Makale Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe HUBsFLOW: A novel interface protocol for SDN-enabled WBANs(Elsevier, 2019) Cicioğlu, Murtaza; Çalhan, AliWireless Body Area Network (WBAN) concept is one of the most promising technologies for healthcare applications. In WBANs, sensor nodes are capable of sensing, gathering the human body signs and sending them to the HUB; the communication between nodes and HUB is called as intra-WBAN communications. Inter-WBAN communication manages all HUBs for communications of various WBANs. WBANs have inherently heterogeneous structures and limited energy sources, and also, installation/configuration network management processes are increasingly quite complex. New approaches are required to implement WBANs in order to overcome these challenges. We propose the Software Defined Networking (SDN) approach aims at constructing a flexible and manageable structure for inter-WBAN communications. Therefore, a new SDN-enabled WBAN architecture with HUBsFIow interface protocol is proposed in this paper. The proposed architecture provides a flexible, manageable, and an energy sensitive structure. Hence, a controller that is a key component for SDN undertakes all management and control processes about network. HUBsFlow interface protocol is utilized on the controller that provides the communications among the controller and HUBs in inter-WBAN communications. All components, protocols, and algorithms of the proposed architecture are developed and simulated using Riverbed Modeler software. Throughput, delay, packet loss ratio, bit error rate, and energy consumption parameters are taken into account for performance evaluation of the proposed architecture. The results show that the proposed architecture outperforms when comparing with traditional WBAN architecture and satisfies IEEE/ISO 11073 service quality requirements. (C) 2019 Elsevier B.V. All rights reserved.Öğe Hybrid Harris Hawk Optimization Based on Differential Evolution (HHODE) Algorithm for Optimal Power Flow Problem(Ieee-Inst Electrical Electronics Engineers Inc, 2019) Biroğul, SerdarHarri's Hawk Optimization (HHO) algorithm manifests as a new meta-heuristic algorithm in literature. When we look at studies that have used with this algorithm, we can see that its results in test functions and in the solutions of some test functions in IEEE Congress on Evolutionary Computation (CEC) are much better compared to other heuristic and meta heuristic algorithm results. In this study, an algorithm has been developed which has been hybridized with the mutation operators of Differential Evolution (DE) to further improve the HHO algorithm. This algorithm is named as Hybrid Harris Hawk Optimization based on Differential Evolution (HHODE). Performance of the proposed HHODE algorithm has been first compared with HHO and then compared with the results of other algorithms which have been most commonly used in the literature. In this comparison process, the most commonly used test functions in the literature and some of the other test functions in CEC2005 and CEC2017 as a new application field, have been solved. When the results of the comparison of HHODE with other algorithms are analyzed, it is observed that the balance between the exploratory tendency and exploitative tendency of the algorithm is well consistent. Formula 1 ranking method is used in the order of HHODE according to HHO and other algorithms. When a general evaluation of HHODE was performed, it was found to be an even more powerful algorithm as a result of the combination of strong features of both HHO and DE. The optimal power flow (OPF) problem is one of the most important problems of the modern power system. The HHODE algorithm is proposed to solve the OPF problem, which is considered without valve-point effect and prohibited zones (1) and with prohibited zones (2) in this paper. The effectiveness of the HHODE hybrid algorithm is tested on modified IEEE 30-bus test system. The result of HHODE algorithms are compared with other optimization algorithms in the literature.Öğe GPU accelerated training of image convolution filter weights using genetic algorithms(Elsevier Science Bv, 2015) Akgün, Devrim; Erdoğmuş, PakizeGenetic algorithms (GA) provide an efficient method for training filters to find proper weights using a fitness function where the input signal is filtered and compared with the desired output. In the case of image processing applications, the high computational cost of the fitness function that is evaluated repeatedly can cause training time to be relatively long. In this study, a new algorithm, called sub-image blocks based on graphical processing units (GPU), is developed to accelerate the training of mask weights using GA. The method is developed by discussing other alternative design considerations, including direct method (DM), population-based method (PBM), block-based method (BBM), and sub-images-based method (SBM). A comparative performance evaluation of the introduced methods is presented using sequential and other GPUs. Among the discussed designs, SBM provides the best performance by taking advantage of the block shared and thread local memories in GPU. According to execution duration and comparative acceleration graphs, SBM provides approximately 55-90 times more acceleration using GeForce GTX 660 over sequential implementation on a 3.5 GHz processor. (C) 2015 Elsevier B.V. All rights reserved.