Ana Sayfa|Yayınlar|Projeler|Araştırma Alanları|Dersler|Öğrenciler|Akademik Deneyim|Duyurular|İletişim


ATIFLAR
Science Citation Index'te taranan dergilerde 475 adet atıf verilmiştir. (Web of Science)
h-index: 12


KİTAPLAR
A novel model for risk estimation in software projects using artificial neural network
Calp M.H., Akcayol M.A.
Book Chapter on Artificial Intelligence and Applied Mathematics in Engineering Problems
Hemanth D.J., Kose U. (Editors)
Springer, pp.295-319, ISBN: 978-3-030-36178-5, 2020.
Ayrık matematik ve uygulamaları (Discrete mathematics and its applications 7th Ed.)
Palme Yayıncılık, ISBN: 978-605-355-357-1 (Bölüm Çevirisi), 2015.
Kenneth H.R.
McGraw-Hill Science/Engineering/Math, 2011.
Etkin ulaşım planlamasında karar destek sistemlerinin kullanımı
IGI Global, ISBN: 9781466686489 (Yayın Danışma Kurulu), 2015.
Web teknolojileri
Erdem O.A., Akcayol M.A.
Seçkin Yayıncılık, ISBN: 975 347 886 0, 1. Baskı: Ocak 2005, 2. Baskı: Ekim 2006.


SCI / SCIE DERGİLER
A new topic modeling based approach for aspect extraction in aspect based sentiment analysis: SS-LDA
Özyurt B., Akcayol M.A.
Expert Systems with Applications, Vol.168, 114231, April 2021.
Abstract | pdf
With the widespread use of social networks, blogs, forums and e-commerce web sites, the volume of user generated textual data is growing exponentially. User opinions in product reviews or in other textual data are crucial for manufacturers, retailers and providers of the products and services. Therefore, sentiment analysis and opinion mining have become important research areas. In user reviews mining, topic modeling based approaches and Latent Dirichlet Allocation (LDA) are significant methods that are used in extracting product aspects in aspect based sentiment analysis. However, LDA cannot be directly applied on user reviews and on other short texts because of data sparsity problem and lack of co-occurrence patterns. Several studies have been published for the adaptation of LDA for short texts. In this study, a novel method for aspect based sentiment analysis, Sentence Segment LDA (SS-LDA) is proposed. SS-LDA is a novel adaptation of LDA algorithm for product aspect extraction. The experimental results reveal that SS-LDA is quite competitive in extracting products aspects.
Deep learning based new prediction model for the next purchase
Utku A., Akcayol M.A.
Advances in Electrical and Computer Engineering, Vol.20(2), pp.35-44, 2020.
Abstract | pdf
Time series represent the consecutive measurements taken at equally spaced time intervals. Time series prediction uses the information in a time series to predict future values. The future value prediction is important for many business and administrative decision makers especially in e-commerce. To promote business, sales prediction and sensing of future consumer behavior can help business decision makers in marketing campaigns, budget and resource planning. In this study, deep learning based a new prediction model has been developed for the time of next purchase in ecommerce. The proposed model has been extensively tested and compared with RF, ARIMA, CNN and MLP using a retail market dataset. The experimental results show that the developed model has been more successful than RF, ARIMA, CNN and MLP to predict the time of the next purchase.
A weighted multi-attribute-based recommender system using extended user behavior analysis
Akcayol M.A., Utku A., Aydoğan E., Mutlu B.
Electronic Commerce Research and Applications,
Vol.28, pp.86-93, 2018.
BibTeX | Abstract | pdf
A new weighted multi-attribute based recommender system (WMARS) has been developed using extended user behavior analysis. WMARS obtained data from number of clicked items in the recommendation list, sequence of the clicked items in recommendation the list, duration of tracking, number of tracking same item, likes/dislikes, association rules of clicked items, remarks for items. WMARS has been applied to a movie web site. The experimental results have been obtained from a total of 567 heterogeneous users, including employers in different sectors, different demographic groups, and undergraduate and graduate students. Using different weighted sets of the attributes’ parameters, WMARS has been tested and compared extensively with collaborative filtering. The experimental results show that WMARS is more successful than collaborative filtering for the data set that was used.
Calculation of electron energy distribution functions from electron swarm parameters using artificial neural network in SF6 and Argon
Tezcan S.S., Akcayol M.A., Ozerdem O.C., Dincer, M.S.
IEEE Transactions on Plasma Science, Vol.38(9), pp.2332-2339, 2010.
Abstract | pdf
This paper proposes an artificial neural network (ANN) to obtain the electron energy distribution functions (EEDFs) in SF6 and argon from the following: 1) mean energies; 2) the drift velocities; and 3) other related swarm data. In order to obtain the required swarm data, the electron swarm behavior in SF6 and argon is analyzed over the range of the density-reduced electric field strength E/N from 50 to 800 Td from a Boltzmann equation analysis based on the finite difference method under a steady-state Townsend condition. A comparison between the EEDFs calculated by the Boltzmann equation and by ANN for various values of E/N suggests that the proposed ANN yields good agreement of EEDFs with those of the Boltzmann equation solution results.
An educational tool for fuzzy logic controlled BDCM
Akcayol M.A., Çetin A., Elmas Ç.
IEEE Transactions on Education, Vol.45(1), pp.33-42, 2002.
BibTeX | Abstract | pdf
Fuzzy logic controllers (FLC) have gained popularity in the past few decades with successful implementation in many areas, including electrical machines’ drive control. Many colleges are now offering fuzzy logic courses due to successful applications of FLCs in nonlinear systems. However, teaching students a fuzzy logic controlled drive system in a laboratory, or training technical staff, is time consuming and may be an expensive task. This paper presents an educational tool for fuzzy logic controlled brushless direct current motor (BDCM), which is a part of a virtual electrical machinery laboratory project. The tool has flexible structure and graphical interface. Motor and controller parameters of the drive system can be changed easily under different operating conditions.
