Search

This literature reviews the work of researchers on ground-penetrating radar (GPR). This research consists of five sections starting from the first section that focuses on the general application and the advantage of the GPR system in comparison to other types of underground detection systems. The main function of the GPR system is to detect the object buried underground and at the end of the full scan, the output image represents the total signals detected by the receiver of the GPR device. One of the main applications of the GPR system is the detection of an underground object, the GPR scans the underground area and the output image represents the total of the signals detected by the receiver. The second section discusses methods for removing unwanted signals such as noise and direct waves from the output image of a GPR system. After removing the noise, the image requires further analysis to discover and interpret the buried object. The third section discusses the common methods used in the process of identifying buried objects. There are different types of buried objects and section four discusses the algorithms used to detect and identify landmines and explosive devices. Finally, the last section summarizes the paper that discussed the detection and identification process using smart algorithm technology. These types of algorithms are the most accurate, have a lower error rate and are cost-effective.

في السنوات القليلة الماضية ، يلعب العلاج الطبيعي دورا مهما للغاية أثناء إعادة التأهيل. يتم بذل العديد من الجهود لإثبات فعالية التطبيقات الطبية / السريرية والتطبيقات البينية بين الإنسان والآلة (HMI). واحدة من أكثر طرق التحكم شيوعا هي استخدام إشارات تخطيط كهربية العضل (EMG) الناتجة عن تقلصات العضلات لتنفيذ أجزاء جسم الإنسان التعويضية. تقدم هذه الورقة نظام تصنيف إشارات تخطيط كهربية العضل EMG على أساس إشارة تخطيط كهربية العضل EMG. يتم جمع البيانات من عضلات العضلة ذات العضلة الثنائية والعضلة ثلاثية لست حركات مختلفة ، مثل الركوع والتصفيق والمصافحة والمعانقة والقفز والركض باستخدام شارة Myo مع ثمانية أجهزة استشعار تخطيط كهربية العضل EMG. يتم استخدام مربع متوسط ​​الجذر (RMS) وقيمة الانحراف المعياري المطلق للاختلاف (DASDV) وتحليل المكونات الأساسية (PCA) لاستخراج البيانات من الإشارة الخام ولتحسين دقة التصنيف. يتم تطبيق طريقة التعلم الآلي (ML) ، أي يتم استخدام جهاز (Vector Vector (SVM و (K-Nearest Neighbours (KNN للتصنيف ، وتبين النتائج أن KNN يحقق نسبة دقة أعلى من SVM

Continuous mode class-J radio-frequency (RF) power amplifier is a promising technique that extends the operating bandwidth of the conventional class-B power amplifier. However, the maximum theoretical efficiency is limited to that of the class-B power amplifier. In this paper, an enhanced mode of operation for the class-J power amplifier is proposed by incorporating a third harmonic voltage component to produce an optimum waveform for maximizing the fundamental voltage component and thereby to increase the drain efficiency and introduce a new design space. A detailed derivation for the necessary relations of output power, drain efficiency, and the required harmonic load impedances is provided, showing a significant improvement in theoretical maximum efficiency from 78.5 to 89.8%. In order to confirm the developed analytic approach, a 10 W prototype amplifier model was designed and fabricated to operate within the global system for mobile communications (GSM) frequency band 850–950 MHz using a commercial GaN power high electron mobility transistor (HEMT). The experimental results have indicated that the drain efficiency of the circuit varies from 68 to 80% within the desired band.

This paper proposes an improved chaos-based M-ary modulation system. It reproduces deterministic chaotic dynamics to create M-ary non-coherent modulation. The proposed modulation system transmits data using autonomous chaotic sequences. It separates the chaotic dynamics through the use of interleavers and realigns them through the use deinterleavers. The simulation results show that the improved scheme overperforms its traditional counterpart. The degree of improvement grows as the M-ary order is increased, with a penalty of increased system complexity.

