Enhanced thermal conductivity and phase change performance of paraffin-based materials using nanostructured additives for thermal energy storage applications Hayder M. Ali, Sudhakar Sengan, Anusha Papasani, Aseel Smerat, Muzaffar Shojonov, et al. Clean Energy Science and Technology, 2026 Phase-change materials (PCMs) provide high-density Solar Thermal Energy Storage (STES) for solar applications but suffer from low thermal conductivity, excessive subcooling, and cycling degradation. This study systematically compares five nanostructure classes—graphene nanoplatelets (GNP), multi-walled carbon nanotubes (MWCNT), metallic nanoparticles (Cu, Ag), and metal oxides (Al₂O₃, TiO₂)—incorporated into paraffin and sodium nitrate PCMs to address these limitations. Nanostructures were characterized using XRD, FTIR, BET, SEM, and TEM to establish morphology-performance relationships. BET surface area (320.5 m2/g for GNPs, 265.4 m2/g for MWCNTs) correlated strongly with thermal conductivity enhancement (R2 = 0.87, p < 0.001), confirming that high-aspect-ratio structures enable percolation network formation. At 3 wt% loading—identified as the optimal concentration through percolation analysis—carbon-based composites achieved 150% (GNPs) and 131% (MWCNTs) conductivity gains at 25 ℃. DSC analysis revealed 60% subcooling suppression with GNPs, reducing crystallization lag from 5.5 ℃ to 2.2 ℃ through heterogeneous nucleation. Charging-discharging experiments verified 30–34% reductions in thermal response time, with temperature uniformity improving by 67%. Statistical analysis using one-way ANOVA with Tukey's HSD test (p < 0.05) confirmed significant performance hierarchies: carbon-based > metallic > metal oxides across all metrics. Extended cycling tests (1000 melt-freeze cycles) validated superior durability, with carbon-enhanced paraffin and oxide-enhanced sodium nitrate retaining >93% of their latent heat capacity, compared with <83% for pristine PCMs. Post-cycling analysis confirmed the maintenance of nanoparticle dispersion and chemical stability. Comparison with recent literature validates that this work advances the field by systematic multi-additive evaluation, extended durability validation (2–3 times longer than typical studies), and dual-PCM coverage spanning 50–350 ℃. The quantified conductivity-loading relationships, percolation thresholds, and 1000-cycle performance data provide engineering guidelines for STES across residential to industrial temperature ranges.
A Comprehensive Survey on Models, Architectures, and Performance Metrics for Medicinal Plant Classification Using Machine Learning and Deep Learning Approaches Abdul Nabi Shaik, Pallavi Malavath, Poluru Eswaraiah, Anusha Papasani, Klodian Dhoska International Journal of Advancement in Life Sciences Research, 2026 The exponential growth in multidisciplinary research on medicinal plants has led to a diverse landscape of techniques spanning phytochemical screening, molecular characterization, image-based classification, and machine learning (ML) applications. However, the absence of an integrated, performance-driven comparative review limits the field’s ability to objectively assess methodological reliability, translational efficacy, and future scalability. This study presents a comprehensive review of 80 peer-reviewed papers, systematically evaluating them across eight performance metrics: accuracy, precision, recall, F1-score, IC₅₀, inhibition zone diameter, AUC, and RMSE. Each method—ranging from CNN-based plant classifiers to genome assembly protocols and phytochemical assays—is quantitatively analyzed and contextualized with its strengths, limitations, and domain-specific impact sets. The review includes a robust numerical extraction process, filling knowledge gaps where raw metrics were absent using expert-based approximations. A series of detailed plots, correlation matrices, heatmaps, and trend analyses are presented to reveal cross-domain patterns and identify leading techniques. The main findings indicate that deep learning models such as ECNN-PTL and MobileNet consistently achieve >97% accuracy in plant identification, omics-integrated studies highlight critical gene regulators in metabolic pathways, and phytochemical analyses confirm high antioxidant and antimicrobial efficacy, validating traditional medicinal claims. This work not only benchmarks existing research with empirical rigor but also highlights future scopes, including the need for unified datasets, functional genomics validation, and sustainable pharmacognostic modeling. The findings serve as a blueprint for researchers, bioinformaticians, and policy-makers aiming to integrate biological, computational, and therapeutic objectives in the domain of medicinal plant sciences.
