Denoising Electrocardiogram Signals using Multiband Filter and its Implementation on FPGA
Download PDF file: (1.12 MB)
Abstract: The electrocardiogram (ECG) signal carries vital information related to cardiac activities. While measuring ECG using electrodes, the signal is contaminated with powerline interference (PLI) from harmonics, baseline wandering (BW), motion artefacts (MA) and high frequency (HF) noise. The extraction of the ECG signal, without the loss of useful information from the noisy environment, is required. Therefore, the selection and implementation of an efficient filter design is proposed. The Finite Impulse Response (FIR)-based multiband needs separate digital filters, such as Lowpass, Highpass, and Bandstop Filter in cascade. The coefficients of the FIR multiband filter are optimised using a least squares optimisation method and realised in a direct form symmetrical structure. The capability of the proposed filter is evaluated on a Physionet ECG ID database, having records of inherent noisy ECG signals. The performance is also verified by measuring the power spectrum of the noisy and filtered ECG waveform. Also, the feasibility of the proposed multiband filter is investigated on Xilinx ISE and the design is implemented on a field programmable gate array (FPGA) platform. A low order simple multiband filter structure is designed and implemented on the reconfigurable FPGA device.
Keywords: Baseline wandering (BW), Electrocardiogram (ECG), Field program¬mable gate array (FPGA), Multiband filter, Motion artefact (MA), Power line interference (PLI).
A Study on Transmission Coil Parameters of Wireless Power Transfer for Electric Vehicles
Download PDF file: (1.16 MB)
Abstract: Electric vehicles (EVs) are becoming more popular as people become more concerned about global issues, such as fossil fuel depletion and global warming, which cause severe climate change. Wired charging infrastructure is inefficient because it requires the construction of one charging station for each electric vehicle. As a result, wireless power transfer via magnetic coupling, which is small, compact, and may be placed underground, is a promising technology for the future of charging electric vehicles. One of the disadvantages of wireless power transfer is that efficiency drops rapidly as air gaps grow larger, and it is particularly sensitive to other electrical characteristics such receiver unit capacitance. The purpose of this paper is to investigate the coil parameter, more specifically the outer diameter of wireless power transfer coil effects on the wireless power transfer efficiency at various air gaps and receiver capacitance values for EV applications. The simulations show that a larger outer diameter coil has a better power transfer efficiency at larger air gaps and a more stable range.
Keywords: Wireless power transfer, Electric vehicles, Air gap, Coil.
Modeling and Realization of Photovoltaic Simulator Based on a Buck DC-DC Converter
Download PDF file: (1.02 MB)
Abstract: This paper presents a simple accurate model for photovoltaic (PV) modules suitable for implementation by digital signal processors (DSPs). A buck DC-DC converter is employed to realize the PV characteristic appropriately. Three controllers set forth for current control according to PV voltage to achieve fast and accurate convergence. Computer simulation results are presented to investigate the effectiveness of the proposed PV system. Moreover, a practical setup is made and the proposed method using the obtained model for different temperatures and solar irradiations is tested in MATLAB/Simulink environment.
Keywords: PV module, PV modeling, PV simulator, Solar panel, Buck DC-DC converter.
Effect of Defective NPC Three Level Inverter on Nonlinear Command of Induction Motor
Download PDF file: (1.11 MB)
Abstract: Speed Induction Motor (IM) control is an area of research that has been in evidence for some time now. In this paper, a nonlinear controller is presented for the induction motor drives. The nonlinear controller is designed based on an input-output feedback linearization control technique. The input-output feedback linearization control decouples the flux from the speed control and makes the synthesis of linear controllers possible. This article presented input-output linearization control of the induction motor associated with NPC three level inverter defective, the inverter faults are usually caused by operating faults in the switch elements. Switching defects occur in rectifier diodes, the capacitor and inverter IGBT switches. The inverter switches defected reduce the performance of the motor, in our study. We applied the input-output linearization control to test their robustness and performance for detection of fault influence on the physical parameters of the motor, for this purpose, we applied two faults, we started by creating a fault in two switches K1 and K7 which are in the first and second arm of the inverter. Then we created a fault in the three switches K1, K7 and K10 which are in the three arms of the inverter. The simulation results are done by the use of Matlab/Simulink that show the detection, fault effect on input-output linearization control of the different induction motor responses.
Keywords: Induction motor, Input Output linearization control, Switch fault Inverter, Performance, Robustness.
