DSpace Arşivi :: by Yazar "Zaim, Abdül Halim" değerine göre listeleniyor

Yazar "Zaim, Abdül Halim" seçeneğine göre listele

Listeleniyor 1 - 20 / 53

Application of neural networks in talent management
(IEEE Computer Society, 2014) Waheed, Sajjad; Zaim, Abdül Halim; Zaim, Halil; Sertbaş, Ahmet; Akyokuş, Selim
Study of talent management is getting more attentions in the recent years. It was found that there are no easy classification methods for verifying talents. This paper discusses the application of neural networks for a talent matrix based talent classification process. The proposed method is easy to implement, and free from biasing and nepotism. © 2014 IEEE.
Comparative evaluation of different classification techniques for masquerade attack detection
(Inderscience Enterprises Ltd., 2020) Elmasry, W.; Akbulut, A.; Zaim, Abdül Halim
Masquerade detection is a special type of intrusion detection problem. Effective and early intrusion detection is a crucial basis for computer security. Although of considerable work has been focused on masquerade detection for more than a decade, achieving a high level of accuracy and a comparatively low degree of false alarm rate is still a big challenge. In this paper, we present an extensive empirical study in the area of user behaviour profiling-based masquerade detection using six of different existed machine learning methods in Azure Machine Learning (AML) studio. In order to surpass previous studies on this subject, we used four free and publicly available datasets with seven data configurations are implemented from them. Moreover, eight well-known masquerade detection evaluation metrics are used to assess methods performance against each data configuration. Finally, intensive quantitative and ROC curves analyses of results are provided at the end of this paper. Copyright © 2020 Inderscience Enterprises Ltd.
A comparative study based on power usage performance for routing protocols in wireless sensor network
(2013) Norouzi, Ali; Zaim, Abdül Halim; Sertbaş, Ahmet
Because of the low-power energy nodes used in a network, energy plays a pivotal role in the life-time of wireless sensor networks (WSNs). This study elaborates on a routing method featured with optimum energy consumption in wireless sensor networks. Some of routing protocols with high energy efficiency (LEACH, Director Diffusion, Gossiping, PEGASIS, and EESR) were examined. We also looked through strategies of the protocol for WSNs such as data aggregation and clustering, routing, different node role assignments, and data-center methods. The routing protocols were compared regarding variety of metrics influencing requirements of the specific application and WSNs in general. © 2013 IEEE.
Dağıtık mesajlaşma altyapısı kullanılarak büyük boyutlu verilerin gerçek zamanlı olarak işlenmesi
(Murat GÖK, 2021) Toprak, Ahmet; Zaim, Abdül Halim
Günümüzde IoT (Internet of Things – Nesnelerin İnterneti) cihazların kullanımındaki artış beraberinde yüksek yoğunluklu ve farklı çeşitte verilerin oluşmasına sebep olmuştur. IoT cihazlarından toplanan bu verilerin formatları, şekilleri ve yoğunlukları birbirinden tamamen farklıdır. Bu verilerin anlık olarak işlenmesi ve ilgili kullanıcıya anlık olarak iletilmesi gerekmektedir. Bu makalede, IoT cihazlarından elde edilen verilerin işlenmesi ve son kullanıcıya anlık olarak iletilmesi amacıyla bir model tasarlanmıştır. Çalışmada öncelikli olarak IoT cihazlarından toplanan yapısal olmayan veriler veri ön işleme adımlarına tabi tutulmuştur. Veri ön işleme adımları sonrası elde edilen verilerden anlamlı kelimeler tespit edilmiştir. Bu amaçla TF-IDF (Term Frequency?-Inverse Document Frequency) metrikleri uygulanmıştır. Anlamlı kelime tespiti sonrası her anlamlı kelime konusuna göre verileri anlık işlemek amacıyla RabbitMQ dağıtık mesaj işleme kuyruğuna yönlendirilmiştir. Böylece mesajların iletilmesi garanti altına alınmıştır. RabbitMQ kuyruğuna iletilen mesajların anlık olarak alınması ve işlenmesi amacıyla Apache Storm topolojisi kullanılmıştır. Garantili mesaj işleme alt yapısı kullanan Apache Storm topolojisi, mesajları RabbitMQ dağıtık kuyruklama teknolojisi üzerinden okuyup, yapması gereken işlem ve hesaplamaları yaptıktan sonra çıktıları Elasticsearch içerisinde saklamıştır. Apache Storm topolojisi içerisinde üretilen sonuçlar daha sonra REST (Representational State Transfer) mimarisi kullanılarak son kullanıcı ile paylaşılmıştır.
