International Journal of Intelligent Systems and Applications in Engineering
International Journal of Intelligent Systems and Applications in Engineering (IJISAE) is an international and interdisciplinary journal for both invited and contributed peer reviewed articles that intelligent systems and applications in engineering at all levels. The journal publishes a broad range of papers covering theory and practice in order to facilitate future efforts of individuals and groups involved in the field. IJISAE, a peer-reviewed double-blind refereed journal, publishes original papers featuring innovative and practical technologies related to the design and development of intelligent systems in engineering. Its coverage also includes papers on intelligent systems applications in areas such as nanotechnology, renewable energy, medicine engineering, Aeronautics and Astronautics, mechatronics, industrial manufacturing, bioengineering, agriculture, services, intelligence based automation and appliances, medical robots and robotic rehabilitations, space exploration and etc.
Articles
53 Documents
Search results for
, issue
" 2016: Special Issue"
:
53 Documents
clear
<![CDATA[A Genuine GLCM-based Feature Extraction for Breast Tissue Classification on Mammograms ]]>
<![CDATA[Ergin, Semih]]>;
<![CDATA[Esener, İdil Işıklı]]>;
<![CDATA[Yüksel, Tolga]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.269453
<![CDATA[A breast tissue type detection system is designed, and verified on a publicly available mammogram dataset constructed by the Mammographic Image Analysis Society (MIAS) in this paper. This database consists of three fundamental breast tissue types that are fatty, fatty-glandular, and dense-glandular. At the pre-processing stage of the designed detection system, median filtering and morphological operations are applied for noise reduction and artifact suppression, respectively; then a pectoral muscle removal operation follows by using a region growing algorithm. Then, 88-dimensional texture features are computed from the GLCMs (Gray-Level Co-Occurrence Matrices) of mammogram images. Besides, a formerly introduced 108-dimensional feature ensemble is also computed and cascaded with the 88-dimensional texture features. Finally, a classification process is realized using Fisher’s Linear Discriminant Analysis (FLDA) classifier in four different classification cases: one-stage classification, first fatty – then others, first fatty-glandular – then others, and first dense-glandular – then others. A maximum of 72.93% classification accuracy is achieved using only texture features whereas it is increased to 82.48% when cascade features are utilized. This consequence clearly exposes that the cascade features are more representative than texture features. The maximum classification accuracy is attained when “first fatty-glandular – then others†classification case is implemented, that is consistent with the fact that fatty-glandular tissue type is easily confused with fatty and dense-glandular tissue types.]]>
<![CDATA[Clustering of Mitochondrial D-loop Sequences Using Similarity Matrix, PCA and K-means Algorithm ]]>
<![CDATA[Eyüpoğlu, Can]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2016Special Issue-146982
<![CDATA[In this study, mitochondrial displacement-loop (D-loop) sequences isolated from different hominid species are clustered using similarity matrix, Principal Component Analysis (PCA) and K-means algorithm. Firstly, the mitochondrial D-loop sequence data are retrieved from the GenBank database and copied into MATLAB. Pairwise distances are computed using p distance and Jukes-Cantor methods. A phylogenetic tree is created and then a similarity matrix is generated according to the pairwise distances. Furthermore, the clustering is performed using only K-means algorithm. After that PCA and K-means are used together in order to cluster mitochondrial D-loop sequences.]]>
<![CDATA[Classification of Structural MRI for Detecting Alzheimer’s Disease ]]>
<![CDATA[Demirhan, Ayşe]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2016Special Issue-146973
<![CDATA[Alzheimer’s Disease (AD) is a pathological form of dementia that degenerates brain structures. AD affects millions of elderly people over the world and the number of people with AD doubles every year. Detecting AD years before the effects of disease using structural magnetic resonance imaging (MRI) of the brain is possible. Neuroimaging features that are extracted from the structural brain MRI can be used to predict AD by revealing disease related patterns. Machine learning techniques can detect AD and predict conversions from mild cognitive impairment (MCI) to AD automatically and successfully by using these neuroimaging features. In this study common structural brain measures such as volumes and thickness of anatomical structures that are obtained from The Open Access Series of Imaging Studies (OASIS) and made publicly available by https://www.nmr.mgh.harvard.edu/lab/mripredict are analysed. State-of-the-art machine learning techniques, namely support vector machines (SVM), k-nearest neighbour (kNN) algorithm and backpropagation neural network (BP-NN) are employed to discriminate AD and mild AD from healthy controls. Training hyperparameters of the classifiers are tuned using classification accuracy which is obtained with 5-fold cross validation. Prediction performance of the techniques are compared using accuracy, sensitivity and specificity. Results of the system revealed that AD can be distinguished from the healthy controls successfully using multivariate morphological features and machine learning tools. According to the performed experiments SVM is the most successful classifier for detecting AD with classification accuracies up to 82%.]]>