Öğe GRAPH-BASED SENTENCE LEVEL SPELL CHECKING FRAMEWORK(Inst Integrative Omics & Applied Biotechnology, 2017) Kabakuş, Abdullah Talha; Kara, ResulSpelling mistakes are very common on the web, especially when it comes to social media, it is much more common since (1) users tend to use an informal language that contains slang, and (2) the character limit defined by some social services such as Twitter. Traditional string similarity measurements (1) do not consider the context of the misspelled word while providing alternatives, and (2) do not provide a certain way to choose the right word when there are multiple alternatives that have the same similarity with the misspelled word. Therefore, we propose a novel sentence level spell checking framework that targets to find "the most frequently used similar alternative word". 146,808 sentences from different corpora are stored in a graph database. The similarity is calculated by using Levenshtein distance algorithm alongside the similarity between two given words. As the experimental results are presented in the discussion, the proposed framework is able to correct misspellings which cannot be corrected by traditional string similarity measurement based approaches. The accuracy of the proposed framework is calculated as 84%. Since the proposed framework uses a slang dictionary to determine misspelled words, it can be used to correct misspellings in the social media platforms.Öğe Finding an optimum location for biogas plant: a case study for Duzce, Turkey(Springer, 2018) Yürük, Fuat; Erdoğmuş, PakizeThis study is a case study for modelling and solving a real-life problem. In this study, a practical approximation for finding an optimum location of a foundation was realized with k-means clustering and optimization. Duzce, in the northwest of Turkey, has been researched for the biogas potential to found biogas plant. With this aim, the number of poultry in Duzce has been determined and presented their potential of biogas. Since the number of poultry is quite enough to found a biogas plant, later the location of the poultry farms and their potentials has been determined. Since there are more than 400 poultry farms in Duzce, firstly locations are clustered with classical k-means algorithm. k is specified as 6-8 with an expert knowledge. Later, the nearest location for each cluster center has been attained with simulated annealing with the objective of minimizing the transportation cost. As a result, it has been determined an optimum location for probable biogas plant for Duzce.Öğe Fast and lightweight detection and filtering method for low-rate TCP targeted distributed denial of service (LDDoS) attacks(Wiley, 2018) Şimşek, Mehmet; Şentürk, ArafatDetection and filtering of low-rate distributed denial of service (LDDoS) attacks is hard since their behavior is similar to legitimate users' behavior. In the literature, there are many filtering approaches and metrics for LDDoS attacks. However, most of the LDDoS detection methods in the literature only monitor congestion state. Actually, precongestion period that the attack has already started has valuable information about the attack. In this study, we proposed a method that uses precongestion period for metric calculation. Also, most of LDDoS filtering approaches have high false-positive and false-negative rates and also require long period of time for detection. Additionally, we developed an efficient method for detection and filtering of LDDoS attacks. According to the experimental results, the proposed LDDoS detection method has zero false-positive and false-negative rates under the scenarios; attack detection time is significantly reduced with using the proposed metric calculation approach. Also, the proposed method has a simple logic, and it requires simple calculations. This increases the applicability of the developed method.Öğe Exploiting cognitive wireless nodes for priority-based data communication in terrestrial sensor networks(Wiley, 2019) Bayrakdar, Muhammed EnesA priority-based data communication approach, developed by employing cognitive radio capacity for sensor nodes in a wireless terrestrial sensor network (TSN), has been proposed. Data sensed by a sensor node-an unlicensed user-were prioritized, taking sensed data importance into account. For data of equal priority, a first come first serve algorithm was used. Non-preemptive priority scheduling was adopted, in order not to interrupt any ongoing transmissions. Licensed users used a nonpersistent, slotted, carrier sense multiple access (CSMA) technique, while unlicensed sensor nodes used a nonpersistent CSMA technique for lossless data transmission, in an energy-restricted, TSN environment. Depending on the analytical model, the proposed wireless TSN environment was simulated using Riverbed software, and to analyze sensor network performance, delay, energy, and throughput parameters were examined. Evaluating the proposed approach showed that the average delay for sensed, high priority data was significantly reduced, indicating that maximum throughput had been achieved using wireless sensor nodes with cognitive radio capacity.