Deep learning approaches for phantom movement recognition
(Institute of Electrical and Electronics Engineers Inc., 2019) Akbulut, Akhan; Aşçı, Güven; Güngör, Feray; Tarakcı, Ela; Aydın, Muhammed Ali; Zaim, Abdül Halim
Phantom limb pain has a negative effect on the life of individuals as a frequent consequence of limb amputation. The movement ability on the lost extremity can still be maintained after the amputation or deafferentation, which is called the phantom movement. The detection of these movements makes sense for cybertherapy and prosthetic control for amputees. In this paper, we employed several deep learning approaches to recognize phantom movements of the three different amputation regions including above-elbow, below-knee and above-knee. We created a dataset that contains 25 healthy and 16 amputee participants' surface electromyography (sEMG) readings via a wearable device with 2-channel EMG sensors. We compared the results of three different deep learning methods, respectively, Multilayer Perceptron, Convolutional Neural Network, and Recurrent Neural Network with the accuracies of two well-known shallow methods, k Nearest Neighbor and Random Forest. Our experiments indicate, Convolutional Neural Network-based model achieved an accuracy of 74.48% in recognizing phantom movements of amputees. © 2019 IEEE.
Deep Learning Approaches for Predictive Masquerade Detection
(Hindawi Limited, 2018) Elmasry, Wisam; Akbulut, Akhan; Zaim, Abdül Halim
In computer security, masquerade detection is a special type of intrusion detection problem. Effective and early intrusion detection is a crucial factor for computer security. Although considerable work has been focused on masquerade detection for more than a decade, achieving a high level of accuracy and a comparatively low false alarm rate is still a big challenge. In this paper, we present a comprehensive empirical study in the area of anomaly-based masquerade detection using three deep learning models, namely, Deep Neural Networks (DNN), Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN), and Convolutional Neural Networks (CNN). In order to surpass previous studies on this subject, we used three UNIX command line-based datasets, with six variant data configurations implemented from them. Furthermore, static and dynamic masquerade detection approaches were utilized in this study. In a static approach, DNN and LSTM-RNN models are used along with a Particle Swarm Optimization-based algorithm for their hyperparameters selection. On the other hand, a CNN model is employed in a dynamic approach. Moreover, twelve well-known evaluation metrics are used to assess model performance in each of the data configurations. Finally, intensive quantitative and ROC curves analyses of results are provided at the end of this paper. The results not only show that deep learning models outperform all traditional machine learning methods in the literature but also prove their ability to enhance masquerade detection on the used datasets significantly. © 2018 Wisam Elmasry et al.
A design of an integrated cloud-based intrusion detection system with third party cloud service
(De Gruyter, 2021) Elmasry, Wisam; Akbulut, Akhan; Zaim, Abdül Halim
Although cloud computing is considered the most widespread technology nowadays, it still suffers from many challenges, especially related to its security. Due to the open and distributed nature of the cloud environment, this makes the cloud itself vulnerable to various attacks. In this paper, the design of a novel integrated Cloud-based Intrusion Detection System (CIDS) is proposed to immunise the cloud against any possible attacks. The proposed CIDS consists of five main modules to do the following actions: monitoring the network, capturing the traffic flows, extracting features, analyzing the flows, detecting intrusions, taking a reaction, and logging all activities. Furthermore an enhanced bagging ensemble system of three deep learning models is utilized to predict intrusions effectively. Moreover, a third-party Cloud-based Intrusion Detection System Service (CIDSS) is also exploited to control the proposed CIDS and provide the reporting service. Finally, it has been shown that the proposed approach overcomes all problems associated with attacks on the cloud raised in the literature.
