Recent Submissions

  • CFAR Different Schemes Behavior and Detection Performance of Moving Targets

    Salem, Nema; Salem, Ahmed; ElBadawy, ElSayed; No Collaboration; Electrical and Computer Engineering; Ahmed Salem; Salem, Ahmed (The International Institute of Informatics and Cybernetics, IIIS, 2004-07)
    In this paper detection probability of different CFAR schemes CA, GO, SO, and OS-CFAR is computed via various values of false alarm probability. The CA-CFAR and GO-CFAR detection performance is superior over other schemes; OS-CFAR detection performance appears to be the quasi of CA-CFAR but needs more processing time than CA-CFAR. Moving target detection is investigated. Each of the CA, GO, OS-CFAR schemes gives acceptable detection probability at higher values of SNR and gives, as well, maximum performance in the range of 10-4 to 10-6 probability of false alarm. The SO-CFAR scheme doesn’t offer any advantage over other CFAR processors.
  • Recommendations on Streaming Data: E-Tourism Event Stream Processing Recommender System

    ElKafrawy, Passent; Bennawy, Mohamed; External Collaboration; Artificial Intelligence & Cyber Security Lab; Computer Science; Bennawy, Mohamed (Springer International Publishing, 2022-07-02)
    The Association for Computing Machinery ACM recommendation systems challenge (ACM RecSys) [1] released an e-tourism dataset for the first time in 2019. Challenge shared hotel booking sessions from trivago website asking to rank the hotels list for the users. Better ranking should achieve higher click out rate. In this context, Trivago dataset is very important for e-tourism recommendation systems domain research and industry as well. In this paper, description for dataset characteristics and proposal for a session-based recommender system in addition to a comparison of several baseline algorithms trained on the data. The developed model is personalized session-based recommender taking into consideration user search preferences. Technically, paper compare between six different models vary from learning to rank, nearest neighbor and popularity approaches and compared results with two benchmark accuracy. Taking into consideration the ability to deploy model into production environments and the accuracy evaluation based on mean reciprocal rate as per challenge guidelines. Our winning experiment is using one learning to rank model achieving 0.64 mean reciprocal rate compared to 37 model achieving 0.68 by ACM challenge winning team [2].
  • Techno-Economic and Environmental Analysis of a Hybrid Renewable Energy System: Al Qurayyat City, KSA

    Hussein, Aziza; Atlam, H.A.; College collaboration; Electrical and Computer Engineering; 1; Atlam, H.A. (Springer, Cham, 2023-03-08)
    Hybrid renewable energy systems (HRESs) are becoming more prevalent as they are viewed as economic off-grid sources of clean energy that could help reduce rural electrification and global warming problems. This paper aims to provide a techno-economic feasibility and environmental analysis of a HRES to be designed for meeting a daily load requirement of 389.4 kWh/day with a peak load of 82.71 kW, represented by the energy demand of thirty houses located in Al-Qurayyat city, Al Jouf Province, KSA. Thus, the aim of this paper coincides with the KSA’s “Vision 2030” and also with the “Net Zero Plan”, which promote sustainable energy solutions and net zero CO2 emissions, respectively. Moreover, the objective is achieved by designing a HRES consisting of PV, WT, a DG, converter and lead-acid BSS after taking into account the weather and operating conditions of Al Qurayyat city, which represents the novelty of this paper. Simulation of the system is achieved by HOMER to obtain the optimum configuration. After considering six arrangements, the results reveal that the ideal arrangement is indeed the PV/WT/DG//BSS with an optimized NPC and COE of $358,616, and $0.166/kWh while attaining a RF percentage of 92.8%. An alternative configuration, consisting of PV/WT//BSS would yield a 100% RF but with a NPC of $475,374 and COE of $0.22/kWh. The technical results show that the proposed HRES produces a total annual energy of 285,750 kWh/year with the PV, WT, and DG contributing 91.2%, 5.21%, and 3.58%, correspondingly. Regarding the environmental assessment, the optimized HRES annually saves a total of 206,678 kg of greenhouse gases.
  • Video De-interlacing: From Spatial to Adaptive Based Motion Detection

