ASAnitha Sammilan

Anitha Sammilan

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Anitha Sammilan has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • MNSO-Based Ensemble Learning for Signal Detection in MIMO-OTFS Systems for B5G Communications

    by Panchaxari Mamadapur, .S. Anitha, .T. Senthil Kumaran, .C.S. Pillai

    The development of MIMO-OTFS (Multiple Input Multiple Output–Orthogonal Time Frequency Space) has proven to be a great breakthrough and a highly viable waveform for next-generation and future 5G wireless communication networks. However, it suffers from performance degradation when MMSE and ZF are applied to large-scale MIMO systems and fast-changing environments. In order to overcome these limitations, this paper proposes an MNSO-based ensemble learning approach for detecting signals in MIMO-OTFS systems. This approach is based on using Modified Non-Smooth Optimization (MNSO) for dimensionality reduction in conjunction with a two-level ensemble learning model. At the first level, there are machine learning classifiers, namely Linear Regression, Random Forest, Decision Tree, and Support Vector Machine, to detect feature-level signals, and at the second level, there is a Gradient Boosting Bayesian Neural Network (GB-BNN) that learns non-linearities in the delay-Doppler domain. In order to test the system, use a set of 5000 signals generated in MATLAB under Rayleigh and Rician fading with 16×16, 64×64, and 256×256 MIMO structures and 0 to 10 dB SNR values. The experimental findings show that the proposed ensemble model using MNSO shows considerable success in reducing BER from 0.0600 at low SNR to 0.0030 at high SNR. In the case of 256×256 MIMO configurations, the proposed model can achieve up to 83.33% error reduction from the traditional MMSE techniques. The ablation study shows the effectiveness of the MNSO as well as ensemble techniques in improving the detection accuracy while reducing complexity. Conclusion: In summary, the proposed framework is scalable and robust and can provide high-accuracy detection solutions for B5G MIMO-OTFS communication systems.

  • AI-Based Lanczos Filtering for Feature Selection and Structural Metrics Analysis, and Classification Method for Automated Detection of Major Conjunctivitis in Retinal Color Fundus Images

    by Madhusudhan S, Anitha S

    Various eye diseases appear differently in red, green, and blue channels of RGB colour models. Colour channels provide the primary information for detecting eye diseases. Selection and training of these channels are the primary tasks in pre-processing colour fundus images and the automatic detection of various eye diseases. Improvements in quality and appearance, as well as image enhancements, are performed during the pre processing stage without affecting the accuracy of fundus images. PSNR, MSE, DSSIM, FSIM, RMSE, UIQI, and SSIM are calculated to preserve structural information between the original image and colour-converted images. The test images are taken from the DRIVE fundus database and evaluated using colour-space structural models. The methods are tested using an OpenCV Python Jupyter notebook on a Windows platform with an Intel i5 processor at 3 GHz and 16 GB of RAM. The results are compared to determine the best colour space model for detecting cotton wool spots before post-processing.

  • Open Access

    A Deep Learning-Based Segmentation Technique for Automatic Detection of Conjunctivitis from Conjunctival Eye Images

    by Madhusudhan S, Anitha S

    Eye diseases are becoming common in day to day life and affecting all age groups of people. The ratio of ophthalmologists to patients suggests the need for an automated technique to detect eye diseases. Conjunctivitis is of many types, including adenoviral conjunctivitis, ocular drug toxic conjunctivitis, pollen allergic conjunctivitis, bacterial conjunctivitis, and many others. Conjunctivitis can be automatically detected using conventional image processing techniques, but with lower accuracy and precision, and more computational time is required compared to deep learning and AI techniques. This paper presents a novel deep learning assisted segmentation technique for the automatic detection of conjunctivitis that overcomes the limitations of conventional methods. The proposed method uses Attention U Net with Transformer Encoder Global Context, Swin ViT CNN , Transformer Monte Carlo Dropout Layer Enabled at inference time, Uncertainty aware and Segmentation Mask Uncertainty Map, which provides better results with Accuracy 90.3 percent, sensitivity 0.87, specificity 0.93, precision 0.88, recall 0.87, F1-Score 0.89, ROC Auc 0.96.

  • Open Access

    A hybrid intelligent model for prediction of coronary artery diseases using TabNet and multiclass SVM

    by Niveditha Honnemadu Rudreshgowda, Balakrishna Kempegowda, Anitha Sammilan

    Cardiovascular disease is one of the significant fatality-causing diseases in this era by affecting the heart and blood vessels. Cardio diseases are classified into coronary heart disease (CHD), heart failure, valve disease, and arrhythmias. Medical diagnosis of heart disease and treating the patient is a challenging process, where early detection can lead to decreased fatality. In this research, hybrid model-based prediction of CHD detection is developed by TabNet and multiclass support vector machine (SVM). We created our datasets for experimentation by visiting the hospitals in the Mysore and Mandya regions of Karnataka, India. Datasets consist of 16 features; the features are pre-processed to normalize, encode, and handle missing values to extract the aggregate features using TabNet, and the multiclass SVM model is trained to classify the disease based on the classes. The proposed hybrid model prediction performance was evaluated using various metrics such as accuracy, recall, precision, and F1-score.