Detection DDOS Attacks Using Machine Learning Methods
(İstanbul Üniversitesi, 2020) Aytaç, Tuğba; Aydın, Muhammed Ali; Zaim, Abdül Halim
Wishing to communicate with each other of people contributes to improving technology, and it has made the internet concept an indispensable part of our daily life. Cyber attacks from extranets to enterprise networks or intranets, which are used as personal, can cause pecuniary loss and intangible damage. It is critical to take due precautions for minimizing the losses by early detection of attacks. This study aims to analyze the rate of success in the intrusion detection system by using different methods. In this study, the CICDDoS2019 data set has been used, and DDOS attacks in this data set were compared. The success rates of threat determination were analyzed as using Artificial Neural Networks (ANN), Support Vector Machine (SVM), Gaussian Naive Bayes, Multinomial Naive Bayes, Bernoulli Naive Bayes, Logistic Regression, K-nearest neighbor (KNN), Decision Tree (entropy-gini) and Random Forest algorithms. It has been seen that the highest of the success rate is the models that ensure almost 100% success that was made by using K-nearest neighbor, Logistic Regression, Naive Bayes, (Multinomial – Bernoulli algorithms).
A dynamic channel assignment method for multichannel multiradio wireless mesh networks
(Turkiye Klinikleri Journal of Medical Sciences, 2018) Odabaşı, Şafak Durukan; Zaim, Abdül Halim
The popularity of wireless communication accelerates research on new technologies that are required to satisfy users' needs. Wireless mesh networks (WMNs), which are additional access technologies instead of being a renewed one, have an important place among next-generation wireless networks. In particular, the capability of working without any infrastructure is the most outstanding advantage of WMNs. There are many studies aimed at WMNs, particularly channel assignment and routing methods for multichannel multiradio structures that provide higher data capacity. Interference, which has a direct effect on the quality of communication, is still a challenge to be addressed. In this study, multichannel multiradio WMNs and various channel assignment schemes are analyzed. Directional mesh (DMesh) architecture, which uses directional antennas to form a multichannel structure, is analyzed in terms of channel assignment procedure. A new interference-aware channel assignment scheme that aims to eliminate DMesh's disadvantages is proposed and performances of both schemes are compared. Several results of experimental analysis prove that the proposed channel assignment scheme improves the performance of DMesh. © TÜBITAK.
EETBR: Energy Efficient Token-Based Routing For Wireless Sensor Networks
(TUBITAK Scientific & Technical Research Council, 2013) Cevik, Taner; Zaim, Abdül Halim
The most significant drawback of wireless sensor networks is energy scarcity. As there is an increasing need for operating these networks for relatively long times, energy saving becomes the key challenge in the design of the architectures and protocols for sensor networks. Therefore, several research studies have been performed for making contributions to the analysis of this energy shortage problem. Most of these research activities have been focused on finding solutions for the energy consumption of the communication unit, which is the dominant energy dissipating component of the sensor nodes. In this paper, a novel, token-based routing protocol adapted with a multitier cluster-based architecture is presented. Most of the other cluster-based schemes mainly focus on intracluster organization and communication. However, it should be mentioned that a considerable amount of energy is dissipated during the intercluster communication when compared with intracluster communication. The architecture proposed here not only deals with intracluster communication, but also considers data aggregation, multihop data transmission, and best-effort next hop selection according to a cost factor that is described for the first time in this paper. The simulation results indicate that this token-based next hop selection method together with the multitier cluster-based architecture achieves a significant amount of energy savings, which inherently yields the prolongation of the network lifetime.