Early Detection Mechanism for Sybil Attacks on Wireless Multimedia Sensor Networks
Download PDF file: (1.04 MB)
Abstract: The rapid developments in wireless multimedia sensor networks (WMSNs) have increased the demand for an efficient method of safeguarding multimedia data from attackers. As data are transmitted over a wireless medium, the authentication process needs to be provided with some efficient detection and prevention methods. The Sybil attack is one of the most common and involves replicating the identity of an original node in the network and behaving like a true node in order to retrieve/destroy information using this fake identity. An efficient enhanced random password comparison technique is proposed to detect and prevent Sybil attacks. The results of simulations indicate that the proposed method detects this type of attack more efficiently than existing methods. In addition to early detection, our application increases the throughput and reduces the average delay with an enhanced true detection rate. The identification of this malicious activity in its initial phases increases the efficiency of the system in terms of the data transmission process.
Keywords: Attacks, Sensor, Node, Sybil, Security, WMSN.
Experimental Analysis of Filtering-Based Feature Selection Techniques for Fetal Health Classification
Download PDF file: (896.34 KB)
Abstract: Machine learning techniques enable computers to acquire intelligence through learning. Trained machines can carry out various tasks, such as prediction, classification, clustering, and recommendation, within a wide variety of applications. Classification is a supervised learning technique that can be improved using feature selection techniques such as filtering, wrapping, and embedding. This paper explores the impact of filtering-based feature selection techniques on classification methods, and focuses on an analysis of correlation-based filtering techniques based on Pearson, Spearman, and Kendall rank correlation. Similarly, we explore the impacts of using statistical filtering techniques such as mutual information, chi-squared score, the ANOVA univariate test, and the univariate ROC-AUC. These filtering techniques are evaluated by implementing them with the k-nearest neighbor, support vector machine, decision tree, and Gaussian naïve Bayes classification methods. Our experiments were carried out using a fetal heart rate dataset, and the performance of each combination of methods was measured based on precision, recall, F1-score, and accuracy. An analysis of the experimental results showed that the performance metrics for the Gaussian naïve Bayes and k-nearest neighbor methods were improved by 3% through the use of the statistical feature selection technique, and a 4% improvement was observed for the decision tree and support vector machine methods using a correlation-based filtering technique. Of the statistical feature selection techniques, ANOVA and ROC-AUC were the best as they improved the accuracy by 92%; compared to the other correlation techniques, the Spearman correlation coefficient gave the best results, as it also improved the accuracy by 92%.
Keywords: Fetal ECG, Machine Learning, Feature Selection, Supervised Learning, Classification, Accuracy.
Feasibility Test of Activity Index Summary Metric in Human Hand Activity Recognition
Download PDF file: (571.53 KB)
Abstract: Activity monitoring is a technique for assessing the physical activity that a person undertakes over some time. Activity Index (AI) is a metric that summarizes the raw measurements from tri-axial accelerometers, often used for measuring physical activity. Our research compared the Activity Index for different activity groups and hand usage . We also tested this metric as a classification feature, and how different data acquisition and segmentation parameter configurations influence classification accuracy. Data acquisition was done with a previously developed system that includes a smartwatch on each wrist and a smartphone placed in the subject’s pocket; raw data from smartwatch accelerometers was used for the analysis. We calculated the Activity Index for labeled data segments and used ANOVA1 statistical test with Bonferroni correction. Significant differences were found between cases of hand usage (left, right, none, both). In the next analysis phase, the Activity Index was used as the classification feature with three supervised machine learning algorithms – Support Vector Machine, k-Nearest Neighbors, and Random Forest. The best accuracy (measured by F1 score) of classifying hand usage was achieved by using the Random Forest algorithm, 50 Hz sampling frequency, and a window of 10 s without overlap for AI calculation, and it was 97%. On the other hand, the classification of activity groups had a low accuracy, which indicated that a specific activity group can’t be identified by using only one simple feature.
Keywords: Activity index, Accelerometry, Smartwatches, ANOVA1, Classification, Machine learning, Random Forest.
Hilbert Spectrum based features for Speech/Music Classification
Download PDF file: (1.03 MB)
Abstract: Automatic Speech/Music classification uses different signal processing techniques to categorize multimedia content into different classes. The proposed work explores Hilbert Spectrum (HS) obtained from different AM-FM components of an audio signal, also called Intrinsic Mode Functions (IMFs) to classify an incoming audio signal into speech/music signal. The HS is a two-dimensional representation of instantaneous energies (IE) and instantaneous frequencies (IF) obtained using Hilbert Transform of the IMFs. This HS is further processed using Mel-filter bank and Discrete Cosine Transform (DCT) to generate novel IF and Instantaneous Amplitude (IA) based cepstral features. Validations of the results were done using three databases – Slaney Database, GTZAN and MUSAN database. To evaluate the general applicability of the proposed features, extensive experiments were conducted on different combination of audio files from S&S, GTZAN and MUSAN database and promising results are achieved. Finally, performance of the system is compared with performance of existing cepstral features and previous works in this domain.
Keywords: EMD, Hilbert Spectrum, Hilbert Huang Transform, Cepstral Features, Speech/Music Classification.