Application of adaptive neuro-fuzzy controller for SRM
Akcayol M.A.
Advances in Engineering Software, Vol.35(3-4), pp.129-137, 2004.
Abstract | pdf
In this paper, an adaptive neuro-fuzzy inference system (ANFIS) has been presented to speed control of a switched reluctance motor (SRM). SRMs have become an attractive alternative in variable speed drives due to their advantages such as structural simplicity, high reliability, high efficiency and low cost. But, the SRM performance often degrades for the machine parameter variations. The SRM converter is difficult to control due to its nonlinearities and parameter variations. In this study, to tackle these problems, an adaptive neurofuzzy controller is proposed. Heuristic rules are derived with the membership functions then the parameters of membership functions are tuned by ANFIS. The algorithm has been implemented on a digital signal processor (TMS320F240) allowing great flexibility for various real time applications. Experimental results demonstrate the effectiveness of the proposed ANFIS controller under different operating conditions of the SRM.
A modified genetic algorithm for a special case of generalized assignment problem
Dörterler M., Bay O.F., Akcayol M.A.
Turkish Journal of Electrical Engineering & Computer Sciences, Vol.25, pp.794-805, 2017.
pdf
Candidate sentence selection for extractive text summarization
Mutlu B., Sezer E., Akcayol M.A.
Information Processing and Management, Vol.57, 2020.
Abstract | pdf
Text summarization is a process of generating a brief version of documents by preserving the fundamental information of documents as much as possible. Although the majority of the text summarization researches have been focused on supervised learning solutions, there are a few datasets indeed generated for summarization task, and most of the existing summarization datasets do not have human-generated goal summaries, which is vital for both summary generation and evaluation. Therefore, a new dataset was presented for abstractive and extractive summarization tasks in this study. This dataset contains academic publications, the abstracts written by the authors, and extracts in two sizes, which were generated by human readers in this research. Then, the resulting extracts were evaluated to ensure the validity of the human extract production process. Moreover, the extractive summarization problem was reinvestigated on the proposed summarization dataset. Here the main point taken into account was to analyze the feature vector to generate more informative summaries. To that end, a comprehensive syntactic feature space was generated for the proposed dataset, and the impact of these features on the informativeness of the resulting summary was investigated. Besides, the summarization capability of semantic features was experienced by using GloVe and word2vec embeddings. Finally, the use of ensembled feature space, which corresponds to the joint use of syntactic and semantic features, was proposed on a long short-term memory-based neural network model. ROUGE metrics evaluated the model summaries, and the results of these evaluations showed that the use of the proposed ensemble feature space remarkably improved the single-use of syntactic or semantic features. Additionally, the resulting summaries of the proposed approach on ensembled features prominently outperformed or provided comparable performance than summaries obtained by state-of-the-art models for extractive summarization.
A GIS based novel active monitoring system for fiber networks
Akdemir Ö.K., Dursun T., Arslan S., Benzer R., Akcayol M.A.
Turkish Journal of Electrical Engineering & Computer Sciences, Vol.24(1), pp.247-261, 2016.
pdf
Multi-document extractive text summarization: a comparative assessment on features
Mutlu B., Sezer E., Akcayol M.A.
Knowledge-Based Systems, Vol.183, 2019.
Abstract | pdf
Text summarization is the process of generating a brief version of a text that preserves the salient information of the text. For information retrieval, it is a good dimension reduction solution. In addition, it reduces the required reading time. This study focused on extracting informative summaries from multiple documents using commonly used hand-crafted features from the literature. The first investigation focused on the generation of a feature vector. The features were the number of sentences, term frequency, similarity with the title, term frequency-inverse sentence frequency, sentence position, sentence length, sentence–sentence similarity, bushy-path results, phrases of the sentence, proper nouns, n-gram co-occurrence, and length of the document. Secondly, several combinations of these features were examined and a shallow multi-layer perceptron and two differently modeled fuzzy inference systems were used to extract salient sentences from texts in the Document Understanding Conference (DUC) dataset. The summarization performances of these models were evaluated using original classification performance metrics, and recall-oriented understudy for gisting evaluation (ROUGE)-n. This study recommended the use of fuzzy systems based on a feature vector and a fuzzy rule set for extractive text summarization. The extraction methods were evaluated against a changing compression ratio. Results of experiments showed that the implemented neural model tended to incorrectly infer sentences that were not considered salient by human annotators. However, for distinguishing between summary-worthy and summary-unworthy sentences, the fuzzy inference systems performed better than the utilized neural network, as well as better than the existing fuzzy inference-based text summarization approaches in the literature.
NEFCLASS-based neuro fuzzy controller for SRM drive
Akcayol M.A., Elmas Ç.
Engineering Applications of Artificial Intelligence, Vol.18(5), pp.595-602, 2005.
BibTeX | Abstract | pdf
Switched reluctance motor (SRM) is increasingly employed in industrial applications where variable speed is required because of their simple construction, ease of maintenance, low cost and high efficiency. However, the SRM performance often degrades for the machine parameter variations. The SRM converter is difficult to control due to its nonlinearities and parameter uncertainties. In this paper, to overcome this problem, a neuro fuzzy controller (NFC) is proposed. Heuristic rules are derived with the membership functions of the fuzzy variables tuned by a neural network (NN). The algorithm is implemented on a digital signal processor (TMS320F240) allowing great flexibility for various real time applications. Experimental results demonstrate the effectiveness of the NFC with various working conditions of the SRM.
An experimental research on the use of recurrent neural networks in landslide susceptibility mapping
Mutlu B., Nefeslioğlu H.A., Sezer E.A., Akcayol M.A., Gökçeoğlu C.
ISPRS International Journal of Geo-Information,
Vol.8(12), 578, 2019.