An efficient big data anonymization algorithm based on chaos and perturbation techniques
(MDPI AG, 2018) Eyüpoğlu, Can; Aydın, Muhammed Ali; Zaim, Abdül Halim; Sertbaş, Ahmet
The topic of big data has attracted increasing interest in recent years. The emergence of big data leads to new difficulties in terms of protection models used for data privacy, which is of necessity for sharing and processing data. Protecting individuals' sensitive information while maintaining the usability of the data set published is the most important challenge in privacy preserving. In this regard, data anonymization methods are utilized in order to protect data against identity disclosure and linking attacks. In this study, a novel data anonymization algorithm based on chaos and perturbation has been proposed for privacy and utility preserving in big data. The performance of the proposed algorithm is evaluated in terms of Kullback-Leibler divergence, probabilistic anonymity, classification accuracy, F-measure and execution time. The experimental results have shown that the proposed algorithm is efficient and performs better in terms of Kullback-Leibler divergence, classification accuracy and F-measure compared to most of the existing algorithms using the same data set. Resulting from applying chaos to perturb data, such successful algorithm is promising to be used in privacy preserving data mining and data publishing. © 2018 by the authors.
Empirical study on multiclass classification-based network intrusion detection
(Blackwell Publishing Inc., 2019) Elmasry, Wisam; Akbulut, Akhan; Zaim, Abdül Halim
Early and effective network intrusion detection is deemed to be a critical basis for cybersecurity domain. In the past decade, although a significant amount of work has focused on network intrusion detection, it is still a challenge to establish an intrusion detection system with a high detection rate and a relatively low false alarm rate. In this paper, we have performed a comprehensive empirical study on network intrusion detection as a multiclass classification task, not just to detect a suspicious connection but also to assign the correct type as well. To surpass the previous studies, we have utilized four deep learning models, namely, deep neural networks, long short-term memory recurrent neural networks, gated recurrent unit recurrent neural networks, and deep belief networks. Our approach relies on the pretraining of the models by exploiting a particle swarm optimization–based algorithm for their hyperparameters selection. In order to investigate the performance differences, we also included two well-known shallow learning methods, namely, decision forest and decision jungle. Furthermore, we used in our experiments four datasets, which are dedicated to intrusion detection systems to explore various environments. These datasets are KDD CUP 99, NSL-KDD, CIDDS, and CICIDS2017. Moreover, 22 evaluation metrics are used to assess the model's performance in each of the datasets. Finally, intensive quantitative, Friedman test, and ranking methods analyses of our results are provided at the end of this paper. The results show a significant improvement in the detection of network attacks with our recommended approach. © 2019 Wiley Periodicals, Inc.
Energy and distance factor based routing protocol for wireless sensor networks using mobile agents
(2011) Akbulut, Akhan; Parmaksızoğu, Cihangir; Zaim, Abdül Halim; Yılmaz, Güray
The wireless sensor networks are networks of compact micro-sensors for data acquisition or monitoring some environment characteristics, such as temperature, sound, vibration, pressure and motion. These sensors are embedded devices capable of data communication. In many applications, sensor nodes are distributed or deployed over a geo-graphically large area. Due to their structure, data of measured values must be transferred among stations through these sensor nodes. For this reason a successful, energy efficient, fault tolerant routing protocol should be implemented to pre-vent data loss and other challenges within limited energy levels. This paper presents an agent based routing algorithm for wireless sensor networks, based on the selection of the idea of active nodes. Our proposed routing algorithm is related with energy and distance factors of each nodes. The main objective is to increase the lifetime of a sensor network while not compromising data delivery. Critical tasks such as measuring, analyzing and monitoring of energy levels of nodes are handled by these autonomous mechanisms. © 2011 IEEE.