Weight Optimized Genetic Algorithm Driven Machine Learning Models for Robust Digital Video Watermarking Methods Ali Mahmoud Ali, Rajkumar N, Saravanan R, Anusha Papasani, Saravanan G, et al. Journal of Machine and Computing, 2025 Video piracy is increasing due to the standard implementation of online streaming services and storage solutions, posing significant concerns about the security of multimedia content and Intellectual Property Rights (IPR). Digital Watermarking (DW) is a revolutionary technology that enables multimedia IPR by hiding and securing intellectual property from cyberattacks. DW is now recognized as the primary point of study for data verification and IPR security measures. Watermarks are hidden tags used to detect IPR crimes and authenticate data reliability. The Least Significant Bit (LSB) to DVW is proposed to enhance data source verification, thereby increasing the possibility of reducing Mean Square Error (MSE). A Genetic Algorithm (GA) is employed to mitigate the adverse effects of LSB while enhancing the Peak Signal-to-Noise Ratio (PSNR), a crucial metric of watermarking quality. This research work employs statistical methods and experiments to analyze the difficulty of computation, accuracy, resource utilization, speed, and endurance as metrics for performance. With PSNRs exceeding 45.19 dB, the method demonstrates robustness against background noise, filtering, and video encoding. With empirical findings from experiments demonstrating a 75% Normalized Cross-Correlation (NCC), 97.89% training accuracy, and 96.78% validation accuracy, the proposed method outperforms hiding and security methods in terms of accuracy.
Securing Voice Software Applications Using 5G, WSN and AI Driven Privacy Preservation Protocols Hayder M A Ghanimi, Swaroopa K, Amit Mishra, Anusha Papasani, Kolluru Suresh Babu, et al. Journal of Machine and Computing, 2025 The reality-based, dynamic, and context-aware user experiences provided by voice software applications have contributed to their common acceptance. But, problems with data privacy and computer performance are challenges. In order to process voice data reliably, the present research proposes a secure integrated model of 5G-Wireless Sensor Networks with Artificial Intelligence (5G + WSN + AI) to apply privacy preservation protocols. To train decentralized models, the model used Federated Learning (FL). To prevent unauthorized inference, it deployed Secure Multi-Party Computation (SMPC). In the end, to secure sensitive data, it applied adaptive encryption methods. Word Error Rate (WER), Feature Extraction Accuracy (FEA), End-to-End Delay (EED), Network Throughput (NT), Packet Loss Rate (PLR), and Encryption Overhead (EO) represent several of the key performance measures that the model is considered superior to conventional networks such as SVPS, BDPS, GACS, and cloud-based centralized models. Additionally, it proved that next-generation Voice Learning Systems (VLS) are reliable, leveraging AI + 5G setup and maintaining robustness against privacy breaches in real-world asymmetric scenarios.
Hybrid optimized multi-objective honey badger algorithm and NSGA-II for feature selection problems Anusha Papasani, Nagaraju Devarakonda Indonesian Journal of Electrical Engineering and Computer Science, 2024 One of the most important aspects of classification is choosing features in such a way as to get rid of redundant or irrelevant elements in the dataset. For the most part, multi-objective feature selection strategies have been offered by a number of scholars as a strategy for this aim. On the other hand, these techniques frequently fail to simultaneously improve classification accuracy while removing redundant feature combinations. This article presents a wrapper-based feature selection strategy that strikes a compromise between classification accuracy and redundancy reduction by combining features of the multi objective (MO) based honey badger algorithm (MO-HBA) and non-dominated sorting genetic algorithm-II (NSGA-II). The technique was developed as part of this investigation. Increasing the accuracy of the classification while simultaneously reducing the number of redundant characteristics is one of the optimizations aims of this approach. The MO-HBA shows excellent performance in exploration and exploitation. A Kernel version of the extreme learning machine (KELM) is used for the process of selecting the features to use. In order to evaluate how well this method of feature selection performs, eighteen benchmark datasets are utilized, and the results are compared to four established methods of multi-objective feature selection based on different metrics.
Machine Learning for Genomic Expression Classification-Based Phenotype Prediction in Topological Data Analysis Narender M, Karrar S. Mohsin, Ragunthar T, Anusha Papasani, Firas Tayseer Ayasrah, et al. Journal of Machine and Computing, 2024 Genomic data has become more prevalent due to sequencing and Machine Learning (ML) innovations, which have increased the biological genomics study. The multidimensional nature of this data provides challenges to phenotype prediction, which is required for individualized health care and the research investigation of genetic problems; nevertheless, it holds tremendous potential for understanding the association between genes and physical features. The authors of this paper introduce a new technique for symptom prediction from data from genomes, which combines Topological Data Analysis (TDA), Graph Convolutional Networks (GCN), and Support Vector Machines (SVM). The proposed method aims to address these challenges. By using TDA for multifaceted feature extraction, GCN to analyze gene interaction networks, and SVM for reliable classification in high-dimensional spaces, the above technique overcomes the drawbacks of conventional approaches. This TDA-GCN-SVM model has been demonstrated to be implemented in a method that is superior to conventional methods on distinct tumor datasets in terms of accuracy and additional measures. A novel method for genomic study and a more significant comprehension of genomic data analysis are both caused by this innovation, which is an enormous achievement in precision healthcare.
