Yazar "Pashaei, Elham" seçeneğine göre listele
Listeleniyor 1 - 16 / 16
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Detection of Man-in-the-Middle Attack Through Artificial Intelligence Algorithm(Springer Science and Business Media Deutschland GmbH, 2024) Taştan, Ahmet Nail; Gönen, Serkan; Barışkan, Mehmet Ali; Kubat, Cemallettin; Kaplan, Derya Yıltaş; Pashaei, ElhamThe amalgamation of information technologies and progressive wireless communication systems has profoundly impacted various facets of everyday life, encompassing communication mediums, occupational procedures, and living standards. This evolution, combined with enhanced wireless communication quality, has culminated in an exponential rise in interconnected devices, including domestic appliances, thereby birthing the Internet of Things (IoT) era. This proliferation, facilitated by cloud computing enabling remote device control, concurrently intensifies cybersecurity threats. Traditional Information and Communication Technology (ICT) architectures, characterized by a hub-and-spoke model, are inherently vulnerable to illicit access and Man-in-the-Middle (MITM) intrusions, thereby endangering information confidentiality. Leveraging Artificial Intelligence (AI) can ameliorate this scenario, enhancing threat training and detection capabilities, enabling precise and preemptive attack countermeasures. This research underscores the criticality of addressing the security implications accompanying technological advancements and implementing protective measures. Deploying AI algorithms facilitates efficient passive attack identification and alleviates network device burdens. Specifically, this study scrutinized the ramifications of an MITM attack on the system, emphasizing the detection of this elusive threat using AI. Our findings attest to AI’s efficacy in detecting MITM attacks, promising significant contributions to future cybersecurity research. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Öğe An efficient binary chimp optimization algorithm for feature selection in biomedical data classification(SPRINGER LONDON LTD, 236 GRAYS INN RD, 6TH FLOOR, LONDON WC1X 8HL, ENGLAND, 2022) Pashaei, Elnaz; Pashaei, ElhamAccurate classification of high-dimensional biomedical data highly depends on the efficient recognition of the data’s main features which can be used to assist diagnose related diseases. However, due to the existence of a large number of irrelevant or redundant features in biomedical data, classification approaches struggle to correctly identify patterns in data without a feature selection algorithm. Feature selection approaches seek to eliminate irrelevant and redundant features to maintain or enhance classification accuracy. In this paper, a new wrapper feature selection method is proposed based on the chimp optimization algorithm (ChOA) for biomedical data classification. The ChOA is a newly proposed metaheuristic algorithm whose capability for solving feature selection problems has not been investigated yet. Two binary variants of the ChoA are introduced for the feature selection problem. In the first approach, two transfer functions (S-shaped and V-shaped) are used to convert the continuous version of ChoA to binary. In addition to the transfer function, the crossover operator is utilized in the second approach to improve the ChOA’s exploratory behavior. To validate the efficiency of the proposed approaches, five publicly available high-dimensional biomedical datasets, and a few datasets from different domains such as life, text, and image are employed. The proposed approaches were then compared with six well-known wrapper-based feature selection methods, including multi-objective genetic algorithm (GA), particle swarm optimization (PSO), Bat algorithm (BA), ant colony optimization (ACO), firefly algorithm (FA), and flower pollination (FP) algorithm, as well as two standard filter-based feature selection methods using three different classifiers. The experimental results demonstrate that the proposed approaches can effectively remove the least significant features and improve classification accuracy. The suggested wrapper feature selection techniques also outperform the GA, PSO, BA, ACO, FA, FP, and other existing methods in the terms of the number of selected genes, and classification accuracy in most cases.