Digital electromechanical system (DES), consisting of automatic sample collection, on-site microwave drying and weighing is a novel technology for soil bulk density measurement. The study investigates the potential use of the DES for in situ measurement of bulk density, and evaluates the thermal efficiency and specific energy consumption during measurement. The experiment was conducted in eight fields with different soil textures of a silty clay, loamy, clay loam, silty loam, and silty clay loam, at three soil depths of 0–10, 10–20 and 20–30 cm. Data management and analysis used include split-plot with systematic plot arrangement. Least significant difference (LSD) analyses at 0.05 confidence were applied to compare between the mean of groups. Results indicate that the dry bulk density (ρb) and wet bulk density (ρn) of soil can be measured successfully by the DES, and accuracy of measurement is significantly influenced by soil texture type and depth. The largest microwave drying time of 37 min was needed for the silty clay soil, while 17 min was the lowest drying time recorded for the sandy loam soil. Thermal efficiency was increased with increased soil depth for different soil textures and moisture content strongly influenced the thermal efficiency. Furthermore, the specific energy consumption decreased with increased soil depth for different soil textures. An inversely proportional relationship between specific energy consumption and soil depth was found and was attributed to soil moisture evaporation. A significant relationship between soil ρb and microwave penetration depths in different soil textures was demonstrated, which was due to changes in soil dielectric constant.

This research describes the automation of the widely used volumetric cylinder (VC) technique to measure bulk density. The VC technique suffers from several major drawbacks. In particular, it is difficult and time-consuming to use. Furthermore, errors are produced when sampling different soil depths under a range of field conditions. This research introduces the design, implementation, and testing of a digital electromechanical system (DES) for measuring and recording of the dry (ρb) and wet (ρn) bulk density of soil at three soil depths, remotely. The DES design is a novel and own design. The results of field testing showed that the DES can measure the bulk density of soil at different depths in considerably less time and labour, showing a better accuracy than the existing VC techniques for specific soil textures. The accuracy of the DES-based estimates soil bulk density influenced by different soil textures and soil depths. The first major finding is that for a 10 cm soil depth, both the DES and VC methods produced lower ρb and ρn values for soil as compared to other soil depths under various soil conditions. The second major finding is that there is a positive correlation between the DES and the VC methods for the measurement of both ρb and ρn of soil, with a coefficient of determination (R2) of 0.87 and 0.73, respectively. The coefficient of variation (CV) of dry ρb and wet ρn of soil with the DES method was 6% and 6.3%, respectively, while for the VC method, the CV was 6.3% for ρb and 6.1% for ρn. Furthermore, there was a linear relationship between the DES and the VC methods under different moisture conditions. We conclude that soil bulk density is generally most accurately and precisely determined by the DES technology.

Blind source separation (BSS) is the extraction (estimation) of the original signals from mixed signals, without knowledge (or very little information) on the source signals or the mixture process. Many applications are used blind source separation like cocktail parties and conferences. Therefore, source separation is considered a vital and important subject in signal processing. The separation problem is based on the mixing criteria, while the gap is for considering the sources is fixed. This paper introduces a random propagation mixing coefficient of an indirect path (moving sources) for Quasi of cocktail parties and press conference. The research also presents new evaluation criteria for the separation process and separation algorithms based on measuring the similarity of source and estimated signals. Where this evaluation criterion is based on signals features similarity. Three separation algorithm SVD, PCA, and ICA are tested with different noise amount with many source signals. The advancement of ICA as a good separation algorithm is clear with gaining a separation ration of 96.1%.

Continuous inverse class-F (CICF) is a recent mode of harmonically-tuned RF power amplifiers used to extend the operating bandwidth of the conventional narrowband class-F−1 power amplifier by producing variable set of drain current waveforms and load admittances that give the same operating efficiency. In this work, a new approach of analysis is developed by suggesting some modified drain current waveforms and comparing the resulting theoretical performance characteristics such as drain efficiency and output RF power with the conventional type. It has been shown that the drain current with a truncated square wave shape can better model the actual behavior of the power amplifier, delivering a theoretical efficiency higher by about 8% than the conventional shape. Besides, a simple analytic technique for extracting the device harmonic load impedances for the desired band is also presented. Based on the theoretical analysis, a 6 W power amplifier circuit was designed and simulated to operate within the frequency band 800 – 1000 MHz. Simulation results indicated that a drain efficiency of values between 82% and 86% was obtained across the specified band.

