Sudarson Jena

Sudarson Jena

Auto-generated profile, based on publicly available information

Sudarson Jena

Sambalpur University Institute of Information Technology, Sambalpur University, Burla, Odisha, India

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2024 in IEEE Access
Verified
Journal Article
Open access
SDShreemat Kumar Dash
Shreemat Kumar Dash
Prabira Kumar SethyPrabira Kumar Sethy
Prabira Kumar Sethy
ADAshis Das
Ashis Das
SJSudarson Jena
Sudarson Jena
ANAziz Nanthaamornphong
Aziz Nanthaamornphong
This review paper presents a thorough analysis of 99 recent studies focused on applying deep learning techniques for the automated diagnosis of various eye diseases, including glaucoma, diabetic retinopathy, cataracts, amblyopia, and macular degeneration. The advent of deep learning methodologies has revolutionized the field of ophthalmic diagnostics, offering promising solutions for enhancing the accuracy, efficiency, and accessibility of disease detection. The comprehensive examination encompasses diverse deep learning architectures, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hybrid models, along with the exploration of diverse imaging modalities, such as fundus photography, optical coherence tomography (OCT), and visual field testing. Each disease category was scrutinized individually, highlighting the unique challenges and opportunities for automated diagnosis. Key findings and advancements in the field are discussed, shedding light on the potential of deep learning algorithms for early disease detection and timely intervention. This review also addresses existing limitations, including data variability, interpretability, and the need for large, diverse datasets. Insights from this literature synthesis aim to guide future research directions, fostering the continued development of reliable and efficient deep learning-based diagnostic tools for eye diseases.

18 April 2024 in IEEE Access
Verified
Journal Article
Open access
SSSuresh Kumar Srichandan
Suresh Kumar Srichandan
SMSantosh Kumar Majhi
Santosh Kumar Majhi
SJSudarson Jena
Sudarson Jena
KMKaushik Mishra
Kaushik Mishra
RBRadhakrishna Bhat
Radhakrishna Bhat
The fast proliferation of internet-enabled devices generates massive amounts of data every day from every aspect of life. These internet-enabled devices lack the storage, processing power, and capacity necessary to handle and store this massive amount of accurate and volumetric data. Cloud computing has been proposed as a compelling substitute to process these requests. However, the ingress traffic to the Cloud is huge which causes latency overhead due to the gap that exists between end devices and the Cloud datacentre. Additionally, processing these dynamic and heterogeneous requests with disparate requirements is a computationally NP-hard problem. In this regard, Fog computing appears to be an appealing solution to surpass the aforementioned challenges as a complementary to Cloud. Therefore, this research integrated a Fog layer between the end devices and Cloud datacenters enabling a collaborative computation framework. For the classification of requests and determining the target layers for processing, this research suggests an Adaptive Neuro-Fuzzy Inference System (ANFIS). Furthermore, an improved Honey Badger Algorithm (IHBA) is implemented for scheduling those requests at the target layer. To improve the convergence rate of the traditional HBA, a chaos mapping function has been implemented with an Opposition-based Learning (OBL) method. The proposed task consolidation approach has been validated using extensive simulations for QoS parameters on real-world benchmark datasets. With percentage improvements of 13.69%, 28.4%, 33.85%, 7.66%, 26.48%, and 5.63% for makespan, resource utilization, energy consumption, service delay, service cost, and delay violation, respectively, the obtained simulation results show that the suggested algorithm works better than the current state-of-the-art.

27 July 2018 in Evolving Systems
Verified
Journal Article
Closed access
PDF file
NAN. Anupama
N. Anupama
SJSudarson Jena
Sudarson Jena

1 August 2017
Verified
Conference Paper
Closed access
BTBalasaheb Tarle
Balasaheb Tarle
SJSudarson Jena
Sudarson Jena
The ultimate aim of the proposed method is to establish a model for classification of medical data. In this paper we present ANN for Diagnosis of Heart disease. ANN works like the neural arrangement of brain. The mind studies from its past experiences. It can solve the problems that are not computable or solvable by current computing systems. Feature selection is most important process for selecting a relevant attribute among the huge data set. This reduced set of attributes is then passed to artificial neural network. ANN uses back propagation algorithm for better prediction of result, also the ANN is based on the knowledge this advantage can be taken for more accurate result. ANN provides better accuracy. The result given by ANN is highly accurate, so it may be charity in the therapeutic area for likelihood of diseases like swine flu and heart disease.