Adaptive Neighborhood Adjustment Strategy Based On MOHHO and NSGA-III Algorithms for Feature Selection Iaeng International Journal of Applied Mathematics, 2024
A Novel Feature Selection Algorithm Using Multi-Objective Improved Honey Badger Algorithm and Strength Pareto Evolutionary Algorithm-II Anusha Papasani, Nagaraju Devarakonda, and Journal of Engineering Research Kuwait, 2023 An important task for classification is feature selection that removes the redundant or irrelevant features from the dataset. Multi-objective feature selection approach is mainly proposed by many researchers. However, these approaches failed to maintain the higher classification accuracy while removing redundancy in the features. In this work, a wrapper based feature selection technique is proposed with a hybrid of Multi Objective Honey Badger Algorithm (MO-HBA) and Strength Pareto Evolutionary Algorithm-II to maintain the balance between classification accuracy and removal of redundancy. Classification accuracy improvement and removal of redundant features are considered as the multi-objective optimization functions of the proposed multi-objective feature selection technique. The Levy flight algorithm is utilized to initialize the population to enhance the ability of the exploration and exploitation of MO-HBA. The regularized Extreme Learning Machine is used to classify the selected features. To evaluate the performance of the proposed feature selection technique, eighteen benchmark datasets are utilized and results are compared with the four well known multi-objective feature selection techniques in terms of accuracy, hamming loss, ranking loss, mean value, standard deviation, length of features, and training time. The proposed approach achieved maximum accuracy of 100% with the maximum value of selected features as 80. The minimum value of hamming loss, ranking loss, mean value and standard deviation value achieved by the proposed approach are 0.0092, 0.0003, 0.018 and 0.001 respectively. The experimental results show that the proposed approach can give improved classification accuracy while the removal of redundancy in large scale datasets.
Identifying Rotten Region on the Plant Leaf in Advance to Increase the Crop Yield using Multinominal Probit Regression Anveshini Dumala, Anusha Papasani, Rajeswari Bommala, Vikkurty Sireesha Proceedings International Conference on Applied Artificial Intelligence and Computing Icaaic 2022, 2022 Detection of plant disease at an early stage increases the crop yield otherwise these diseases may negatively impact the agro market economy. The conventional methods were time consuming and practically infeasible to cover thousands acres of farming areas to detect leaf diseases. A methodology is proposed in this paper, to spot and to analyze the plant leaf diseases using digital image processing techniques through a supervised machine learning technique called multi-support vector machine (m-SVM) algorithm. SVM handles both semi structured and unstructured data. The proposed model recognizes and classifies the images of the leaves that were captured by digital camera or a mobile phone or drones or web camera. A novel way of training and methodology was used to accelerate the speedy, easy and simple implementation of the system in real-time. The experimental outcomes make evident that the proposed system detects and classifies the major 6 plant leaves diseases successfully: Cercospora leaf spot, Alternaria Alternata, Rust, Anthracnose, Powdery Mildew and Bacterial Blight. Also some of the unanswered challenges are discussed that require to be answered by developing a sensible automatic plant disease recognition system to apply in field conditions.
