D. P. Acharjya

Bio: D. P. Acharjya is an academic researcher from VIT University. The author has contributed to research in topics: Rough set & Information system. The author has an hindex of 14, co-authored 42 publications receiving 492 citations.

Crop suitability prediction in Vellore District using rough set on fuzzy approximation space and neural network

Abstract: In Indian economy, agriculture is the prime vocation that avails in the overall development of the country. Tamil Nadu occupies approximately 7% of the nation's population, with 3% of water resources and 4% of land resources at the country level. The crop suitability prediction is of prime importance to enhance the nutritional security to the developing country. Based on several crops grown in a particular place, and the availability of natural resources, one can identify the suitability of crops that can be grown in a particular place. To this end, many mathematical tools were developed, but they failed to include processing of uncertainties present in the accumulated data. Therefore, in this paper an effort has been made to process the uncertainties by hybridizing rough set on fuzzy approximation space and neural network. The rough set on fuzzy approximation space identifies the almost indiscernibility among the natural resources and helps in minimizing the computational procedure on employing data reduction techniques, whereas neural network helps in prediction process. The proposed model is analysed on agriculture data of Vellore District of Tamil Nadu, India, and achieved 93% of classification accuracy in validation. The model is compared with an earlier model and achieved 8% more accuracy while predicting unseen associations.

A Hybrid Scheme for Heart Disease Diagnosis Using Rough Set and Cuckoo Search Technique

Abstract: Large volumes of raw data are created from the digital world every day. Acquiring useful information from these data is challenging, and it turned into a prime zone of momentum explore. More research is done in this direction. Further, in disease diagnosis, many uncertainties are involved in the information system. To handle such uncertainties, intelligent techniques are employed. In this paper, we present an integrated scheme for heart disease diagnosis. The proposed model integrates cuckoo search and rough set for inferencing decision rules. At the underlying phase, we employ a cuckoo search to discover the main features. Further, these main features are analyzed using rough set generating rules. An empirical analysis is carried out on heart disease. Besides, a comparative study is also presented. The comparative study demonstrates the feasibility of the proposed model.

Breast Cancer Detection using Intuitionistic Fuzzy Histogram Hyperbolization and Possibilitic Fuzzy c-mean Clustering algorithms with texture feature based Classification on Mammography Images

Abstract: During past 20 years, it is stated that cancer belongings are mounting all-inclusive. Amid innumerable natures of cancers, breast cancer is witnessed as key reason of demise among women. Ultrasound, x-ray (mammograms and x-ray computed tomography), magnetic resonance imaging, thermography and nuclear medicine functional imaging are different modalities offered for early stage breast cancer detection. Mammography technology is a unadventurous breast cancer practice that can perceive tumorous masses on lower cost and better truthfulness. This paper designates the digital execution of a model, based on an intuitionistic fuzzy histogram hyperbolization and possibilitic fuzzy c-mean clustering algorithm for early breast cancer detection. Clustering plays a key role in segmentation fragment. Classical fuzzy clustering assigns data to multiple clusters at different degrees of membership but irrelevant data are also allocated to some clusters that do not relate to them. In our newfangled work we bound possibilistic method with fuzzy c-mean to resolve this issue after applying intuitionistic fuzzy histogram hyperbolization algorithm in initial preprocessing phase in the mammogram images. Further texture feature extraction technique is used for extracting features. Developed rules was applied in classifier to detect about the presence of cancerous tumor in mammogram images. The inclusive classification accuracy achieved 94% during training stage.

