@woxsen.edu.in
Assistant Professor
woxsen university
Information Systems, Computer Science, Computer Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Amrutashree Hota, S. Gopal Krishna Patro, Sanjaya Kumar Panda, Mohammad Amir Khan, Mohd Abul Hasan, Saiful Islam, Majed Alsubih, Nadeem A. Khan, and Sasan Zahmatkesh
Elsevier BV
Priyavrat Misra, Niranjan Panigrahi, S. Gopal Krishna Patro, Ayodeji Olalekan Salau, and Sinnappampatty S. Aravinth
Springer Science and Business Media LLC
Debabrata Dansana, S Gopal Krishna Patro, Brojo Kishore Mishra, Vivek Prasad, Abdul Razak, and Anteneh Wogasso Wodajo
Wiley
AbstractLoans are a crucial source of income for the financial sector, but they also come with significant financial risks. The interest on loans constitutes a significant portion of a bank's assets. The demand for loans is growing worldwide, and organizations are devising efficient business strategies to attract more clients. Every day, a large number of people apply for loans for various reasons, but not all of them can be approved due to the risk of loan default. It is not uncommon for people to default on their loans, causing significant losses to banks. The purpose of this article is to determine whether to grant loans to specific individuals or organizations. The Random Forest Regressor model has been utilized to measure performance and identify suitable customers for loan approval. The model suggests that banks should not only target affluent clients but also consider other customer characteristics that are critical in credit granting and predicting loan default. The research examines various loan approval parameters such as gender, educational qualification, employment type, business type, loan term, and marital status. Additionally, the study analyzes the number of approved, drawn, and rejected loans, which provides valuable insights into loan approval and prediction.
Debabrata Dansana, Prafulla Kumar Behera, S. Gopal Krishna Patro, Quadri Noorulhasan Naveed, Ayodele Lasisi, and Anteneh Wogasso Wodajo
Institute of Electrical and Electronics Engineers (IEEE)
Cognitive Radio Ad-hoc Networks (CRAHNs) are under constant attacks from compromised primary & secondary nodes. These attacks focus on bandwidth manipulation, internal configuration manipulation, and selective spoofing, which can disturb the normal working of the CRAHNs. Researchers propose various security models to mitigate these attacks, each with limitations. Most of these models have higher complexity, while others cannot be used to mitigate multiple attack types. To overcome these issues while maintaining higher security and Quality of Service (QoS) under attacks, this text proposes a design of a novel blockchain-based security model for improving attack resilience in CRAHNs. The model initially collects multiple information sets from different cognitive radio controllers and creates active & redundant miners for the storage of these sets. The number of active & redundant miners is decided via a Mayfly Optimizer (MO) Model, which assists in improving resource utilization while reducing deployment costs. Cognitive rules and configurations are stored on these nodes and updated via a secure blockchain verification. Due to this, the proposed model demonstrated significant improvements in cognitive radio communications across various metrics, even under different attack scenarios. It reduced communication delay by up to 18.5%, increased communication throughput by up to 19.5%, and improved the Packet Delivery Ratio (PDR) by up to 19.4% when compared with existing models such as SRC, Prob Less, and DDQL. Additionally, the model achieved energy savings of up to 12.5%. These enhancements were made possible by the optimized selection of miner nodes, enabling quicker mining for high-speed communication, low-energy mining tasks for prolonged use, and high-performance mining for consistency. The results affirm the model’s suitability for various real-time cognitive radio scenarios. Due to the integration of the MO Model, the CRAHN showcases better communication speed, lower energy consumption, higher throughput, and higher packet delivery performance when compared with existing methods under real-time scenarios.
K. Sunil Kumar, Raviteja Surakasi, S Gopal Krishna Patro, Nikhil Govil, M.K. Ramis, Abdul Razak, Prabhakar Sharma, Majed Alsubih, Saiful Islam, T.M.Yunus Khan,et al.
Elsevier BV
Vivek Kumar Prasad, Debabrata Dansana, S Gopal Krishna Patro, Ayodeji Olalekan Salau, Divyang Yadav, and Madhuri Bhavsar
Springer Science and Business Media LLC
AbstractDue to the huge impact of COVID-19, the world is currently facing a medical emergency and shortage of vaccine. Many countries do not have enough medical equipment and infrastructure to tackle this challenge. Due to the lack of a central administration to guide the countries to take the necessary precautions, they do not proactively identify the cases in advance. This has caused Covid-19 cases to be on the increase, with the number of cases increasing at a geometric progression. Rapid testing, RT-PCR testing, and a CT-Scan/X-Ray of the chest are the primary procedures in identifying the covid-19 disease. Proper immunization is delivered on a priority basis based on the instances discovered in order to preserve human lives. In this research paper, we suggest a technique for identifying covid-19 positive cases and determine the most affected locations of covid-19 cases for vaccine distribution in order to limit the disease's impact. To handle the aforementioned issues, we propose a cloud based image analysis approach for using a COVID-19 vaccination distribution (CIA-CVD) model. The model uses a deep learning, machine learning, digital image processing and cloud solution to deal with the increasing cases of COVID-19 and its priority wise distribution of the vaccination. Graphical Abstract
Papabathina Mastan Rao, Sneha Haresh Dhoria, S Gopal Krishna Patro, Radha Krishna Gopidesi, Meshel Q. Alkahtani, Saiful Islam, Murkonda Vijaya, Juturi Lakshmi Jayanthi, Mohammad Amir Khan, Abdul Razak,et al.