Öğe Dynamic HUB Selection Process Based on Specific Absorption Rate for WBANs(Ieee-Inst Electrical Electronics Engineers Inc, 2019) Cicioğlu, Murtaza; Çalhan, AliWireless body area networks (WBANs) play an important role in remote health monitoring applications nowadays. WBANs consist of several sensor nodes and a fixed HUB on, in, or around the human body. HUB collects the data from the sensor nodes and sends the received data to a gateway. High data rates from HUB cause to increase in temperature of tissues. If an organ receives electromagnetic signals for longer time period, then it will be affected by heat and might be damaged. In this paper, specific absorption rate, battery level, and priority of the sensor nodes are taken into account for dynamical HUB selection process in WBANs. Therefore, the task of the HUB is shared among the sensor nodes to reduce the negative effects of electromagnetic signals due to fixed HUB placement.Öğe Design and Realization of a Microcontroller Based E-Test Strip Application Device(Taylor & Francis Inc, 2009) Çelik, Bahar; Güler, Nihal Fatma; Güler, İnanIn this study, a device that supplies a microcontroller controlled E-test strip application was developed. It was aimed to gather two devices which are needed for E-test strip application's stages, i.e., inoculation onto agar plate and placement of E-test strip, into a device to thus reduce the cost and time required for this application. A PIC16F877A microcontroller was used in the system and it was programmed in Microcode Studio Plus Editor by using the PIC Basic Programming Language. The circuit whose design was realized was tested under circumstances in the laboratory and real medium. The designed system is in a state that can be used in hospitals as it is.Öğe Deep Learning-Based Parkinson's Disease Classification Using Vocal Feature Sets(Ieee-Inst Electrical Electronics Engineers Inc, 2019) Gündüz, HakanParkinson's Disease (PD) is a progressive neurodegenerative disease with multiple motor and non-motor characteristics. PD patients commonly face vocal impairments during the early stages of the disease. So, diagnosis systems based on vocal disorders are at the forefront on recent PD detection studies. Our study proposes two frameworks based on Convolutional Neural Networks to classify Parkinson's Disease (PD) using sets of vocal (speech) features. Although, both frameworks are employed for the combination of various feature sets, they have difference in terms of combining feature sets. While the first framework combines different feature sets before given to 9-layered CNN as inputs, whereas the second framework passes feature sets to the parallel input layers which are directly connected to convolution layers. Thus, deep features from each parallel branch are extracted simultaneously before combining in the merge layer. Proposed models are trained with dataset taken from UCI Machine Learning repository and their performances are validated with Leave-One-Person-Out Cross Validation (LOPO CV). Due to imbalanced class distribution in our data, F-Measure and Matthews Correlation Coefficient metrics are used for the assessment along with accuracy. Experimental results show that the second framework seems to be very promising, since it is able to learn deep features from each feature set via parallel convolution layers. Extracted deep features are not only successful at distinguishing PD patients from healthy individuals but also effective in boosting up the discriminative power of the classifiers.Öğe What Static Analysis Can Utmost Offer for Android Malware Detection(Kaunas Univ Technology, 2019) Kabakuş, Abdullah TalhaMalicious applications are widespread for Android despite the taken serious actions by the operating system. Static and dynamic analysis techniques are utilized to detect malware by identifying the signatures of malicious applications by inspecting both the resources and behaviors of malware, respectively. In this study, what static analysis can utmost offer to detect malware in Android ecosystem is discussed and experimented on commonly used datasets in the literature by proposing a novel Android malware detection approach based on static analysis techniques. With the proposed study, the effectiveness of novel static analysis features' in terms of detecting malware in Android ecosystem are proved. These features were underestimated by the related work in the literature. The experimental result shows that the proposed Android malware detection approach is very effective in terms of detecting Android malware. Each feature used by the proposed approach is evaluated by using different types of machine learning techniques in order to highlight its impact on detecting malware and inform the digital investigators. The accuracy of the proposed static analysis approach is calculated as high as 0.987 for 10,865 applications.Öğe TwitterSpamDetector A Spam Detection Framework for Twitter(Igi Global, 2019) Kabakuş, Abdullah Talha; Kara, ResulTwitter is the most popular microblogging platform which lets users post status messages called tweets. This popularity and the advanced API provided by Twitter to read and write Twitter data programmatically attracts the attention of spammers as well as legitimate users. Since Twitter has some unique characteristics, the traditional spam detecting methods cannot be directly used to detect spam on Twitter. Therefore, a spam detection framework which is specially designed for Twitter namely TwitterSpamDetector is proposed in this paper. TwitterSpamDetector uses Twitter-specific features to detect spam on Twitter. 77,033 tweets which are posted by 50,490 users collected using the API provided by Twitter. Naive Bayes is used to train TwitterSpamDetector using the selected features of Twitter which clearly classify the spammers from legitimate users. According to the evaluation result, TwitterSpamDetector's accuracy and sensitivity are calculated as 0.943 and 0.913, respectively.