<![CDATA[Modeling of Wood Bonding Strength Based on Soaking Temperature and Soaking Time by means of Artificial Neural Networks ]]>
<![CDATA[Tiryaki, Sebahattin]]>;
<![CDATA[Bardak, Selahattin]]>;
<![CDATA[Aydın, Aytaç]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2016Special Issue-146964
<![CDATA[Adhesive bonding of wood enables sufficient strength and durability to hold wood pieces together and thus produce high quality wood products. However, it is well known that many variables have an important influence on the strength of an adhesive bonding. The objective of the present paper is to predict the bonding strength of spruce (Picea orientalis (L.) Link.) and beech (Fagus orientalisLipsky.) wood joints subjected to soaking by using artificial neural networks. To obtain the data for modeling, beech and spruce samples were subjected to the soaking at different temperatures for different periods of time. In the ANN analysis, 70% of the total experimental data were used to train the network, 15% was used to test the validation of the network, and remaining 15% was used to test the performance of the trained and validated network. A three-layer feedforward back propagation artificial neural network trained by Levenberg–Marquardt learning algorithm was found as the optimum network architecture for the prediction of the bonding strength of soaked wood samples. This architecture could predict wood bonding strength with an acceptable level of the error. Consequently, modeling results demonstrated that artificial neural networks are an efficient and useful modeling tool to predict the bonding strength of wood samples subjected to the soaking for different temperatures and durations.]]>
<![CDATA[A Hybrid Genetic Algorithm for Mobile Robot Shortest Path Problem ]]>
<![CDATA[Boğar, Eşref]]>;
<![CDATA[Beyhan, Selami]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2016Special Issue-146987
<![CDATA[This paper proposes an algorithm to solve the problem of shortest path planning for a mobile robot in a static environment with obstacles. The proposed algorithm is a Hybrid Genetic Algorithm (HGA) which includes Genetic and Dijkstra Algorithms together. The Genetic Algorithm (GA) is preferred since the structure of robot path planning problem is very convenient to apply genetic algorithm’s coding and operators such as permutation coding, crossover and mutation. GA provides diversification while searching possible global solutions, but Dijkstra Algorithm (DA) makes more and more intensification in local solutions. The simulation results show that the mobile robot can plan a set of optimized path with an efficient algorithm.]]>
<![CDATA[Comparison of the effect of unsupervised and supervised discretization methods on classification process ]]>
<![CDATA[HACIBEYOĞLU, MEHMET]]>;
<![CDATA[IBRAHIM, Mohammed H.]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.267490
<![CDATA[Most of the machine learning and data mining algorithms use discrete data for the classification process. But, most data in practice include continuous features. Therefore, a discretization pre-processing step is applied on these datasets before the classification. Discretization process converts continuous values to discrete values. In the literature, there are many methods used for discretization process. These methods are grouped as supervised and unsupervised methods according to whether a class information is used or not. In this paper, we used two unsupervised methods: Equal Width Interval (EW), Equal Frequency (EF) and one supervised method: Entropy Based (EB) discretization. In the experiments, a well-known 10 dataset from UCI (Machine Learning Repository) is used in order to compare the effect of the discretization methods on the classification. The results show that, Naive Bayes (NB), C4.5 and ID3 classification algorithms obtain higher accuracy with EB discretization method.]]>
<![CDATA[A Multistage Deep Belief Networks Application on Arrhythmia Classification ]]>
<![CDATA[ALTAN, Gokhan]]>;
<![CDATA[KUTLU, Yakup]]>;
<![CDATA[ALLAHVERDI, Novruz]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2016Special Issue-146978