Elsevier BV
Niranjan Panigrahi, S. Gopal Krishna Patro, Raghvendra Kumar, Michael Omar, Tran Thi Ngan, Nguyen Long Giang, Bui Thi Thu, and Nguyen Truong Thang
Springer Science and Business Media LLC
Prabhakar Yadlapalli, Leela Rajani Myla, Naga Venkata Sai Deekshitha Sandaka, and S. Gopal Krishna Patro
IGI Global
Systems for course arranging help city sightseers and suburbanites in settling on the best course between two irregular focuses. Nonetheless, while prompting multi-modular courses, present day organizer calculations frequently don't consider client inclinations or the aggregate insight. Multimodal courses can be suggested in light of the assessments of purchasers with comparative preferences as per a method called cooperative separating (CF). In this chapter, the authors present a component—a portable recommender system for redid, multimodal courses—that consolidates CF with information-based ideas to improve the nature of course proposals. They give a full clarification of the crossover strategy and show the way things are integrated into a functioning model. The consequences of a client concentrated on show that the model, which joins CF, information-based, and well-known course suggestions, outflanks cutting-edge course organizers.
Abhishek Kumar Sinha, S Gopal Krishna Patro, and Amrutashree Hota
IGI Global
The recommendation system works on an idea of suggesting or recommending items, products, books, movies, etc. by analyzing and using some filtering to find the user's interest. To maximize the growth of business and profit gain, users need to be recommended with products belonging to their area of interest. To fulfill this requirement, the recommendation system has been implemented. In this study, the discussion is over recommendation system and how different concepts come to work out individually as well as together for recommendation. In this analysis, the focus is on recommending the method of e-commerce. In that scenario, “cold start problem” comes into consideration. Cold start problems are also studied, and a purposed idea has also been highlighted to reduce cold start problem to some extent. ‘LCW Aspect' is going to execute and analyze user's culture, weather, local scarcity, and focused on solving recommendation problems for new emerging users.
Amrutashree Hota, S Gopal Krishna Patro, Ahmed J. Obaid, Satish Khatak, and Raghvendra Kumar
Elsevier BV
S. Gopal Krishna Patro, Brojo Kishore Mishra, Sanjaya Kumar Panda, Raghvendra Kumar, Hoang Viet Long, and David Taniar
Springer Science and Business Media LLC
Arabinda Dash, Prabira Kumar Sethy, S Gopal Krishna Patro, and Ayodeji Olalekan Salau
Elsevier BV
Bosubabu Sambana, Yagireddi Ramesh, Satyabrata Patro, N. P. Patnaik M, P. J. V. Prakasa Rao, Adimalla Rama Rao, and Priyanka Mishra
Springer International Publishing
B. S. Panda, Satyabrata Patro, and Jyotirmaya Mishra
Springer International Publishing
S. Gopal Krishna Patro, Brojo Kishore Mishra, and Sanjaya Kumar Panda
CRC Press
S. Gopal Krishna Patro, Brojo Kishore Mishra, Sanjaya Kumar Panda, Amrutashree Hota, Raghvendra Kumar, Shiyang Lyu, and David Taniar
Institute of Electrical and Electronics Engineers (IEEE)
When a new customer enters the spectrum of the E-Commerce system, the informative records and dataset, such as about the new user, purchasing history and other browsing data become insufficient, resulting in the emergence of one serious issue such as a Cold start problem (CSP). Furthermore, when the interaction among the product items becomes limited, a new problem such as Sparsity arises to handle such problems in E-Commerce system, we have designed an extensive and hybridized methodological approach known as Cold start and sparsity aware hybridized recommendation system (CSSHRS), to reduce the Sparsity of dataset as well as to overcome the cold start problem in the recommendation framework. The proposed CSSHRS technique has been predicted by using the dataset of Last. FM, and Book-Crossing resulted in Mean absolute percentage error (MAPE) of 37%, recalls 0.07, precision 0.18, Normalized Discounted Cumulative Gain (NDCD) 0.61, and F-measure 0.1. This article proves the proposed CSSHRS technique as an effective and efficient hybrid of RS against the issue of data sparsity as well as CSP.
