DJDuraiswamy Jothinath Jagannath

Duraiswamy Jothinath Jagannath

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Duraiswamy Jothinath Jagannath has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Retracted

    RETRACTED: Deep reinforcement learning‐based precise prediction model for Smart M‐Health system

    by Duraiswamy Jothinath Jagannath, Raveena Judie Dolly, James Dinesh Peter

    The use of Android mobile phones and other wireless technology in the field of healthcare infers to mHealth (mobile health). Modern Science and technological developments have paved way for better and more sophisticated solutions towards Smart mHealth systems and preventive Smart Healthcare services for disease—treatment, surveillance, management of chronic disease and tracking epidemic outbreaks. Thus, the mHealth data can be collected from various end users, deposited in repository, perform analysis and suitable Smart Healthcare services can be made accessible to end users, anytime, anywhere, over the internet. This can be achieved by incorporating the methodologies of advanced Soft Computing methodologies, data communication, cloud storage and cloud computing, big data analysis, artificial intelligence, computer communication/networking and other engineering techniques. However, the analysis of such huge volumes of data and to provide precise Smart Healthcare services is a million‐dollar question. This research article exposes a Deep Reinforcement Learning model for precisely predicting the disease and offer precise Smart m‐Healthcare services to the end users. This research provides an intensive experimental analysis and investigation using synthetic health parameters that were simulated using various mHealth sensors. The dataset includes 15 varieties of mHealth metrics with a total dataset size of 285.


  • Software-Defined Networking Routing Algorithms: Issues, QoS and Models

    by G. Shine Let, C. Benin Pratap, D. J. Jagannath, D. Raveena Judie Dolly, L. Diana Evangeline


  • An IoT enabled smart healthcare system using deep reinforcement learning

    by Duraiswamy Jothinath Jagannath, Raveena Judie Dolly, Gunamony Shine Let, James Dinesh Peter

    Smart healthcare systems do exist with a variety of architectures. However, the hunt for better smart healthcare systems is more predominant. The cutting‐edge field of IoT (internet of things) and technological developments provide better solutions for smart healthcare systems using Sensor–Body Area Networks. Thus, the patient's sensor data can be collected, stored, analyzed, and suitable treatments can be offered, over the inter‐network, anytime, anywhere. The most complex part in such systems is the physician analysis of the huge volume of patient's data, to handle and prepare suitable diagnose and treatment for humanity. This article reveals a methodology of Deep Reinforcement Learning for smart healthcare decisions in an IoT interfaced Smart Healthcare–intelligent monitoring system. The system incorporates four layers, patient data collection, Edge computing, patient data transmission and Cloud computing. IoT is employed for automatic collection of Patient's data and for transmission of data, to data centers. Artificial intelligence techniques are used to analyze these data to provide suitable decisions, diagnosis, and treatment for those patients and humanity. Deep Reinforcement Learning provides the platform for smart decisions, diagnosis, and treatment. The investigation was experimented with synthetic simulated data of various BAN sensors. We developed a data set of size 286, which contains 21 different health parameters. After pre‐processing, these data were stored in the Amazon web services (AWS) cloud server using (message queue telemetry and transport) MQTT–IoT protocol. Initially, the Deep Q‐Network (DQN) was imposed to the training algorithm. The methodology was examined in PyTorch using a single GTX 1080 Ti X GPU with the training data sizes from 27 to 1536. The training time was about 10,000 to 90,000 s for training 500 epochs. In the high dimensional action space environment, the algorithm responded slowly to analyze, explore, and determine effective healthcare strategies. The systems convergence response of estimated hidden health state (g') and the actual health state (g) for the 21 different health parameters were estimated, whose values range from 0 to 1. The system responded with smart decisive interventions, which were good and close to that of a Physician's decision. The proposed methodology is definitely a promising solution for a smart and economic telemedicine.


  • A Novel Adaptive Frame Determination Methodology with Fixed and Adaptive Thresholds Using Affine Motion Parameter for Video Quality Enhancement

    by D. Raveena Judie Dolly, G. Josemin Bala, J. Dinesh Peter, D. J. Jagannath

    The present epoch of technology suffers owing to the shortage of novel methodologies in obtaining a better quality compressed video. Diverse exploration has aroused in espousing Group of pictures aiming at Intra, Bi-directional & Predicted frame identification for performing compression. The conventional GoP practices fixed frame pattern irrespective of the movement by the camera. This paper deals with the choice of adaptive frame identification by incorporating fixed and empirical values. The fixed values are chosen based on the various motion types. NSEW affine translation is incorporated to substitute B frames obtained from fixed and empirical threshold values with I or P frame. Motion Estimation & warping using affine are preferred for compression and decompression to obtain the compressed data and the warped. Four metrics explicitly have been analyzed to demonstrate the superiority of the suggested procedure.

  • Open Access

    Assistive Methodologies for Parkinson's Disease Tremor Management—A Health Opinion

    by V. Dineshkumar, D. Raveena Judie Dolly, D. J. Jagannath, J. Dinesh Peter

    Assistive Methodologies for Parkinson's Disease Tremor Management—A Health Opinion


  • Retracted

    RETRACTED: Investigations on optimization techniques for stabilized clinical images

    by D. Raveena Judie Dolly, J. Dinesh Peter, D. J. Jagannath

    Clinical imaging is the most vital part for precise medical analysis by physicians. Huge number of researcher's explore various possibilities to come up with an optimal solution. Innumerable innovative progressions aligned to medical images are radically growing. This article emphasizes on the various optimization techniques which helps the clinicians to have a clear picture on the region of interest. Unique modalities provide detailed information on a specific area, such sequences are made to stabilize to reduce the artefacts and they are allowed to pass through the processing stage for fusing so that the doctors can envisage the common features of CT and MRI. Further, Registration of the images is initialized to effectively align and overlay for appropriate determination by the physicians. To ensure the quality, essential optimization is performed and the assessments are performed subjectively and objectively. The proposed method is instigated with appropriate optimization procedures and is found that it outperforms the existing approaches subjectively and objectively. The proposed approach is also statistically investigated to prove its predominance. Quantum computation is being extensively used for research in medical applications. The computation complexity becomes less while adopting quantum processing.

  • Deep learning strategies for foetal electrocardiogram signal synthesis

    by D.J. Jagannath, D. Raveena Judie Dolly, J. Dinesh Peter


  • A novel Bayesian deep learning methodology for enhanced foetal cardiac signal mining

    by D. J. Jagannath, D. Raveena Judie Dolly, J. Dinesh Peter

    Cardiac defects are amongst the most common birth defects. Cardiac diagnosis is indispensably imperative in the foetal stage as it might help provide an opportunity to plan and manage the baby during Antepartum and Intrapartum stages, when the baby is born. It is from the Antepartum stage where the foetal electrocardiogram (fECG) signal can actually be detected. At present, monitoring the foetus is completely focused on the heart rate. Currently fECG analysis is used in the clinical domain to analyse heart rate and the allied variations. Analysis using the morphology of the fECG is generally not undertaken for cardiac-anomaly populations. The ultimate reason for this scenario is due to unavailability in technology to yield trustworthy fECG measurements with desired quality required by Physicians. A novel hybrid methodology called BDL (Bayesian Deep Learning) methodology is proposed. The BDL includes a Bayesian filter and a deep learning (DL) Artificial Intelligent neural network for maternal electrocardiogram (mECG) elimination and non-linear artefacts removal to yield high quality non-invasive fECG signal. The outcomes of the research by the proposed BDL system proved valuable and provided high quality fECG signal for efficient foetal diagnosis.