Öğe A fusion approach based on black hole algorithm and particle swarm optimization for image enhancement(Springer, 2023) Pashaei, Elnaz; Pashaei, ElhamThe main objective of this paper is to present a new 2-stage hybrid optimization algorithm based scheme named PSO-BHA for image enhancement. A parameterized mapping function and a novel objective function are utilized in this paper to achieve the best-enhanced images. The suggested scheme combines the merits of particle swarm optimization (PSO) with the black hole algorithm (BHA) in two sequential stages to find the best parameters for the mapping function with the aid of the proposed objective function. The objective function uses contrast, edge, entropy, and universal quality index (UQI) for measuring contrast, and different improved information in the enhanced image. In the proposed scheme, PSO is applied first to adjust the tunable parameters of the mapping function and as a result, new pixel intensities are produced. Then, in the second stage, the obtained pixel intensities are again passed through the mapping function whose parameters are tuned by the use of the BHA. The suggested framework overcomes the limitations of the traditional histogram equalization (HE) based enhancement techniques in which excessive contrast enhancement and image information loss can occur. The suggested method is evaluated on several test images and compared with different state-of-the-art methods. The results indicate that the proposed framework provides superior performance to all existing methods in terms of various metrics. The proposed scheme also contributes to substantial feature enhancement and contrast boosting in the enhanced image, while retaining the natural feel of the original image.Öğe Gaussian quantum arithmetic optimization-based histogram equalization for medical image enhancement(SPRINGER, VAN GODEWIJCKSTRAAT 30, 3311 GZ DORDRECHT, NETHERLANDS, 2023) Pashaei, Elnaz; Pashaei, ElhamThe quality of medical images is critical for accurate diagnosis. This paper introduces a novel Quantum-behaved Arithmetic Optimization Algorithm (QAOA) for medical images. A mutation operator with Gaussian probability distribution is used in the proposed QAOA as a powerful strategy to enhance QAOA performance in preventing premature convergence to local optima. Gaussian QAOA (GQAOA) is tailored for medical image enhancement and hybridized with Contrast Limited Adaptive Histogram Equalization (CLAHE) to boost the information contents and details of medical images. GQAOA computes the optimal clip limit and other parameters of CLAHE using a new multiobjective fitness function. A combination of five image quality measurements including contrast, information entropy, edge information, Structural Similarity Index Measure (SSIM), and sharpness is suggested as an efficient fitness function to help the proposed framework produce good results. A comparative study is conducted with well-known histogram-based process techniques and state-of-art methods to demonstrate the efficiency of the suggested algorithm. The experimental results prove that the suggested approach performs better than the most current well-established enhancement strategies in the terms of visual interpretation, information entropy, SSIM, Peak Signal to Noise Ratio (PSNR), Naturalness Image Quality Evaluator (NIQE), Absolute Mean Brightness Error (AMBE), and Quality Index (QI) metrics.Öğe Gene Selection for Cancer Classification using a New Hybrid of Binary Black Hole Algorithm(IEEE, 2020) Pashaei, Elnaz; Pashaei, ElhamThis paper proposes a new hybrid approach for solving gene selection problems in cancer microarray data, which is one of the most challenging tasks in bioinformatics. Minimum-redundancy-maximum-relevance (mRMR) filter approach is combined with the binary black hole optimization algorithm (BBHA) to pick out extremely discriminative genes from cancer datasets. The support vector machine (SVM) is employed as a fitness function to accurately diagnose cancer. The experimental results prove that the suggested method exhibits better classification accuracy with the smallest gene subset compared to existing state-of-art methods.Öğe Gene selection using hybrid dragonfly black hole algorithm: A case study on RNA-seq COVID-19 data(ACADEMIC PRESS INC ELSEVIER SCIENCE, 525 B ST, STE 1900, SAN DIEGO, CA 92101-4495, 2021) Pashaei, Elnaz; Pashaei, ElhamThis paper introduces a new hybrid approach (DBH) for solving gene selection problem that incorporates the strengths of two existing metaheuristics: binary dragonfly algorithm (BDF) and binary black hole algorithm (BBHA). This hybridization aims to identify a limited and stable set of discriminative genes without sacrificing classification accuracy, whereas most current methods have encountered challenges in extracting disease-related information from a vast amount of redundant genes. The proposed approach first applies the minimum redundancy maximum relevancy (MRMR) filter method to reduce the dimensionality of feature space and then utilizes the suggested hybrid DBH algorithm to determine a smaller set of significant genes. The proposed approach was evaluated on eight benchmark gene expression datasets, and then, was compared against the latest state-of-art techniques to demonstrate algorithm efficiency. The comparative study shows that the proposed approach achieves a significant improvement as compared with existing methods in terms of classification accuracy and the number of selected genes. Moreover, the performance of the suggested method was examined on real RNASeq coronavirus-related gene expression data of asthmatic patients for selecting the most significant genes in order to improve the discriminative accuracy of angiotensin-converting enzyme 2 (ACE2). ACE2, as a coronavirus receptor, is a biomarker that helps to classify infected patients from uninfected in order to identify subgroups at risk for COVID-19. The result denotes that the suggested MRMR-DBH approach represents a very promising framework for finding a new combination of most discriminative genes with high classification accuracy.Öğe Gene Selection using Intelligent Dynamic Genetic Algorithm and Random Forest(IEEE, 2019) Pashaei, Elham; Pashaei, ElnazMicroarray gene expression data has provided a successful framework for investigating cancer and genetic diseases. Finding cancer-related genes using feature selection methods is of the greatest importance in microarray analysis. However, selecting a small number of informative genes is a challenging task due to the curse of dimensionality in the microarray dataset. This study introduces a new hybrid model based on the Intelligent Dynamic Genetic Algorithm (IDGA) and random forest to distinguish a small meaningful set of genes for cancer classification. This random forest-based IDGA algorithm uses not only random forest in filtering noisy and redundant genes but also in its fitness function. The proposed method was evaluated on two benchmark datasets, namely leukemia and colon cancer data and top explored genes were reported. Experimental results demonstrate that the suggested method has an excellent selection and classification performance compared to several recently proposed approaches.Öğe Hybrid binary arithmetic optimization algorithm with simulated annealing for feature selection in high‑dimensional biomedical data(SPRINGER, VAN GODEWIJCKSTRAAT 30, 3311 GZ DORDRECHT, NETHERLANDS, 2022) Pashaei, Elham; Pashaei, ElnazGene expression data play a signifcant role in the development of efective cancer diagnosis and prognosis techniques. However, many redundant, noisy, and irrelevant genes (features) are present in the data, which negatively afect the predictive accuracy of diagnosis and increase the computational burden. To overcome these challenges, a new hybrid flter/wrapper gene selection method, called mRMR-BAOACSA, is put forward in this article. The suggested method uses Minimum Redundancy Maximum Relevance (mRMR) as a frst-stage flter to pick top-ranked genes. Then, Simulated Annealing (SA) and a crossover operator are introduced into Binary Arithmetic Optimization Algorithm (BAOA) to propose a novel hybrid wrapper feature selection method that aims to discover the smallest set of informative genes for classifcation purposes. BAOAC-SA is an enhanced version of the BAOA in which SA and crossover are used to help the algorithm in escaping local optima and enhancing its global search capabilities. The proposed method was evaluated on 10 well-known microarray datasets, and its results were compared to other current state-of-the-art gene selection methods. The experimental results show that the proposed approach has a better performance compared to the existing methods in terms of classifcation accuracy and the minimum number of selected genes.Öğe Hybrid binary COOT algorithm with simulated annealing for feature selection in high-dimensional microarray data(Springer London Ltd, 2023) Pashaei, Elnaz; Pashaei, ElhamMicroarray analysis of gene expression can help with disease and cancer diagnosis and prognosis. Identification of gene biomarkers is one of the most difficult issues in microarray cancer classification due to the diverse complexity of different cancers and the high dimensionality of data. In this paper, a new gene selection strategy based on the binary COOT (BCOOT) optimization algorithm is proposed. The COOT algorithm is a newly proposed optimizer whose ability to solve gene selection problems has yet to be explored. Three binary variants of the COOT algorithm are suggested to search for the targeting genes