<![CDATA[An electrocardiogram (ECG) is a biomedical signal type that determines the normality and abnormality of heart beats using the electrical activity of the heart and has a great importance for cardiac disorders. The computer-aided analysis of biomedical signals has become a fabulous utilization method over the last years. This study introduces a multistage deep learning classification model for automatic arrhythmia classification. The proposed model includes a multi-stage classification system that uses ECG waveforms and the Second Order Difference Plot (SODP) features using a Deep Belief Network (DBN) classifier which has a greedy layer wise training with Restricted Boltzmann Machines algorithm. The multistage DBN model classified the MIT-BIH Arrhythmia Database heartbeats into 5 main groups defined by ANSI/AAMI standards. All ECG signals are filtered with median filters to remove the baseline wander. ECG waveforms were segmented from long-term ECG signals using a window with a length of 501 data points (R wave centered). The extracted waveforms and elliptical features from the SODP are utilized as the input of the model.  The proposed DBN-based multistage arrhythmia classification model has discriminated five types of heartbeats with a high accuracy rate of 96.10%.]]>
<![CDATA[A Survey on Learning System Applications in Energy System Modeling and Prediction ]]>
<![CDATA[Turhal, Ümit Çiğdem]]>;
<![CDATA[Demirci, Türker]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2016Special Issue-146969
<![CDATA[Learning Systems (LS) such as machine learning, statistical pattern recognition and neural networks are computer programs that can learn from sample data and develop a prediction model that makes prediction for new cases. The most important think related with a prediction model is to achieve results as closer as to real situation while making predictions. This is important because being closer to real results help to reduce the costs of feasibility studies in system installation. The performance of Learning Systems has been raised in latest years such as it sometimes exceeds the performance of humans. That’s why the applications of Learning Systems have been increased in many areas. This paper reviews the present applications of Learning Systems in energy system modeling and prediction especially in renewable energy systems such as wind and solar. The aim of this paper is to create a vision for researchers by gathering the present applications and outline their merits and limits and the prediction of their future performance on specific applications. ]]>
<![CDATA[An Integrated Approach for Sustainable Supplier Selection in Fuzzy Environment ]]>
<![CDATA[ŞENOCAK, Ahmet Alp]]>;
<![CDATA[GÖREN, Hacer GÜNER]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.270080
<![CDATA[The term sustainability, which means maintaining a balance or acting responsibly for the future, has come into prominence in many fields. One of the most crucial practice is cooperating with convenient collaborators and composing effective supply chains in terms of social, economic and environmental considerations. Therefore, sustainable supplier selection is getting more and more important to compete in rapidly changing environment. To deal with sustainable supplier selection problem, this study aims to determine the selection of appropriate suppliers and allocation of orders to them. The proposed approach operates in three stages. In the first stage, Fuzzy Decision Making Trial and Evaluation Laboratory is used to obtain the weights of the criteria from sustainability perspective. In the second stage, by using Fuzzy Grey Relational Analysis, a set of suppliers are ranked and their suitability scores are calculated. In the last stage, optimal order quantities to be procured by the suppliers are obtained via fuzzy linear programming including imprecise data of demand, error rate and capacity.]]>
<![CDATA[Estimation of Credit Card Customers Payment Status by Using kNN and MLP ]]>
<![CDATA[KOKLU, Murat]]>;
<![CDATA[SABANCI, Kadir]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering 2016: Special Issue ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2016Special Issue-146983
<![CDATA[The Default of Credit Card Clients dataset in the UCI machine learning repository was used in this study. The credit card customers were classified if they would do payment or not (yes=1 no=0) for next month by using 23 information about them. Totally 30000 data in the dataset’s 66% was used for training and rest of them as 33% was used for tests. The Weka (Waikato Environment for Knowledge Analysis) software was used for estimation. In estimation Multilayer Perceptron (MLP) and k Nearest Neighbors (kNN) machine learning algorithms was used and success rates and error rates were calculated. With kNN estimation success rates for various number of neighborhood value was calculated one by one. The highest success rate was achieved as 80.6569% when the number of neighbor is 10. With MLP neural network model the estimation success rates was calculated when there are different number of neurons in the hidden layer of MLP. The best estimation success rate was achieved as 81.049% when there was only one neuron in the hidden layer. MAE and RMSE values were obtained for this estimation success rate as 0.3237 and 0.388 respectively. ]]>