    Salem, Nema; ElBadawy, ElSayed; No Collaboration; Electrical and Computer Engineering; Salem, Nema (The International Institute of Informatics and Cybernetics, IIIS, 2008-07)
    While interlacing succeeds in reducing the transmission bandwidth, it introduces a number of high-frequency artifacts that can distract the human eye, such as flickers and thin vertical lines. Thus, a lot of de-interlacing algorithms are developed. Subjective and objective assessments of spatial and temporal de-interlacing techniques are given in this paper. Combining the benefits of the spatial and temporal algorithms, a motion detector is used to segment the frame into static and dynamic portions. The dynamic is segmented into slow- and high-motion pixels. Finally, an adaptive de-interlacing algorithm based on the results obtained from the motion detector is proposed and judged.
  • Optimizing ADWIN for steady streams

    ElKafrawy, Passent; Moharram, Hassan; Awad, Ahmed; External Collaboration; Artificial Intelligence & Cyber Security Lab; Computer Science; Moharram, Hassan (2022-05-22)
    With the ever-growing data generation rates and stringent constraints on the latency of analyzing such data, stream analytics is overtaking. Learning from data streams, aka online machine learning, is no exception. However, online machine learning comes with many challenges for the different aspects of the learning process, starting from the algorithm design to the evaluation method. One of these challenges is the ability of a learning system to adapt to the change in data distribution, known as concept drift, to maintain the accuracy of the predictions. Over time, several drift detection approaches have been proposed. A prominent approach is adaptive windowing (ADWIN) which can detect changes in features data distribution without explicit feedback on the correctness of the prediction. Several variants for ADWIN have been proposed to enhance its runtime performance, w.r.t throughput, and latency. However, the drift detection accuracy of these variants was not compared with the original algorithm. Moreover, there is no study concerning the memory consumption of the variants and the original algorithm. Additionally, the evaluation was done on synthetic datasets with a considerable number of drifts not covering all types of drifts or steady streams, those that do not have drifts at all or almost negligible drifts. The contribution of this paper is two-fold. First, we compare the original Adaptive Window (ADWIN) and its variants: Serial, HalfCut, and Optimistic in terms of drift detection accuracy, detection speed, and memory consumption, represented in the internal window size. We compare them using synthetic data sets covering different types of concept drifts, namely: incremental, gradual, abrupt, and steady. We also use two real-life datasets whose drifts are unknown. Second, we present ADWIN++. We use an adaptive bucket dropping technique to control window size. We evaluate our technique on the same data sets above and new datasets with fewer drifts. Experiments show that our approach saves about 80% of memory consumption. Moreover, it takes less time to detect concept drift and maintains the drift detection accuracy.
  • All-Optical Logic Circuits Based on the Non-linear Properties of the Semiconductor Optical Amplifier

    Salem, Nema; Awad, Amira; No Collaboration; Electrical and Computer Engineering; Amira Awad; Salem, Nema (IEEE, 2004-07-28)
    This work shows the importance of utilising the nonlinear properties of the semiconductor optical amplifier SOA in constructing optical logic gates, half and full adders, flip-flops, counters and registers. Consequently, SOA may be considered as a promising component for building all-optical digital computer. By using the SOASIM software, This work shows how the optical buffer, inverter, unit-step pulse and falling/rising clock edges can be generated.
  • CMOS Implementation of Programmable Logic Gates and Pipelined Full Adders using Threshold Logic Gates Based on NDR Devices

    Salem, Nema; ElSayed, Mohamed; Mira, Ramy; External Collaboration; Electrical and Computer Engineering; Mira, Ramy (IEEE, 2004-08-16)
    This paper presents a new prototyping technique, which allows efficient verification of circuit concepts based on negative differential resistance (NDR) devices. This prototype, which is called MOS-NDR, has been used to implement programmable logic gates and pipelined-ripple-carry full adders using linear threshold gates (LTGs).
  • Real-time glove and android application for visual and audible Arabic sign language translation

    Salem, Nema; Alharbib, Saja; Khezendarc, Raghdah; Alshami, Hedaih; No Collaboration; Saja Alharbib , Raghdah Khezendarc , Hedaih Alshami; Electrical and Computer Engineering; Salem, Nema (Elsevier: Procedia computer science (163), 2019)
    Researchers can develop new systems to capture, analyze, recognize, memorize and interpret hand gestures with machine learning and sensors. Acoustic communication is a way to convey human opinions, feelings, messages, and information. Deaf and mute individuals communicate using sign language that is not understandable by everyone. Unfortunately, they face extreme difficulty in conveying their messages to others. To facilitate the communication between deaf/mute individuals and normal people, we propose a real-time prototype using a customized glove equipped with five flex and one-accelerometer sensors. These sensors are able to detect the bindings of the fingers and the movements of the hand. In addition, we developed an android mobile application to recognize the captured Arabic Sign Language (ArSL) gestures and translate them into displayed texts and audible sounds. The developed prototype is accurate, low cost and fast in response.
  • IoST: A Multi-CubeSat Cognitive Radio Network

