R M Mallika

@sietk.org

ASSOCIATE PROFESSOR AND CSE DEPARTMENT
SIDDHARTH INSTITUTE OF ENGINEERING & TECHNOLOGY

R M Mallika


               Download Compact PDF  
https://researchid.co/drmallika521
Having 19 yrs Teaching experience

EDUCATION

Ph.D in Computer Science , Padmavathi Mahila Visvavidyalayam, Tirupati.

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Information Systems, Computer Engineering, Artificial Intelligence
9

Scopus Publications

31

Scholar Citations

2

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • KAZENET: Robust Feature Detection Model for Lung CT using KAZE Features
    Maria Arockia Dass John, M. Giri, R. M. Mallika
    Aip Conference Proceedings, 2025
  • Empowering Fake News Detection Through Innovative Hybrid Deep Learning-Based Approach
    A Suresh, R M Mallika, S Gireesh, G Hari Kiran Singh, E S Jeevanandham, et al.
    Proceedings of 2025 International Conference on Computing for Sustainability and Intelligent Future Comp Sif 2025, 2025
    The essence of getting information to the populace in the shortest time possible through social media and other interactive technologies has made it easier for fake news to thrive hence creating a menace to any society as well as its decision-making systems. This research work presents a sound AI-based approach to classify fake news using DL algorithms embedded within a CNN-BiLSTM model. Using the ISOT dataset, the comparison of the outcomes achieved by the proposed model with the original models shows that the proposed model has the highest accuracy score of 94.07%, a precision of 93.50%, a recall of 94.60%, and an F1-score of 94.00%. The proposed hybrid model architecture of CNN for spatial feature extraction and BiLSTM for capturing contextual dependencies that are essential for text analysis and have relatively high accuracy compared to conventional ML algorithms, including CNN, RNN, LSTM, and other DL methods. The proposed approach is verified by a set of comprehensive measures, including ROC curve analysis and various training-validation metrics that reveal the effectiveness of the presented approach in overcoming the challenges of fake news identification.
  • Emotion Based Music Recommendation System Using CNN & HARR Cascade
    Thammisetty Swetha, Srilakshmi Cherukuri, R. M. Mallika, V. Deepika, K Divya Reddy, et al.
    2025 IEEE International Conference on Advanced Computing Technologies Icact 2025, 2025
  • Large Language Model based Personalized Learning Assistant for Career-Oriented Skills
    K Hemalatha, V Deepika, R M Mallika, Kona Mahesh Babu
    2nd International Conference on Signal Processing Communication Power and Embedded Systems Scopes 2024, 2024
    Large Language Models (LLMs) are recently emerged as a variant of Artificial Intelligence algorithms in Natural Language Processing task such as analyzing extensive datasets, generating, summarizing content and predicting new information. LLMs fall under Generative AI, designed specifically for text generation. Their exceptional training and numerous model parameters significantly enhance the LLMs capacity to mimic human-like performances in natural language understanding. The advent of LLMs has revolutionized the interaction between humans and machines. In contrast to conventional recommendation systems and search engines, LLMs are the adoptive active user engagement. This interactive capability opens up new possibilities for the users towards personalization, enabling the provision of personalized services based on individualized information. Despite their potential, the applications of LLMs in personalization remain largely unexplored. Consequently, this study explores into the domain of personalization within education, aiming to uncover the potential contributions of Large Language Models (LLMs). In the context of this research, an innovative personalized LLM-based Human Machine Interface is crafted to individualize learning experiences for each learner. This system is adept at crafting personalized learning plans and adjusting learning materials accordingly. Additionally, it formulates assessments to analyze user strengths and weaknesses. These assessments undergo automatic evaluation, offering learners instant feedback. This feedback mechanism allows learners to promptly identify and understand their mistakes, fostering a more efficient learning process and aiding them in successfully completing their courses. The proposed personalized LLM based Assistant enhances the learner's unique journey by creating adaptive leaning plans, real time assessments with instant feedback.
  • Enhance the Context-Based Online Recommendation System using Deep Reccurrent Neural Network with Enhaned Pigeon Search Optimization
    A Suresh, J Sridhar, R M Mallika, D Nagaraju, G Indiravathi