Visual identification is an exciting field because it reflects the primary form of understanding of objects used by humans. At the beginning of artificial intelligent technology, multiple experiments were suggested by the researcher to develop a computer image recogniser similar to human recognition. One such application is in the speech recognition system in a noisy environment, where the visual cue representing the movement of the lips contains some essential information added to the audio signal, as well as how the person merges audio-visual stimuli to identify output words. A little, but unresolved, part of this problem is the classification of utterance using only the visual signals without the speaker’s acoustic signal being available. Taking into account a collection of frames from a recorded video for a person speaking a word; a robust image processing technique is adopted to isolate the region of the lips; then extracting correct geometric characteristics that reflect the variation of the mouth shape during the speech. The observed features are utilised by the identification stage to identify the spoken word. This paper aims to solve this problem by introducing a new segmentation technique to isolate the area of the lips together with a collection of visual shape features centred on the boundary of the extracted lips that can read the lips with significant results. Weightless neural network classifier is proposed to enhance the utterance identification with hardware implementation based on FPGA. Furthermore, A specialised laboratory is designed to collect the utterance of twenty-six English letters from thirty speakers who are adopted in this paper.

In the radar system, detection represents a basic and important stage in the receiver side. The detection process is based on the thresholding criteria; two philosophies of this criteria, constant and adaptive threshold. The constant threshold is simple in design, but it has a mis-detection and does not control the false alarm rate. As for the adaptive threshold, it is powerful in target detection, and better control of the false alarm rate, where it is called Constant False Alarm Rate (CFAR). Lots of research in the CFAR design, but the gap in the previous works is that there is no CFAR algorithm can be working with all or most environmental fields and all or most target situations.In this paper, The CFAR, which can work with the most environment and most of the target situations, has been presented. The producing the design and implementation of the new practical CFAR processor is presented. Where, the new CFAR is a combination of the properties of three different CFAR algorithm (CA, OSGO, and OSSO), and from two different families; averaging and statistical. Where it has overperformed of it's is 97.25% for simulation and 96.25% for the implementable version for different target situations. The simulation analysis is made by using Matlab 2015, while the implementation is done by using Xilinx Spartan 700 3a.

Doppler radar has been used as a sensing device for human gait identification because it possesses the ability to work in adverse weather and penetrate invisible barriers with maintaining privacy. Doppler explains the velocity of the target's motion, and the micro-Doppler explains the micro-motions of its moving parts. The Doppler and micro-Doppler signatures are used to classify the target. Many studies and approaches were presented for human recognition like fingerprints, retina, palm, face, and voice. The gap of this subject is concentrated on three points, the first one needs the subject's permission and physical attention, the second one is maintaining the privacy. Also, the location of the detector device and the detected human part. This paper introduces a novel approach for human gait recognition based on his shoulder's movement signature and periodic motion to satisfy the recognition and to fill this gap. The micro-Doppler of shoulders (or head) is detected by radar, which was fixed in the ceiling. The radar location was decided because the shoulder movement is in-phase with the line of sight (LOS) of the radar signal. The support vector machine (SVM) was used as a classifier. Five people were tested as classes with many patterns for each class related to a different speed and motion status. The Euclidean and Bhattacharyya distances were used to measure the similarity. The Euclidean distance is overperformed the Bhattacharyya distance in this application by 14% caused by its linearity. Simplicity and accuracy can be considered as the distinguishing features of the proposed system in which the gained classification rate is 96.2%.

The combination of different CFARs algorithms has been done to overcome the limitations of individual ones with different return signals in the non-homogenous environment. A comparative study of two kinds of algorithms; the combination between CFAR in the same family and diverse families. TM, AND, OR, CASH, ACGCA-CFAR algorithms have been tested with four kinds of return signals, single, multi, close targets and clutter edge. Also, the probability of detection has been evaluated for these algorithms. This study appears that the CASH, OR and TM have an overperform than the other in the multi-target case, while the ACGCA, VI, and TM are advance the other in the adjacent target state, in this context, the OR, VI, and ACGCA are best in clutter edge case. In this study, the Matlab 2015b is used to evaluate the performance of different types of CFAR algorithms.

Object tracking is an important task within the field of computer vision. Where, it is the process of segmenting an object of interest from a video scene and keeping track of its motion, orientation occlusion to extract useful information. This paper is intended to the improve the measurement accuracy of the closing moving object by using the median filter for denoising and Kalman filter for tracking. At the denoising stage, 70-80% of the noise is reduced by using a median filter. The median filter has been used instead of the Wiener filter because the noise which is assumed is salt and pepper, and it is less complexity than the Wiener filter. While in the tracking stage, the KF has been used as estimated filter. However, the measurements have been improved by 11.27%. The simulation has been done by using Matlab 2014, while the proposal is applied to the real video.

