Lakshmana Rao Kalabarige

RESEARCH INTERESTS

Information security, sensor network security, cognitive radio networks, machine learning, deep learning and natural language processing

Scopus Publications

Tree-Based Machine Learning and Nelder–Mead Optimization for Optimized Cr(VI) Removal with Indian Gooseberry Seed Powder
Lakshmana Rao Kalabarige, D. Krishna, Upendra Kumar Potnuru, Manohar Mishra, Salman S. Alharthi, and Ravindranadh Koutavarapu
MDPI AG
Wastewater containing a mixture of heavy metals, a byproduct of chemical, petrochemical, and refinery activities driven by urbanization and industrial expansion, poses significant environmental threats. Analyzing such wastewater through adsorbate-adsorbent experiments yields extensive datasets. However, traditional methodologies like the Box–Behnken design (BBD) within the response surface methodology (RSM) struggle with managing large datasets and capturing the complex, nonlinear relationships inherent in such experimental data. To address these challenges, ML techniques have emerged as promising tools for accurately predicting the removal percentage of heavy metals from wastewater. In this study, we utilized tree-based regression models—specifically decision tree regression (DTR), random forest regression (RFR), and extra tree regression (ETR)—to forecast the efficiency of gooseberry seed powder in removing chromium (Cr(VI)) from wastewater. Additionally, we employed an ML-based Nelder–Mead optimization approach to identify the optimal values for key features (initial Cr(VI) concentration, pH, and Indian gooseberry powder dosage) which maximized the Cr(VI) removal percentage. Our experimental results reveal that the ETR model achieved an impressive R2 score of 0.99, demonstrating a low error rate in predicting the Cr(VI) removal percentage. Furthermore, we used DTR-Nelder–Mead, RFR-Nelder–Mead, and ETR-Nelder–Mead optimization approaches on a synthesized dataset of 2000 instances while varying the initial Cr(VI) concentration, pH, and Indian gooseberry powder dosage. The analysis determined that the DTR-Nelder–Mead and RFR-Nelder–Mead approaches yielded the highest Cr(VI) removal percentages of 78.21% and 78.107% at an initial concentration of 95.55 mg/L, respectively, a pH level of four, and an adsorbent dosage of 8 g/L of gooseberry seed powder. Furthermore, the ETR-Nelder–Mead approach obtained the maximum Cr(VI) removal percentage of 85.11% at an initial concentration of 99.25 mg/L, a pH level of 4.97, and an adsorbent dosage of 9.62 g/L of gooseberry seed powder. These results reported an increase in the Cr(VI) removal percentage ranging from 4.66% to 11.56% more than the Cr(VI) removal percentage obtained by experimentation. These findings underscore the efficacy of tree-based regression models and ML-based Nelder–Mead optimization in elucidating chromium removal processes from wastewater, offering valuable insights into effective treatment strategies.


Multimodal imputation-based stacked ensemble for prediction and classification of air quality index in Indian cities
Routhu Srinivasa Rao, Lakshmana Rao Kalabarige, Bhavya Alankar, and Aditya Kumar Sahu
Elsevier BV



Boosting Pineapple Maturity Classification: Impact of Data Augmentation and Visual Transformer Integration with Transfer Learning
Lakshmana Rao Kalabarige, A. Venkata Ramana, Routhu Srinivasa Rao, and M. Raviraja Holla
Institute of Electrical and Electronics Engineers (IEEE)
Pineapple is a tropical fruit with varying degree of ripeness. It plays an important role in tribal agricultural markets. The effective pineapple maturity grading is essential for optimizing distribution and maximizing profits of tribal farmers. This study utilizes a pineapple dataset from Kaggle which include raw and ripe pineapple images. These raw and ripe are categorized into four maturity classes—fully ripe, medium ripe, partially ripe, and unripe—using Hue, Saturation, and Value (HSV) color space technique. Furthermore, the original dataset further divided into four specialized datasets: cluttered-unbalanced (<inline-formula> <tex-math notation="LaTeX">$d_{1}$ </tex-math></inline-formula>), cluttered-balanced (<inline-formula> <tex-math notation="LaTeX">$d_{2}$ </tex-math></inline-formula>), fine-tuned-unbalanced (<inline-formula> <tex-math notation="LaTeX">$d_{3}$ </tex-math></inline-formula>), and fine-tuned-balanced (<inline-formula> <tex-math notation="LaTeX">$d_{4}$ </tex-math></inline-formula>). In this study, we explore the effectiveness of four Transfer Learning Models (TLMs): DenseNet121, VGG19, MobileNetV2, and InceptionV3, in conjunction with Visual Transformer (VT) technology for pineapple maturity classification. In addition, this work introduced four Hybrid models popularly named as VT-TLMs (VT-DenseNet121, VT-VGG19, VT-MobileNetV2 and VT-InceptionV3). These Hybrid models make the best use of the features that are extracted from the final layers of TLMs to capture complex features, detailed patterns and long-range dependencies inherent in image classification tasks. The proposed TLMs can decide maturity of pineapples with an accuracy ranging from 91.49% to 93.64%. Moreover, VT integration with TLMs obtained better accuracy ranging between 94.43% and 99.57%. Additionally, VT-DenseNet121 performs exceptionally well, with an average accuracy of 99.57%, when compared to previous research in the field.