to classify cancer and diseases. The proposed algorithms are BCOOT, BCOOT-C, and BCOOT-CSA. In the first method, a hyperbolic tangent transfer function is used to convert the continuous version of the COOT algorithm to binary. In the second approach, a crossover operator (C) is used to improve the global search of the BCOOT algorithm. In the third method, BCOOT-C is hybridized with simulated annealing (SA) to boost the algorithm's local exploitation capabilities in order to find robust and stable informative genes. Furthermore, minimum redundancy maximum relevance (mRMR) is used as a prefiltering technique to eliminate redundant genes. The proposed algorithms are tested on ten well-known microarray datasets and then compared to other powerful optimization algorithms, and recent state-of-the-art gene selection techniques. The experimental results demonstrate that the BCOOT-CSA approach surpasses BCOOT and BCOOT-C and outperforms other techniques in terms of prediction accuracy and the number of selected genes in most cases.Öğe Hybrid Hypercube Optimization Search Algorithm and Multilayer Perceptron Neural Network for Medical Data Classification(HINDAWI LTD, ADAM HOUSE, 3RD FLR, 1 FITZROY SQ, LONDON W1T 5HF, ENGLAND, 2022) Tunay, Mustafa; Pashaei, Elnaz; Pashaei, ElhamThe hypercube optimization search (HOS) approach is a new efficient and robust metaheuristic algorithm that simulates the dove's movement in quest of new food sites in nature, utilizing hypercubes to depict the search zones. In medical informatics, the classification of medical data is one of the most challenging tasks because of the uncertainty and nature of healthcare data. This paper proposes the use of the HOS algorithm for training multilayer perceptrons (MLP), one of the most extensively used neural networks (NNs), to enhance its efficacy as a decision support tool for medical data classification. The proposed HOS-MLP model is tested on four significant medical datasets: orthopedic patients, diabetes, coronary heart disease, and breast cancer, to assess HOS's success in training MLP. For verification, the results are compared with eleven different classifiers and eight well-regarded MLP trainer metaheuristic algorithms: particle swarm optimization (PSO), biogeography-based optimizer (BBO), the firefly algorithm (FFA), artificial bee colony (ABC), genetic algorithm (GA), bat algorithm (BAT), monarch butterfly optimizer (MBO), and the flower pollination algorithm (FPA). The experimental results demonstrate that the MLP trained by HOS outperforms the other comparative models regarding mean square error (MSE), classification accuracy, and convergence rate. The findings also reveal that the HOS help the MLP to produce more accurate results than other classification algorithms for the prediction of diseases.Öğe Hybrid Krill Herd Algorithm with Particle Swarm Optimization for Image Enhancement(Springer, 2021) Pashaei, Elnaz; Pashaei, Elham; Aydin, NizamettinImage enhancement, aimed at improving the image contrast and information quality, is one of the most critical steps in image processing. Due to insufficient enhancement and the mean shift problem of conventional image enhancement techniques, new artificial intelligence-based image enhancement approaches have become an inevitable need in image processing. This paper employs the krill herd algorithm (KHA) and particle swarm optimization (PSO) to suggest a novel hybrid approach, called (PSOKHA) for image enhancement. The suggested PSOKHA method is used in search of optimum transfer function parameters to increase the quality of the images. For comparative evaluation, the performance of the PSOKHA is compared with six latest successful enhancement methods: PSO, KHA, screened Poisson equation (SPE), histogram equalization (HE), brightness preserving dynamic fuzzy HE (BPDFHE), and adaptive gamma correction weighted distribution (AGCWD). Experiments results in testing images include a medical image, a satellite image, and a handwritten image, demonstrate that the suggested strategy can produce better enhanced images in terms of several measurement criteria such as contrast, PSNR, entropy, and structure similarity index (SSIM). © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe Konuşmalardaki duygunun evrişimsel LSTM modeli ile tespiti(DÜ Mühendislik Fakültesi / Dicle Üniversitesi, 2021) Öztürk, Ömer Faruk; Pashaei, ElhamKonuşmada duygu tanıma İngilizce adıyla Speech emotion recognition (SER), duyguların konuşma sinyalleri aracılığıyla tanınması işlemidir. İnsanlar, iletişiminin doğal bir parçası olarak bu işlemi verimli bir şekilde yerine getirebilse de programlanabilir cihazlar