Satyabrata Patro, B. Vasantha Lakshmi, V. Sailaja, V. Sailaja, Bhavani Sankar Panda, and Devvret Verma
IEEE
Breast cancer is one of the most prevalent diseases that claims the lives of thousands of women every year. Artificial intelligence has been used to identify breast cancer early, fast, and correctly (AI). The objective of this essay is to assess current classification work on these tumours. Using machine learning techniques like Support Vector Machine (SVM), K Nearest Neighbor (K-NN), and Random Forest, medical pictures are divided into benign and malignant categories (RF). Convolutional Neural Network C Nearest Neighbor (CNN) is one of the deep learning techniques recently employed for comparable purposes. Due to its high mortality and morbidity rates, breast cancer presents a particular concern to female patients. Therefore, it is essential to have an algorithm that can recognise the early symptoms of breast cancer. In order to predict breast cancer, the results were assessed using the four techniques: Convolutional Neural Network, Decision Trees, Logistic Regression and random forests is essential for identifying the early signs of breast cancer. Three distinct classification ML techniques will be employed in this investigation. The effectiveness and accuracy of each algorithm will next be assessed. For classification systems, data with unbalanced classes constitute a substantial problem, requiring careful management and pre-processing. Using a dataset of breast cancer patients, we'll train a variety of machine learning models. The best solution for this issue is finally found by evaluating the accuracy and performance of each algorithm. In order to choose the most effective course of action, this research will display the effectiveness of multiple ways for categorising breast cancer.
Chandrakanta Mahanty, Raghvendra Kumar, and S. Gopal Krishna Patro
Springer Science and Business Media LLC
S. Gopal Krishna Patro, Brojo Kishore Mishra, Sanjaya Kumar Panda, and Raghvendra Kumar
Springer Nature Singapore
S Gopal Krishna Patro, Brojo Kishore Mishra, Sanjaya Kumar Panda, and Amrutashree Hota
The Electrochemical Society
The users of electronic commerce (e-commerce), otherwise known as internet commerce portals, most commonly depend upon the customer reviews when they make any purchase decisions. But it is observed that one product may have more than hundreds of miscellaneous reviews, which leads to an overload of information on the customer. This information overload tends one to work on the objective of developing a recommender mechanism to recommend a review subset having high content score as well as various aspects of products with associated sentiments. Therefore, these recommendation systems (RSs) have been established parallel to web networks. This contribution delivers an orderly explanation for hybrid RS along with a novel method with slight modification of the contemporary techniques, such as collaborative filtering. It also describes their evolution, progression, and fruitfulness and also identifies various future implementation areas selected for future, present, and past importance.
S Gopal Krishna Patro, Brojo Kishore Mishra, Sanjaya Kumar Panda, Raghvendra Kumar, and Atithee Apoorva
IEEE
Electronic commerce, widely known as e-commerce, has been a very promising sector for buying and selling products over the Internet. Primarily, this is of wide-ranging importance due to the huge involvement of all sorts of transactions. Use of recommendation systems (RSs) in aid of e-commerce will not only increase the profit, but also render in the conversion of browsers to buyers and enhance the loyalty of a user. In this paper, we discuss various hybrid social RSs that make use of several social factors. In addition, we use Thomas-Kilmann conflict mode instrument (TKI) test and analytic hierarchy process (AHP) to show their efficiency in the RSs. There is always a quest to involve maximum social information to enhance the recommendations about a given product. Therefore, this paper inculcates maximum social factors, namely the distance between the individuals, similarity in the recommendations made, trust and relationships to improve the accuracy of the recommendations. We discuss a proposal on a hybrid social RS, which uses TKI test and AHP. It is observed that there is a huge involvement of intimacy and intensity with respect to trust and relationship in order to make the recommendations.
Sunkuru Gopal Krishna Patro, Brojo Kishore Mishra, Sanjaya Kumar Panda, Raghvendra Kumar, Hoang Viet Long, and Tran Manh Tuan
IOS Press
A recommender system (RS) delivers personalized suggestions on products based on the interest of a particular user. Content-based filtering (CBF) and collaborative filtering (CF) schemes have been previously used for this task. However, the main challenge in RS is cold start problem (CSP). This originates once a new user joins the system which makes the recommendation task tedious due to the shortage of information (clickstream, dwell time, rating, etc.) regarding the user’s interest. Therefore, CBF and CF are combined together by developing a knowledge-based preference learning (KBPL) system. This system considers the demographic data that includes gender, occupation, and age for the recommendation task. Initially, the dataset is clustered using the self-organizing map (SOM) technique, then the high dimensional data is decomposed by higher-order singular value decomposition (HOSVD) and finally, Adaptive neuro-fuzzy inference system (ANFIS) predicts the output. For the big dataset, SOM is a robust clustering method and the similarities among the users can be easily observed by grid clustering. The HOSVD extracts the required information from the available data set to find the user similarity by decomposing the dataset in lower dimensions. ANFIS uses IF-THEN rules to recommend similar product to the new users. The proposed KBPL system is evaluated with the Black Friday dataset and the obtained error value is compared with the existing CF and CBF techniques. The proposed KBPL system has obtained root mean squared error (RMSE) of 0.71%, mean absolute error (MAE) of 0.54%, and mean absolute percentage error (MAPE) of 37%. Overall, the outcome of the comparative analysis shows minimum error and better performance in terms of precision, recall, and f-measure for the proposed KBPL system compared to the existing techniques and therefore more suitable for accurately recommending the products for the new users.