Algebraic Properties of Rough Set on Two Universal Sets based on Multigranulation

Abstract: The rough set philosophy is based on the concept that there is some information associated with each object of the universe. The set of all objects of the universe under consideration for particular discussion is considered as a universal set. So, there is a need to classify objects of the universe based on the indiscernibility relation (equivalence relation) among them. In the view of granular computing, rough set model is researched by single granulation. The granulation in general is carried out based on the equivalence relation defined over a universal set. It has been extended to multi-granular rough set model in which the set approximations are defined by using multiple equivalence relations on the universe simultaneously. But, in many real life scenarios, an information system establishes the relation with different universes. This gave the extension of multi-granulation rough set on single universal set to multi-granulation rough set on two universal sets. In this paper, we define multi-granulation rough set for two universal sets U and V. We study the algebraic properties that are interesting in the theory of multi-granular rough sets. This helps in describing and solving real life problems more accurately.

A decision making model using soft set and rough set on fuzzy approximation spaces

Abstract: In modern era of computing, there is a need of development in data analysis and decision making. Most of our tools are crisp, deterministic and precise in character. But general real life situations contains uncertainties. To handle such uncertainties many theories are developed such as fuzzy set, rough set, rough set on fuzzy approximation spaces etc. But all these theories have their own limitations. To overcome the limitations, the concept of soft set is introduced. But, soft set also fails if the attributes in the information system are almost identical rather exactly identical. In this paper, we propose a decision making model that consists of two processes such as preprocess and postprocess to mine decisions. In preprocess we use rough set on fuzzy approximation spaces to get the almost equivalence classes whereas in postprocess we use soft set techniques to obtain decisions. The proposed model is tested over an institutional dataset and the results show practical viability of the proposed research.

A review on genetic algorithm: past, present, and future

Abstract: In this paper, the analysis of recent advances in genetic algorithms is discussed. The genetic algorithms of great interest in research community are selected for analysis. This review will help the new and demanding researchers to provide the wider vision of genetic algorithms. The well-known algorithms and their implementation are presented with their pros and cons. The genetic operators and their usages are discussed with the aim of facilitating new researchers. The different research domains involved in genetic algorithms are covered. The future research directions in the area of genetic operators, fitness function and hybrid algorithms are discussed. This structured review will be helpful for research and graduate teaching.

A Novel PCA-Firefly Based XGBoost Classification Model for Intrusion Detection in Networks Using GPU

Abstract: The enormous popularity of the internet across all spheres of human life has introduced various risks of malicious attacks in the network. The activities performed over the network could be effortlessly proliferated, which has led to the emergence of intrusion detection systems. The patterns of the attacks are also dynamic, which necessitates efficient classification and prediction of cyber attacks. In this paper we propose a hybrid principal component analysis (PCA)-firefly based machine learning model to classify intrusion detection system (IDS) datasets. The dataset used in the study is collected from Kaggle. The model first performs One-Hot encoding for the transformation of the IDS datasets. The hybrid PCA-firefly algorithm is then used for dimensionality reduction. The XGBoost algorithm is implemented on the reduced dataset for classification. A comprehensive evaluation of the model is conducted with the state of the art machine learning approaches to justify the superiority of our proposed approach. The experimental results confirm the fact that the proposed model performs better than the existing machine learning models.

A survey of decision making methods based on certain hybrid soft set models

Abstract: Fuzzy set theory, rough set theory and soft set theory are all generic mathematical tools for dealing with uncertainties. There has been some progress concerning practical applications of these theories, especially, the use of these theories in decision making problems. In the present article, we review some decision making methods based on (fuzzy) soft sets, rough soft sets and soft rough sets. In particular, we provide several novel algorithms in decision making problems by combining these kinds of hybrid models. It may be served as a foundation for developing more complicated soft set models in decision making.

A Survey on Big Data Analytics: Challenges, Open Research Issues and Tools

Abstract: A huge repository of terabytes of data is generated each day from modern information systems and digital technolo-gies such as Internet of Things and cloud computing. Analysis of these massive data requires a lot of efforts at multiple levels to extract knowledge for decision making. Therefore, big data analysis is a current area of research and development. The basic objective of this paper is to explore the potential impact of big data challenges, open research issues, and various tools associated with it. As a result, this article provides a platform to explore big data at numerous stages. Additionally, it opens a new horizon for researchers to develop the solution, based on the challenges and open research issues.