V G Sujadevi

Anomaly Detection in Phonocardiogram Employing Deep Learning

Phonocardiogram (PCG) is the recording of heart sounds and murmurs. PCG compliments electrocardiogram in detection of heart diseases especially in the initial screenings due to its simplicity and low cost. Detecting abnormal heart sounds by algorithms is important for remote health monitoring and other scenarios where having an experienced physician is not possible. While several studies exist, we explore the possibility of detecting anomalies in heart sounds and murmurs using Deep-learning algorithms on well-known Physionet Dataset. We performed the experiments by employing various algorithms such as RNN, LSTM, GRU, B-RNN, B-LSTM and CNN. We achieved 80% accuracy in CNN 3 layer Deep learning model on the raw signals without performing any preprocessing methods. To our knowledge this is the highest reported accuracy that employs analyzing the raw PCG data.

Denoising of phonocardiogram signals using variational mode decomposition

Recent advances in signal processing and the revolution by the mobile technologies have spurred several innovations in all the areas and albeit more so in home based tele-medicine. We used variational mode decomposition (VMD) based denoising on large-scale phonocardiogram (PCG) data sets and achieved better accuracy. We have also implemented a reliable, external hardware and mobile based phonocardiography system that uses VMD signal processing technique to denoise the PCG signal that visually displays the waveform and inform the end-user and send the data to cloud based analytics system.

Imu sensor based self stabilizing cup for elderly and parkinsonism

Hand tremor is a neurological disorder that affects people with Parkinsons disease and elderly affecting day to day activities. Hand vibration is a rhythmic muscle movement that occurs due to disorder in the motor system of human body. There are no permanent treatment options available. The subjects typically do life style modifications to cope up with the disease. In this work, we propose a wearable auto stabilizing cup holder that helps in performance the routine activities such as drinking water etc. The proposed system uses Inertial measurement unit (IMU) sensor and actuators for stabilizing the cup when under severe hand vibration. Dynamic modelling of the system is performed including slosh dynamics. A PID controller performance under disturbance and Cross-coupling effect has been analyzed. The prototype design is implemented using solid works and the controller simulation is performed using MATLAB Simulink. Initial tests show satisfactory performance of the system.

Real-Time Detection of Atrial Fibrillation from Short Time Single Lead ECG Traces Using Recurrent Neural Networks

Atrial fibrillation (AF) is the predominant type of cardiac arrhythmia affecting more than 45 Million individuals globally. It is one of the leading contributors of strokes and hence detecting them in real-time is of paramount importance for early intervention. Traditional methods require long ECG traces and tedious preprocessing for accurate diagnosis. In this paper, we explore and employ deep learning methods such as RNN, LSTM and GRU to detect the Atrial Fibrillation (AF) faster in the given electrocardiogram traces. For this study, we used one of the well-known publicly available MIT-BIH Physionet dataset. To the best of our knowledge this is the first time Deep learning has been employed to detect the Atrial Fibrillation in real-time. Based on our experiments RNN, LSTM and GRU offer the accuracy of 0.950, 1.000 and 1.000 respectively. Our methodology does not require any de-noising, other filtering and preprocessing methods. Results are encouraging enough to begin clinical trials for the real-time detection of AF that will be highly beneficial in the scenarios of ambulatory, intensive care units and for real-time detection of AF for life saving implantable defibrillators.

A Novel Cyclic Convolution Based Regularization Method for Power-Line Interference Removal in ECG Signal.

Applying signal processing to bio-signal record such as electrocardiogram or ECG signals provide vital insights to the details in diagnosis. The diagnosis will be exact when the extracted information about the ECG is accurate. However, these records usually gets corrupted/contaminated with several artifacts and power-line interferences (PLI) thereby affects the quality of diagnosis. Power-line interferences occurs in the range close to 50 Hz/60 Hz. The challenge is to remove the interferences without altering the original characteristics of ECG signal. Since the ECG signals frequency range is close to PLI, several articles discuss PLI removal methods which are mathematically complex and computationally intense. The present paper proposes a novel PLI removal method that uses a simple optimization method involving a circular convolution based ({ell _2})-norm regularization. The solution is obtained in closed form and hence computationally simple and fast. The effectiveness of the proposed method is evaluated using output signal-to-noise-ratio (SNR) measure, and is found to be state-of-the-art.

Effortless exchange of personal health records using near field communication

Personal health records (PHR) either resides in the hospital or resides with the patient in the form of paper-based records. When PHR is in the printed form it is bulky and inconvenient to carry by the user. Since smart phones has become ubiquitous and a necessity in day to day life, and most of them are equipped with contactless near field communication (NFC), we propose to exploit the inherent advantages of NFC or near field communication to transfer the personal health records from health care settings to patients smart phone and vice versa. This solution will make it convenient for the patient to carry the personal health records with them. This also achieve the quick access to PHR during medical emergencies, that ensures faster intervention. Also it will empower the patient to always carry his or her personal health records with them that come in handy during any medical emergencies. In this paper we prove that peer-to-peer mode in NFC that uses NFC and Bluetooth technologies can be leveraged for secure and seamless transfer of the personal health records from one healthcare network to another. We have analyzed and presented the advantages and disadvantages of this method and demonstrated the effectiveness of a novel method that uses NFC for sharing Personal Health records.