Face recognition (FR) has received an important concern in our contemporary life, especially in control and security applications. This work proposes a novel method for tackling the problem of FR using the minimum number of states (i.e. one state) of continuous Hidden Markov Model (HMM). The contribution of the proposed method can be viewed in the use of continuous one-state HMM, which has not yet been used in other approaches. Furthermore, the concept that early adopted, regarding the relationship between facial regions and number of states, is invalidated, accordingly. The implementation of this method can be summarized as follows: i) filtering the face image using a median filter, ii) reduction of additional noise and image size using multiple level of discrete wavelet transform (DWT), iii) training the outcomes of the DWT using one-state HMM of continuous output density with one Gaussian mixture coefficient, and iv) recognizing images for validation. The advantage of using continuous output densities appears in conducting noisy images, such that the proposed method highly reduces the effect of noise. The simulation results present that the recognition rate is about 100% despite the presence of 25% and 50% of impulsive noise densities on the images of the ORL and Yale databases, respectively.

Video summarization used in many applications such as video object recognition and classification. Different methods used for this purpose: key frame extraction using edge detection and key frame extraction using discrete wavelet transform (DWT). In video processing, numerous frames containing similar information, this leads to time consumption and slow processing speed and complexity. New method Hybrid DWT-Edge Key Frame Detection (HDEKFD) of dynamic sign language presented in this paper. This method combined two algorithms edge detection and DWT to increase processing speed by reduce the numbers of redundant frames. Simulation results illustrate the efficient of the proposed algorithm compare to other methods.

In class-F RF power amplifiers, there are several methodologies used to characterize the RF power device in order to present the proper harmonic impedances at its terminals, the most widely used of which is the load-pull method. This paper presents an alternative technique based on the analytic derivation of the optimum terminal load impedances at the first three harmonic frequencies using both the device intrinsic and package parasitic elements. The output matching network is then synthesized analytically to present the calculated harmonic impedances at the device output terminal. As a confirmation to the proposed technique, a 6-W power amplifier circuit has been designed and simulated using a commercial GaN HEMT power device to operate at 900 MHz. The simulated results show a drain efficiency of more than 84%, output power of more than 38 dBm, and power gain of more than 13 dB at the specified frequency.

The humanoid robot represents a promising application in the medical, handicapped and industrial limbs fields. The control of the hand fingers of the spoken command is one of the importance of these applications. This paper presents the proposed design of the hand-fingers controls circuit through the spoken letter. This design is based on the control of servo motors for each finger by Arduino controller. The Arduino has received a coded signal from the recognition algorithm to give the signals with different' duration to the servo motors to take the required hand-fingers form which is corresponding to the spoken letters. Where these codes relate to the statistical features of that letter, which are extracted from the spoken signals. Then, by using the Multilayer Feed-Forward Neural Network algorithm as a classifier, the simulation recognition, which has been gained is 96.33% while the experimental recognition is 94.8 %. The difference between these results is caused by the reject some patterns caused by the motor's errors.

The detection of the target depends on the accuracy of the classification of the radar return signals. This classification accuracy is based on the features which extracted from that signal. This paper presents an optimal algorithm for select optimal features. Three cases were studied of the situation of targets in receiving signal; single, multi-, and close multi-targets. The types and number of features represent the base of the algorithm, while the processing time and the classification rate represent the criteria for features selection. Hybrid methods, which combine the optimum characteristics of wrappers and filter methods are used for making the compromise between the number of features and best candidate subset. Multilayer perceptron back propagation neural network has been used as a classifier, while the classification is 98% for single target with two third processing time of multi-targets for the same classification rate, and nearly half processing time for the close-multi target.

In image processing, feature extraction acts a key role. It is very imperative to know and extract the required features for further assessment. In this paper, the feature extraction of Arabic isolated sign language word based on chain code model is proposed. The features are extracted from the hand trajectory tracking, features obtained of the single hand or two hands that enter to a classifier which can determine the meaning of the gesture. In this study, More than forty isolated sign words are collected in collaboration with the Iraqi Ministry of Labor and Social Affairs. Four isolated words were taken as an example. The features were extracted from the isolated words; these features represent the feature vector of the isolated word that is used in the classification stage.