Öğe TwitterSentiDetector: a domain-independent Twitter sentiment analyser(Taylor & Francis Inc, 2018) Kabakuş, Abdullah Talha; Kara, ResulSentiment analysis has become more crucial after the rise of social media, especially the Twitter since it provides structured and publicly available data. TwitterSentiDetector is a domain-dependent and unsupervised Twitter sentiment analyser that focuses on the differences occurred by the informal language used in Twitter. TwitterSentiDetector uses natural language processing techniques alongside the proposed linguistic methods to classify sentiments of tweets into positive, negative, and neutral through the polarity scores obtained from sentiment lexicons. According to tests on widely used Twitter data-sets that contain manually detected sentiments labels alongside tweets, TwitterSentiDetector's sentiment detection ratio is calculated as up to 69%. When the target sentiment classes are decreased to positive and negative, the detection ratio is increased up to 87%. The results are calculated very similarly when the same data-set is evaluated by the proposed tweet-level context aware sentiment analysis module which confirms the validity of each approach.Öğe Two-Layer Approach for Mixed High-Rate and Low-Rate Distributed Denial of Service (DDoS) Attack Detection and Filtering(Springer Heidelberg, 2018) Toklu, Sinan; Şimşek, MehmetDistributed denial of service (DDoS) attacks are one of the most important attacks due to reducing the performance of computer networks nowadays. In recent years, the number of devices connected to the internet has been increasing. These devices are not only computers, but also objects of everyday use. The concept of internet has accelerated the increase considerably. Therefore, many problems arise in terms of DDoS attacks. One of them is low-rate DDoS attacks. While high-rate DDoS attacks are often performed with computers, low-rate DDoS attacks can be easily performed by computers and internet-connected objects. Therefore, effective defense mechanism against both attacks must be developed. In this study, new approaches are proposed to filter mixed high-rate DDoS and low-rate DDoS attacks. The ns-2 simulation tool was used to evaluate the performance of the proposed methods. Experimental results show that the proposed methods are successfully filtered mixed DDoS attacks.Öğe SEAM CARVING BASED IMAGE RESIZING DETECTION USING HYBRID FEATURES(Univ Osijek, Tech Fac, 2017) Şentürk, Zehra Karapınar; Akgün, DevrimDetection of seam carving-based digital image resizing is a challenging task in image processing field since the method investigates the images on hand semantically. Resizing with seam carving is realized by inserting or removing relatively unimportant pixel paths to/from the images and so the changes in image content are mostly unnoticeable. Local Binary Patterns (LBP), a visual descriptor, unearths local changes in image texture. Therefore, using LBP transform of the images besides intensity values contributes to the detection ratio. In this paper, we proposed a hybrid detection mechanism for more accurate seam carving detection especially in low scaling ratios. We extracted LBP-based and non-LBP based features and trained a Support Vector Machine (SVM) with sixty features. We achieved approximately 9 % improvement in low detection ratios. The experimental results show that more satisfactory detection ratios can be obtained by the proposed hybrid approach.Öğe SDN-based wireless body area network routing algorithm for healthcare architecture(Wiley, 2019) Cicioğlu, Murtaza; Çalhan, AliThe use of wireless body area networks (WBANs) in healthcare applications has made it convenient to monitor both health personnel and patient status continuously in real time through wearable wireless sensor nodes. However, the heterogeneous and complex network structure of WBANs has some disadvantages in terms of control and management. The software-defined network (SDN) approach is a promising technology that defines a new design and management approach for network communications. In order to create more flexible and dynamic network structures in WBANs, this study uses the SDN approach. For this, a WBAN architecture based on the SDN approach with a new energy-aware routing algorithm for healthcare architecture is proposed. To develop a more flexible architecture, a controller that manages all HUBs is designed. The proposed architecture is modeled using the Riverbed Modeler software for performance analysis. The simulation results show that the SDN-based structure meets the service quality requirements and shows superior performance in terms of energy consumption, throughput, successful transmission rate, and delay parameters according to the traditional routing approach.