Showing papers in "WSEAS Transactions on Signal Processing archive in 2021"

Deep Learning Based on CNN for Emotion Recognition Using EEG Signal

Abstract: Emotion recognition based on brain-computer interface (BCI) has attracted important research attention despite its difficulty. It plays a vital role in human cognition and helps in making the decision. Many researchers use electroencephalograms (EEG) signals to study emotion because of its easy and convenient. Deep learning has been employed for the emotion recognition system. It recognizes emotion into single or multi-models, with visual or music stimuli shown on a screen. In this article, the convolutional neural network (CNN) model is introduced to simultaneously learn the feature and recognize the emotion of positive, neutral, and negative states of pure EEG signals single model based on the SJTU emotion EEG dataset (SEED) with ResNet50 and Adam optimizer. The dataset is shuffle, divided into training and testing, and then fed to the CNN model. The negative emotion has the highest accuracy of 94.86% fellow by neutral emotion with 94.29% and positive emotion with 93.25% respectively. With average accuracy of 94.13%. The results showed excellent classification ability of the model and can improve emotion recognition.

Interference Cancellation for MIMO Systems Employing the Generalized Receiver with High Spectral Efficiency

Abstract: In this paper, we investigate the performan-ce in terms of symbol error probability (SEP) of multiple-input multiple-output (MIMO) systems employing the ge-neralized receiver with high spectral efficiency. In particu-lar, we consider the coherent detection of M-PSK signals in a flat Rayleigh fading environment. We focus on spectrally efficient MIMO systems where after serial-to-parallel con-version, several sub-streams of symbols are simultaneously transmitted by using an antenna array, thereby increasing the spectral efficiency. The reception is based on linear mi-nimum mean-square-error (MMSE) combining, eventually followed by successive interference cancellation. Exact and approximate expressions are derived for an arbitrary nu-mber of transmitting and receiving antenna elements. Sim-ulation results confirm the validity of our analytical meth-odology.

A Novel Deep Learning Architecture for Image Hiding

Abstract: Watermarking is a today's digital hiding technique within certain electronic content: for example, message, image, video, or audio recordings. Recent times, it was created as a modern copyright security tool. The pattern in zero watermarking technique isn't really inserted directly in the cover image, but has a logical relation with that cover image. In this article, we propose a powerful convolution neural Networks (CNN) and deep learning algorithm-based-watermarking technique in which the CNN produces robust inherent selected features and is merged with the XOR activity of host's watermark sequence. The outcomes of our proposed method present the courage of the watermark counter to many typical image processing techniques.

Three-Wheeled Omnidirectional Robot Localization in RFID-Tag Environments using UFIR Filtering

Abstract: This paper describes a way to improve the indoor navigation of mobile robots using radio frequency identification (RFID) technology. A net of RFID tags is deployed in the navigation space. A measurement system measures distances from the tags to the robot with in the presence of the firstorder Markov-Gauss colored measurement noise (CMN) and is combined with a digital gyroscope to measure the robot heading. To increase the localization accuracy, the Kalman filter (KF) and unbiased finite impulse response (UFIR) modified for CMN are used. It is shown that the navigation system developed is more accurate than the basic one employing the standard KF and UFIR filter

Simple Closed Analytic Formulas for the Approximation of the Legendre Complete Elliptic Integrals K(k) and E(k) (and their First Derivatives)

Abstract: This paper describes the specifications of newly developed compact isolation transformers for signaling networks such as telecommunication installations and information installations. These networks can use isolation transformers to mitigate surges occurring on services. It means that isolation transformers are used to eliminate the affect of noise and common mode voltage. Also the isolation transformers provide lightning protection for these networks. As the specifications of conventional isolation transformers are not sufficient, small-sized isolation transformers were developed. The new isolation transformers offer high isolation withstand voltage (50kV, 1.2/50μs) with low insertion loss (0.5dB) in the transmission frequency band of 500Hz to 30 MHz. The weight is only 0.3kg and the size is only 6×6×5cm. Key-Words: isolation transformer, isolation withstand voltage, low insertion loss Received: February 25, 2020. Revised: November 3, 2020, Accepted: November 24, 2020. Published: December 3, 2020.