    IEEE International Conference on Recent Advances in Science and Engineering Technology Icraset 2024, 2024
    Most research in the area of Recommendation Systems (RS) seeks to improve quality by applying multiple methodologies. The main objective is to improve predictive performance while disregarding other design objectives, including the environment of a patient’s article. As a result, at numerous levels, a learning-based RS was proposed in this research. It is an efficient RS to improve the smallest amount of error during suggestion. The information started with the Python framework. Following preprocessing, the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm was used to present the extracted and contextual information from each preprocessing evaluation. The resulting characteristics were used as an entry for density-based clustering, which groups client evaluations into negative, neutral and favourable attitudes. Each item had an uncertain chance of being appreciated by a customer. The effectiveness of the recommendation system was measured according to its regrets, using an Oracle method that would know the probability of a benchmark. The hybrid Deep Recurring Neural Network- Enhanced Pigeon Search Optimization (DRNN-EPSO) method has been used to initialize the Recurrent Neural Network (RNN) modeling input variables. Also, the article used RNN, logistic regression, Multi-Layer Perceptron (MLP) and other supervised learning methods. Our study indicates the weighting factor of the various components of disappointment (i) the element emerging from the restriction of not trying to present the very same product to the very same consumer 2 times, (ii) the element emerging from having to learn the opportunities consumers like goods, & lastly the element emerging from having to learn the internal structure. The proposed model’s performance was measured using correctness, specificity, & recall measures, and it is contrasted latest systems. The proposed model has an average accuracy of $99.6 \\%$, which would be more accurate than previous machine learning techniques.
  • Skin cancer classification using AI-based techniques
    K.Jagadeesh, R.M.Mallika, B.Sreelatha, C. Venkata Sai Harsha Vardhan Raju, Shaik Akbar, et al.
    Proceeding of 2024 International Conference on Communication Computing and Energy Efficient Technologies I3ceet 2024, 2024
    We've created an AI tool using CNN and MobileNet to analyze skin images for initial dermatological diagnosis. The system categorizes diseases, offers descriptions, remedies, and severity assessments, suggesting dermatologists for appointments. Supporting English and Telugu languages, it aims to narrow the gap in dermatological care.
  • Texture Features Based Hybrid Multi Support Vector Machine Model for the diagnosis of Alzheimer's disease through Brain MRI Images
    R.M. Mallika, K Usha Rani, K Hemalatha, M. Giri
    2023 International Conference on Computational Intelligence Networks and Security Iccins 2023, 2023
    Alzheimer's Disease (AD) is a complex neurodegenerative disorder that severely affects cognitive functions and poses significant challenges in early and accurate diagnosis. In recent years, machine learning techniques have shown remarkable potential in medical image analysis, particularly when applied to Brain MRI Images for AD diagnosis. This study proposes a novel approach utilizing a Texture Features based Hybrid Multi-Support Vector Machine Model to enhance the precision and early detection of Alzheimer's disease through Brain MRI Images. The proposed model combines the strength of texture features extracted from Brain MRI Images with a Hybrid Multi- Support Vector Machine framework. Texture features capture subtle patterns and structural variations within brain images, making them valuable in distinguishing different stages of Alzheimer's disease. By leveraging the optimization capabilities of the Hybrid Multi-Support Vector Machine, the model effectively handles high-dimensional data and complex patterns, contributing to improved diagnostic accuracy. To evaluate the model's performance, a comprehensive dataset of Brain MRI Images, encompassing AD patients, Mild Cognitive Impairment cases, and non-AD individuals, was employed. The experimental results demonstrate the effectiveness of the proposed Texture Features based Hybrid Multi-Support Vector Machine Model in accurately classifying Alzheimer's disease cases, outperforming traditional diagnostic methods.
  • A Comparison of Multi Support Vector Machine Performance with Popular Decomposition Strategies on Alzheimer’s Data
    R. M. Mallika, K. Usha Rani, K. Hemalatha
    Learning and Analytics in Intelligent Systems, 2020
  • A fuzzy-based expert system to diagnose alzheimer’s disease
    R. M. Mallika, K. UshaRani, K. Hemalatha
    Springerbriefs in Applied Sciences and Technology, 2019