Weight-Optimized Genetic Algorithm-Driven Machine Learning Models for Robust Digital Video Watermarking Methods AM Ali, N Rajkumar, R Saravanan, A Papasani, G Saravanan, KS Latha 2025
Securing Voice Software Applications Using 5G WSN and AI Driven Privacy Preservation Protocols HMA Ghanimi, K Swaroopa, A Mishra, A Papasani, KS Babu, ... J. Mach. Comput 5 (3), 1803-1822 , 2025 2025 Citations: 1
Hybrid optimized multi-objective honey badger algorithm and NSGA-II for feature selection problems A Papasani, N Devarakonda Indonesian Journal of Electrical Engineering and Computer Science 36 (1 … , 2024 2024 Citations: 2
Adaptive Neighborhood Adjustment Strategy Based On MOHHO and NSGA-III Algorithms for Feature Selection. A Papasani, R Durgam, N Devarakonda IAENG International Journal of Applied Mathematics 54 (5) , 2024 2024 Citations: 5
A novel feature selection algorithm using multi-objective improved honey badger algorithm and strength pareto evolutionary algorithm-II A Papasani, N Devarakonda Journal of Engineering Research 11 (2), 71-83 , 2023 2023 Citations: 10
A Quick Dynamic Attribute Subset Method for High Dimensional Data Using Correlation-Guided Cluster Analysis and Genetic Algorithm N Bhagya Lakshmi, N Devarakonda, Z Polkowski, A Papasani Innovations in Computational Intelligence and Computer Vision: Proceedings … , 2022 2022
Identifying Rotten Region on the Plant Leaf in Advance to Increase the Crop Yield using Multinominal Probit Regression A Dumala, A Papasani, R Bommala, V Sireesha 2022 International Conference on Applied Artificial Intelligence and … , 2022 2022 Citations: 2
Feature Selection Using PSO Optimized-Framework with Machine Learning Classification System via Breast Cancer Survival Data A Papasani, N Devarakonda, Z Polkowski, M Thotakura, ... Computational Vision and Bio-Inspired Computing: Proceedings of ICCVBIC 2021 … , 2022 2022 Citations: 4
A Novel Feature Selection Algorithm Using Decomposition Based Multi-Objective Guided Honey Badger Algorithm (MO-GHBA) And NSGA-III A Papasani, N Devarakonda Kuwait Journal of Science , 2022 2022 Citations: 10
Retracted: Parkinson’s Neurodegenerative Disease Prediction with Robust Methods Of Machine Learning A Papasani, N Devarakonda, Z Polkowski 2021 Fourth International Conference on Electrical, Computer and … , 2021 2021 Citations: 1
COVID-19 face mask live detection using OpenCV A Dumala, A Papasani, S Vikkurty Smart Computing Techniques and Applications: Proceedings of the Fourth … , 2021 2021 Citations: 10
Time Series Analysis on COVID-19 AP Anveshini Dumala Journal of Xi'an University of Architecture & Technology 12 (06), 567-574 , 2020 2020
Back Off Algorithm for Reducing the Connection Loss In AD-HOC Network PR P.Anusha1, P.Satya Gopi2, K.Santhi Sri3 Test engineering & Management 83, 11046 - 11057 , 2020 2020
Energy Priority With Link Aware Mechanism For On-Demand Multipath Routing In Manets PAARVLNVR Maddumala4 International Journal of Advanced Science and Technology 29 (03), 8979 - 8991 , 2020 2020 Citations: 11
Classification of Cancer Cells Detection Using Machine Learning Concepts VRMSGGPAPS Krishna4 International Journal of Advanced Science and Technology 29 (03), 9177 - 9190 , 2020 2020
USE OF BLOCK CHAIN TECHNOLOGY IN PROVIDING SECURITY DURING DATA SHARING GVL Banavathu Mounika, P. Anusha, V. Lakshman Narayana Journal of Critical Reviews 7 (06), 338-343 , 2020 2020 Citations: 21
SUPERVISED AND UNSUPERVISED ASPECT BASED CATEGORY DETECTION USING SENTIMENT ANALYSIS WITH RANDOM FOREST ALGORITHM AP Ch. Puspa Satvika1, P.Tejaswini2, M.Jyothsna3 , T.Mahitha4 Journal of Enginnering sciences 11 (04), 0377-9254 , 2020 2020
Use of Blockchain in Malicious Activity Detection for Improving Security BTRVLNVPP Anusha4 International Journal of Advanced Science and Technology 29 (03), 9135 - 9146 , 2020 2020 Citations: 16
SOCIAL NETWORK MENTAL DISORDER DETECTION VIA ONLINE SOCIAL MEDIA MINING USING MACHINE LEARNING FRAMEWORK P Farjana, GN Nikhila, KK Nandini, M Afrin, A Papasani 2020 Citations: 2
FUZZY BASE ARTIFICIAL NEURAL NETWORK MODEL FOR TEXT EXTRACTION FROM IMAGES VL Narayana, BN Sudheer, VR Maddumala, P Anusha Journal of Critical Reviews 7 (6), 2020 , 2020 2020 Citations: 17
