×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerIris pattern is one of the most important biological traits of humans. In last years, the iris pattern is used for human verification because of uniqueness of its texture. In this paper, biometric system based iris recognition is designed and implemented using two comparative approaches. The first approach is the Fourier descriptors, in this method the iris features have been extracted in frequency domain, where the low spectrums define the general description of iris pattern, while the high spectrums describes the fine detail. The second approach, the principle component analysis uses statistic technique to select the most important feature values by reducing its dimensionality. The biometric system is tested by applying one-to-one pattern matching procedure for 50 persons. The distance measurement method is applied for Manhattan, Euclidean, and Cosine classifiers for purpose of comparison. In all three classification methods, Fourier descriptors were always advanced principle component analysis in matching results. It satisfied 96%, 94%, and 86% correct matching against 94%, 92%, and 80% for principle component analysis using Manhattan, Euclidean, and Cosine classifiers respectively.
The electrical load is affected by the weather conditions in many countries as well as in Iraq. The weather-sensitive electrical load is, usually, divided into two components, a weather-sensitive component, and a weather-insensitive component. The research provides a method for separating the weather-sensitive electrical load into five components. and aims to prove the efficiency of the five-component load Forecasting model. The artificial neural network was used to predict the weather-sensitive electrical load using the MATLAB R17a software. Weather data and loads were used for one year for Mosul City. The performance of the artificial neural network was evaluated using the mean squared error and the mean absolute percentage error. The results indicate the accuracy of the prediction model used, MAPE equal to 0.0402.
Independent Component Analysis (ICA) has been successfully applied to a variety of problems, from speaker identification and image processing to functional magnetic resonance imaging (fMRI) of the brain. In particular, it has been applied to analyze EEG data in order to estimate the sources form the measurements. However, it soon became clear that for EEG signals the solutions found by ICA often depends on the particular ICA algorithm, and that the solutions may not always have a physiologically plausible interpretation. Therefore, nowadays many researchers are using ICA largely for artifact detection and removal from EEG, but not for the actual analysis of signals from cortical sources. However, a recent modification of an ICA algorithm has been applied successfully to EEG signals from the resting state. The key idea was to perform a particular preprocessing and then apply a complex- valued ICA algorithm. In this paper, we consider multiple complex-valued ICA algorithms and compare their performance on real-world resting state EEG data. Such a comparison is problematic because the way of mixing the original sources (the “ground truth”) is not known. We address this by developing proper measures to compare the results from multiple algorithms. The comparisons consider the ability of an algorithm to find interesting independent sources, i.e. those related to brain activity and not to artifact activity. The performance of locating a dipole for each separated independent component is considered in the comparison as well. Our results suggest that when using complex-valued ICA algorithms on preprocessed signals the resting state EEG activity can be analyzed in terms of physiological properties. This reestablishes the suitability of ICA for EEG analysis beyond the detection and removal of artifacts with real-valued ICA applied to the signals in the time-domain.
Vast number of researches deliberated the separation of speech mixtures due to the importance of this field of research . Whereas its applications became widely used in our daily life; such as mobile conversation, video conferences, and other distant communications. These sorts of applications may suffer from what is well known the cocktail party problem. Independent component analysis (ICA) has been extensively used to overcome this problem and many ICA algorithms based on different techniques have been developed in this context. Still coming up with some suitable algorithms to separate speech mixed signals into their original ones is of great importance. Hence, this paper utilizes thirty ICA algorithms for estimating the original speech signals from mixed ones, the estimation process is carried out with the purpose of testing the robustness of the algorithms once against a different number of mixed signals and another against different lengths of mixed signals. Three criteria namely Spearman correlation coefficient, signal to interference ratio, and computational demand have been used for comparing the obtained results. The results of the comparison were sufficient to signify some algorithms which are appropriate for the separation of speech mixtures.
Power transformer protective relay should block the tripping during magnetizing inrush and rapidly operate the tripping during internal faults. Recently, the frequency environment of power system has been made more complicated and the quantity of 2nd frequency component in inrush state has been decreased because of the improvement of core steel. And then, traditional approaches will likely be maloperated in the case of magnetizing inrush with low second harmonic component and internal faults with high second harmonic component. This paper proposes a new relaying algorithm to enhance the fault detection sensitivities of conventional techniques by using a fuzzy logic approach. The proposed fuzzy-based relaying algorithm consists of flux-differential current derivative curve, harmonic restraint, and percentage differential characteristic curve. The proposed relaying was tested with MATLAB simulation software and showed a fast and accurate trip operation.