RECENT SCHOLAR PUBLICATIONS

  • Emotion Based Music Recommendation System Using CNN & HARR Cascade
    T Swetha, S Cherukuri, RM Mallika, V Deepika, KD Reddy, T Chaithanya
    2025 IEEE International Conference on Advanced Computing Technologies (ICACT … , 2025
    2025.0
  • KAZENET: Robust feature detection model for lung CT using KAZE features
    MAD John, M Giri, RM Mallika
    AIP Conference Proceedings 3237 (1), 030006 , 2025
    2025.0
  • Enhance the Context-Based Online Recommendation System using Deep Reccurrent Neural Network with Enhaned Pigeon Search Optimization
    RMMASJSDNG indiravai
    IEEE , 2025
    2025.0
  • KAZENET: Robust feature detection model for lung CT using KAZE features
    MG R M Mallika, Maria Arockia Dass
    API Conference Proceedings 3237 (1) , 2025
    2025.0
  • Large Language Model based Personalized Learning Assistant for Career-Oriented Skills
    K Hemalatha, V Deepika, RM Mallika, KM Babu
    2024 2nd International Conference on Signal Processing, Communication, Power … , 2024
    2024.0
    Citations: 2
  • Skin cancer classification using AI-based techniques
    K Jagadeesh, RM Mallika, B Sreelatha, CVSHV Raju, S Akbar, P Vinay
    2024 International Conference on Communication, Computing and Energy … , 2024
    2024.0
  • Texture features based hybrid multi support vector machine model for the diagnosis of Alzheimer's disease through brain MRI images
    RM Mallika, KU Rani, K Hemalatha, M Giri
    2023 International Conference on Computational Intelligence, Networks and … , 2023
    2023.0
    Citations: 8
  • GA based Feature Selection Model using MSVM for the Diagnosis of Alzheimer’s Disease
    RM Mallika, K UshaRani, K Hemalatha
    Design Engineering, 8891-8900 , 2021
    2021.0
  • Early Diagnosis of Alzheimer’s Disease using Soft Computing Based Deep Learning Technique
    DB Geethavani, RM Mallika, DDW Albert, DMA Manivasagam
    Solid State Technology 64 (Issue Vol. 64 No. 2 (2021)) , 2021
    2021.0
    Citations: 2
  • Decomposition Strategies on Alzheimer's
    RM Mallika, KU Rani, K Hemalatha
    Advances in Computational and Bio-Engineering: Proceeding of the … , 2020
    2020.0
  • HUMAN CARDIOVASCULAR DISEASE PREDICTION SYSTEM USING HYBRID MACHINE LEARNING ALGORITHM IN HEALTH CARE INDUSTRY
    DV SAGARI, RM MALLIKA
    The International Jounal of Analytical and experimental modal Analysis 12 … , 2020
    2020.0
  • A Comparison of Multi Support Vector Machine Performance with Popular Decomposition Strategies on Alzheimer’s Data
    RM Mallika, KU Rani, K Hemalatha
    International Conference On Computational And Bio Engineering, 469-479 , 2020
    2020.0
    Citations: 1
  • Feature Based Analysis of MSVM on Brain MRI Images
    RM Mallika, KU Rani, K Hemalatha
    TEST (Engineering and Management) 83 (May-June 2020), 5748 - 5752 , 2020
    2020.0
  • A Secure Location Based Service Search in Cost Efficient Cloud Environments
    M NARMADHA, RM MALLIKA
    International Journal of Advanced Technology and Innovative Research 11 (01 … , 2019
    2019.0
  • A fuzzy-based expert system to diagnose Alzheimer’s disease
    RM Mallika, K UshaRani, K Hemalatha
    Internet of Things and Personalized Healthcare Systems, 65-74 , 2018
    2018.0
    Citations: 18
  • A Novel Approach for Node Failure Detection in Mobile WSN
    S MANI, RM MALLIKA
    2017.0
  • Enhancing Security in Dynamic Multi Keyword Ranked Search Over Cloud Data
    C RADHA, RM MALLIKA
    2017.0
  • Secure And Synchronized City-Scale Taxi Ridesharing
    R SRAVYA, RM MALLIKA

