Auto Encoders based Neural Networks to Predict Faultiness of VLSI Circuits
Smart Electrical Vehicle
Development of Smart Electronic System to Implement Smart Home
Multilingual Speaker Identification System through Multiple Features Analysis of Speech Signal in Multilingual Environment
Photographing a Black Hole
Development of an Intelligent Battery Charging System Based on PIC16F877A Microcontroller
Blockchain 3.0: Towards a Secure Ballotcoin Democracy through a Digitized Public Ledger in Developing Countries
Brief Introduction to Modular Multilevel Converters and Relative Concepts and Functionalities
Fetal ECG Extraction from Maternal ECG using MATLAB
Detection of Phase to Phase Faults and Identification of Faulty Phases in Series Capacitor Compensated Six Phase Transmission Line using the Norm of Wavelet Transform
A Novel Approach to Reduce Deafness in Classical Earphones: MUEAR
A novel mathematical ECG signal analysis approach for features extraction using LabVIEW
Filtering of ECG Signal Using Adaptive and Non Adaptive Filters
Application of Polynomial Approximation Techniques for Smoothing ECG Signals
A Novel Approach to Improve the Wind Profiler Doppler Spectra Using Wavelets
Wearable Health Monitoring Smart Gloves
There are various types of noises in an automobile. It includes tire noises, belt noises, noises due to braking systems, and engine. The engine noise reduction techniques play a major role to improve the life and efficiency of the engine. However, these noises need to be reduced and cancelled in a real-time environment using statistical Digital Processing techniques. This paper proposes the use of adaptive filters using LMS and RLS algorithms to cancel the engine noise. The performance analysis is done using MATLAB through proven simulation results and by comparing the parameters like Mean Square Error, Convergence speed, and Stability of the system.
In this paper, the authors analyzed the performances of well known array signal processing algorithms for adaptive beam forming namely, Sample Matrix Inversion (SMI), and Least Mean Square (LMS) algorithms. From the simulation results, it is observed that, for SMI as the number of user increases, the main lobe spreads in all the directions. As a result of this, beam forming in the user direction may not be accurate. To overcome this problem, LMS algorithm can be used. The LMS algorithm is a best choice in most of the commercial wireless applications due to its low complexity. 5G and beyond 5G networks require beam forming algorithms with high directivity and fast converengence rate. Hence, in this work, they have modified the LMS algorithm to improve the converengence rate and then they applied improved LMS algorithms to horizontal-vertical Uniform Linear Array (ULA). This is also called as two dimensional ULA (2D-ULA). Hence these algorithms are called as 2D-LMS1 and 2D-LMS2. Simulation results show that the proposed algorithms have improved convergence rate, directivity as compared to conventional LMS algorithm. Hence these algorithms are best suited for 5G and beyond mobile communications.
The malignant melanoma is a deadly form of the skin cancer in humans. It develops quickly, and effortlessly metastasizes. Late identification of the dangerous melanoma is in charge of 75% of deaths connected with skin growths. Early diagnosis is an important factor that increases chances of successful cure as there is a rapid course of the disease. Computer analysis and image processing are efficient tools supporting quantitative medical diagnosis. Therefore it is relevant to develop computer based methods for dermatological images. So, in order to get the effective results and information about distinctive stages of the infected portion, one needs the corresponding features of that particular area in order to decide the stage. So, the feature extraction phase is hugely dependent on the region detected which has the disease. So appropriate segmentation algorithm is required which can affectivity detect the skin melanoma pixels in the information image. In this work, an algorithm is presented which can adequately detect the pixels having melanoma region and ordinary skin. The proposed work uses a hybrid technique in which space complexity of intensity values is reduced by taking pre-segmentation results from Gaussian mixtures posterior algorithm. The algorithm first chooses some candidates from different regions of the images having distinctive intensity values and then Gaussian models are built from the chosen places by taking their neighborhood pixels. After this, posterior testing is carried out to get pre-segmented results. In the end neural network based training and testing is implemented to get final segmentation results. Experimental results show that the proposed algorithm gives 98% accuracy results on the tested database images.
In this generation of Internet of Things (IoT), a lot of image processing algorithms are applied on high resolution displays which are used in mobile devices of various sizes. It becomes vital to design a high speed and low-power image processing algorithm for high speed transmission and processing of data. This paper proposes a progressive design of 2D-DCT and quantization which is one of the abundantly used image processing algorithm and is realized using Dadda and Vedic multipliers which work in real time exceptionally in both parallel and pipelined process for calculating 2D-DCT. The high speed, accuracy and less hardware complexity of the proposed systems outclass with those of other presentday systems. The frequency of proposed system is increased to 185.048 which is 19% when compared to the prevailing systems. The proposed system architecture can be easily modified to compute 2D-IDCT which decompress the coefficients to get the image value.
ECG is an important signal which is most commonly used for the diagnosing of various heart diseases. The analysis of an ECG signal includes preprocessing and feature extraction. Signal processing of an ECG wave, which includes noise reduction and R-Peak detection of the signal, is one of the most important part for its analysis. The presented paper discusses several techniques of noise reduction and R-Peak detection which were proved effective in last few decades. Efficiency of various methods can be defined in terms of detection error rate. Latest research has shown very effective results with error rate less than 0.3%.