Research on the Denoising of the Beidou Carrier Signal based on EEMD Algorithm with Adaptive Reconstruction Optimizing of IMF Numbers

Abstract: The Beidou carrier signal is coupled into a certain noise during propagation and reception, and these noise will directly affect the processing procedure associated with it. To deal with the problem of the influence due to the manually setting the IMF (Intrinsic Mode Function) component number for the reconstruction signal, a new measuring index that used for finding the optimal IMF components to reconstruct the signal has been designed in this paper. The index has taken the shape of the signal, signal noise ratio and correlation index into consideration. Upon on the basis, an adaptive index optimization Ensemble Empirical Mode Decomposition (AIO-EEMD) algorithm has been proposed in this paper. To verify the validity of the algorithm, four different algorithms are used to denoised the collected Beidou signal. The experiment results show that the noise reduction using the AIO-EEMD method can not only automatically obtain the optimal IMF components number, but also has a significant advantage over the other three methods.

Real Time Implementation of Face Recognition based Smart Attendance System

Abstract: This research work addresses the issue of incorporating an automatic attendance system to the frame of an institution using face detection and recognition techniques. The proposed system aims at reducing computational time with available hardware to yield more efficient results. The proposed model utilizes Histogram Oriented Gradients and facial encodings derived from facial landmarks. It also addresses the problems related to accuracy of facial recognition and the resource requirement for quick, real-time facial recognition by applying multi-processing. The improvement in performance in terms of accuracy across two different methods, and the improvement in terms of time requirement for the same method using different strategies have also been documented for demonstration. The designed system demonstrates the effectiveness of task parallelization with a minimum amount of hardware desiderata. The system has been designed to an optimum self-sustaining ecosystem which can efficiently operate on its own accord and compute comprehensible feedback without the requirement of any third-party human interference. A Graphical User Interface has been incorporated into the system for maximum user comprehensibility

GNSS Signal Processing with EKF and UKF for Stationary User Position Estimation

Abstract: Precise and accurate estimation of state vectors is an important process during position determination. In this study, Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) of stationary user, state vectors defined in Earth Centered Inertial (ECI) coordinate system, accompanied by GNSS measurement data. It is aimed to make estimations with methods. EKF and UKF methods were compared with each other. In this study, the effects of nonlinear motion analysis and linearization methods on state vector estimations were investigated. Thanks to this study, estimations of the positioning information required during the specific tasks of many moving platforms have been made.

Distributed UFIR Filtering with Applications to Environmental Monitoring

Abstract: Environmental monitoring requires an analysis of large and reliable amount of data collected through node stations distributed over a very wide area. Equipments used in such stations are often expensive that limits the amount of sensing stations to be deployed. The technology known as Wireless Sensor Networks (WNS) is a viable option to deliver low-cost sensor information. However, electromagnetic interference, damaged sensors, and the landscape itself often cause the network to suffer from faulty links as well as missing and corrupted data. Therefore robust estimators are required to mitigate such effects. In this sense, the unbiased finite impulse response (UFIR) filter is used as a robust estimator for applications over WSN, especially when the process statistics are unknown. In this paper, we investigate the robustness of the distributed UFIR (dUFIR) filter with optimal consensus on estimates against missing and incorrect data. The dUFIR algorithm is tested in two different scenarios of very unstable WSN using real data. It is shown that the dUFIR filter is more suitable for real life applications requiring the robustness against missing and corrupted measurements under the unknown noise statistics.

QoS Scheduling Algorithm for Videoclips Denoising

Abstract: This article presents a general frame-work for scheduling videoclips denoising processes ensuring the quality of service (QoS). In general, a denoising algorithm has two phases which are run sequentially: the first one determines the noisy pixels in the videoclip frames and the second applies a median filtering over the each frame considering the only good pixels. In all such denoising algorithms, the first phase is run for multiple times depend on the noise power. The second phase also may be executed more than one time but this depends on the specific algorithm. The issue in such applications is the denoising process may not terminate within its deadline. The proposed solution adapts the execution time in such way so the deadline to be respected by determining the remaining time to the deadline before running each phase and reducing the number of runs in each phase in order to not exceed the deadline. The goals of the article are the following: presents the QoS scheduling algorithm and proposes an implementation solution of based on Blackfin microcomputer with support of Visual DSP kernel (VDK). The article is organized in 5 sections: a briefly introduction to set up the general context of quality of services in videoclips denoising applications and to present the original video processing algorithm, two sections that present the proposed solution and its VDK implementation, the performance evaluation and the conclusions.