MOST CITED SCHOLAR PUBLICATIONS

  • A fuzzy-based expert system to diagnose Alzheimer’s disease
    RM Mallika, K UshaRani, K Hemalatha
    Internet of Things and Personalized Healthcare Systems, 65-74 , 2018
    2018.0
    Citations: 18
  • Texture features based hybrid multi support vector machine model for the diagnosis of Alzheimer's disease through brain MRI images
    RM Mallika, KU Rani, K Hemalatha, M Giri
    2023 International Conference on Computational Intelligence, Networks and … , 2023
    2023.0
    Citations: 8
  • Large Language Model based Personalized Learning Assistant for Career-Oriented Skills
    K Hemalatha, V Deepika, RM Mallika, KM Babu
    2024 2nd International Conference on Signal Processing, Communication, Power … , 2024
    2024.0
    Citations: 2
  • Early Diagnosis of Alzheimer’s Disease using Soft Computing Based Deep Learning Technique
    DB Geethavani, RM Mallika, DDW Albert, DMA Manivasagam
    Solid State Technology 64 (Issue Vol. 64 No. 2 (2021)) , 2021
    2021.0
    Citations: 2
  • A Comparison of Multi Support Vector Machine Performance with Popular Decomposition Strategies on Alzheimer’s Data
    RM Mallika, KU Rani, K Hemalatha
    International Conference On Computational And Bio Engineering, 469-479 , 2020
    2020.0
    Citations: 1
  • Emotion Based Music Recommendation System Using CNN & HARR Cascade
    T Swetha, S Cherukuri, RM Mallika, V Deepika, KD Reddy, T Chaithanya
    2025 IEEE International Conference on Advanced Computing Technologies (ICACT … , 2025
    2025.0
  • KAZENET: Robust feature detection model for lung CT using KAZE features
    MAD John, M Giri, RM Mallika
    AIP Conference Proceedings 3237 (1), 030006 , 2025
    2025.0
  • Enhance the Context-Based Online Recommendation System using Deep Reccurrent Neural Network with Enhaned Pigeon Search Optimization
    RMMASJSDNG indiravai
    IEEE , 2025
    2025.0
  • KAZENET: Robust feature detection model for lung CT using KAZE features
    MG R M Mallika, Maria Arockia Dass
    API Conference Proceedings 3237 (1) , 2025
    2025.0
  • Skin cancer classification using AI-based techniques
    K Jagadeesh, RM Mallika, B Sreelatha, CVSHV Raju, S Akbar, P Vinay
    2024 International Conference on Communication, Computing and Energy … , 2024
    2024.0
  • GA based Feature Selection Model using MSVM for the Diagnosis of Alzheimer’s Disease
    RM Mallika, K UshaRani, K Hemalatha
    Design Engineering, 8891-8900 , 2021
    2021.0
  • Decomposition Strategies on Alzheimer's
    RM Mallika, KU Rani, K Hemalatha
    Advances in Computational and Bio-Engineering: Proceeding of the … , 2020
    2020.0
  • HUMAN CARDIOVASCULAR DISEASE PREDICTION SYSTEM USING HYBRID MACHINE LEARNING ALGORITHM IN HEALTH CARE INDUSTRY
    DV SAGARI, RM MALLIKA
    The International Jounal of Analytical and experimental modal Analysis 12 … , 2020
    2020.0
  • Feature Based Analysis of MSVM on Brain MRI Images
    RM Mallika, KU Rani, K Hemalatha
    TEST (Engineering and Management) 83 (May-June 2020), 5748 - 5752 , 2020
    2020.0
  • A Secure Location Based Service Search in Cost Efficient Cloud Environments
    M NARMADHA, RM MALLIKA
    International Journal of Advanced Technology and Innovative Research 11 (01 … , 2019
    2019.0
  • A Novel Approach for Node Failure Detection in Mobile WSN
    S MANI, RM MALLIKA
    2017.0
  • Enhancing Security in Dynamic Multi Keyword Ranked Search Over Cloud Data
    C RADHA, RM MALLIKA
    2017.0
  • Secure And Synchronized City-Scale Taxi Ridesharing
    R SRAVYA, RM MALLIKA

Publications

37 publications

RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)

3 patents