kullanarak duygu tanıma işlemi hali hazırda devam eden bir çalışma alanıdır. Makinelerin de duyguları algılaması, onların insan gibi görünmesini ve davranmasını sağlayacağından dolayı, konuşmada duygu tanıma, insan-bilgisayar etkileşiminin gelişmesinde önemli bir rol oynar. Geçtiğimiz on yıl içerisinde çeşitli SER teknikleri geliştirilmiştir, ancak sorun henüz tam olarak çözülmemiştir. Bu makale, Evrişimsel Sinir Ağı (Convolutional neural networks -CNN) ve Uzun-Kısa Süreli Bellek (Long Short Term Memory-LSTM) olmak üzere iki derin öğrenme mimarisinin birleşimine dayanan bir konuşmada duygu tanıma tekniği önermektedir. CNN lokal öznitelik seçiminde etkinliğini gösterirken, LSTM büyük metinlerin sıralı işlenmesinde büyük başarı göstermiştir. Önerilen Evrişimsel LSTM (Convolutional LSTM – Co-LSTM) yaklaşımı, insan-makine iletişiminde etkili bir otomatik duygu algılama yöntemi oluşturmayı amaçlamaktadır. İlk olarak, Mel Frekansı Kepstrum Katsayıları (Mel Frequency Cepstral Coefficient- MFCC) kullanılarak önerilen yöntemde konuşma sinyalinden bir görüntüsel öznitelikler matrisi çıkarılır ve ardından bu matris bir boyuta indigenir. Sonrasında modelin eğitimi için öznitelik seçme ve sınıflandırma yöntemi olarak Co-LSTM kullanılır. Deneysel analizler, konuşmanın sekiz duygusunun tamamının RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song) ve TESS (Toronto Emotional Speech Set) veri tabanlarından sınıflandırılması üzerine yapılmıştır. MFCC Spektrogram öznitelikleri kullanılarak Co-LSTM ile %86,7 doğruluk oranı elde edilmiştir. Elde edilen sonuçlar, önceki çalışmalar ve diğer iyi bilinen sınıflandırıcılarla karşılaştırıldığında önerilen algoritmanın etkinliğini ikna edici bir şekilde kanıtlamaktadır.Öğe Medical Image Enhancement using Guided Filtering and Chaotic Inertia Weight Black Hole Algorithm(Institute of Electrical and Electronics Engineers Inc., 2021) Pashaei, ElhamIn this study, a new hybrid approach is suggested for medical image enhancement. The main idea is based on the hybrid of the guided filter and chaotic inertia weight black hole algorithm (GFCBH) to enhance and highlight the image information using a new objective function. GFCBH is a two-stage approach that, first, applies the guided filter to the input image which performs as an edge-preserving smoothing operator, and then, uses the CBH algorithm to automatically find optimal parameters for transformation function based on the objective function. In the proposed objective function, universal image quality index (Q), entropy, edge pixels, and gray level cooccurrence matrix (GLCM) based contrast and energy are considered to achieve the best-enhanced image. The experimental results are verified by comparison with ten well-known image enhancement techniques using entropy and peak signal-to-noise-ratio (PSNR) measurement criteria. The extensive experiments along with qualitative and quantitative evaluations show that the suggested method can successfully enhance images and performs better than most state-of-art techniques. © 2021 IEEE.Öğe Mutation-based Binary Aquila optimizer for gene selection in cancer classification(ELSEVIER SCI LTD, THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, OXON, ENGLAND, 2022) Pashaei, ElhamMicroarray data classification is one of the hottest issues in the field of bioinformatics due to its efficiency in diagnosing patients’ ailments. But the difficulty is that microarrays possess a huge number of genes where the majority of which are redundant or irrelevant resulting in the deterioration of classification accuracy. For this issue, mutated binary Aquila Optimizer (MBAO) with a time-varying mirrored S-shaped (TVMS) transfer function is proposed as a new wrapper gene (or feature) selection method to find the optimal subset of informative genes. The suggested hybrid method utilizes Minimum Redundancy Maximum Relevance (mRMR) as a filtering approach to choose top-ranked genes in the first stage and then uses MBAO-TVMS as an efficient wrapper approach to identify the most discriminative genes in the second stage. TVMS is adopted to transform the continuous version of Aquila Optimizer (AO) to binary one and a mutation mechanism is incorporated into binary AO to aid the algorithm to escape local optima and improve its global search capabilities. The suggested method was tested on eleven well-known benchmark microarray datasets and compared to other current state-ofthe-art methods. Based on the obtained results, mRMR-MBAO confirms its superiority over the mRMR-BAO algorithm and the other comparative GS approaches on the majority of the medical datasets strategies in terms of classification accuracy and the number of selected genes. R codes of MBAO are available at https://github. com/el-pashaei/MBAO.