MOST CITED SCHOLAR PUBLICATIONS
USE OF BLOCK CHAIN TECHNOLOGY IN PROVIDING SECURITY DURING DATA SHARING GVL Banavathu Mounika, P. Anusha, V. Lakshman Narayana Journal of Critical Reviews 7 (06), 338-343 , 2020 2020 Citations: 21
Enhanced Morphological Operations for Improving the Pixel Intensity Level VRMKMLPAVL Narayana4 International Journal of Advanced Science and Technology 29 (03), 9191 - 9201 , 2020 2020 Citations: 18
FUZZY BASE ARTIFICIAL NEURAL NETWORK MODEL FOR TEXT EXTRACTION FROM IMAGES VL Narayana, BN Sudheer, VR Maddumala, P Anusha Journal of Critical Reviews 7 (6), 2020 , 2020 2020 Citations: 17
Use of Blockchain in Malicious Activity Detection for Improving Security BTRVLNVPP Anusha4 International Journal of Advanced Science and Technology 29 (03), 9135 - 9146 , 2020 2020 Citations: 16
Energy Priority With Link Aware Mechanism For On-Demand Multipath Routing In Manets PAARVLNVR Maddumala4 International Journal of Advanced Science and Technology 29 (03), 8979 - 8991 , 2020 2020 Citations: 11
A novel feature selection algorithm using multi-objective improved honey badger algorithm and strength pareto evolutionary algorithm-II A Papasani, N Devarakonda Journal of Engineering Research 11 (2), 71-83 , 2023 2023 Citations: 10
A Novel Feature Selection Algorithm Using Decomposition Based Multi-Objective Guided Honey Badger Algorithm (MO-GHBA) And NSGA-III A Papasani, N Devarakonda Kuwait Journal of Science , 2022 2022 Citations: 10
COVID-19 face mask live detection using OpenCV A Dumala, A Papasani, S Vikkurty Smart Computing Techniques and Applications: Proceedings of the Fourth … , 2021 2021 Citations: 10
Improving Relevant Text Extraction Accuracy using Clustering Methods PA K. Sarada1, V. Lakshman Narayana2, A. Peda Gopi3 Test engineering & Management 83, 15212 - 15219 , 2020 2020 Citations: 9
Adaptive Neighborhood Adjustment Strategy Based On MOHHO and NSGA-III Algorithms for Feature Selection. A Papasani, R Durgam, N Devarakonda IAENG International Journal of Applied Mathematics 54 (5) , 2024 2024 Citations: 5
Feature Selection Using PSO Optimized-Framework with Machine Learning Classification System via Breast Cancer Survival Data A Papasani, N Devarakonda, Z Polkowski, M Thotakura, ... Computational Vision and Bio-Inspired Computing: Proceedings of ICCVBIC 2021 … , 2022 2022 Citations: 4
Improvement of AOMDV routing protocol in MANET and performance analysis of security attacks A Papasani, N Devarakonda Int J Res Comput Sci Eng 6 (5), 4674-4685 , 2016 2016 Citations: 4
Hybrid optimized multi-objective honey badger algorithm and NSGA-II for feature selection problems A Papasani, N Devarakonda Indonesian Journal of Electrical Engineering and Computer Science 36 (1 … , 2024 2024 Citations: 2
Identifying Rotten Region on the Plant Leaf in Advance to Increase the Crop Yield using Multinominal Probit Regression A Dumala, A Papasani, R Bommala, V Sireesha 2022 International Conference on Applied Artificial Intelligence and … , 2022 2022 Citations: 2
SOCIAL NETWORK MENTAL DISORDER DETECTION VIA ONLINE SOCIAL MEDIA MINING USING MACHINE LEARNING FRAMEWORK P Farjana, GN Nikhila, KK Nandini, M Afrin, A Papasani 2020 Citations: 2
Securing Voice Software Applications Using 5G WSN and AI Driven Privacy Preservation Protocols HMA Ghanimi, K Swaroopa, A Mishra, A Papasani, KS Babu, ... J. Mach. Comput 5 (3), 1803-1822 , 2025 2025 Citations: 1
Retracted: Parkinson’s Neurodegenerative Disease Prediction with Robust Methods Of Machine Learning A Papasani, N Devarakonda, Z Polkowski 2021 Fourth International Conference on Electrical, Computer and … , 2021 2021 Citations: 1
Weight-Optimized Genetic Algorithm-Driven Machine Learning Models for Robust Digital Video Watermarking Methods AM Ali, N Rajkumar, R Saravanan, A Papasani, G Saravanan, KS Latha 2025
A Quick Dynamic Attribute Subset Method for High Dimensional Data Using Correlation-Guided Cluster Analysis and Genetic Algorithm N Bhagya Lakshmi, N Devarakonda, Z Polkowski, A Papasani Innovations in Computational Intelligence and Computer Vision: Proceedings … , 2022 2022
Time Series Analysis on COVID-19 AP Anveshini Dumala Journal of Xi'an University of Architecture & Technology 12 (06), 567-574 , 2020 2020