    Barkat, Enfel; No Collaboration; Electrical and Computer Engineering; Enfel Barkat (2022-07-26)
    Fifth- generation communication also known as internet of things is rolling out worldwide. It has provided higher network capacity and speed for mobile broadband communications; however, 5G network focuses only on terrestrial coverage. 6G and Cognitive Radio (CR) is expected to be the future solution to all heavy data traffic and globe coverage. Satellite communication is anticipated to cover rural areas, sea, spanning air, and space in what is known as Internet of Space Things (IoST). Low Earth Orbit (LEO) CubeSat orbits earth provide real time measurements with low transmission power and high data rate. Cognitive radio will focus on providing efficient spectrum use and resources allocations. In this paper, a multi CubeSat cognitive radio network is proposed to improve time delay, increase data exchange, and increase the Signal to Noise Ratio (SNR) of the communication system. simulation results demonstrate the convergence of the multi CubeSat system improving the signal to noise ratio for different number of CubeSats structure.
  • Applications of Capacity Enlargement and Traffic Management Control in Hybrid Satellite-Terrestrial 5G Networks

    Hussein, Aziza; M Mourad Mabrook; External Collaboration; Electrical and Computer Engineering; M Mourad Mabrook (IEEE, 2022-12-16)
    The significant volume of data traffic, ultimate data rates, reduced latency, more transmissions with efficient energy, spectrum consumption, and novel technological use cases must all be considered using the fifth generation (5G) mobile network. Future 5G networks will connect billions of objects, known as the Internet of Things (IoT) or massive Machine-T Communications (mMTC), in addition to standard Mobile Broadband (MBB) services. Non-Terrestrial Networks (NTNs) may serve connection requests anywhere and anytime by offering wide-area coverage and preserving service continuity, availability, and scalability. The satellite platform is a crucial NTN for integrating with the 5G network and delivering the necessary services. Soon, 5G network development will depend on satellite access, as stated in the 3Gpp Release 16 specification. This paper provides options for incorporating satellite systems into a 5G network design to increase capacity and extend coverage in 5G mobile networks. In addition, 5G networks must address a network model to resolve outage, congestion, and cell edge context issues. The last phase is the simulation of the problem formulation for the investigation of capacity and traffic in hybrid satellite-terrestrial 5G mobile backhauling networks.
  • Medical image enhancement based on histogram algorithms

    Salem, Nema; Asmaa Shams; Malik, Hebatullah; No Collaboration; Hebatullah Malik, and Asmaa Shams; Electrical and Computer Engineering; Salem, Nema (Elsevier, 2019)
    Medical images constitute important information that clinicians need to diagnose and make the suitable treatment decisions. The diagnostic process extremely involves the image visual perception. Unfortunately, the possibility of error existence in perception is not acceptable as it mainly affects the patients’ lives. Image enhancement improves the visual quality of image, helps the clinician in his decision and thus saves the patients’ lives. Histogram is a common tool for improving contrast in medical imaging. It recovers the lost contrast by redistributing the image brightness values that unfortunately may generate undesirable artifacts. Therefore, researchers developed the histogram-based algorithms to overcome this problem. This paper presents a comprehensive study of many histogram-based algorithms. We utilized the powerful MATLAB package to analyze the enhancement performance of these histogram-based algorithms. Moreover, this paper quantitatively compares the results and thus evaluates their performance by three metric parameters, which are the mean square error, standard deviation, and the peak signal to noise ratio
  • Life Distribution of Commercial Concentrator III-V Triple-Junction Solar Cells in View of Inverse Power law and Arrhenius Life-stress Relationships

    Dunya Y Dennah; Salwa B Ammach; Abdul Majid, Mohammed; Barkat, Enfel; External Collaboration; Electrical and Computer Engineering; Dennah, Dunya Y (IEEE, 2022-03-30)
    The paper shows that the life distributions of the commercial concentrator lattice match Triple-Junction III-V solar cells are significantly different when extrapolated using the inverse power law and Arrhenius life-stress relationships. This conclusion is drawn after applying the two relationships on real data of accelerated lifetimes of such solar cells that are assumed to follow Weibull distribution. The mathematical treatment for both cases is provided in more detail.
  • Life Distribution of Commercial Concentrator III-V Triple-Junction Solar Cells in View of Inverse Power law and Arrhenius Life-stress Relationships