Multimodal Imputation based Multimodal autoencoder framework for AQI classification and prediction of Indian cities
Routhu Srinivasa Rao, Lakshmana Rao Kalabarige, M. Raviraja Holla, and Aditya Kumar Sahu
Institute of Electrical and Electronics Engineers (IEEE)
Rising urbanization necessitates robust air quality monitoring and prediction systems, particularly in developing nations like India, to mitigate adverse health impacts. Previous research primarily focused on machine learning algorithms for Air Quality Index (AQI) prediction and classification. We propose a novel MI-MMA-XGB which coupled features of multimodal imputer(MI) with the features of multi-modal autoencoder (MMA) and fed to an XGBoost(XGB) algorithm for AQI prediction and classification. Moreover, imputation approaches namely, KNN, MICE, and SVD were employed to address problems with null values and outliers. Furthermore, SMOTE is employed to balance the imputed data and then the model was trained on both balanced and unbalanced imputed data to extract predictive features. In this process, our model MI-MMA-XGB achieves significant accuracy, reaching 97.14% and 93.87% with and without SMOTE, respectively. Additionally, it attains an $R^{2}$ score of 0.9578 and an RMSE of 0.203 for AQI prediction in Indian cities. The proposed model outperforms baseline models in both classification and regression tasks across various evaluation metrics.


Machine learning-based modeling of variable compression ratio engine performance and emissions with JME-ZnO nanoemulsion
Chiranjeeva Rao Seela, Lakshmana Rao Kalabarige, and Siva Prasad Kattela
Informa UK Limited



Machine Learning Modeling Integrating Experimental Analysis for Predicting Compressive Strength of Concrete Containing Different Industrial Byproducts
Lakshmana Rao Kalabarige, Jayaprakash Sridhar, Sivaramakrishnan Subbaram, Palaniappan Prasath, and Ravindran Gobinath
Hindawi Limited
This study aimed to develop accurate models for estimating the compressive strength (CS) of concrete using a combination of experimental testing and different machine learning (ML) approaches: baseline regression models, boosting model, bagging model, tree-based ensemble models, and average voting regression (VR). The research utilized an extensive experimental dataset with 14 input variables, including cement, limestone powder, fly ash, granulated glass blast furnace slag, silica fume, rice husk ash, marble powder, brick powder, coarse aggregate, fine aggregate, recycled coarse aggregate, water, superplasticizer, and voids in mineral aggregate. To evaluate the performance of each ML model, five metrics were used: mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), coefficient of determination (R2-score), and relative root mean squared error (RRMSE). The comparative analysis revealed that the VR model exhibited the highest effectiveness, displaying a strong correlation between actual and estimated outcomes. The boosting, bagging, and VR models achieved impressive R2-scores in the range of 86.69%–92.43%, with MAE ranging from 3.87 to 4.87, MSE from 21.74 to 38.37, RMSE from 4.66 to 4.87, and RRMSE between 8% and 11%. Particularly, the VR model outperformed all other models with the highest R2-score (92.43%) and the lowest error rate. The developed models demonstrated excellent generalization and prediction capabilities, providing valuable tools for practitioners, researchers, and designers to efficiently evaluate the CS of concrete. By mitigating environmental vulnerabilities and associated impacts, this research can significantly contribute to enhancing the quality and sustainability of concrete construction practices.