Energy efficient clustering-based mobile routing algorithm on WSNs
(IEEE, 2021) Aydın, Muhammed Ali; Karabekir, Baybars; Zaim, Abdül Halim
In this paper, we propose and discuss two types of algorithms to improve energy efficiency in Wireless Sensor Networks. An efficient approach for extending the life of a network is known as ‘‘sensor clustering’’ in wireless sensor networks. In proposed algorithms, the study area where sensor nodes are randomly distributed is divided into clusters. In each cluster, the sensor that is the closest to the cluster center and has the highest residual energy is chosen as the cluster head. To make this choice, a greedy approach and artificial neural network methods are applied. In addition, to reduce the energy consumption of cluster heads, a mobile sink is used. The list of routes to be used by the mobile sink is calculated with the genetic algorithm. According to the route information, the mobile sink moves to the clusters and initiates the data collection process for each cluster. We compared our models according to the round value at which all sensor nodes run out of energy and the energy consumption by the network per round. Simulation results show that the proposed models increase the energy efficiency and extend the network lifespan.
Energy-based scheduling optimization to minimize the total energy consumption and the total tardiness in a single machine manufacturing system with the sequence-dependent setup times
(Gazi Üniversitesi, 2022) Tarakçı, Elif; Zaim, Abdül Halim; Öztaş, Oğuzhan
Nowadays, reducing energy consumption is an important target for energy-intensive manufacturing systems due to many reasons such as global warming, legal obligations and lowering company expenses. Therefore, this paper focuses on energy-based scheduling problem in manufacturing systems. A mixed-integer nonlinear programming (MINLP) model is developed for a single machine scheduling problem with the sequence-dependent setup times and different arrival times in order to minimize the total energy consumption and the total tardiness. An energy-based genetic optimization (EGOP) method is proposed by adopting the genetic algorithm (GA) approach, which is a heuristic method to solve the problem. The objective values and the computation times are compared with the analytical solution and the General Algebraic Modeling System (GAMS) solution so as to evaluate the performance of the proposed method. As a result, it is seen that the proposed EGOP method provides effective results.
Energy-efficient clustering-based mobile routing algorithm for wireless sensor networks
(İstanbul Üniversitesi Cerrahpaşa, 2021) Karabekir, Baybars; Aydın, Muhammed Ali; Zaim, Abdül Halim
In this paper, we propose and investigate two types of algorithms for improving energy efficiency in wireless sensor networks. Clustering sensors in wireless sensor networks is considered an effective approach to prolonging network lifetime. In this paper, we divide the study area into clusters at 30-m2 intervals. In each cluster, the sensor that is the closest to the cluster center and has the highest residual energy is selected as the cluster head. In addition, a mobile sink is used to reduce the energy consumption of the cluster heads. The mobile sink travels to all clusters starting with the nearest cluster and collects data from the cluster heads. In the first model, cluster head selection is performed and the mobile sink route is calculated using a greedy approach. In the second model, cluster head selection is performed using an artificial neural network, and the mobile sink route is calculated using a greedy approach. We compared our models with the energy-efficient scalable routing algorithm by the first node dies parameter, all nodes die, and the residual energy of the network for each round condition. The simulation results demonstrated that the proposed models improved the energy efficiency and extended the network lifetime
Evaluation of effective parameters of energy consumption in wireless sensor networks
(Nova Science Publishers, Inc., 2014) Norouzi, Ali; Sertbaş, Ahmet; Zaim, Abdül Halim
The development of wireless sensor networks (WSNs) has never been free of challenges and many researchers have been interested in overcoming these challenges. The energy consumption, longevity, and performance of the networks are among the main challenges and have drawn a great deal of attention from researchers. Delving deeper into the issues we encounter more detailed parameters that are the cause of these challenges. To put it another way, there are trivial but at the same time effective parameters whose improvement can enhance the network and overcome the challenges. This chapter tries to introduce and survey all the parameters from a technical viewpoint and presents a general report on the previous works. In addition, advantages and weaknesses of the factors and approaches to improving WSNs are discussed. The study proposes a classification of the parameters and processes that affect different layers of the networks. Furthermore, a comparison of the common methods and further recommendations are represented. Each comparison is concluded by a proposal of the best method to deal with the challenges and improve the networks. © 2014 by Nova Science Publishers, Inc. All rights reserved.