Training the user in Brain-Computer Interface (BCI) systems based on brain signals that recorded using Electroencephalography Motor Imagery (EEG-MI) signal is a time-consuming process and causes tiredness to the trained subject, so transfer learning (subject to subject or session to session) is very useful methods of training that will decrease the number of recorded training trials for the target subject. To record the brain signals, channels or electrodes are used. Increasing channels could increase the classification accuracy but this solution costs a lot of money and there are no guarantees of high classification accuracy. This paper introduces a transfer learning method using only two channels and a few training trials for both feature extraction and classifier training. Our results show that the proposed method Independent Component Analysis with Regularized Common Spatial Pattern (ICA-RCSP) will produce about 70% accuracy for the session to session transfer learning using few training trails. When the proposed method used for transfer subject to subject the accuracy was lower than that for session to session but it still better than other methods.
Brain machine interface provides a communication channel between the human brain and an external device. Brain interfaces are studied to provide rehabilitation to patients with neurodegenerative diseases; such patients loose all communication pathways except for their sensory and cognitive functions. One of the possible rehabilitation methods for these patients is to provide a brain machine interface (BMI) for communication; the BMI uses the electrical activity of the brain detected by scalp EEG electrodes. Classification of EEG signals extracted during mental tasks is a technique for designing a BMI. In this paper a BMI design using five mental tasks from two subjects were studied, a combination of two tasks is studied per subject. An Elman recurrent neural network is proposed for classification of EEG signals. Two feature extraction algorithms using overlapped and non overlapped signal segments are analyzed. Principal component analysis is used for extracting features from the EEG signal segments. Classification performance of overlapping EEG signal segments is observed to be better in terms of average classification with a range of 78.5% to 100%, while the non overlapping EEG signal segments show better classification in terms of maximum classifications.
In recent years, there has been a lot of interest in the study of P300 potential-based approaches for lie detection. The variations in brain signal activity (EEG-P300 component) that distinguish between lying and starting the truth are investigated. As soon as participants respond to an experiment stimulus for the first time, their brain signals are examined and the P300 signal is extracted. This paper aims to improve the signal-to-noise ratio (SNR) of P300, which leads to an increase in the classification accuracy of lie detection. Ten subjects were randomly assigned to groups of lying and innocent people, and 14 electrodes captured the EEG data for each group. This work proposed to use some denoising techniques like averaging the raw EEG signal, regression-based baseline correction, and independent component analysis (ICA). The suggested approach and other early published methods vary mostly in the regression-based technique used in bassline correction to adaptively indicate the baseline interval (baseline window). Compared to other studies, the suggested technique gives an increase in the mean amount of SNR by up to 20% was obtained.
Various methods have been exploited in the blind source separation problems, especially in cocktail party problems. The most commonly used method is the independent component analysis (ICA). Many linear and nonlinear ICA methods, such as the radial basis functions (RBF) and self-organizing map (SOM) methods utilise neural networks and genetic algorithms as optimisation methods. For the contrast function, most of the traditional methods, especially the neural networks, use the gradient descent as an objective function for the ICA method. Most of these methods trap in local minima and consume numerous computation requirements. Three metaheuristic optimisation methods, namely particle, quantum particle, and glowworm swarm optimisation methods are introduced in this study to enhance the existing ICA methods. The proposed methods exhibit better results in separation than those in the traditional methods according to the following separation quality measurements: signal-to-noise ratio, signal-to-interference ratio, log-likelihood ratio, perceptual evaluation speech quality and computation time. These methods effectively achieved an independent identical distribution condition when the sampling frequency of the signals is 8 kHz.
The paper presents a novel approach that merges the abilities of the biological environment with the concept of hierarchical trees to attack a specific stream cipher. The model being presented introduces a systematic method that targets a group of stream ciphers, such as the GCM family, these devices are composed of components that are suitable for the proposed method. A restricted set of binaries for the final key sequence is required to implement this technique as an input. The attacked algorithm comprises feedback shift registers, memories, delays, and so on. The stream ciphers are widely used in modern encryption to secure communication devices, so any attempt to analyze or attack it is of the utmost importance. The results of this method have been confirmed to lead to the destruction of the cipher’s security. Many novelties and contributions of the present work can be summarized as follows: firstly, the key generator’s components are attacked individually, disrupting the cohesion between them. This was not possible previously except in rare cases and under difficult conditions. Secondly, the method of verifying the correct initial values is unrelated to the generator’s operation. Thirdly, the technique applies biological concepts and processes to laboratory test tubes for genetic engineering, it can be said that the prepared model targets a broad class of stream key generators, rather than a single algorithm. The proposed technique requires a specific and deterministic number of final key sequence bits, which are easy to provide. The proposed technique creates a search E -tree in the style of hierarchical clusters, in which the first level containsE nodes. Then each successive level contains the square of E nodes of the number of nodes in the previous level, and the root is composed of the total solution space of the stream key generator and produces the nodes of each level from the intersection of the cluster contents in the test tubes for all clusters in the level above it. The contribution and novelty of the present work is cryptanalyzing and attacking shift register-based stream key generators involves fragmentation. The attacking principle entails disassembling generator components from registers and individually attacking them. DNA logic clustering aids in this process, as the strength of these generators relies on component cohesion. Because the components are cryptanalyzed individually, the time complexity of the attack is equal to O(C2N) , where N is the length of the largest component, and C is a constant.