Tampering Detection and Localization on Copy-Move Images Using Deep Learning Approaches
Kalabarige Lakshmana Rao, Sanapathi Tejaswari, Patnana Meghana, Shaik Juveria, and Sankili Sathwika
IEEE
Images can be used as legal evidence in forensics, journalism, and other fields. Image tampering is modifying images using modern technologies, which might create false evidence. There are many tampering with images like copy-move image forging, image slicing, and recoloring. Now the detection of those types of images whether tampered with or not and the process of recognizing copied and pasted portions for the copy-move tampered images is a challenging task. In this connection, this work employed CNN, ResNet-50, and VGG-16 for the detection of tampering images. These models were trained on CASIAv2 and COMOFOD datasets. Moreover, error-level analysis techniques and Resizing are used to preprocess for detection. SIFT, and Gray Scaling were applied to preprocess the Copy-Move images to identify similar features in the image. Furthermore, preprocessed images are fed to the DBSCAN algorithm to locate the portions of the image where it is copied and pasted in copy-move tampered images. From the results, it was observed that the CNN model trained on the CASIAv2 dataset outperformed all other models. Hence, it was tested on the MICC-F220 dataset followed by DBSCAN for localization of tampered images.


A Boosting based Hybrid Feature Selection and Multi-layer Stacked Ensemble Learning Model to detect phishing websites
Lakshmana Rao Kalabarige, Routhu Srinivasa Rao, Alwyn R. Pais, and Lubna Abdelkareim Gabralla
Institute of Electrical and Electronics Engineers (IEEE)
Phishing is a type of online scam where the attacker tries to trick you into giving away your personal information, such as passwords or credit card details, by posing as a trustworthy entity like a bank, email provider, or social media site. These attacks have been around for a long time and unfortunately, they continue to be a common threat. In this paper, we propose a boosting based multi layer stacked ensemble learning model that uses hybrid feature selection technique to select the relevant features for the classification. The dataset with selected features are sent to various classifiers at different layers where the predictions of lower layers are fed as input to the upper layers for the phishing detection. From the experimental analysis, it is observed that the proposed model achieved an accuracy ranging from 96.16 to 98.95% without feature selection across different datasets and also achieved an accuracy ranging from 96.18 to 98.80% with feature selection. The proposed model is compared with baseline models and it has outperformed the existing models with a significant difference.


Facial Landmark-based Cursor Control and Speechto-Text System for Paralyzed Individuals
Lakshmana Rao Kalabarige, Kella Akhil Abhilash, Kondamudi Anirudh Trivedi, and Mala Dathatreya
IEEE
Computers are crucial in today’s world, but disabled individuals, particularly those who are paralyzed, may face challenges in using them. Paralysis can limit movement to just the eyes, head, and voice, making computer usability difficult without others assistance or help. Few techniques have been developed to improve cursor control systems, such as voice control and gesture control. However, some users have found these methods to be inconvenient or challenging to use. A new model has been proposed that eliminates the need for assistance. It identifies specific facial characteristics, or landmarks, that allow for the control of cursor movement and clicking events without requiring direct physical contact with the user. The system uses eye gaze and facial movements to achieve this. An Integrated Speech-to-Text system is also incorporated into the cursor control system to enable textual interpretation. The system features a user-friendly interface that makes it easy to use and provides a better user experience.


Potential Assessment of Wind Power Generation Using Machine Learning Algorithms for Southern Region of India
P. Upendra Kumar, K. Lakshmana Rao, and T. S. Kishore
Springer Nature Singapore



Multilayer Stacked Ensemble Learning Model to Detect Phishing Websites
L. Kalabarige, Routhu Srinivasa Rao, Ajith Abraham and L. A. Gabralla

