Yazar "Mazher, Wamidh Jalil" seçeneğine göre listele
Listeleniyor 1 - 9 / 9
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A grasshopper optimizer approach for feature selection and optimizing SVM parameters utilizing real biomedical data sets(Springer London Ltd, 2019) Ibrahim, Hadeel Tariq; Mazher, Wamidh Jalil; Uçan, Osman Nuri; Bayat, OğuzSupport vector machines (SVM) are one of the important techniques used to solve classifications problems efficiently. Setting support vector machine kernel factors affects the classification performance. Feature selection is a powerful technique to solve dimensionality problems. In this paper, we optimized SVM factors and chose features using a Grasshopper Optimization Algorithm (GOA). GOA is a new heuristic optimization algorithm inspired by grasshoppers searching for food. It approved its ability to solve real-world problems with anonymous search space. We applied the proposed GOA + SVM approach on biomedical data sets for Iraqi cancer patients in 2010-2012 and for University of California Irvine data sets.Öğe AIoT in healthcare: a systematic mapping study(Institute of Electrical and Electronics Engineers Inc., 2022) Ibrahim, Hadeel Tariq; Mazher, Wamidh Jalil; Uçan, Osman Nurihe Internet of Things (IoT) infrastructure and artificial intelligence (AI) technologies are combined to create artificial intelligence of things (AIoT). AIoT in healthcare is a key factor in enabling physicians' offices and hospitals as well as giving patients access to superior scientific facilities. To this end, we conduct a Systematic Mapping Study (SMS) to provide critical information about various applications of AIoT in healthcare. The primary goals of this research are to provide an overview of AIoT research in healthcare and to categorize AIoT research based on annual number of publications, publication venues, and journal distribution. We present some AIoT techniques used in healthcare fields in nine well-known online libraries (IEEE, Springer, Elsevier, MDPI, Taylor and Francis, Hindawi, Wiley online lib., ACM and Google). Initially, we used a number of research questions related to the issue, and when we applied them, 71 studies were produced.Öğe Boosting Multiverse Optimizer by Simulated Annealing for Dimensionality Reduction(Airlangga University, 2025) Mutlag, Wamidh K.; Mazher, Wamidh Jalil; Ibrahim, Hadeel Tariq; Uçan, Osman NuriBackground: Because of The Multi-Verse Optimizer (MVO) has gained popularity in feature selection due to its strong global and local search capabilities. However, its effectiveness diminishes when tackling high-dimensional datasets due to the exponential growth of the search space and a tendency for premature convergence. Objective: This study aims to enhance MVO’s performance by integrating it with the Simulated Annealing Algorithm (SAA), creating a hybrid model that improves search convergence and optimizes feature selection efficiency. Methods: A High-level Relay Hybrid (HRH) architecture is proposed, where MVO identifies promising regions of the feature space and passes them to SAA for local refinement. The resulting MVOSA-FS model was evaluated on ten high-dimensional benchmark datasets from the Arizona State University (ASU) repository. Support Vector Machine (SVM) classifiers were used to assess the classification accuracy. MVOSA-FS achieved superior performance compared to six state-of-the-art feature selection algorithms: Atom Search Optimization (ASO), Equilibrium Optimizer (EO), Emperor Penguin Optimizer (EPO), Monarch Butterfly Optimization (MBO), Satin Bowerbird Optimizer (SBO), and Sine Cosine Algorithm (SCA). Results: The proposed model yielded the lowest average classification error rate (1.45%), smallest standard deviation (0.008), and most compact feature subset (0.91%). The hybrid MVOSA-FS model effectively balances exploration and exploitation, delivering robust and scalable performance in feature selection for high-dimensional data. Conclusion: This hybridization approach demonstrates improved classification accuracy and reduced computational burden.Öğe Drone swarm with free-space optical communication to detect and make deep decisions about physical problems for area surveillance(Spie-Soc Photo-Optical Instrumentation Engineers, 2018) Mazher, Wamidh Jalil; Ibrahim, Hadeel T.; Uçan, Osman Nuri; Bayat, OğuzThis paper aims to design a drone swarm network by employing free-space optical (FSO) communication for detecting and deep decision making of topological problems (e.g., oil pipeline leak), where deep decision making requires the highest image resolution. Drones have been widely used for monitoring and detecting problems in industrial applications during which the drone sends images from the on-air camera video stream using radio frequency (RF) signals. To obtain higher-resolution images, higher bandwidth (BW) is required. The current study proposed the use of the FSO communication system to facilitate higher BW for higher image resolution. Moreover, the number of drones required to survey a large physical area exceeded the capabilities of RF technologies. Our configuration of the drones is V-shaped swarm with one leading drone called mother drone (DM). The optical decode-and-forward (DF) technique is used to send the optical payloads of all drones in V-shaped swarm to the single ground station through DM. Furthermore, it is found that the transmitted optical power (Pt) is required for each drone based on the threshold outage probability of FSO link failure among the onboard optical-DF drones. The bit error rate of optical payload is calculated based on optical-DF onboard processing. Finally, the number of drones required for different image resolutions based on the size of the considered topological area is optimized. (C) 2018 Society of Photo-Optical Instrumentation Engineers (SPIE)Öğe Feature selection using salp swarm algorithm for real biomedical datasets(Int Journal Computer Science & Network Security-Ijcsns, 2017) Ibrahim, Hadeel Tariq; Mazher, Wamidh Jalil; Uçan, Osman Nuri; Bayat, Oğuz; Uçan, Osman NuriThe main objective of this paper is to develop a new powerful heuristic optimization algorithm to be used in feature selection. Here, the use of Salp Swarm Algorithm in feature selection (SSA-FS) is proposed for the first time in literature. SSA-FS has been compared with Particle Swarm Optimization and Differential Evolution performance with criteria of accuracy and runtime. In this paper, real datasets obtained from Iraqi hospitals for breast, bladder and colon cancers and synthetic datasets for evaluation. We have found that SSA-FS has been achieved the highest accuracies with less runtime in comparison with other selected algorithms for both real and synthetic datasets.