1 August 2016 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
SCSmita Chormunge
Smita Chormunge
SJSudarson Jena
Sudarson Jena
Feature selection approach solves the dimensionality problem by removing irrelevant and redundant features. Existing Feature selection algorithms take more time to obtain feature subset for high dimensional data. This paper proposes a feature selection algorithm based on Information gain measures for high dimensional data termed as IFSA (Information gain based Feature Selection Algorithm) to produce optimal feature subset in efficient time and improve the computational performance of learning algorithms. IFSA algorithm works in two folds: First apply filter on dataset. Second produce the small feature subset by using information gain measure. Extensive experiments are carried out to compare proposed algorithm and other methods with respect to two different classifiers (Naive bayes and IBK) on microarray and text data sets. The results demonstrate that IFSA not only produces the most select feature subset in efficient time but also improves the classifier performance.

4 July 2025 in IEEE Access
Verified
Journal Article
Open access
ALAtul Vikas Lakra
Atul Vikas Lakra
SJSudarson Jena
Sudarson Jena
KMKaushik Mishra
Kaushik Mishra
Decision trees in machine learning achieved satisfactory performance in classification. Decision trees offer the advantage of handling high-dimensional and complexly correlated data through feature combination and selection. Extreme Gradient Boosting (XGBoost) overcomes the issue of overfitting in decision trees by integrating multiple tree models. Weighted cognitive avoidance particle swarm optimization for the XGBoost (WCAPSO-XGB) model has been proposed for credit score classification. The structure of the XGBoost (XGB) model is determined by the hyperparameters, which must be initialized prior to model evaluation. The optimal hyperparameter values for the XGBoost model can vary significantly depending on the specific problem at hand. Manually setting these hyperparameters can be a time-consuming process. Therefore, to automate this process, weighted cognitive avoidance particle swarm optimization (WCAPSO) is employed for hyperparameter optimization. The novelty of the proposed work includes a modified version of the particle swarm optimizer (PSO), which is used to address the issue of getting trapped into a local optimal solution. The proposed WCAPSO restricts the movement of particles toward local optima and enhances exploration of the search space for better solutions. Here, the hyperparameters of XGBoost are represented as particles in WCAPSO, which defines the state and its movement in a continuous search space. The proposed WCAPSO-XGB model tunes the hyperparameters of XGBoost and classifies the credit scoring, and the experimental results are compared with various classifier such as Random Forest (RF), K-neighbors (KNN), Gaussian Naive Bayes (NB), AdaBoost, Gradient Boosting, Logistic Regression (LR), Neural Network (NN), Decision Tree (DT) and Linear Discriminant Analysis (LDA), and hyperparameter optimization methods, such as Grid Search (GS), Random Search (RS), Bays Optimization, Optuna Optimization, Hybrid Snake Optimizer Algorithm (HSOA), Exploratory Cuckoo Search, island Cuckoo Search (iCSPM and iCSPM2), and Improved SSA (ISSA) with HDPM, on four different datasets with a varying number of instances from small to large. The experimental results and analysis show that the proposed model secures better results in accuracy of 76.75%, 82.43%, 88.98%, and 88.74%; F1-score of 66.52%, 89.44%, 93.53%, and 90.64%; precision of 78.79%, 84.31%, 88.46%, and 90.41%; and recall of 64.07%, 95.24%, 99.21%, and 90.87% in the UCI German, UCI Taiwan dataset, P2P US lending club, and Credit scoring Kaggle dataset, respectively. Further, the overall confidence interval of the proposed model ranges from 82% to 83% in accuracy, 73.1% to 74.2% in F1-score, and 71% to 72% in AUC, with a confidence of 95% measured over 20 evaluations on each dataset.