  • Open Access

    A Hybrid Machine Learning Model for Peripheral Artery Disease Prediction and Real-Time Applications

    by H. R. Niveditha, S. Anitha, Nataraj Kanathur Ramaswamy, Rekha Kanathur Ramaswamy, Srikantaswamy Mallikarjunaswamy

    Peripheral Artery Disease (PAD) is a common and serious circulatory problem for which early and definite diagnosis is necessary to prevent further health complications. The existing diagnostic techniques of Ankle-Brachial Index (ABI) and Doppler ultrasound have several disadvantages: the examination is operator-dependent, the processing times are long, and may be inapplicable or have adaptability in complicated cases. The use of Machine Learning (ML) techniques, such as Support Vector Machines and Random Forest, to overcome these issues, may face problems handling real-time application and non-homogeneous data. The research at hand overcomes such challenges by proposing a Hybrid ML Algorithm for Peripheral Artery Prediction (HMAPAP) based on GBM combined with LSTM networks. The proposed method improved the diagnostic accuracy by 0.25%, processing efficiency by 0.20%, and real-time adaptability by 0.30%, of the traditional ML methods.


  • Digital Tools and Methods

    by Nikitha Sreekanthaswamy, S. Anitha, Amanpreet Singh, Sujay Mugaloremutt Jayadeva, Sandeep Gupta, Deemed to be University, T. C. Manjunath, P. Selvakumar

    Introduction to Research and serves as a comprehensive guide for leveraging modern technologies in the research landscape. In an era where data generation and processing have become increasingly digital, understanding and utilizing digital tools and methods are essential for researchers across various disciplines. The proliferation of digital technologies has transformed how research is conducted, enabling more efficient data collection, enhanced data analysis, and improved dissemination of findings. Digital tools for research encompass a broad range of software and platforms designed to assist in different stages of the research process. These several data analysis, and visualization. Data collection, such as online surveys and web scraping applications, allow researchers to gather large volumes of data with unprecedented speed and accuracy. For example, platforms like SurveyMonkey or Google Forms facilitate the distribution of surveys to diverse populations, while tools and, providing insights into trends and behaviors.


  • Addressing Ethical and Regulatory Challenges in AI-Driven Healthcare

    by P. Selvakumar, S. Anitha, Law Kumar Singh, P. V. Sathish Jackson, Deepika Yadav, T. C. Manjunath

    This shift toward AI-driven; it represents a fundamental change in how medical services are delivered and managed. datasets. These technologies can facilitate, making healthcare more efficient and effective.opportunities presented potential processes, AI has shown promise in areas such as radiology, where it can detect tumors in imaging scans with a level of accuracy that rivals that of experienced radiologists. Furthermore, diagnostic capabilities over time as they are exposed to new data considering their unique genetic makeup, lifestyle, and health history. This approach not only enhances treatment efficacy but also minimizes adverse effects, as therapies can be customized to fit the specific needs of each patient. Predictive analytics, powered by AI, can also forecast disease progression and treatment responses, healthcare providers to intervene early and optimize care strategies.Despite these opportunities, the integration of AI into healthcare misuse.


  • Open Access

    Automated Detection of Conjunctiva Nevus and Choroidal Nevus Using Colour Models and Fundus Mask Generation Technique

    by Madhusudhan S, Anitha S

    Diabetics and eye related diseases are becoming a global cause for eye related problems from infants to the old age persons, eye diseases are more intense in case of diabetics in urban and rural parts. The number of ophthalmologist to the number of raising patient’s ratio suggest that an automated technique needed to screen patients, especially present in remote location or rural areas for fast and accurate diagnose of eye related problems. This includes conjunctiva nevus which is a freckle or mole-like spot around iris and need to be diagnosed before it becomes type of cancer called melanoma, Choroidal nevus which is present inside eye under retinal tissue called the choroid will be of multiple colour and need to be examine before it can become small choroidal melanoma. This paper presents an automatic technique to screen conjunctiva nevus and choroidal nevus for diabetic retinopathy screening by automated mask generation technique.

  • Open Access

    Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson Nano

    by H. M. Mohan, S. Anitha, Rifai Chai, Sai Ho Ling

    The history of medicine shows that myocardial infarction is one of the significant causes of death in humans. The rapid evolution in autonomous technologies, the rise of computer vision, and edge computing offers intriguing possibilities in healthcare monitoring systems. The major motivation of the work is to improve the survival rate during a cardiac arrest through an automatic emergency recognition system under ambient intelligence. We present a novel approach to chest pain and fall posture-based vital sign detection using an intelligence surveillance camera to address the emergency during myocardial infarction. A real-time embedded solution persuaded from “edge AI” is implemented using the state-of-the-art convolution neural networks: single shot detector Inception V2, single shot detector MobileNet V2, and Internet of Things embedded GPU platform NVIDIA’s Jetson Nano. The deep learning algorithm is implemented for 3000 indoor color image datasets: Nanyang Technological University Red Blue Green and Depth, NTU RGB + D dataset, and private RMS dataset. The research mainly pivots on two key factors in creating and training a CNN model to detect the vital signs and evaluate its performance metrics. We propose a model, which is cost-effective and consumes low power for onboard detection of vital signs of myocardial infarction and evaluated the metrics to achieve a mean average precision of 76.4% and an average recall of 80%.