Abstract | pdf
Natural hazards have a great number of influencing factors. Machine-learning approaches have been employed to understand the individual and joint relations of these factors. However, it is a challenging process for a machine learning algorithm to learn the relations of a large parameter space. In this circumstance, the success of the model is highly dependent on the applied parameter reduction procedure. As a state-of-the-art neural network model, representative learning assumes full responsibility of learning from feature extraction to prediction. In this study, a representative learning technique, recurrent neural network (RNN), was applied to a natural hazard problem. To that end, it aimed to assess the landslide problem by two objectives: Landslide susceptibility and inventory. Regarding the first objective, an empirical study was performed to explore the most convenient parameter set. In landslide inventory studies, the capability of the implemented RNN on predicting the subsequent landslides based on the events before a certain time was investigated respecting the resulting parameter set of the first objective. To evaluate the behavior of implemented neural models, receiver operating characteristic analysis was performed. Precision, recall, f-measure, and accuracy values were additionally measured by changing the classification threshold. Here, it was proposed that recall metric be utilized for an evaluation of landslide mapping. Results showed that the implemented RNN achieves a high estimation capability for landslide susceptibility. By increasing the network complexity, the model started to predict the exact label of the corresponding landslide initiation point instead of estimating the susceptibility level.
A heuristic routing protocol and congestion control at wireless networks
Şimşek M., Akcayol M.A.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.23(1), pp.57-63, 2008.
pdf
Develop a 3G based remote controlled car
Şimşek M., Yoldaş M., Bulut A., Doğru İ.A., Akcayol M.A.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.27(1), pp.135-142, 2012.
pdf
Modelling (using artificial neural-networks) the performance parameters of a solar-driven ejector-absorption cycle
Sözen A., Akcayol M.A.
Applied Energy, Vol.79(3), pp.309-325, 2004.
Abstract | pdf
Theoretical thermodynamic analysis of the absorption thermal systems is at present too complex because of analytic functions calculating the thermodynamic properties of fluid couples involving the solution of complex differential equations and simulation programs. This paper proposes a new approach to performance analysis of a solar-driven ejector-absorption refrigeration system (EARS) with an aqua/ammonia working fluid. Use of artificial neuralnetworks (ANNs) has been proposed to determine the performance parameters as functions of only the working temperature, under various working conditions. Thus, this study is considered to be helpful in predicting the performance of an EARS prior to it being set up in an environment where the temperatures are known. The statistical coefficient of multiple determinations (R2 – value) equals to 0.976, 0.9825, 0.9855 for the coefficient of performance (COP), exergetic coefficient of performance (ECOP) and circulation ratio (F), respectively. These accuracies are acceptable for the design of an EARS. The present method greatly reduces the time required by design engineers to find the optimum solution and in many cases reaches a solution that could not be easily obtained from simple modelling programs. The importance of the ANN approach, apart from reducing the time required, is that it is possible to find solutions that make solar-energy applications more viable and thus more attractive to potential users, such as solar engineers. Also, this approach has the advantages of computational speed, low cost for feasibility, rapid turnaround (which is especially important during iterative design-phases), and ease of design by operators with little technical experience.
PICTool: Integrated hardware and software for teaching/learning FLC using microcontrollers
Erdem O.A., Akcayol M.A., Orman A.
Intelligent Automation and Soft Computing, Vol.12(4), pp.411-417, 2006.
BibTeX | pdf
Gene selection for breast cancer classification based on data fusion and genetic algorithm
Yıldız O., Tez M., Bilge H.S.., Akcayol M.A., Güler İ.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.27(3), pp.659-668, 2012.
pdf
A scalable routing protocol for wireless mesh networks
Kocaoğlu R, Akcayol M.A.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.27(4), pp.891-899, 2012.
pdf
Application of fuzzy logic controlled cathodic protection on Iraq-Turkey crude oil pipeline
Akcayol M.A.
Applied Intelligence, Vol.24(1), pp.43-50, 2006.
BibTeX | pdf
Congestion control in WAP traffic and transport layer protocols
Toklu S., Akcayol M.A.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.24(3), pp.397-408, 2009.
pdf
Genetic algorithm based a new algorithm for time dynamic shortest path problem
Dener M., Akcayol M.A., Toklu S., Bay Ö.F.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.26(4), pp.915-928, 2011.
pdf
A hybrid genetic algorithm for multistage integrated logistics network optimisation problem
Demirel N., Gökçen H., Akcayol M.A., Demirel E.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.26(4), pp.926-936, 2011.
pdf
Neuro-fuzzy controller implementation for an adaptive cathodic protection on Iraq-Turkey crude oil pipeline
Akcayol M.A., Sağıroğlu Ş.
Applied Artificial Intelligence, Vol.21(3), pp.241-256, 2007.
BibTeX | pdf
A Computer-based educational tool for pulse width modulator for static converters
Akcayol M.A., Yiğit T.
Computer Applications in Engineering Education, Vol.12(4), pp.215-223, 2004.
BibTeX | pdf
Artificial neural network based modeling of heated catalytic converter performance
Akcayol M.A., Çınar C.
Applied Thermal Engineering, Vol.25(14-15), pp.2341-2350, 2005.
(Top 25 Hottest Articles, Nisan - Haziran 2005, Temmuz - Eylül 2005, Ekim - Aralık 2005)
pdf
Virtual electrical machinery laboratory: a fuzzy logic controller for induction motor drive
Elmas Ç., Akcayol M.A.
International Journal of Engineering Education, Vol.20(2), pp.226-233, 2004.
pdf
An educational tool for fuzzy logic controller and classical controllers
Akcayol M.A., Elmas Ç., Erdem O.A., Kurt M.
Computer Applications in Engineering Education, Vol.12(2), pp.126-135, 2004.
BibTeX | pdf
Performance prediction of a solar driven ejector-absorption cycle using fuzzy logic
Sözen A., Kurt M., Akcayol M.A., Özalp M.