    Dunya Y Dennah; Salwa B Ammach; Barkat, Enfel; Abdul Majid, Mohammed; External Collaboration; Electrical and Computer Engineering (IEEE, 2022-03-30)
    The paper shows that the life distributions of the commercial concentrator lattice match Triple-Junction III-V solar cells are significantly different when extrapolated using the inverse power law and Arrhenius life-stress relationships. This conclusion is drawn after applying the two relationships on real data of accelerated lifetimes of such solar cells that are assumed to follow Weibull distribution. The mathematical treatment for both cases is provided in more detail.
  • Comparison between Two-Port Converter and Three-Port Converter at Different Weather Conditions

    Hussein, Aziza; Amani S. Alzahrani; Marwa M. Ahmed; Mohamed A. Enany; External Collaboration; Electrical and Computer Engineering; 1
    Worldwide energy demand is growing fast because of the population explosion. Technological advancements paved the way toward utilizing renewable energy sources instead of fossil fuels as they cause harmful effects on the environment. To increase the efficiency of a solar PV system, Maximum Power Point Tracking (MPPT) techniques are applied to a power converter that is connected to the PV array. Thus, maximum power is extracted from the PV array. Since sunlight is not always available, a battery is used as a storage device. Traditionally, two two-port converters are used with such systems. Recently, three-port converter that connect the PV, the battery, and the load together using a single converter is introduced in the literature. This paper compares between these two types of converters based on the PV power output when the solar irradiance changes. The simulation is done using MATLAB/SIMULINK software. It is found out that two-port converter responds more efficiently to irradiance changes than the three-port converter. However, three- port converter has more steady attitude when the temperature is constant for a certain amount of time. The significance of this paper reiles on comparing between these two types of converters to determine the best choice for a certain application.
  • RIFD Fibonacci Zeckendorf Hybrid Encoding and Decoding Algorithm for Medical Image Compression and Reconstruction

    Salem, Nema; Elnaggar, Fathy; No Collaboration; Electrical and Computer Engineering; Salem, Nema (IEEE, 2020-11-23)
    Digital medical images are an important source of information that help doctors in diagnosis and treatment. The raw form of a digital image requires a tremendous amount of storage memory and a longer time for transmission from one node to another through a limited bandwidth network. Thus, many algorithms are developed and implemented for image compression that eliminates the redundant information while keeping the essential ones. The decoding algorithms are able to extract this essential information and reconstruct the original images without losing the original image quality. Rounding a pixel's Intensity Followed by a Division process is called RIFD algorithm. It minimizes the information redundancy of the images and maintains the image visual quality with insignificant distortion. The integration of Fibonacci sequence and Zeckendorf's theorem produces a simple and fast variable length code for representing integer data. This article proposes a hybrid encoding and decoding algorithm for medical image compression by merging the RIFD and the suffix variable length second order Fibonacci-Zeckendorf codes. Performance metrics such as number of bits per pixel, compression ratio, memory saving percentage, run time, mean square error, peak signal to noise ratio and similarity structure index are used in evaluating the efficiency of the proposed algorithm on nine medical images. The simulation results shows the efficiency of the proposed algorithm especially in compressing images with non uniform distributed histograms.
  • A Comparative Study on the Performance of Hidden Markov Model in Appliance Modeling

    Salem, Nema; Malik, Hebatullah; AlSabban, Maha; Department Collaboration; Hebatullah Malik, and Maha AlSabban; Electrical and Computer Engineering; Malik, Hebatullah (IEEE, 2021)
    Load modeling using data-driven algorithms is a widely used technique in applications like load identification. It is also one of the fundamental concepts which enable Non-Intrusive Appliance Load Modeling (NIALM). This paper develops a load modeling framework using Hidden Markov Models (HMMs) to identify a two-state home appliance. Unlike previous studies, the training and testing dataset is derived from different monitored domestic houses to analyze the effect of the training data trends on the model’s accuracy. We used the Reference Energy Disaggregation Dataset (REDD) in the load modeling process. The developed system utilizes adaptive measures to construct HMM models that can identify foreign variants of the same two-state appliance. We measured the accuracy of our proposed methodology by comparing a known state sequence with a Viterbi-generated one. The accuracy results are up to 96%, depending on the nature of the used training dataset.
  • Data dimensional reduction and principal components analysis