The development of renewable resources and the deregulation of the market have made forecasting energy demand more critical in recent years. Advanced intelligent models are created to ensure accurate power projections for several time horizons to address new difficulties. Intelligent forecasting algorithms are a fundamental component of smart grids and a powerful tool for reducing uncertainty in order to make more cost- and energy-efficient decisions about generation scheduling, system reliability and power optimization, and profitable smart grid operations. However, since many crucial tasks of power operators, such as load dispatch, rely on short-term forecasts, prediction accuracy in forecasting algorithms is highly desired. This essay suggests a model for estimating Denmark’s power use that can precisely forecast the month’s demand. In order to identify factors that may have an impact on the pattern of a number of unique qualities in the city direct consumption of electricity. The current paper also demonstrates how to use an ensemble deep learning technique and Random forest to dramatically increase prediction accuracy. In addition to their ensemble, we showed how well the individual Random forest performed.
The evolution of wireless communication technology increases human machine interaction capabilities especially in controlling robotic systems. This paper introduces an effective wireless system in controlling the directions of a wheeled robot based on online hand gestures. The hand gesture images are captured and processed to be recognized and classified using neural network (NN). The NN is trained using extracted features to distinguish five different gestures; accordingly it produces five different signals. These signals are transmitted to control the directions of the cited robot. The main contribution of this paper is, the technique used to recognize hand gestures is required only two features, these features can be extracted in very short time using quite easy methodology, and this makes the proposed technique so suitable for online interaction. In this methodology, the preprocessed image is partitioned column-wise into two half segments; from each half one feature is extracted. This feature represents the ratio of white to black pixels of the segment histogram. The NN showed very high accuracy in recognizing all of the proposed gesture classes. The NN output signals are transmitted to the robot microcontroller wirelessly using Bluetooth. Accordingly the microcontroller guides the robot to the desired direction. The overall system showed high performance in controlling the robot movement directions.
The main objective of this paper project was to create a state-of-the-art face identification technique that can handle the various difficulties caused by changes in illumination, occlusions, and facial emotions. Face detection is a cornerstone of computer vision, facilitating diverse applications ranging from surveillance systems to human-computer interaction. Throughout this paper, the comprehensive exploration of advancing face detection methodologies has been undertaken, culminating in developing and evaluating a novel approach. The challenges posed by variations in facial expressions, lighting conditions, and occlusions necessitated a multifaceted solution. Our proposed method, which consists of interconnected steps, works quite well to overcome these challenges. Using deep learning architectures to increase feature extraction and discrimination was beneficial in the initial stage of fine-tuning Residual Networks (ResNet-50) to serve as the Region-based Convolutional Neural Network (Faster R-CNN) framework classifier. The process of gradually optimizing thresholds, such as batch size, learning rate, and detection threshold, involved using the Gray Wolf optimization technique (GWO). The conversion process was accelerated and improved overall detection process efficiency and accuracy using a clever fusion of machine learning and metaheuristic optimization techniques. A key component of our methodology is the careful data processing, which was necessary to ensure. The suggested method was carefully examined on a particular dataset, and the 94% training accuracy that was attained together with an identical test dataset accuracy highlights the method’s resilience. These findings support the effectiveness of our approach in reducing false positives and negatives, resulting in unmatched recall and precision in the detection system. The discovery has significant significance as it can potentially improve face detection systems’ performance and reliability in various real-world applications, such as human-computer interaction and surveillance. Convolutional neural networks, deep learning architectures, and metaheuristic optimization approaches were synergized to produce a new and reliable solution.