Renewable Energy, Vol.29(1), pp.53-71, 2004.
pdf
PC based educational tool for a switched reluctance drive with fuzzy logic
Elmas Ç., Akcayol M.A.
International Journal of Electrical Engineering Education, Vol.40(4), pp.208-219, 2003.
pdf
Performance prediction of a vapour-compression heat-pump
Sözen A., Arcaklıoğlu E., Erişen A., Akcayol M.A.
Applied Energy, Vol.79(3), pp.327-344, 2004.
(Top 25 Hottest Articles, Temmuz - Eylül 2004, Ekim - Aralık 2004)
pdf
Forecasting net energy consumption using artificial neural network
Sözen A., Akcayol M.A., Arcaklioğlu E.
Energy Sources, Part B, Vol.1(2), pp.147-155, 2006.
pdf
Temperature prediction in a coal fired boiler with a fixed bed by fuzzy logic based on numerical solution
Bıyıkoğlu A., Akcayol M.A., Özdemir V., Sivrioğlu M.
Energy Conversion and Management, Vol.46(1), pp.151-166, 2005.
pdf
Reformulation, as a function of only working temperatures, of performance parameters of a solar driven ejector-absorption cycle using artificial neural networks
Sözen A., Akcayol M.A.
Energy Sources, Vol.27(12), pp.1133-1149, 2005.
pdf
NEFCLASS based extraction of fuzzy rules and classification of risks of low back disorders
Akay D., Akcayol M.A., Kurt M.
Expert Systems with Applications, Vol.35, pp.2107-2112, 2008.
BibTeX | pdf
A simple neuro fuzzy model for ISE 100 index prediction
Ok Y., Atak M., Akcayol M.A.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.26(4), pp.897-904, 2011.
pdf


ESCI DERGİLER
Design and implementation of web based risk management system based on artificial neural networks for software projects: WEBRISKIT
Calp M.H., Akcayol M.A.
Pamukkale University Journal of Engineering Sciences, Vol.26(5), pp.993-1014, 2020.
Abstract | pdf
The software industry is increasingly involved in every aspect of life and software projects are being developed to a large extent. This situation causes very important faults and negative results in the developed projects. Therefore, in order to prevent or minimize this situation, software risk management activities must be successfully implemented. In this study, a new web-based risk management process based on artificial intelligence in software projects was designed and developed. The purpose of the study is to estimate the deviations that might occur in the project outputs according to the risk factors using artificial neural networks (ANN), to minimize the harm that may be encountered in the first stages of the software life cycle and thus to provide a preventive approach for users. In order to create the ANN model of the study, a checklist form was created by preliminary discussions with academicians, experts and project managers in the software engineering field. By using this form, the actual project data were collected from 774 different companies in the software companies located in Teknokent. The generated ANN model has forty-five entrances, a single hidden layer (with fifteen neurons) and five outlets (with 45-15-5); the education R rate is 0.9978; the test R ratio is 0.9935 and the error rate is 0.001. The model is integrated into the application developed by creating the .dll library. The developed application, real project data from different areas were obtained and after obtaining the opinions of experts and academicians (10 people), 4 different scenarios were tested and results were obtained. The results clearly demonstrate that the performance of the application is high and that the use of ANN in such applications provides positive contributions to the project's success. In addition, it has been found that there is a need for applications that provide an artificial intelligence-based risk management process for the software industry.
Deep learning based new model for video captioning
Özer E.G., Karapınar İ.N., Başbuğ S., Turan S., Utku A., Akcayol M.A.
International Journal of Advanced Computer Science and Applications, Vol.11(3), 2020.
Abstract | pdf
Visually impaired individuals face many difficulties in their daily lives. In this study, a video captioning system has been developed for visually impaired individuals to analyze the events through real-time images and express them in meaningful sentences. It is aimed to better understand the problems experienced by visually impaired individuals in their daily lives. For this reason, the opinions and suggestions of the disabled individuals within the Altınokta Blind Association (Turkish organization of blind people) have been collected to produce more realistic solutions to their problems. In this study, MSVD which consists of 1970 YouTube clips has been used as training dataset. First, all clips have been muted so that the sounds of the clips have not been used in the sentence extraction process. The CNN and LSTM architectures have been used to create sentence and experimental results have been compared using BLEU 4, ROUGE-L and CIDEr and METEOR.
Prediction of the next time of an event with deep learning based model
Utku A., Akcayol M.A.
Journal of Polytechnic, Vol.24(1), pp.1-15, 2021.
Abstract | pdf
Studies have been going on for many years to predict the time before some events happen. Thus, it is aimed to minimize the damage that occurs when the event occurs or to maximize the benefit to be obtained. Studies on the prediction of subsequent events in many different areas, such as the prediction of the subsequent behavior of a customer, the prediction of the subsequent occurrence of natural disasters, the estimate of the number of future demands in a given time interval, are gradually increasing. However, in the literature, there is no successful study for predicting the time and type of event before the occurrence of crimes and emergency calls. Crime analysis is a field of research aimed at securing the threatened areas, reducing the rate of crime and saving law enforcement. High success is achieved with the use of up-to-date technologies in the efforts to resolve the crime shortly after it is committed. Similarly, emergency call analysis reduces response time and optimizes resource usage. In this study, a deep learning based prediction model for crime and emergency call analysis has been developed. With the developed model, the time of the next crime and the time of the next emergency call are predicted. The results obtained with the developed model has been compared with ARIMA which is one of the statistical time series prediction methods. Experimental results have shown that the developed deep learning-based model is more successful than ARIMA in forward-looking event time prediction.


EI DERGİLER
An efficient multi-threaded Web crawler using HashMaps
Kansu Y., Mutlu B., Utku A., Akcayol M.A.
Journal of Advances in Computer Networks, Vol.5(1&2), pp.66-70, 2017. (Selected from ICEEE 2017.)