A Ground-penetrating radar (GPR) is considered an efficient non-destructive device for detecting the buried object. The GPR operation is based on the analysis of the received scattered of the transmitted signal. Its output is the two-dimensional image radiogram hyperbolic curve, this image represents the reflected signal of the buried object. To date, studies investigating targets (buried objects) have produced equivocal results. Therefore, this paper highlights the importance of the effect of changing target-detection parameters (material type, target to surface distance, size, and scan to target location angle) concerning the hyperbolic curve on the GPR experiment image. A practical model has been built for this experiment with three material types (metal, plastic, and pottery) that are buried in the sand soil. Three tests have been done for different types of material, in the different depth for each buried object of the same material. Then, changing the size of the buried object (small and big size), also, changing the location angle of the buried objects concerning the direction of the GPR scan. For these tests, the effect on the hyperbolic curve has been recognized. A MALA 1 GHz geophysical GPR system is used in these experiments. As a result, the strength of the reflected EMW changes concerning the type of material, size, depth, and location angle of the buried object.

Speech separation is attracting widespread interest due to the sound mixing in real environments in and out door applications. Although the researchers have used many algorithms, the separation rate in the real environment is still poor. This paper presents speech separation using a modified Deep learning neural (DLN) algorithm. Interestingly, the modification has reduced the complexity of the original DLN algorithm, while, high value of separation rate has been gained caused by using Hamming instead of Hanning windows against the other algorithms. The separation rate reaches 98.6%, while, the advancement over the nearest algorithm is 2.8%.

paper presents a fast face recognition (FR) method using only three states of Hidden Markov Model (HMM), where the number of states is a major effective factor in computational complexity. Most of the researchers believe that each state represents one facial region, so they used five states or more according to the number of facial regions. In this work, a different idea has been proven, where the number of states is independent of the number of facial regions. The image is resized to 56x56, and order-statistic filters are used to improve the preprocessing operations and thereby reducing the influence of the illumination and noise. Up to three coefficients of Singular Value Decomposition (SVD) are utilized to describe overlapped blocks of size 5x56. Experimental results show that the proposed work manages to achieve 100% recognition rate on ORL face database using the maximum variance and two coefficients of SVD and can, therefore, be considered as the fastest face recognition type. Keywordsrecognition, Hidden Markov Model, Order Statistic Filter, Number of states of HMM, Singular Value Decomposition.

In the past few years, physical therapy plays a very important role during rehabilitation. Numerous efforts have been made to demonstrate the effectiveness of medical/clinical and human-machine interface (HMI) applications. The prevalent control methods are using electromyography (EMG) signals generated by muscle contractions to implement the prosthetic human body parts. This paper aims to provide and summarize ideas about recent researches in the field of Pattern Recognition (PR) based on EMG signals to save time and efforts for the readers working in this field. The first step starts by demonstrating a general overview of the various techniques to collect the database by taking into consideration the factors that affect the accuracy of the collected data. Hence, different types of filters are presented to process the signals and reduce the noise of the raw EMG signals. This research clarifies the features extraction methods using time-domain (TD), frequency domain (FD), and time-frequency domain (TFD) and which of these methods will be suitable to use for EMG signals. Finally, a group of studies is reviewed based on three classification methods i.e. artificial neural network (ANN), machine learning (ML), and deep learning (DL). Depending on these methods, the accuracy range can be specified for each classifier, also the factors which affect the accuracy percentage. Therefore, the researchers can avoid these issues that reduce accuracy.

The hidden Markov model (HMM) has recently achieved impressive success in the field of pattern recognition, but some limitations and drawbacks restrict its performance. In this study, a new simple model is proposed to overcome the restrictions of HMM with a high reduction in the computational complexity. The training algorithm of the proposed model is built without iterations. It depends on the number of occurrences of each symbol in the training array, in case the discrete data form is used. However, for the continuous form, it uses the mean and covariance of the training data. On the other hand, the log-likelihood and the Mahalanobis distance are employed in the testing algorithm for indicating the highest matching between the testing data and the training parameters. This new model has been tested for face recognition; the experiments exhibit its advantage in terms of memory usage and processing time requirements, as well as recognition rate.