Vehicular Ad hoc Networks (VANETs), a subsection of Mobile Ad hoc Networks (MANETs), have strong future application prospects. Because topology structures are rapidly changing, determining a route that can guarantee a good Quality of Service (QoS) is a critical issue in VANETs. Routing is a critical component that must be addressed in order to utilize effective communication among vehicles. The purpose obtained from this study is to compare the AODV and GPSR performance in terms of Packet Delivery Ratio, Packet Drop Ratio, Throughput, and End-to-End Delay by applying three scenarios, the first scenario focuses on studying these protocols in terms of QoS while changing the number of vehicles at a constant speed of 40Km/h, and for the second scenario changing the speed value while keeping a constant number of vehicles which is 100, the third involves changing the communication range at a constant speed and vehicle number. This study represents a foundation for researchers to help elaborate on the strength and weaknesses of these two protocols. OMNeT++ in conjunction with SUMO is used for simulation.
Speaker recognition refers to identifying the speaker by his or her voice. People talk in a variety of tones and each speaking voice has features that distinguish one person from another. Speaker verification (SV)involves comparing a set of measures of the speaker’s utterances with a reference for the person whose identification is being asserted to accept or reject the speaker’s identity claim. An identity claim is made during speaker verification which consists of two steps: extraction of feature and matching of feature. In this work, the analysis of correlations of Mel-scale coefficients for the voice of utterance to identify the intended speaker is presented. Short text-dependent word and other text-independent word is represented in this study. The correlation accuracy ranged from 98% to 99% for user1 (same speaker) for text-dependent. whereas 83% and 61% for user1 correlation with other speakers for text-dependent and independent respectively. Furthermore, the MFCC feature extraction approach based on distributed Discrete Cosine Transform (DCT) is provided in this research. SV tests are carried out using the MFCC feature extractions method where close variance for the target speaker and away variance for other speakers is obtained. Additionally, the principle component analysis (PCA) is provided to improve the discriminative system performance. Where the PCA chooses the optimal path between every pair of extremely confusing speakers. The results obtained from PCA were similar to the correlation finding from the Mel-scale results with enhancing the discriminative information and with lowering the dimension of MFCCs data..
In this paper two theoretical models have been considered for the prediction of path loss for two different districts in Mosul city, using MATLAB 7.4 program. The Walfisch-Ikegami (W-I) model for uniform heights and similar buildings in the Karama district . The other model is Okumura-Hata (OH) model applied for irregular and dissimilar buildings in the Almajmoa'a district. The information buildings heights are obtained from the civil Eng. Depart. in Mosul university. In this paper it can be shown that The effect of distance in regular area (karama) on path loss is about 10 dB larger than irregular area (Almajmoa'a), and The effect of varying antenna height in regular area (karama) on path loss is about 7 dB greater than irregular area (Almajmoa'a) for 40 meter variation.
Preserving privacy and security plays a key role in allowing each component in the healthcare system to access control and gain privileges for services and resources. Over recent years, there have been several role-based access control and authentication schemes, but we noticed some drawbacks in target schemes such as failing to resist well-known attacks, leaking privacy-related information, and operational cost. To defeat the weakness, this paper proposes a secure electronic healthcare record scheme based on Schnorr Signcryption, crypto hash function, and Distributed Global Database (DGDB) for the healthcare system. Based on security theories and the Canetti-Krawczyk model (CK), we notice that the proposed scheme has suitable matrices such as scalability, privacy preservation, and mutual authentication. Furthermore, findings from comparisons with comparable schemes reveal that the suggested approach provides greater privacy and security characteristics than the other schemes and has enough efficiency in computational and communicational aspects.
Analog filters constitute indispensible component of analog circuits and still playing an important part in interface with analog real world. realizing filters with odd order is preferred because of its time response . Therefore, this paper is conducted to introduce a new generalized Chebyshev – like approximation for analog filters. The analyses presented to realize the filters with odd order. This proposed novel approach offer good results in terms of flat delay and time domain response. Also, the achieved results are validated by comparison to normal Chebyshev filter via investigation several examples .
In recent years, self-driving cars and reducing the number of accident casualties have drawn a lot of attention. Although it is crucial to increase driver awareness on the road, autonomous vehicles can emulate human driving and guarantee improved levels of road safety. Artificial intelligence (AI) technologies are often employed for this purpose. However, deep learning, a subset of AI, is prone to numerous errors, a wide range of threats, and needs to handle vast amounts of data, which imposes high-performance hardware requirements. This study suggests a deep learning model for object recognition that employs characteristics to describe data rather than images. Our model employs the COCO dataset as the training foundation, and it was suggested that the features be retrieved using the principal component analysis PCA extraction method. The current results demonstrate the efficacy and precision of our model, with an accuracy of 99.96 %. Furthermore, the performance indices, i.e., recall, precision, and F1-score, achieved about 1 for most of the COCO classes in training phase and promising results in testing phase.