Öğe Performance evaluation of machine learning techniques in predicting cumulative absolute velocity(Elsevier Sci Ltd, 2023) Kuran, Fahrettin; Tanircan, Gulum; Pashaei, ElhamCumulative absolute velocity (CAV) is a powerful intensity measure for quantifying potential earthquake damage to structures. Machine learning (ML) methods can provide more accurate and reliable predictions of cumulative absolute velocity due to handling nonlinear relationships, adaptability to changing conditions, automation, efficiency, and the potential for real-time predictions. This study aims to identify machine learning regressions with the highest accuracy for CAV prediction. Several supervised machine learning algorithms were applied and comprehensively compared for performance and accuracy in CAV prediction using the recently compiled Turkish strong-motion database. Support Vector Machine, Linear Regression, Random Forest, Artificial Neural Network, Bayesian Ridge Regression, and Gradient Boosting algorithms were evaluated and compared with traditional Ground Motion Models (GMMs). Two new datasets including 24,667 strong-motion recordings from Turkiye along with global strong-motion recordings are used to build machine learning models. The first dataset contains all recordings of events with 3.5 <= Moment Magnitude (M-w) <= 7.6, while the second dataset contains only recordings with M-w >= 5.5. Moreover, feature selection and outlier detection were performed as preprocessing steps to choose the best of seven CAV estimator parameters in order to boost the ML model performance. To measure the performance of ML methods five evaluation metrics were utilized which are mean square error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), and correlation coefficient (R). Comparative assessment of the machine learning algorithms suggests that models trained by M-w >= 5.5 dataset are quite successful in CAV prediction compared to predictive models trained by the 3.5 <= M-w <= 7.6 dataset. The result proves that the Gradient Boosting models significantly outperform the other machine learning algorithms in terms of R and RMSE. Machine learning techniques are more successful with user-selected estimators representing the key components that make up earthquake recordings. Finally, the machine learning-based CAV prediction models for Turkiye are compared with available CAV GMMs, and it is observed that the machine learning-based models can predict CAV as successfully as GMMs if there are a sufficient number of recordings for training machine learning algorithms.Öğe Training Feedforward Neural Network Using Enhanced Black Hole Algorithm: A Case Study on COVID-19 Related ACE2 Gene Expression Classification(SPRINGER HEIDELBERG, TIERGARTENSTRASSE 17, D-69121 HEIDELBERG, GERMANY, 2021) Pashaei, Elham; Pashaei, ElnazThe aim of this paper is twofold. First, black hole algorithm (BHA) is proposed as a new training algorithm for feedforward neural networks (FNNs), since most traditional and metaheuristic algorithms for training FNNs sufer from the problem of slow coverage and getting stuck at local optima. BHA provides a reliable alternative to address these drawbacks. Second, complementary learning components and Levy fight random walk are introduced into BHA to result in a novel optimization algorithm (BHACRW) for the purpose of improving the FNNs’ accuracy by fnding optimal weights and biases. Four benchmark functions are frst used to evaluate BHACRW’s performance in numerical optimization problems. Later, the classifcation performance of the suggested models, using BHA and BHACRW for training FNN, is evaluated against seven various benchmark datasets: iris, wine, blood, liver disorders, seeds, Statlog (Heart), balance scale. Experimental result demonstrates that the BHACRW performs better in terms of mean square error (MSE) and accuracy of training FNN, compared to standard BHA and eight well-known metaheuristic algorithms: whale optimization algorithm (WOA), biogeography-based optimizer (BBO), gravitational search algorithm (GSA), genetic algorithm (GA), cuckoo search (CS), multiverse optimizer (MVO), symbiotic organisms search (SOS), and particle swarm optimization (PSO). Moreover, we examined the classifcation performance of the suggested approach on the angiotensin-converting enzyme 2 (ACE2) gene expression as a coronavirus receptor, which has been overexpressed in human rhinovirus-infected nasal tissue. Results demonstrate that BHACRW-FNN achieves the highest accuracy on the dataset compared to other classifers.