Parallel Implementation of Nios Ii Multiprocessors, Cepstral Coefficients of Mel Frequency and MLP Architecture in Fpga: the Application of Speech Recognition

Abstract: Speech processing in real time requires the use of fast, reconfigurable electronic circuits capable of handling large amounts of information generated by the audio source. This article presents hardware implementations of a multilayer perceptron (MLP) and the MFCC algorithm for speech recognition. These algorithms have been implemented in hardware and tested in an on-board electronic card based on a reconfigurable circuit (FPGA). We also present a comparative study between several architectures of MLP and with the literature on the level of costs with regard to the surface of silicon, the speed and the computing resources required. Following the FPGA circuit modification, we created NIOSII processors to physically implement the architecture of ANN-type MLPs and MFCC speech recognition algorithms and perform real-time speech recognition functions.

Dimension Reduction Analysis of Signal Manifold for Vowels in Time and Frequency Domain

Abstract: In this paper, the LLE and ISOMAP algorithms in manifold learning are applied them to the analysis of vowel signals in time and frequency domain. Time domain simulation results show that the two dimensionality reduction methods can implement two-dimensional visualization of signals while preserving the high-dimensional manifold structure of original signals as much as possible. The time-frequency domain dimension reduction analysis of vowel signal manifold effectively solves the problem that high-dimensional speech signals can’t be intuitively felt, and provides a new potential way for signal classification. The frequency domain analysis is further optimized on the basis of time domain simulation. Because half of the amplitude values in DFT is used in the simulation, the two-dimensional manifold of the signal is roughly linearly distributed, which can effectively reduce redundancy and make the signal more compactly expressed in the frequency domain

One-Step Predictive H2 FIR Tracking under Persistent Disturbances and Data Errors

Abstract: Information loss often occurs in industrial processes under unspecified impacts and data errors. Therefore robust predictors are required to assure the performance. We design a one-step H2 optimal finite impulse response (H2-OFIR) predictor under persistent disturbances, measurement errors, and initial errors by minimizing the squared weighted Frobenius norms for each error. The H2-OFIR predictive tracker is tested by simulations assuming Gauss-Markov disturbances and data errors. It is shown that the H2-OFIR predictor has a better robustness than the Kalman and unbiased FIR predictor. An experimental verification is provided based on the moving robot tracking problem

Recognition of Power Quality Disturbances using Fuzzy Expert Systems

Abstract: This paper presents a new approach to detect and classify power quality disturbances in the power system using Fuzzy C-means clustering, Fuzzy logic (FL) and Radial basis Function Neural Networks (RBFNN). Feature extracted through wavelet is used for training, after training, the obtained weight is used to classify the power quality problems in RBFNN, but it suffers from extensive computation and low convergence speed. Then to detect and classify the events, FL is proposed, the extracted characters are used to find out membership functions and fuzzy rules being determined from the power quality inherence. For the classification,5 types of disturbance are taken in to account. The classification performance of FL is compared with RBFNN.The clustering analysis is used to group the data in to clusters to identifying the class of the data with Fuzzy C-means algorithm. The classification accuracy of FL and Fuzzy C-means clustering is improved with the help of cognitive as well as the social behavior of particles along with fitness value using Particle swarm optimization (PSO),just by determining the ranges of the feature of the membership funtion for each rules to identify each disturbance specifically.The simulation result using Fuzzy C-means clustering possess significant improvements and gives classification results in less than a cycle when compared over other considered approach.