This paper presents a robust clutter classifier based on the neural network to assist the radar receiver by choosing optimal constant false alarm rate where this classifier has been trained for 16 classes, four radar return distribution with different situations. The return radar signal distributions are Rayleigh, Weibull, lognormal and K-distribution, while the situations are, signal, multi-target, closed multi-target, and clutter edge. Multilayer perceptron with back-propagation as a neural network with seven features, mean, variance, mode, kurtosis, skewness, median, and entropy, have been used to classify the return signal. A least mean square error is used to evaluate the classifier performance. The simulation is evaluated for the signal to clutter ration from +35 dB to −35 dB, with 5-20 neurons of the hidden layer, and 60-360 samples. By performing, the optimisation has been gained by using 240 samples and 20 neurons then lead to 98.1% return signal classification.

This paper presents the recognition of digital signal modulation by combining four cumulants as signal features and a threshold discriminator assigned for each cumulant. In this paper, the problem of recognition has been solved by finding a suitable relationship among these features and their classifier. The decision of each classifier has been compared with other classifier outputs. Then, the classifier with the highest priority has been considered as the final efficient decision. The priority of each classifier is based on how its cumulant is robust against a wide range of signal to noise ratio (SNR), for different types of digital modulations under investigation. Many types of quadrature amplitude modulation (16, 32, 64, 128, and 256) have been recognized with low SNR down to −5 dB. Using such combination, the average recognition percentage was increased with low SNR. The recognition gained 81.166%–100% for 4096 samples while the percentages are from 86.9% to 98.6% with a variable number of sam...

In n-tuple and Hidden Markov Model(HMM) the recognition has been based on the feature selection. The feature selection in n-tuple depends on the number of tuples and its location. While, in HMM the feature has been related to the states. Where, the suitable features selection lead to optimal recognition. In this paper, a novel approach has presented for n-tuple and Hidden Markov model feature selection by using the Sierpiński fractal technique. The memory size and the recalling time taken to get individual classifier response has been reduced by 29.35% while the recognition is advancing the conventional n-tuple by 12.5% and 11.6% with and without frequency of occurrence respectively. In addition, the improvements noted in the HMMF proposed algorithm is 2.19% in recognition side, while it is 60% in complexity reduction. This approach is found to be robust in the presence of noise, where, the n-tupleF has advanced in recognition by 38.27% the conventional n-tuple algorithms, while HMMF has overperformed the n-tupleF by 14.44%. Simulation results show the maximum recognition is 92.3% for n-tupleF for character recognition, and HMMF is 99.98% for face recognition.

The trend for about twenty years, the research regarding the number of states in Hidden Markov Model (HMM) was mainly aimed at increasing it in order to ensure the robustness of the face recognition system. In this paper, a novel face recognition method is presented based on one state of discrete HMM, where it seemed impossible in the past. Contrary to other approaches that use the three parameters of the HMM to recognize faces, the proposed work uses only one parameter for discrimination, while the two others are fixed. The method starts with a pre-processing step to remove the influence of noise from the images using the median filter and the discrete wavelet transform (DWT), where at the same time; the DWT possesses a size reduction feature. The reduced size image is prepared to generate a sequence of overlapping blocks. The data manipulated by the model are produced by converting each block to an integer value using some statistical techniques and a quantization process, such that each image is described by a sequence of integers. The experimental results show that the use of one-state model highly reduces the computational complexity of the system and continues in achieving 100% recognition rate, which can be considered a practical breakthrough in the field of face recognition that has superseded the other research efforts in reducing the number of states of HMM, and consequently accomplished reduction of computational complexity and ultimate enhancement of system performance.

An effective error-correction scheme based on normalized correlation for a non coherent chaos communication system with no redundancy bits is proposed in this paper. A modified logistic map is used in the proposed scheme for generating two sequences, one for every data bit value, in a manner that the initial value of the next chaotic sequence is set by the second value of the present chaotic sequence of the similar symbol. This arrangement, thus, has the creation of successive chaotic sequences with identical chaotic dynamics for error correction purpose. The detection symbol is performed prior to correction, on the basis of the suboptimal receiver which anchors on the computation of the shortest distance existing between the received sequence and the modified logistic map’s chaotic trajectory. The results of the simulation reveal noticeable Eb/No improvement by the proposed scheme over the prior to the error- correcting scheme with the improvement increasing whenever there is increase in the number of sequence N. Prior to the error-correcting scheme when N=8, a gain of 1.3 dB is accomplished in Eb/No at 10-3 bit error probability. On the basis of normalized correlation, the most efficient point in our proposed error correction scheme is the absence of any redundant bits needed with minimum delay procedure, in contrast to earlier method that was based on suboptimal method detection and correction. Such performance would render the scheme good candidate for applications requiring high rates of data transmission.

