RamyaDevi

Scopus Publications

An implementation of personalized therapy in Clinical Decision Support System using adaptive transformer and hybrid deep learning network
S. Praveena Rachel Kamala, Saraswathi. T, V. Kaliraj, A. Nithya, R. Hema, R. Ramyadevi
Australian Journal of Electrical and Electronics Engineering, 2025
This paper suggests a new mechanism from deep learning concept for personalised therapy in Clinical Decision Support Systems (CDSS). Basically, the texts used for the observation are acquired from the standard data sources and then forwarded to the text preprocessing task. In the pre-processing phase, the punctuation and special character removal, stop word removal, and stemming process are applied to remove noise and help to eliminate the redundant information in order to improve the data quality. Further, the pre-processed text is applied to the Adaptive Transformer Net (ATN) for the feature extraction purpose, where the attributes in this task are optimally determined with the aid of the Adaptive Walrus Optimization Algorithm (AWOA). Finally, the resultant text is subjected to the Hybrid Deep Learning Network (HDLNet). The HDLNet model is implemented by integrating the 'Residual Long Short-Term Memory (Residual LSTM) with Dilated Recurrent Neural Network (Dilated RNN)'. From the results, the sensitivity analysis performed in the implemented technique secured 3.7% more efficient than LSTM, 7.76% improved than MobileNet, 6.7% superior to residual LSTM, and 0.90% effective than dilated RNN in dataset 1. Throughout the validation, the conventional techniques are evaluated with the suggested personalised therapy in CDSS to prove its efficacy.
A Hybrid Model for Prediction of Diabetes Using Machine Learning Classification Algorithms and Random Projection
V. Poornima, RamyaDevi R.
Wireless Personal Communications, 2024
Smart Blind Stick with Wristband: Obstacle Detection and Warning System
R. Ramyadevi, R. Loganathan, R. Karthikeyan, A. Vijay
Springer Proceedings in Mathematics and Statistics, 2024
A Cost-Effective, Agar-based Phantom for Thermogram- Guided Malignancy Analysis
R. Ramyadevi
Eai Springer Innovations in Communication and Computing, 2023
Utilisation of audible steganography to organise and analyse the text within WAV files
R. Ramyadevi, V. Poornima
International Journal of Intelligent Engineering Informatics, 2022
This project seeks to encrypt audio cover files and create temporal domain audio steganography, an audio file with hidden options and text. The mean square error (MSE), mean absolute error (MAE), signal-to-noise ratio (SNR), and cross-correlation analysis identify audio stream text data by comparing 8-bit and 16-bit pulse-code modulation (PCM) audio. This study estimates how many characters can be added to an audio file without changing its structure. MP3's bit rate is audible. Audio steganography is a secure, cost-effective approach to encrypting network data. It's useful for steganography due to low noise distortion. Undetectable embedding is preferable. The suggested technique improves accuracy at low embed levels, according to testing. The suggested strategy delivers the highest peak signal-to-noise ratio (PSNR) with hidden information in the first, second, and third least-significant bit (LSBs). Three LSB had 98% accuracy and the lowest false alarm rate (less than 5%). Experiments reveal that this study's method extracts audio. The recommended method is hard and capable. Novel audio file steganography is imperceptible and recovers messages, and text message length affects robustness.
Analysis of Breast Thermograms Using Asymmetry in Infra-Mammary Curves
R. Ramya Devi, G. S. Anandhamala
Journal of Medical Systems, 2019
User-anomaly detection in telecommunication using big data analytics
International Journal of Recent Technology and Engineering, 2019
Recent trends in medical imaging modalities and challenges for diagnosing breast cancer
R. Ramya Devi, G.S. Anandhamala
Biomedical and Pharmacology Journal, 2018
Breast cancer is the leading deadly cancer and most commonly diagnosed in women. New technologies in supplement to existing imaging modalities improve breast cancer screening. This article contributes to identify the high potential device that suggested high accuracy and reliable tool for breast screening and also to examine new screening modalities. An improved imaging system which ensures early detection, non-invasive and radiation free is expected in diagnosis. Numerous imaging modalities like positron emission tomography/computed tomography (PET/CT) imaging, ultrasound, magnetic resonance imaging (MRI), thermography, electrical impedance tomography and few others with recent developments show great potential for diagnosis. Some of the techniques aim for lesion detection and characterization with increased specificity and accuracy. In this paper, the capabilities of traditional and emerging breast imaging modalities used in breast cancer screening are summarized and their advantages and disadvantages are discussed.
Ideal Sampling Rate to Reduce Distortion in Audio Steganography
R.Ramya Devi, D. Pugazhenthi
Procedia Computer Science, 2016
This report presents a method to embed and extract digital data in an audio file using LSB embedding technique. The intended use of this system regards for reducing noise level that is added during audio steganography process. The aim was to study the effects of sampling rate on audio cover during the process of digitization. The motivation came from our human auditory system (HAS) which is sensitive towards distortions added during steganography process and making the process suspicious. We first show how to embed the text data into audio file by LSB embedding techniques by applying cipher key. Basic audio sampling is discussed. We further segment audio by using Nyquist–Shannon sampling theorem. The report concludes that our system successfully preforms audio steganography with decreased noise level in terms of Signal to Noise Ratio (SNR) when sampled at the rate proposed in Nyquist–Shannon techniques.