Öğe Rule Based Collector Station Selection Scheme for Lossless Data Transmission in Underground Sensor Networks(China Inst Communications, 2019) Bayrakdar, Muhammed EnesThere are fundamentally two different communication media in wireless underground sensor networks. The first of these is a solid medium where the sensor nodes are buried underground and wirelessly transmit data from underground to aboveground. The second is an underground medium such as tunnel, cave etc. and the data is transmitted from underground to the aboveground through partially solid medium. The quality of conununication is greatly influenced by the humidity of the soil in both environments. The placement of wireless underground sensor nodes at hard-to-reach locations makes energy efficient work compulsory. In this paper, rule based collector station selection scheme is proposed for lossless data transmission in underground sensor networks. In order for sensor nodes to transmit energy-efficient lossless data, rulebased selection operations are carried out with the help of fuzzy logic. The proposed wireless underground sensor network is simulated using Riverbed software, and fuzzy logic-based selection scheme is implemented utilizing Matlab software. In order to evaluate the performance of the sensor network; the parameters of delay, throughput and energy consumption are investigated. Examining performance evaluation results, it is seen that average delay and maximum throughput are accomplished in the proposed underground sensor network. Under these conditions, it has been shown that the most appropriate collector station selection decision is made with the aim of minimizing energy consumption.Öğe Priority based health data monitoring with IEEE 802.11af technology in wireless medical sensor networks(Springer Heidelberg, 2019) Bayrakdar, Muhammed EnesIn this work, the IEEE 802.11af technology-based wireless sensor network for health data monitoring with priority classes is proposed. In IEEE 802.11af technology, a White Space Device (WSD), a Station (STA), and an Access Point (AP) communicate through television white spectrum opportunistically without causing any harmful interference to licensed` services. In the proposed network; WSDs, STA, and AP employ Frequency Division Multiple Access (FDMA) technique with the aim of communicating through the white space spectrum determined by White Space Map (WSM). WSD collects health data such as body temperature and blood pressure from an implant or on-body sensors. The priority class is determined according to the emergency of a patient as red, yellow, and green. After obtaining the analytical model of the proposed network, the simulation model is carried out using Riverbed Modeler. The graphical results prove the validity and applicability of the proposed network in terms of delay (0.17 s) and energy consumption (4.7 mJ/s) without any spectrum cost for priority-based health data monitoring. Graphical abstract Cognitive radio based IEEE 802.11af environment for priority based health data monitoring.Öğe PREDICTING HOUSING SALES IN TURKEY USING ARIMA, LSTM AND HYBRID MODELS(Vilnius Gediminas Tech Univ, 2019) Temur, Ayşe Soy; Akgün, Melek; Temur, GunayHaving forecast of real estate sales done correctly is very important for balancing supply and demand in the housing market. However, it is very difficult for housing companies or real estate professionals to determine how many houses they will sell next year. Although this does not mean that a prediction plan cannot be created, the studies conducted both in Turkey and different countries about the housing sector are focused more on estimating housing prices. Especially the developing technological advances allow making estimations in many areas. That is why the purpose of this study is both to provide guiding information to the companies in the sector and to contribute to the literature. In this study, a 124-month data set belonging to the 2008 (1)-2018 (4) period has been taken into account for total housing sales in Turkey. In order to estimate the time series of sales, ARIMA (Auto Regressive Integrated Moving Average as linear model), LSTM (Long Short-Term Memory as nonlinear model) has been used. As to increase the estimation, a HYBRID (LSTM and ARIMA) model created has been used in the application. When MAPE (Mean Absolute Percentage Error) and MSE (Mean Squared Error) values obtained from each of these methods were compared, the best performance with the lowest error rate proved to be the HYBRID model, and the fact that all the application models have very close results shows the success of predictability. This is an indication that our study will contribute significantly to the literature.Öğe Performance Evaluation of TDMA Medium Access Control Protocol in Cognitive Wireless Networks(Inst Mathematics & Computer Science Acad, 2017) Bayrakdar, Muhammed Enes; Çalhan, AliCognitive radio paradigm has been revealed as a new communication technology that shares channels in wireless networks. Channel assignment is a crucial issue in the field of cognitive wireless networks because of the spectrum scarcity. In this work, we have evaluated the performance of TDMA medium access control protocol. In our simulation scenarios, primary users and secondary users utilize TDMA as a medium access control protocol. We have designed a network environment in Riverbed simulation software that consists of primary users, secondary users, and base stations. In our system model, secondary users sense the spectrum and inform the base station about empty channels. Then, the base station decides accordingly which secondary user may utilize the empty channel. Energy detection technique is employed as a spectrum sensing technique because it is the best when information about signal of primary user is acquired. Besides, different number of users is selected in simulation scenarios in order to obtain accurate delay and throughput results. Comparing analytical model with simulation results, we have shown that performance analysis of our system model is consistent and accurate.
