M Pallavi

Bio: M Pallavi is an academic researcher from Siddaganga Institute of Technology. The author has contributed to research in topics: Variety (cybernetics) & Artificial intelligence. The author has an hindex of 1, co-authored 1 publications receiving 3 citations.

Study and analysis of ECG compression algorithms

Abstract: Electrocardiogram (ECG) is one testing method for measuring electrical activity of heart. ECG is the graphical representation of the electrical signal generated from heart. Heart is an organ of human which pump blood for the entire body. It require huge amount of data to store and transmit these ECG signals. So it is necessary for compression of the ECG signals. In few last years, many algorithms have evolved to compress the ECG signals, in that four algorithms such as Amplitude Zone Time Epoch Coding algorithm (AZTEC), Turning Point (TP), compression by using Discrete Cosine Transform (DCT) and Backward difference and compression by using Empirical Mode Decomposition (EMD) are implemented and explained detail. The performance of all the algorithms are analyzed by using two parameters namely, Percent Root means square Difference (PRD) and Compression Ratio (CR). The CR and PRD are calculated for all 48 ECG records from the database of MIT-BIH arrhythmia. Finally the CR and PRD values are compared with all the four algorithms. The experimental result indicates that the compression by EMD gives better CR and PRD compare to all other methods.

Sentiment Analysis Using Machine Learning

Abstract: Abstract: Sentiment analysis falls within the category of analytics research. This can make sense by reading raw data using computational methods. This is what analysis is. Written expressions that are neutral, unfavourable, or indifferent can be assessed using sentiment analysis. People use a variety of social media platforms, including Facebook and Twitter, which is a useful tool for gauging public sentiment. This uses a variety of machine learning techniques. We have considered a variety of sentiment analysis techniques in this study. Using machine learning classifiers, sentiment analysis has been carried out. Users' tweets are categorised as having "positive" or "negative" sentiment using polarity-based sentiment analysis and deep learning models. Sentiment Analysis, one of the branches of computer science that is now gaining the most ground.

Energy-Efficient Intelligent ECG Monitoring for Wearable Devices

Abstract: Wearable intelligent ECG monitoring devices can perform automatic ECG diagnosis in real time and send out alert signal together with abnormal ECG signal for doctor's further analysis. This provides a means for the patient to identify their heart problem as early as possible and go to doctors for medical treatment. For such system the key requirements include high accuracy and low power consumption. However, the existing wearable intelligent ECG monitoring schemes suffer from high power consumption in both ECG diagnosis and transmission in order to achieve high accuracy. In this work, we have proposed an energy-efficient wearable intelligent ECG monitor scheme with two-stage end-to-end neural network and diagnosis-based adaptive compression. Compared to the state-of-the-art schemes, it significantly reduces the power consumption in ECG diagnosis and transmission while maintaining high accuracy.

Arrhythmia Classifier Using a Layer-wise Quantized Convolutional Neural Network for Resource-Constrained Devices

Abstract: An arrhythmia diagnosis neural network can perform real-time diagnosis through continuous monitoring, and it can warn against potential risks. Moreover, these networks can be installed in resources-constrained devices like wearable devices. However, the existing neural networks suffer from high memory consumption and power consumption, which limit their application in low-power resources-constrained devices. Here, we proposed a novel neural network classifier to classify 17 different rhythm classes using 1,000 long-duration electrocardiograms, achieving a classification accuracy of 95.72%, which is 4.32% higher than current state-of-the-art methods. Additionally, we proposed a layer-wise quantization method based on the greedy algorithm and compared it to other quantization methods. The proposed classifier achieved a 95.39% classification accuracy and reduced memory consumption by 15.5 times. Our study realizes a neural network with high performance and low resources consumption, and it demonstrates the possibility of implementing neural networks in resources-constrained devices for continuous monitoring, real-time diagnosis, and potential risk warnings.

A novel compression framework using energy-sensitive QRS complex detection method for a mobile ECG

Abstract: Dear editor, Novel wearable applications provide improved data compression for reduced power consumption [1, 2]; however, real-time monitoring of a single source electrocardiogram (ECG) signal leads to extended data usage of 2.77 GB per day. The Q wave, R wave, and S wave (QRS) complex seen on an ECG is the basis for the automatic determination of heart rate and an entry point for the classification schemes of the cardiac cycle [3]. Therefore, it is necessary that the compressed data should retain maximum QRS area information, which is the origin of the concept of areas of interests in compressed sensing [4]. Currently, most researches concentrate on developing methods for efficient extraction of QRS waves without redundant calculations from the complex and noisy ECG signals and compression frameworks. This study aims to propose a novel framework that includes an energy-sensitive QRS complex detection algorithm based on simplified empirical mode decomposition and Hilbert transform (EMD-HT) method and a multi-compression ratio CS strategy. The proposed framework encompasses three advantages: (a) In comparison with a previous study [4], the proposed method uses percentage root-mean-square difference (PRD) and improved reduction quality under the same compression ratio (CR); (b) it can accurately locate the interested area of the QRS cluster, which solves the interference problem of stationary noise and; (c) it is indicated that EMD-based compression results in a better CR and PRD than the other methods [2]. Considering the specific conditions for the wearable devices, we employ a simplified EMD algorithm whose operation for detecting interested area for ECG reconstruction is characterized by sufficient accuracy. Using the EMD-HT method, the proposed framework can overcome the limitations associated with stationary noise interference and thus, can achieve precise positioning.