The important task in the computer interaction is the languages recognition and classification. In the Arab world, there is a persistent need for the Arabic spoken language recognition To help those who have lost the upper parties in doing what they want through speech computer interaction. While, the Arabic automatic speech recognition (AASR) did not receive the desired attention from the researchers. In this paper, the Radial Basis Function(RBF) is used for the improvement of the Arabic spoken language letter. The recognition and classification process are based on three steps; these are; preprocessing, feature extraction and classification (Recognition). The Arabic Language Letters (ALL) recognition is done by using the combination between the statistical features and the Temporal Radial Basis Function for different letter situation and noisy condition. The recognition percent are from 90% - 99.375% has been gained with independent speaker, where these results are over-perform the earlier works by nearly 2.045%. The simulati.on has been made by using Matlab 2015b.

Radar is a promising device for detection and recognition of invisible moving objects, Where, the micro-Doppler frequency shift caused by moving the object's parts have been represented as an attractive feature in the recognition process. In spite of that, no thorough analysis of human movement by bicycle and no discriminate from the running one through the wall in the literature. This paper presents a mathematical model of bicycle movement, then, the recognition of moving objects through the wall. Where three human movements; walking, running and on a bicycle have been recognized through two types of wall wood and cork. The theoretical analysis and measured was given a recognition 98.7% for human walking on his feet, 99% of the passenger on a bicycle, and 98% of the person running have been achieved without walls. While, a 95.4%, 96.2%, and 95% recognition have been gained from walking, moving by bicycle and running with wooden wall and 94%, 94.8%, and 93.3% respectively with cork wall. 2.4 GHz as a detector and SVM as classifier are used.

This paper presents a simple and fast face recognition system based on two states of discrete Hidden Markov Model (HMM). The minimization in the number of states leads to high processing speed and less memory occupation. Median filter is applied to each image under process, where it is the most suitable filter used to eliminate the effect of noise on images, and thereby enhancing the performance of the system. The features are extracted from reduced size images using a combination of maximum variance and Singular Value Decomposition (SVD). More reduction in processing data is achieved by assigning a single value to each feature vector. This process greatly speeds up the training and classification steps, where a discrete type of left-to-right HMM is used in this work. Experimental results verify that the proposed work is superior to previous approaches of HMM face recognition, where it achieves 100% recognition rate, high speed, and extremely low memory usage.

Based on the radar field environment, the detection process is generally based on the adaptive threshold required to detect the received radar cell signal. Many algorithms are used to design this adaptive threshold to satisfy a Constant False Alarm Rate (CFAR) in line with detection criteria in non-homogenous environments. Although CFAR algorithms have increasingly become a vital factor in the detection process, the performance of these algorithms differs according to their treatment of the received radar bins. In cases of targets in a clutter edge and multi-targets, the performance of the GO-, VI-, OSSO- and OSGO-CFAR algorithms are better than the performance of the CA-CFAR algorithm, while the CA-CFAR and OS-CFAR algorithms lose such targets. In this context, the SO-CFAR has a higher Pfa than the above algorithms for small targets in a clutter edge. OSSO-, OSGO, VI, and CMLD also have higher PD S based on their outcomes than the other algorithms in the same Pfa in non-homogenous environments. However, CA-CFAR is simpler and has less complexity than the other algorithms. MATLAB 2015b was used to evaluate the performance of these different types of CFAR algorithm.

Video summarization used for a different application like video object recognition and classification. In video processing, numerous frames containing similar information, this leads to time consumption and slow processing speed and complexity. By using key frames reducing the amount of memory needed for video data processing and complexity greatly. In this paper key frame extraction of Arabic isolated word using discrete wavelet transform (DWT) with modified threshold factor is proposed with different bases. The results for different wavelet basis db, sym and coif show the best result for numbers of key frames at the threshold factor value (0.75).