Öğe Impact of pointing error on SISO/MISO drones swarm-based free space optical system in weak turbulence regime(Indonesian Journal of Electrical Engineering and Computer Science, 2021) Mahdi, Abdullah Jameel; Mazher, Wamidh Jalil; Uçan, Osman NuriApplying the drone-based free space optical (FSO) technology is recent in communication systems. The FSO technology has high-security features due to narrow beamwidth, insusceptible to interferences, free license, and landline connection is not appropriate. However, these advantages face many obstacles that affect the system's performance, such as random weather conditions and misalignment. The pointing error Hp is one of the critical factors of the channel gain H. The related parameters of the Hp factor: the pointing error angles θr and the path length Z, were manipulated to extract the applicable values at various receiver diameter values. The proposed system has two topologies: single input single output (SISO) and multiple input single output (MISO), flying in weak atmospheric turbulence. The simulation was done using MATLAB software 2020. The average bit error rate (ABER) for the system versus signal-to-noise ratio (SNR) were verified and analyzed. The results showed that at θr=10−3 rad, Z increased in the range 10~100m for each one-centimeter increase of DR. At θr=10−2 rad, the applicable Z was nearly 10% of the link distance Z when θr=10−3 rad was applied. Consequently, an increase in θr must correspond decrease in Z and vice versa to maintain the system at high performance.Öğe Optical onboard double decoding/forward performance with long codes for optical routing(Spie-Soc Photo-Optical Instrumentation Engineers, 2019) Mazher, Wamidh Jalil; Ibrahim, Hadeel Tariq; Mathboob, Yaareb M.; Uçan, Osman NuriThe optical decoding and forward (ODF) performance with long systematic Hamming distance-4 (LSD_4) codes is suggested. Hereby, the LSD_4 codes are produced via generating 224 codewords of 15 bits length. The LSD_4 codes length is extremely long (equal to 4096 bits); accordingly, the encoding/decoding by the LSD_4 codes becomes more compatible with optical speed and consistency. Apparently, increasing the length of coding is concurrent with the ODF speed. Our model is grounded on hiring the LSD_4 codes in the encoding/decoding process of the onboard ODF for optical routing serial. The net gain of plugging the planned LSD_4 codes in optical routing is obtained within 5- to 15-dB range for diverse optical routing forms at code length 4096 bits with Q-ary pulse-position modulation. The numeric and simulated results confirmed the significant improvements of the planned LSD_4 codes performance with ODF over the non-LSD_4 codes ODF counterparts. (C) 2019 Society of Photo-Optical Instrumentation Engineers (SPIE)Öğe Parameter optimization for hovering multi-rotor drones-based free-space optical links(Applied Nanoscience, 2021) Mahdi, Abdullah Jameel; Mazher, Wamidh JalilMulti-rotor (MR) Drones have recently emerged as a viable method for creating fexible free-space optical (FSO) connections. In this study, we look at how precise parameters optimization can be used to evaluate the benefts of using MR Drones for such nanometer links, with consideration of the combined efect of atmospheric turbulence along with pointing error factor hp. The related parameters of hp are the connection distance d and pointing error angle (PEA) θ. In contrast to past studies on the subject, this one increased the connection distance d between drones swarm for high values PEAs that had been got high Bit Error Rate (BER). The system consists of two channels type: Single Input–Single Output (SISO) and Multiple Input–Single Output (MISO), and was simulated using MATLAB 2020. The results showed that for PEA θ=10−3 and 10−2 rad, the connection distance d increased from 5 to 20 percent per one centimeter increasing in the receiver diameter Dr, and for PEA θ=10−1 rad, the connection distance d increased few meters; therefore, it is not recommended to increase the receiver diameter.Öğe Performance of systematic distance-4 codes in free-space optical communication system(Int Journal Computer Science & Network Security-Ijcsns, 2017) Mazher, Wamidh Jalil; Bayat, Oğuz; Uçan, Osman NuriIn this paper, we reconfigured the SD-4 code with both: long and very long code lengths. Firstly, we generated SD-4 code with 15 codeword length that implies SD-4 code 3,900 lengths, secondly, we extended SD-4 code to 32,768 which is very long code length. Our model is based on SD-4 code as an encoding/decoding block cascaded by multiple pulse-position modulations (Q-PPM) in FSO communication environment. Such model performance is evaluated by lognormal atmospheric turbulent fading channels. Furthermore, coding gains are compared with different code lengths and Q-PPM modulations to demonstrate such codes ability of coding with pulse position modulation (Q-PPM). The optimal obtained raw code gain is equal to 0.56 dB for SD-4 at code length (4096) which analyzed with BPPM regarding the other related codewords (channel throughput is not considered). Meanwhile; the real code gain results have been obtained and equal to 3.87 dB at code length (32768) for such channel(channel throughput is considered). Tto demonstrate the SD-4 code ability to be coded with Q-PPM, we analyzed such code utilizing 4PPM and 8PPM. Also, we compared our results with existing results for other techniques namely : Hamming, Reed-Solomon, and Bose-Chaudhuri-Hocquenghem.