In this paper, explicit model predictive controller is applied to an inverted pendulum apparatus. Explicit solutions to constrained linear model predictive controller can be computed by solving multi-parametric quadratic programs. The solution is a piecewise affine function, which can be evaluated at each sample to obtain the optimal control law. The on-line computation effort is restricted to a table-lookup. This admits implementation on low cost hardware at high sampling frequencies in real-time systems with high reliability and low software complexity. This is useful for systems with limited power and CPU resources.
The main objective of this paper project was to create a state-of-the-art face identification technique that can handle the various difficulties caused by changes in illumination, occlusions, and facial emotions. Face detection is a cornerstone of computer vision, facilitating diverse applications ranging from surveillance systems to human-computer interaction. Throughout this paper, the comprehensive exploration of advancing face detection methodologies has been undertaken, culminating in developing and evaluating a novel approach. The challenges posed by variations in facial expressions, lighting conditions, and occlusions necessitated a multifaceted solution. Our proposed method, which consists of interconnected steps, works quite well to overcome these challenges. Using deep learning architectures to increase feature extraction and discrimination was beneficial in the initial stage of fine-tuning Residual Networks (ResNet-50) to serve as the Region-based Convolutional Neural Network (Faster R-CNN) framework classifier. The process of gradually optimizing thresholds, such as batch size, learning rate, and detection threshold, involved using the Gray Wolf optimization technique (GWO). The conversion process was accelerated and improved overall detection process efficiency and accuracy using a clever fusion of machine learning and metaheuristic optimization techniques. A key component of our methodology is the careful data processing, which was necessary to ensure. The suggested method was carefully examined on a particular dataset, and the 94% training accuracy that was attained together with an identical test dataset accuracy highlights the method’s resilience. These findings support the effectiveness of our approach in reducing false positives and negatives, resulting in unmatched recall and precision in the detection system. The discovery has significant significance as it can potentially improve face detection systems’ performance and reliability in various real-world applications, such as human-computer interaction and surveillance. Convolutional neural networks, deep learning architectures, and metaheuristic optimization approaches were synergized to produce a new and reliable solution
Automatic handwriting recognition is a fundamental component of various applications in various fields. During the last three decades, it has become a challenging issue that has attracted much attention. Latin language handwriting recognition has been the primary focus of researchers. As for the Kurdish language, only a few researches have been conducted. This study uses a Kurdish character dataset, which contains 40,940 characters written by 390 native writers. We present an ensemble transfer learning-based model for automatically recognizing handwritten Kurdish letters using Densenet-201, InceptionV3, Xception, and an ensemble of these pre-trained models. The model’s performance and results obtained by the proposed ensemble model are promising, with a 97% accuracy rate, outperforming other studies on Kurdish character recognition.
An essential component of every RF system’s reception chain is the Low-Noise Amplifier(LNA). The sensitivity and performance of subsequent stages in the receiver chain are significantly influenced by the LNA, which is the initial step. Creating an LNA requires carefully balancing trade-offs in order to have the best possible performance in terms of gain and noise characteristics. Achieving optimal functioning and efficiency in the radio frequency system requires finding the correct balance. This article presents the design of an LNA circuit at the lowest cost without adding components such as inductors, active components, or several stages, which increase the complexity of the circuit, consume power, and add additional noise, by controlling the lengths of the microstrip line, LNA circuit was created by ADS software, and add a matching circuit. At the operating frequency of 2.4 GHz, the suggested design achieved good results with a gain of 17.48dB, NF of 0.7dB, stability factor of 1.5dB, and S11-S22 (-41dB, -25dB) in that order.
Face recognition technique is an automatic approach for recognizing a person from digital images using mathematical interpolation as matrices for these images. It can be adopted to realize facial appearance in the situations of different poses, facial expressions, ageing and other changes. This paper presents efficient face recognition model based on the integration of image preprocessing, Co-occurrence Matrix of Local Average Binary Pattern (CMLABP) and Principle Component Analysis (PCA) methods respectively. The proposed model can be used to compare the input image with existing database images in order to display or record the citizen information such as name, surname, birth date, etc. The recognition rate of the model is better than 99%. Accordingly, the proposed face recognition system is functional for criminal investigations. Furthermore, it has been compared with other reported works in the literature using diverse databases and training images. .