Abstract | pdf
In last decades, the number of web pages on the Internet has been exposed a rapid increase intrinsically, and the information on the Internet has reached a very large size. Search engines have been developed to access this large-scale information efficiently. Web crawlers play a very important role in search engines. In this paper, an efficient multi-threaded web crawler is proposed, and empirically analyzed in terms of crawling speed and coverage.
A comprehensive analysis of architectures and methods of real-time big data analytics
Ay S., Akcayol M.A.
Lecture Notes on Information Theory, Vol. 5(1), pp.7-12, 2017.
(Selected from 4th International Conference on Electrical and Electronics Engineering).
pdf
Genetic algorithm and fuzzy logic based flexible querying in databases
Şenol A., Karacan H., Akcayol M.A.
Journal of Computers, Vol.13(6), pp.678-691, 2018.
(Selected from 4th International Conference on Electrical and Electronics Engineering)
BibTeX | pdf
Priority queue based estimation of importance of Web pages for Web crawlers
Baker M.R., Akcayol M.A.
International Journal of Computer and Electrical Engineering, Vol.9(1), pp.330-342, 2017.
(Selected from 3rd International Conference on Computer and Information Technology)
pdf
Analyzing the route cache timeout parameter of DSR protocol in mobile ad hoc networks
Özyurt B., Doğru İ. A, Akcayol M. A.
International Journal of Computer and Communication Engineering, Vol. 6 (1), pp. 40-48, 2017.
pdf
A survey of multicast routing protocols in ad-hoc networks
Baker M.R., Akcayol M.A.
Gazi University Journal of Science, Vol.24(3), pp.451-462, 2011.
pdf
Implementation of real-time optimization of page layout of Internet newspaper using simulated annealing
Canbek G., Akcayol M.A.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.21(2), pp.341-348, 2006.
pdf
Real-time optimization of Web page layout using genetic algorithm
Gözüdeli Y., Akcayol M.A.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.22(2), pp.431-439, 2007.
pdf
Artificial neural network based modeling of injection pressure in diesel engines
Akcayol M.A., Çinar C., Bülbül H.İ., Kılıçarslan A.
WSEAS Transactions on Computers, Vol.5(3), pp.1538-1544, 2004.
pdf
Fuzzy PI controller for speed control of swıtched reluctance motor
Elmas C., Akcayol M.A., Yiğit T.
Journal of the Faculty of Engineering and Architecture of Gazi University, Vol.22(1), pp.65-72, 2007.
pdf


ULUSLARARASI İNDEKSLİ DİĞER DERGİLER
A model for prediction of customer behavior: a case study for banking sector
Özdem K., Akcayol M.A.
Niğde Ömer Halisdemir University Journal of Engineering Sciences, Vol.10(1), pp.1-8, 2021.
Abstract | pdf
Campaign based sales continue to increase at a very rapid rate in recent years. Today, sales in many sectors are based on the campaign. Therefore, campaign management has become a very important issue. There is no detailed study on campaign planning and management in the literature. In this article, a model is developed for campaign management in the banking sector and prediction of prospective behaviors of customers towards the campaign. Using the association analysis structure developed specifically for the banking sector, frequent itemsets and association rules were created from the campaign data of a Portuguese bank. The prospective behavior of the customers participating in the campaign was estimated with the rules obtained. In addition, attributes that affect the behavior of customers have been identified. Experimental results have shown that marital status and credit status affect customer behavior the most. Using the developed model, a prediction is made on whether the customers will participate in the campaign or not. 87% success was achieved in the prediction of customers' participation in the campaign.
A comprehensive review on using of deep learning approaches in video captioning applications
Alpay Ö., Akcayol M.A.
Journal of Engineering Sciences and Design, Vol.8(5), pp.271-289, 2020.
A comprehensive study on stream data characterization, generation and analytics
Utku A., Akcayol M.A.
Erzincan University Journal of Science and Technology, Vol.12(1), pp.379-410, 2019.
A comprehensive review on the use of big data in recommendation systems
Utku A., Akcayol M.A.
International Journal of Advances in Engineering and Pure Sciences, Vol.30(4), pp.339-357, 2018.
pdf
Optimization of project scheduling activities in dynamic CPM and PERT networks using genetic algorithms
Calp M.H., Akcayol M.A.
SDU Journal of Natural and Applied Sciences, Vol.22(2), pp.615-627, 2018.
BibTeX | pdf
A survey on sentiment analysis and opinion mining, methods and approaches
Özyurt B., Akcayol M.A.
Selcuk University, Journal of Engineering Science and Technology, Vol.6(4), pp.668-693, 2018.
pdf
Develop a reserved reliable flow control algorithm in mobile ad hoc networks
Doğru İ.A., Erdem O.A., Akcayol M.A.
Gazi Journal of Engineering Sciences, Vol.4(3), pp.144-156, 2018.
A new context-sensitive decision making system for mobile cloud offloading
Tanrıverdi M., Akcayol M.A.
International Journal of Computer Science & Information Technology, Vol. 10(3), pp.71-90, 2018.
Improvement of realization quality of aerospace products using augmented reality technology
Bahar N., Akcayol M.A.
International Journal of Mechanical, Aerospace, Industrial, Mechatronic and Manufacturing Engineering, Vol. 10(1), pp.75-78, 2016.
(Selected from 18th International Conference on Virtual and Augmented Reality).
pdf
Context-aware decision making system for mobile cloud offloading
Tanrıverdi M., Akcayol M.A.
International Journal of Computer Networks & Communications, Vol.7(6), pp.69-85, 2015.
pdf
A new packet scheduling algorithm for real-time multimedia streaming
Simsek M., Doğan N., Akcayol M.A.
Network Protocols and Algorithms, Vol.9(1&2), pp.28-47, 2017.
BibTeX | pdf
Internet based remote security system design and implementation
Erdem O.A., Akcayol M.A., Tuna H.
e-Journal of New World Sciences Academy Natural and Applied Sciences, Vol.2, No.2, pp.78-86, 2007.
