... It is not an extractive summary or classification of entire documents by simply considering topic-indicative words or phrases. Instead, Sentiment classification involves tasks like generation of semantic feature-set, sentiment words or opinionated word identification corresponding to the features, determination of the semantic polarity orientation of the feature-opinion pairs, and find out overall sentiment by aggregating the mined results [1,2,23]. Second, the association of the extracted sentiment to a specific topic is difficult. ...
... It aims to determine the polarity of the text through sentences that evidently show whether the reaction of the author is positive, negative, or neutral [1]. Many researchers have studied the concept of sentiment analysis and tried to gain accurate results from the classification of texts using different machine learning (ML) techniques [16][17][18][19][20][21][22][23] and pre-trained universal language models [24][25][26][27][28], which has achieved a great deal of success in the English language. However, doing the same for text in Arabic is considered a challenge by researchers because of the diversity in its terminology and grammar, apart from the fact that there is only a small number of available resources and studies analyzing Arabic texts. ...
... Hemalatha et al (Hemalatha, 2012) applied a specially designed algorithm implemented for preprocessing to perform sentiment analysis on tweets. Their proposed preprocessing techniques are to remove URLs, filter repeating characters of words, replace, remove special characters, remove question words, and removal of retweets to improve the accuracy of sentiment analysis. ...