The approximate computing paradigm emerged as a key alternative for trading off accuracy and energy efficiency. Error-tolerant applications, such as multimedia and signal processing, can process the information with lower-than-standard accuracy at the circuit level while still fulfilling a good and acceptable service quality at the application level. The automatic detection of R-peaks in an electrocardiogram (ECG) signal is the essential step preceding ECG processing and analysis. The Haar discrete wavelet transform (HDWT) is a low-complexity pre-processing filter suitable to detect ECG R-peaks in embedded systems like wearable devices, which are incredibly energy-constrained. This work presents an approximate HDWT hardware architecture for ECG processing at very high energy efficiency. Our best-proposal employing pruning within the approximate HDWT hardware architecture requires just seven additions. The use of a truncation technique to improve energy efficiency is also investigated herein by observing the evolution of the signal-to-noise ratio and the ultimate impact in the ECG peak-detection application. This research finds that our HDWT approximate hardware architecture proposal accepts higher truncation levels than the original HDWT. In summary: Our results show about 9 times energy reduction when combining our HDWT matrix approximation proposal with the pruning and the highest acceptable level of truncation while still maintaining the R-peak detection performance accuracy of 99.68% on average.

Approximate Pruned and Truncated Haar Discrete Wavelet Transform VLSI Hardware for Energy-Efficient ECG Signal Processing

Owing to changing climatic conditions, crops often get affected, as a result of which agricultural yield decreases drastically. If the condition gets worse, crops may get vulnerable towards infections caused by fungal, bacterial, virus, etc. diseases causing agents. The method that can be adopted to prevent plant loss can be carried out by real-time identification of plant diseases. Our proposed model provides an automatic method to determine leaf disease in a plant using a trained dataset of pomegranate leaf images. The test set is used to check whether an image entered into the system contains disease or not. If not, it is considered to be healthy, otherwise the disease if that leaf is predicted and the prevention of plant disease is proposed automatically. Further, the rodent causing disease is also identified with image analysis performed on the image certified by biologists and scientists. This model provides an accuracy of the results generated using different cluster sizes, optimized experimentally, with image segmentation. Our model provides useful estimation and prediction of disease causing agent with necessary precautions.

Prediction Model for Automated Leaf Disease Detection & Analysis

In this study, we are proposing a practical way for human identification based on a new biometric method. The new method is built on the use of the electrocardiogram (ECG) signal waveform features, which are produced from the process of acquiring electrical activities of the heart by using electrodes placed on the body. This process is launched over a period of time by using a recording device to read and store the ECG signal. On the contrary of other biometrics method like voice, fingerprint and iris scan, ECG signal cannot be copied or manipulated. The first operation for our system is to record a portion of 30 seconds out of whole ECG signal of a certain user in order to register it as user template in the system. Then the system will take 7 to 9 seconds in authenticating the template using template matching techniques. 44 subjects‟ raw ECG data were downloaded from Physionet website repository. We used a template matching technique for the authentication process and Linear SVM algorithm for the classification task. The accuracy rate was 97.2% for the authentication process and 98.6% for the classification task; with false acceptance rate 1.21%.

/pdf/utilizing-ecg-waveform-features-as-new-biometric-4tbegrqn1q.pdf

Utilizing ECG Waveform Features as New Biometric Authentication Method

The paper presents a low power ECG signal processing ASIC chip design to extract the ECG features for wearable health system. The new design is used for the diagnosis of ECG arrhythmia based on features. The design consists of an acquisition unit, analog to digital conversion, pre-processing stage and feature extraction stage. The proposed design is advantage as it acquires both analog and digital ECG data. In addition to that the power consumed is less and area occupied is optimum. The proposed ASIC is designed using 90nm Technology.

Design of a low power ECG signal processor for wearable health system-review and implementation issues

The goal of this paper is to develop a novel technique to validate diagnosed respiratory noises in infants and children with high accuracy and reduced time consumption. A large number of recorded lung sounds are acquired with varied cases of normal and abnormal respiratory sounds. Wavelet-based Dynamic Time Warping technique is utilized in the proposed approach and the recognition accuracy was found to be above 88% in average. All the sounds represent infants and children below 13 years old and collected from AUCH-Alexandria, Egypt.

A novel technique for validating diagnosed respiratory noises in infants and children

An Electrocardiogram is a significant recording for measuring the electrical activity of the heart. The Feature Extraction of an ECG signal plays a significant role in diagnosing most of the cardiac diseases. This paper concentrates on the algorithm for extraction of the fiducial points of an ECG signal and its performance analysis. To analyze these signals, time-frequency domain is the best suited method. In order to analyze these physiological and non-stationary signals, a Wavelet Transform in which Discrete Wavelet Transform is preferred to Fast Fourier and Short time - Fourier transform. A Discrete Wavelet Transform (DWT) is employed for the better understanding of the ECG signal in Time -Frequency plane with (Haar) as a Mother Wavelet function. The Samples are taken from the available ECG databases PTBDB & QTDB and are checked against the CSE tolerance limits. Since, real time signals like ECG can be easily processed using a DSP processor, the algorithm is targeted onto a ADSP - 2181 to reduce the complexity of the code and obtain optimized power levels.

K. Shaloam Suvarna Sujan

Papers

Performance analysis for the Feature Extraction algorithm of an ECG signal