The importance of human-computer interaction in the development process of software projects
Calp M.H., Akcayol M.A.
Global Journal of Information Technology, Vol.5, No.1, pp.48-54, 2015.
BibTeX | pdf
A comparative and comprehensive review for learning and adaptive recommendation systems
Utku A., Akcayol M.A.
Erciyes University Journal of Institue of Science and Technology, Vol.33(3), pp.13-34, 2017.
pdf
Implementation of a new recommendation system based on decision tree using implicit relevance feedback
Utku A., Karacan H., Yıldız O., Akcayol M.A.
Journal of Software, Vol.10(1), pp.1367-1374, 2015.
BibTeX | pdf
Risk analysis and success levels of the software project developed in technocity
Calp M.H., Akcayol M.A.
Düzce University Journal of Science and Technolgy, Vol.3(1), pp.57-75, 2015.
BibTeX | pdf
Risk factors and risk management process encountered in software project
Calp M.H., Akcayol M.A.
International Journal of Advances in Engineering and Pure Sciences, Vol.27(1), pp.1-13, 2015.
pdf
Secure routing protocols in wireless networks
Ünal M., Akcayol M.A.
Journal of Informatics Technologies, Vol.1(3), pp.7-13, 2008.
pdf
A mobility management protocol on mobile ad-hoc networks
Doğru İ.A., Şimşek M., Akcayol M.A.
Gazi University Journal of Polytechnic, Vol.11(4), pp.313-318, 2008.
pdf
Congestion control and solution methods in computer networks
Şimşek M., Akcayol M.A.
Journal of Informatics Technologies, Vol.1(3), pp.51-56, 2008.
pdf
Application of GSM based smart home
İnal K., Akcayol M.A.
Journal of Informatics Technologies, Vol.2(2), pp.37-43, 2009.
pdf
Prediction based handover algorithms in wireless networks
Ateş V., Akcayol M.A.
Journal of Informatics Technologies, Vol.3(3), pp.27-36, 2010.
pdf
Performance analysis and solutions for wireless mesh networks
Kocaoğlu R., Akcayol M.A.
Journal of Informatics Technologies, Vol.4(3), pp .1-12, 2011.
pdf
XML database query optimization using simulated annealing
Gözüdeli Y., Akcayol M.A.
Journal of Informatics Technologies, Vol.1(1), pp.13-22, 2008.
pdf
A heuristic routing protocol and congestion control at wireless networks
Şimşek M., Akcayol M.A.
Journal of Informatics Technologies, Vol.1(3), pp.51-56, 2008.
pdf
Benefits of data compression in computers
Erdem O.A., Akcayol M.A., Aydın E.
Gazi University Journal of Science, Vol.8(1), pp.46-55, 1995.
Computer controlled trafo-redresor unit design and application
Akcayol M.A.
Gazi University Journal of Science, Vol.16(3), pp.493-502, 2003.
pdf
NEFCLASS based estimator for inductance variation of SRM
Akcayol M.A.
Erciyes University Journal of the Institute of Science and Technology, Vol.20(1-2), pp.28-36, 2004.
pdf
Neuro-fuzzy modeling of inductance variation of switched reluctance motor
Akcayol M.A.
Gazi University Journal of Polytechnic, Vol.5(4), pp.287-292, 2002.
pdf
Fuzzy logic based speed control of brushless DC motor
Elmas Ç., Akcayol M.A.
Gazi University Journal of Polytechnic, Vol.3(3), pp.7-14, 2000.
Fuzzy logic controlled cathodic protection circuit design
Akcayol M.A.
Gazi University Journal of Science, Vol.17(1), pp.111-127, 2004.
pdf
A software development for smart card applications for use in health system
Akcayol M.A., Elmas Ç.
S.D.U. Journal of Science, Vol.9(2), pp.120-125, 2005.
Present condition analysis and suggestions for e-signature applications in the Turkey
Erol H., Akcayol M.A.
The Journal of Turkish Law World, Vol.3, pp.157-174, 2007.
(Selected from 1st National Electronic Signature Symposium)


ULUSLARARASI SEMPOZYUM
Deep learning-based forecasting of cancellation, delay and orientation on flights
Ayaydın A., Akcayol M.A.
International Conference on Informatics and Computer Science (ICI-CS2021), Ankara, Turkey, December 9-11, 2021.
A comprehensive review on the use of deep learning approaches for video captioning applications
Alpay Ö., Akcayol M.A.
International Conference on Artificial Intelligence and Applied Mathematics in Engineering, Antalya, Turkey, October 24-26, 2020.
Anomaly detection in the stream data by using nearest neighbor regression and linear regression analysis
Acar O.C., Akcayol M.A.
International Conference on Artificial Intelligence and Applied Mathematics in Engineering, Antalya, Turkey, April 20-22, 2019.
Deep learning based an application for anomaly detection at institutional network
Erginay E., Akcayol M.A.
International Data Science and Engineering Symposium, Karabük, Turkey, May 2-3, 2019.
A novel model for risk estimation in software projects using artificial neural network
Calp M.H., Akcayol M.A.
International Conference on Artificial Intelligence and Applied Mathematics in Engineering, Antalya, Turkey, April 20-22, 2019.
End-to-end hierarchical fuzzy inference solution
Mutlu B., Sezer E.A., Akcayol M.A.
IEEE World Congress on Computational Intelligence,
Rio de Janerio, Brazil, 08-13 July, 2018.