Robust Real Time Multiple Human Detection and Tracking for Automatic Visual Surveillance System

Abstract: Detection of human for visual surveillance system provides most important rule for advancement in the design of future automation systems. Human detection and tracking are important for future automatic visual surveillance system (AVSS). In this paper we have proposed a flexible technique for proper human detection and tracking for the design of AVSS. We used graph cut for segment human as a foreground image by eliminating background, extract some feature points by using HOG, SVM classifier for proper classification and finally we used particle filter for tracking those of detected human. Our system can easily detect and track humans in poor lightening conditions, color, size, shape, and clothing due to the use of HOG feature descriptor and particle filter. We use graph cut based segmentation technique, therefore our system can handle occlusion at about 88%. Due to the use of HOG to extract features our system can properly work in indoor as well as outdoor environments with 97.61% automatic human detection and 92% automatic human detection and tracking accuracy of multiple human

Predication and Analysis of Epileptic Seizure Neurological Disorder using Intracranial Electroencephalography (iEEG)

Abstract: Epileptic seizure is one of the neurological brain disorder approximately 50 million of world’s population is affected. Diagnosis of seizure is done using medical test Electroencephalography. Electroencephalography is a technique to record brain signal by placing electrodes on scalp. Electroencephalography suffers from disadvantage such as low spatial resolution and presence of artifact. Intracranial Electroencephalography is used to record brain electrical activity by mounting strip, grid and depth electrodes on surface of brain by surgery. Online standard Intracranial Electroencephalography data is analyzed by our system for predication and analysis of Epileptic seizure. The pre-processing of Intracranial Electroencephalography signal is done and is further analyzed in wavelet domain by implementation of Daubechies Discrete Wavelet Transform. Features were extracted to classify as preictal and ictal state. Analysis of preictal state was carried out for predication of seizure. Intracranial Electroencephalography signals provide better result and accuracy in seizure detection and predication. Earlier warning can also be issued to control seizure with antiepileptic drugs. Keywords—Artifact, Daubechies Discrete Wavelet transform, Epileptic Seizure, Intracranial Electroencephalography, Seizure Classification, Seizure Predication.

UFIR State Estimator for Network Systems with Two-Step Delayed and Lost Data

Abstract: Wireless communication over networks often produces issues associated with delayed and missing data. In this paper, we consider one-step and two-step delays. The state space model is transformed to have no delay with new system and observation matrices. To mitigate the effect, we develop the unbiased finite impulse response (UFIR) filter, Kalman filter (KF), and game theory H∞ filter for Bernoulli-distributed delays with possible packet dropouts. A comparative study of the filters developed is provided under the uncertain noise and transmission probability. Numerical simulation is conducted employing a GPSbased tracking network system. A better performance of the UFIR filter is demonstrated experimentally

Energy Distribution Evaluation Using Renyi Entropy Measures With Application in EEG Data Analysis

Abstract: The ”corrected” EEG recordings, after artifact removing, may be the subject of further investigations, for example segmentation and energy distribution, resulting new informa- tion to be used for feature extraction, of great help for medical diagnosis. The paper presents a generally method for energy distribution evalua- tion using measures of R´enyi entropy. The pre- sented approach ensures the possibility of quan- titative analysis of the information contained in time-frequency distribution of EEG signals. The proposed procedure is applied with good results in the analysis of a sample lowpass event-related potentials (ERP) data, collected from 13 scalp and 1 EOG electrodes.

UFIR Filtering Under Uncertain One-Step Delayed and Missing Data

Abstract: This paper develops the unbiased finite impulse response (UFIR) filter for wireless sensor network (WSN) systems whose measurements are affected by random delays and packet dropout due to inescapable failures in the transmission and sensors. The Bernoulli distribution is used to model delays in arrived measurement data with known transmission probability. The effectiveness of the UFIR filter is compared experimentally to the KF and game theory recursive H1 filter in terms of accuracy and robustness employing the GPS-measured vehicle coordinates transmitted with latency over WSN.

Power Quality Disturbances Detection and Classification Rule-Based Decision Tree

Abstract: In this paper, the power quality (PQ) disturbances have been detected and classified using Stockwell’s transform (S-transform) and rule-based decision tree (DT) according to IEEE standards. The proposed technique based on the extracted features of the PQ events signals, which are extracted from the time- frequency analysis. Several PQ disturbances are considered with simple and complex disturbances to include spike, flicker, oscillatory transient, impulsive transient, and notch. The performance and robustness of the proposed technique for the recognition of PQ disturbances have been demonstrated through the results of the various disturbances. By comparing the performance of the proposed technique with other reported studies it was distinguished results under noiseless and noisy conditions