Evaluation of signal times and comparison with queueing models at signalized intersections in urban area
(Digital Library, 2020) Güneş, Fatih; Bayraklı, Selim; Zaim, Abdül Halim
The growing population of cities causes many problems such as air pollution, traffic congestion, fuel consumption and energy efficiency. Especially the traffic problem has come to the fore as one of the main factors of many other problems. In literature has been developed different methods to solve this problem. Queuing theory (Queuing models) are studies involving all the analytical approaches performed for the analysis and design of these systems. In this article, the analysis results obtained from the real data collected from the field are shared. The results obtained in the study were analyzed by the methods provided by the queue models. The signal duration was improved based on the data obtained, and the effect on the result was examined. As a result of improving the signal times, it was seen that parameters such as queue lengths and time consumed in the system decreased.
Evolving deep learning architectures for network intrusion detection using a double PSO metaheuristic
(Elsevier B.V., 2020) Elmasry, Wisam; Akbulut, Akhan; Zaim, Abdül Halim
The prevention of intrusion is deemed to be a cornerstone of network security. Although excessive work has been introduced on network intrusion detection in the last decade, finding an Intrusion Detection Systems (IDS) with potent intrusion detection mechanism is still highly desirable. One of the leading causes of the high number of false alarms and a low detection rate is the existence of redundant and irrelevant features of the datasets, which are used to train the IDSs. To cope with this problem, we proposed a double Particle Swarm Optimization (PSO)-based algorithm to select both feature subset and hyperparameters in one process. The aforementioned algorithm is exploited in the pre-training phase for selecting the optimized features and model's hyperparameters automatically. In order to investigate the performance differences, we utilized three deep learning models, namely, Deep Neural Networks (DNN), Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN), and Deep Belief Networks (DBN). Furthermore, we used two common IDS datasets in our experiments to validate our approach and show the effectiveness of the developed models. Moreover, many evaluation metrics are used for both binary and multiclass classifications to assess the model's performance in each of the datasets. Finally, intensive quantitative, Friedman test, and ranking methods analyses of our results are provided at the end of this paper. Experimental results show a significant improvement in network intrusion detection when using our approach by increasing Detection Rate (DR) by 4% to 6% and reducing False Alarm Rate (FAR) by 1% to 5% from the corresponding values of same models without pre-training on the same dataset. © 2019
Examination and comparison of the communication protocols on the application layer in iot
(İstanbul Ticaret Üniversitesi, 2018) Gültunca, Cem; Zaim, Abdül Halim
Today the Internet has become ubiquitous, has touched almost every corner of the globe, and is affecting human life in unimaginable ways. We are now entering an era of even more pervasive connectivity where a very wide variety of appliances will be connected to the web. We are entering an era of the “Internet of Things” (abbreviated as IOT). IOT is defined as a paradigm in which objects equipped with sensors, actuators, and processors communicate with each other to serve a meaningful purpose. Several IOT protocols have been introduced in order to provide an efficient communication for resource-constrained applications. However, their performance is not as yet well understood. I evaluated and compared four communication protocols, namely, AMQP, MQTT, XMPP, and COAP. I implemented a some IOT application using open source software for these protocols and measured their performance. In our tests, we compare AMQP and MQTT protocols. As a result, AMQP protocol transmits data faster than MQTT

Yazar "Zaim, Abdül Halim" seçeneğine göre listele

Sayfa Başına Sonuç

Sıralama seçenekleri