BibTeX | Abstract | pdf
Hierarchical Fuzzy System (HFS) is a popular approach for handling curse of dimensionality problem occurred in complex fuzzy rule-based systems with various and numerous inputs. However, the processes of modeling and reasoning of HFS have some critical issues to be considered. In this study, the effect of these issues on the accuracy and stability of the resulting system has been investigated, and an end-to-end HFS framework has been proposed. The proposed framework has three main steps such as single system modeling, rule partitioning and HFS reasoning. It is fully automated, generic, almost independent from data, and applicable for any kind of inference problem. In addition, the proposed framework preserves accuracy and stability during the HFS reasoning. These judgments have been ensured by a number of experimental studies on several datasets about software faulty prediction (SFP) problem with a large feature space. The main contributions of this paper are as follows: (i) it provides the entire HFS implementation from problem definition to calculation of final output, (ii) it increases the accuracy of recently proposed rule generation scheme in the literature, (iii) it presents the only possible fuzzy system solution for SFP problem containing a large feature space with reasonable accuracy.
A fuzzy approach to determine the quality of automatic summaries
Mutlu B., Sezer E. A., Akcayol M.A.
International Fuzzy Systems Symposium, Turkey, 14-15 October, 2017.
Automatic rule generation of fuzzy systems: a comparative assessment on software defect prediction
Mutlu B., Sezer E.A., Akcayol M.A.
International Conference on Computer Science and Engineering, Sarajevo, Bosnia, 20-21 September, 2018.
Smart home system using sequential pattern mining
Kaya G., Yetkin B.B., Akcayol M.A.
International Conference on Technology, Engineering and Science,
Antalya, Turkey, 26-29 October, 2018.
Abstract | pdf
Smart home systems are one of today's active working issues because of the increase comfort, raised living standards, security, health, economic benefits. Smart home systems should interact with the activities of people living in a house and be remotely accessible, monitorable and controllable. A smart home system with the mentioned features has been developed in this study. The system collects data from the behaviors and interactions of the people in the house. It evaluates the collected data adaptively and outputs the results. It produces control signals by using the results. In addition, a simulation was developed to collect data from devices such as an IoT device. The resulting data is examined using rule subtraction from sequential patterns, a data mining method. In this way, the habits of the users in a house are added to the system as a scenario. By using scenarios and rules, the interaction with the user of the system is increased by predicting what the user can do next. The results show energy saving and comfort increase with the developed system.
Specification based automatic product categorization from unstructured data
Hüseynli A., Yıldız O., Akcayol M.A.
Signal Processing and Communications Applications Conference, İzmir, Turkey, 02-05 May, 2018.
BibTeX | pdf
Decision tree based android malware detection system
Utku A., Doğru İ.A., Akcayol M.A.
Signal Processing and Communications Applications Conference, İzmir, Turkey, 02-05 May, 2018.
BibTeX | pdf
Permission based android malware detection with multilayer perceptron
Utku A., Doğru İ.A., Akcayol M.A.
Signal Processing and Communications Applications Conference, İzmir, Turkey, 02-05 May, 2018.
BibTeX | pdf
Deep learning approach for author verification problem on Twitter
Yılmaz M., Mutlu B., Utku A., Akcayol M.A.
Signal Processing and Communications Applications Conference, İzmir, Turkey, 02-05 May, 2018.
BibTeX | pdf
Assembly inspection in aircraft manufacturing using augmented reality technology
Güdekli N., Akcayol M.A.
International Conference on Computer and Information Technology, İzmir, Turkey, 12-14 April, 2017.
Priority queue based estimation of importance of Web pages for Web crawlers
Baker M.B., Akcayol M.A.
International Conference on Computer and Information Technology, İzmir, Turkey, 12-14 April, 2017.
Genetic algorithm and fuzzy logic based flexible querying in databases
Şenol A., Karacan H., Akcayol M.A.
International Conference on Electrical and Electronics Engineering, Ankara, Turkey, 08-10 April, 2017.
A new recommender system based on multiple parameters and extended user behavior analysis
Utku A., Aydoğan E., Mutlu B., Akcayol M.A.
International Conference on Information Management and Engineering, Barcelona,Spain, 09-11 October, 2017.
BibTeX | pdf
A comprehensive analysis of architectures and methods of real-time big data analytics
Ay S., Akcayol M.A.
International Conference on Electrical and Electronics Engineering, Ankara, Turkey, 08-10 April, 2017.
An efficient multi-threaded Web crawler using HashMaps
Kansu Y., Mutlu B., Utku A., Akcayol M.A.
International Conference on Electrical and Electronics Engineering, Ankara, Turkey, 08-10 April, 2017.
Crime analysis based on association rules using Apriori algorithm
Sevri M., Karacan H., Akcayol M.A.
International Conference on Electrical and Electronics Engineering, Ankara, Turkey, 08-10 April, 2017.
Improvement of realization quality of aerospace products using augmented reality technology
Bahar N., Akcayol M.A.
International Conference on Virtual and Augmented Reality, Vol.10(1), pp.18-21, Singapore, 07-08 January, 2016.
pdf

A comprehensive survey for sentiment analysis tasks using machine learning techniques
Aydoğan E., Akcayol M.A.
Innovations in Intelligent Systems and Applications, Vol.10(1), pp.18-21, Romania, 02-05 August, 2016.
BibTeX | pdf

A new method based on tree simplification and schema matching for automatic web result extraction and matching
Gozudeli Y., Karacan H., Yildiz O., Baker M.R., Minnet A., Kalender M., Ozay O., Akcayol M.A.
The International MultiConference of Engineers and Computer Scientists, Hong Kong, 18-20 March, 2015.
Abstract | pdf
In this paper, a new method proposed for extracting and matching the Search Result Record (SRR) data items from different search engines. The method first detects SRRs for a given Web search result. Afterwards, an SRR simplification algorithm is devised to deal with complexity of SRR Document Object Model (DOM) Trees. SRRs and their data items (or properties) are extracted after simplification. Data items are normalized in local and global domain as a last step. Experimental results show that the proposed methods are successful in extracting and merging the SRRs.
Gene selection for breast cancer
Yıldız O., Tez M., Bilge H.S., Akcayol M.A., Güler İ.