    Salem, Nema; Hussien, Sahar; Department Collaboration; Electrical and Computer Engineering; Salem, Nema (Elsevier, 2019)
    Research in the fields of machine learning and intelligent systems addresses essential problem of developing computer algorithms that can deal with huge amounts of data and then utilize this data in an intellectual way to solve a variety of real-world problems. In many applications, to interpret data with a large number of variables in a meaningful way, it is essential to reduce the number of variables and interpret linear combinations of the data. Principal Component Analysis (PCA) is an unsupervised learning technique that uses sophisticated mathematical principles to reduce the dimensionality of large datasets. The goal of this paper is to provide a complete understanding of the sophisticated PCA in the fields of machine learning and data dimensional reduction. It explains its mathematical aspect and describes its relationship with Singular Value Decomposition (SVD) when PCA is calculated using the covariance matrix. In addition, with the use of MATLAB, the paper shows the usefulness of PCA in representing and visualizing Iris dataset using a smaller number of variables.
  • Transient Performance of Voltage Source Converter in V2G and G2V Electric Vehicles Application

    Ahmed, Toqeer; Mian Qaisar, Saeed; Waqar, Asad; Hussain, Tanveer; Iqbal, Ahsan; External Collaboration; Electrical and Computer Engineering (IEEE, 2022-12-30)
    Electric vehicles (EVs) always integrate into the utility grid via power electronics interfaces like voltage source converters (VSCs). The VSCs manage the power flow between the utility grid and the EVs in bidirectional mode depending upon various conditions. However, the smooth transition of the bidirectional mode depends upon the controller used to drive the references of the VSC. In this paper, the transient performance of the VSC in vehicle- to-grid (V2G) and grid- to-vehicle( G 2V) EVs application is tested under voltage sag/swell using the fractional order sliding mode control (FOSMC). The primary focus is to manage the power flow between the utility grid and the EVs based on the state of charge (SOC) of the EV battery and the ampacity of the utility grid under grid transients. A simulation model with a utility grid, VSC, and an EV battery has been modeled at 180kVAR, 400V, and 50 Hz distribution feeder. The stability analysis of FOSMC has been ensured with the Lyapunov candidate function. The results of the proposed control have been compared with the classical PI control. It has been noticed that the proposed control is robust in terms of speedy tracking, fast convergence, and finest damping.
  • Shape factors for analysis of breast tumors in mammograms

    Salem, Nema; Rangayyan, Rangaraj; Desautels, J. E. Leo; Alim, Onsy; External Collaboration; Electrical and Computer Engineering; Salem, Nema (IEEE, 2002-08-06)
    Distinguishing between benign and malignant breast tumors requires careful analysis of their shape complexity and radiographic definition. In this paper we examine the usefulness of shape factors such as compactness, moments, Fourier descriptors, and statistics of chord lengths in distinguishing between circumscribed/spiculated and benign/malignant masses. A database of 54 tumors was used in pattern classification experiments. Classification accuracies of 95% for circumscribed/spiculated, 76% for benign/malignant, and 77% for four-group classification were obtained, which indicate the usefulness of the proposed methods in breast cancer diagnosis.
  • Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) Power Forecasting

    Salem, Nema; Malik, Hebatullah; AlSabban, Maha; No Collaboration; 2; Electrical and Computer Engineering; AlSabban, Maha (IEEE, 2022-02-02)
    The geographical position of the Kingdom of Saudi Arabia has significant potentials for utilizing renewable energy resources, which aligns with the country's vision for 2030. This paper proposes a solution to achieve energy sustainability by forecasting future load demands through adopting three different scenarios. We used the outsourced Individual Household Electric Power Consumption Dataset, University of California-Irvine repository, for testing our proposed system. We utilized the Long Short-term Memory-Recurrent Neural Network (LSTM-RNN) algorithm to estimate the whole house power consumption for different horizons: every 15 minutes, daily, weekly, and monthly. Next, we evaluated the performance of the system by Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), and R2 score metrics. Then, we applied the Mean Absolute Percentage Error (MAPE) to find its accuracy. The results showed that the monthly forecasting interpretation scenario was the best performing model. That scenario used (n-1) months for training and the last month for testing. The scores for that model were 0.034 (MAE), 0.001 (MSE), 0.034 (RMSE), and 97.16% (accuracy). The constructed model successfully achieved its goals of predicting the active power of the household and now can be accommodated on energy applications not only in Saudi Arabia but also in any other country.

View more