HBHemalatha Balan

Hemalatha Balan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hemalatha Balan has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    AI-driven framework for accurate detection of Alzheimer’s disease in EEG

    by B. Hemalatha, K. Venkatachalam, Siuly Siuly, Jaehyuk Cho

    Alzheimer’s Disease (AD) is a rapidly growing neurodegenerative disorder that severely impairs cognitive function, particularly among older adults. Early detection is critical for timely intervention and effective management. While electroencephalography (EEG) provides a non-invasive, cost-effective tool with high temporal resolution for diagnosing Alzheimer’s Disease (AD), traditional EEG-based approaches often struggle to extract informative features accurately from complex brain signals, thus limiting their diagnostic performance. This study addresses these challenges by proposing a novel artificial intelligence-based framework that integrates feature fusion with a Convolutional Long Short-Term Memory (Conv-LSTM) architecture. The model combines spectral features and deep learning-derived representations into a unified feature set, which is then processed by the LSTM network to capture both spatial and temporal patterns associated with AD. The proposed method achieves a classification accuracy of 99.8%, outperforming existing techniques and demonstrating its effectiveness in distinguishing between multiple stages of AD. Experimental results confirm the superiority of the fusion-based approach in learning high-level, discriminative features from EEG signals. This research represents a significant advancement in EEG-based Alzheimer’s disease (AD) detection, with strong potential for enhancing early diagnostic systems. It supports the development of intelligent, scalable clinical tools for dementia screening and contributes to the broader effort to integrate AI into the diagnosis of neurodegenerative diseases.


  • Open Access

    Optimizing Osteoporosis Detection with Cascaded Convolutional Neural Network and Real-Coded Genetic Algorithm

    by Hemalatha Balan, Madhavi Latha Pandala, Venkatasubramanian Srinivasan, Venkatachalam Kandasamy

    A peer-reviewed journal of applied informatics that covers a broad range of topics, especially dealing with the social and business aspects of informatics.

  • Automatic Detection of Dental Age Assessment Using an Efficient Elman Neural Network with Dragonfly Optimization

    by B. Hemalatha, N. Rajkumar

    Age is considered as an essential factor for all individuals in their lives. Identification of individuals is also considered as a vital feature of legal dentistry than medicine. Gender, age and race are determined by the documentation of individuals. Chronological age is measured as the birth date for registration. Age is an essential factor in court law, clinics and research. Foremost dental clues are essentially considered to resolve crime. Age is evaluated based on dental age (DA), bone age and mental age. DA is more vital for tooth development illustration than other development characteristics and has low variability related to chronological age. Therefore, DA is considered a significant factor for establishing individuals’ age. So, an efficient Elman Neural Network (ENN) with Dragonfly Optimization (DO) algorithm is proposed for DA classification. Initially, an Orthopantomogram (OPG) input image is pre-processed for image smoothing and noise reduction with Improved Kaun Filter (IKF). Teeth from image are portioned with Improved Artificial Bee Colony (IABC) clustering and morphological post-processing outcome to enhance precision. Specific characteristics are extracted to upgrade precision. Age is classified with ENN–DO. With ENN, DO is utilized to resolve the training issues. The DA can be predicted the chronological age from 4 to 18 years of South Indian subject used it for various applications. Experimental outcomes demonstrate that ENN–DO acquires better accuracy than the existing classifiers such as ELM-SRC, MELM-SRC and RBFN. The DA of an individual can be predicted up to 18 years of age for various applications. In future, other classification schemes will be evaluated by using large dataset of teeth images and will be also predicted for all ages.

  • Detection of Mammograms Using Honey Bees Mating Optimization Algorithm (M-HBMO)

    by R. Durgadevi, B. Hemalatha, K. Vishnu Kumar Kaliappan

    Mammography is the best available technique used by radiologists for screening early detection of breast cancer. In digital mammography the crisis of finding efficient and precise breast profile segmentation technique is time-consuming. In this research work, a novel hybrid method named M-HBMO (Mammogram based Honey Bees Mating Optimization) algorithm has been proposed to segment the lesion. The cancer profile segmentation is based on texture feature and extraction of the lesion. The M-HBMO is evaluated with conventional ROI (region of interest) Algorithm. The experiment is conducted with MRI images retrieved from the medical hospital database. The result proves that the M-HBMO method segments the breast region accurately correspond to respective MRI images.


  • Efficient Kernel-Based Fuzzy C-Means Clustering for Pest Detection and Classification

    by N. Vinushree, B. Hemalatha, Vishnu Kumar Kaliappan

    Plant pest detection is an essential for food security, quality of life and steady agricultural economy. Through rapid infestation by pests and insects various problems faced in enormous agricultural yield for every year. Many researches are being carried out worldwide to identify scientific methodologies for detection of pests. In the recent past, several approaches based on automation and image processing has come to light on the way to address this issue. In this paper we present a clustering technique, the popular algorithm for clustering is kernel-based fuzzy c-means clustering algorithm (KFCM) is used to identify density of pest in plant. A supervised learning neural network was applied to the classification of feature extraction of leaf. The methods studied are for increasing throughput & reducing subjective arising from human experts in detecting the pests in plant.