Phishing is a cyber attack that tricks the online users into revealing sensitive information with a fake website imitating a legitimate website. The attackers with stolen credentials not only use them for the targeted website but also can be used for accessing the other popular legitimate websites. There exists many anti-phishing techniques, toolbars, extensions to counter the phishing sites but still the phishing attacks are major concern in the current digital world. In this paper, we propose a multilayered stacked ensemble learning technique which consists of estimators at different layers where the predictions of estimators from current layer are fed as input to the next layer. From the experimental results, it is observed that the proposed model achieved a significant performance when evaluated with different datasets with an accuracy of ranging from 96.79% to 98.90%. The proposed model is evaluated with datasets from UCI(D1), Mendeley 2018(D2) and Mendeley 2020(D3,D4). The proposed model achieved detection rate of 97.76% with D1 dataset, achieved an accuracy of 98.9% with D2 dataset. Finally, the technique is tested with D3 and D4 which resulted in accuracy of 96.79% and 98.43% respectively. Also, the proposed model outperformed baseline models corresponding to datasets with a significant difference in accuracy and F score metrics.


Symptom based COVID-19 test recommendation system using machine learning technique
Lakshmana Rao Kalabarige and Himabindu Maringanti
IOS Press
At present, the mankind of the entire world is under serious threat due to the unexpected COVID-19 pandemic. The advent of this pandemic exposes many drawbacks in the medical and healthcare system. As per the guidelines of WHO, the spread of the virus must be controlled through proper measures that help cease the virus. Tracing infected subjects (people/patients) is exceedingly difficult across the globe. The testing process in many countries is hampered by the unavailability of COVID-19 Test kits. Therefore, a testing process needs a robust mechanism to identify the infected subject to reduce the infection rate. To address this issue, a Symptom-based COVID-19 Test Recommendation System using Machine Learning methods is proposed and tested on real data set. It is found that the results of the system are promising and accurate up to 99%. The proposed piece of work undergoes four steps. First, it creates synthesized data set by using inputs of the Superintendent of Physical Health Centre (Rajam). Second, the synthesized data set is balanced by using Random under-sampling (RUS) followed by Synthetic minority oversampling (SMOTE). Third, different machine learning techniques such as K-Nearest Neighbor (KNN), Decision Tree (DT), Naïve Bayes, Random Forest (RF), Stochastic Gradient Descent (SGD), and Support vector machine (SVM) are applied on both the Synthesized and balanced data sets to classify subjects into different classes based on age, comorbidity-chronic disease- and other symptoms (cold, cough, fever, and breathlessness). Finally, the COVID-19 Test Recommended System is created and integrated with the best classification model. From the experimental results, it is observed that the training and testing accuracy of all the classification models is more than 99% consequently, the COVID-19 Testing recommended system also gives 100% accuracy in predicting the category of a subject based on input symptoms.


Stop-Phish: an intelligent phishing detection method using feature selection ensemble
A. V. Ramana, K. Lakshmana Rao, and Routhu Srinivasa Rao
Springer Science and Business Media LLC



On the convergence and optimality of the firefly algorithm for opportunistic spectrum access
Shanti Chilukuri, Sireesha Rodda, and Lakshmana Rao Kalabarige
Inderscience Publishers



A Survey on Identity-Based Security in Wireless Sensor Networks
Lakshmanarao Kalabarige and Hima Bindu Maringanti
Springer Singapore



Supporting QoS Differentiation in Energy-Constrained Cognitive Radio Networks
Lakshmana Rao Kalabarige and Shanti Chilukuri
Springer Science and Business Media LLC
Routing protocols for cognitive radio ad hoc networks (CRNs) select a route between the source and destination nodes based on the spectrum opportunity at intermediate nodes. When multiple routes are possible, most routing protocols for CRNs use some metric—independent of the traffic class—to select routes. However, a route that works well for transferring a particular class of data may not be the right one for a different data class, as its quality of service (QoS) requirements may differ. In this paper, we propose a reactive energy efficient routing protocol with differentiated services (REEDS) for cognitive radio networks. Route selection in REEDS is based on different (multiple) hop metrics calculated dynamically for different traffic classes so that a minimum level of QoS is guaranteed. Another characteristic feature of REEDS is the prediction and dodging of nodes that may be excessively loaded with traffic. This results in the avoidance of formation of holes due to heavy energy expenditure by some nodes. Simulation shows that routes in REEDS are established so that the QoS requirements of each traffic class are satisfied and lesser energy is consumed compared to other routing protocols for CRNs.


A sturdy compression based cryptography algorithm using self-key (ASCCA)




Hashed identity based secure key and data exchange in wireless sensor networks using IEEE 802.15.4 standard