IEEE Signal Processing and Communications Applications Conference, Muğla, Turkey, 18-20 April, 2012.
BibTeX | pdf
A comprehensive analysis of e-learning studies in Turkey, problems and suggestions
Doğru İ.A., Simsek M., Akcayol M.A.
IADIS International Conference e-Learning 2011, Rome, Italy, 20-22 July, 2011.
Extraction of automatic search result records using content density algorithm based on node similarity
Gozudeli Y., Yildiz O., Karacan H., Baker M.R., Minnet A., Kalender M., Ozay O., Akcayol M.A.
The International Conference on Data Mining, Internet Computing, and Big Data, Kuala Lumpur, Malaysia, 17-19 November, 2014.
Abstract | pdf
In this paper, a new method proposed for finding and extracting the SRRs. The method first detects content dense nodes on HTML DOM and then extracts SRRs to suggest a list of candidate HTML DOM nodes for a given single research result Web page instance. Afterwards an evaluation algorithm has been applied to the candidate list to find the best solution without any human interaction and manual process. Experimental results show that the proposed methods are successful for finding and extracting the SRRs.
Implementation of a new recommendation system based on decision tree using implicit relevance feedback
Utku A., Karacan H., Yildiz O., Akcayol M.A.
International Conference on Software Technology and Engineering, Hong Kong, 19-20 September, 2015.
The importance of human-computer interaction in the development process of software projects
Calp M.H., Akcayol M.A.
World Conference on Innovation and Computer Scıences, Queen Elizabeth Elite Suite Hotel Convention Center, Antalya, Turkey, May 14-16, 2015.
pdf
Design of an expert system supported portable cardiotocograph (CTG)
Simsek M., Doğru İ.A., Akcayol M.A.
The IADIS WWW/Internet Conference, Rome, Italy, July 20-22, 2011.
pdf
A priority based protocol and load balancing for queue management on wireless networks
Toklu S., Simsek M., Yildiz O., Bay I., Simsek A., Akcayol M.A.
The International Conference on Wireless Networks, Monte Carlo Resort, Las Vegas, Nevada, USA, sJuly 14-17, 2008.
BibTeX
Genetic algorithm based method for water distribution location problem
Aksakal E., Akcayol M.A., Dağdeviren M.
International Conference on Operations Research, Zurich, Switzerland, 30 August-02 September, 2011.
Rule-based mobility management routing for mobile ad hoc networks
Dogru I. A., Simsek M., Toklu S., Yildiz O., Akcayol M.A.
The International Conference on Wireless Networks, Monte Carlo Resort, Las Vegas, Nevada, USA, July 14-17, 2008.
BibTeX
A comprehensive analysis of e-government studies in Turkey, problems and suggestions
Simsek M., Toklu S., Akcayol M.A., Soncul H., Ergun M.A.
The IADIS WWW/Internet Conference, Rome, Italy, 19-22 November, 2009.
pdf
Determination of the response of Ar + SF6 to crossed electric and magnetic fields using an artificial neural network
Akcayol M.A., Hızıroğlu, H.R., Dinçer, M.S.
IEEE Conference on Electrical Insulation and Dielectric Phenomena, Vancouver BC, Canada, 14-17 October, 2007.
pdf
Adaptive cathodic protection for crude oil pipeline
Akcayol M.A., Taplamacıoğlu C.
Electronics, Computers and Artificial Intelligence, University of Pitesti and IEEE Romania, Pitesti, Romania, 29th-30th June, 2007.
Artificial neural network based modeling of stirling engine
Çınar C., Akcayol M.A.
International Conference on Computational Intelligence, Near East University, Nicosia, North Cyprus, 27-29 May, 2004.
SCADA based TRU design and application
Işık, H., Akcayol M.A.
VIII. International Corrosion Symposium, p.343-352, Osmangazi University, Eskişehir, 2002.
Genetic PI controller for a permanent magnet synchronous motor drive
Elmas Ç., Akcayol M.A.
International Turkish Symposium on Artificial Intelligence and Neural Networks, Çanakkale 18 Mart University, Çanakkale, 02-04 July, 2003.
Genetic algorithm based location optimization of emergency service units
Akcayol M.A., Şimşek, M., Bay, İ., Toklu, S., Doğru, I.A.
FAE International Symposium, European University of Lefke, 30 November-01 December, 2006.


ULUSAL SEMPOZYUM
A simulated annealing algorithm for multiple part type scheduling in two machine robotic cells
Batur G.D., Erol S., Akcayol M.A.
National Symposium for Production Research, İstanbul, 23-24 June, pp.71-80, 2011.
A solution for warehouse location allocation problem of fast moving consumer goods with genetic algorithm
Yılmaz B., Dağdeviren M., Akcayol M.A.
National Symposium for Production Research, İstanbul, 23-24 June, pp.485-494, 2011.
Logistic networks design and heuristic method for product recovery
Demirel N., Gökçen H., Akcayol M.A.
National Operations Research and Industrial Engineering Congress, Sakarya, 05-07 Temmuz, 2011.
E-government studies in Turkey, problems and solutions
Akcayol M.A.
Informatics Association of Turkey National Informatics Symposium, pp.274-290, METU Conference Center, Ankara, Turkey, 04-06 October, 2004.
E-library studies in Turkey, analysis and proposals
Akcayol M.A., Şimşek M., Bay İ.
Academic Informatics 2005, Gaziantep University, Gaziantep, Turkey, 02-04 February, 2005.
Present condition analysis and suggestions for e-signature applications in the Turkey
Erol, H., Akcayol M.A.
1st National Electronic Signature Symposium, Gazi Üniversity, Ankara, Turkey, 07-08 December, 2006.
E-signature in institutional networks and a sample application for Gazi University
Erol, H., Akcayol M.A.
1st National Electronic Signature Symposium, Gazi Üniversity, Ankara, Turkey, 07-08 December, 2006.