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
200 Documents
<![CDATA[Text line Segmentation in Compressed Representation of Handwritten Document using Tunneling Algorithm ]]>
<![CDATA[R, Amarnath]]>;
<![CDATA[P, Nagabhushan]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering Vol 6, No 4 (2018) ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2018448451
<![CDATA[Operating directly on the compressed document images without decompression would be an additional advantage for storage and transmission. In this research work, we perform text line segmentation directly in compressed representation of an unconstraint handwritten document image using tunneling algorithm. In this relation, we make use of text line terminal point which is the current state-of-the-art that enables text line segmentation. The terminal points spotted along both margins (left and right) of a document image for every text line are considered as source and target respectively. The effort in spotting the terminal positions is performed directly in the compressed domain. The tunneling algorithm uses a single agent to identify the coordinate positions in the compressed representation to perform text-line segmentation of the document. The agent starts at a source point and progressively tunnels a path routing in between two adjacent text lines and reaches the probable target. The agent’s navigation path from source to the target bypassing obstacles, if any, results in segregating the two adjacent text lines. However, the target point would be known only when the agent reaches destination; this is applicable for all source points and henceforth we could analyze the correspondence between source and target nodes. In compressed representation of a document image, the continuous pixel values in a spatial domain are available in the form of batches known as white-runs (background) and black-runs (foreground). These batches are considered as features of a document image represented in a Grid map. Performing text-line segmentation using these features makes the system inexpensive compared to spatial domain processing. Artificial Intelligence in Expert systems with dynamic programming and greedy strategies is employed for every search space for tunneling. An exhaustive experimentation is carried out on various benchmark datasets including ICDAR13 and the performances are reported.]]>
<![CDATA[Feature Selection on MR Images Using Genetic Algorithm with SVM and Naive Bayes Classifiers ]]>
<![CDATA[Adar, Nihat]]>;
<![CDATA[Okyay, Savaş]]>;
<![CDATA[Özkan, Kemal]]>;
<![CDATA[Şaylısoy, Suzan]]>;
<![CDATA[Adapınar, Belgin Demet Özbabalık]]>;
<![CDATA[Adapınar, Baki]]>
<![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.270422
<![CDATA[Dementias are termed as neuropsychiatric disorders. Brain images of dementia patients can be obtained through magnetic resonance imaging systems. The relevant disease can be diagnosed by examining critical regions of those images. Certain brain characteristics such as the cortical volume, the thickness, and the surface area may vary among dementia types. These attributes can be expressed as numerical values using image processing techniques. In this study, the dataset involves T1 medical image sets of 63 samples. Each particular sample is labeled with one of the three dementia types: Alzheimers disease, frontotemporal dementia, and vascular dementia. The image sets are processed to create different feature groups. These are cortical volumes, gray volumes, surface areas, and thickness averages. The main objective is seeking brain sections more effective in establishing the clinical diagnosis. In other words, searching an optimal feature subset process is carried out for each feature group. To that end, a wrapper feature selection technique namely genetic algorithm is used with Naive Bayes classifier and support vector machines. The test phase is performed by using 10-fold cross validation. Consequently, accuracy results up to 93.7% with different classifiers and feature selection parameters are shown.Anahtar Kelimeler]]>
<![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[Lupsix: A Cascade Framework for Lung Parenchyma Segmentation in Axial CT Images ]]>
<![CDATA[Koyuncu, Hasan]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering Vol 6, No 4 (2018) ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2018448460
<![CDATA[Lung imaging and computer aided diagnosis (CAD) play a critical role in detection of lung diseases. The most significant part of a lung based CAD is to fulfil the parenchyma segmentation, since disease information is kept in the parenchyma texture. For this purpose, parenchyma segmentation should be accurately performed to find the necessary diagnosis to be used in the treatment. Besides, lung parenchyma segmentation remains as a challenging task in computed tomography (CT) owing to the handicaps oriented with the imaging and nature of parenchyma. In this paper, a cascade framework involving histogram analysis, morphological operations, mean shift segmentation (MSS) and region growing (RG) is proposed to perform an accurate segmentation in thorax CT images. In training data, 20 axial CT images are utilized to define the optimum parameter values, and 150 images are considered as test data to objectively evaluate the performance of system. Five statistical metrics are handled to carry out the performance assessment, and a literature comparison is realized with the state-of-the-art techniques. As a result, parenchyma tissues are segmented with success rates as 98.07% (sensitivity), 99.72% (specificity), 99.3% (accuracy), 98.59% (Dice similarity coefficient) and 97.23% (Jaccard) on test dataset.]]>
<![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[Breast Cancer Diagnosis by Different Machine Learning Methods Using Blood Analysis Data ]]>
<![CDATA[Aslan, Muhammet Fatih]]>;
<![CDATA[Celik, Yunus]]>;
<![CDATA[Sabanci, Kadir]]>;
<![CDATA[Durdu, Akif]]>
<![CDATA[ International Journal of Intelligent Systems and Applications in Engineering Vol 6, No 4 (2018) ]]>
Publisher : <![CDATA[Prof. Dr. Ismail SARITAS ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.18201/ijisae.2018648455
<![CDATA[Today, one of the most common types of cancer is breast cancer. It is crucial to prevent the propagation of malign cells to reduce the rate of cancer induced mortality. Cancer detection must be done as early as possible for this purpose. Machine Learning techniques are used to diagnose or predict the success of treatment in medicine. In this study, four different machine learning algorithms were used to early detection of breast cancer. The aim of this study is to process the results of routine blood analysis with different ML methods and to understand how effective this method is for detection. Methods used can be listed as Artificial Neural Network (ANN), standard Extreme Learning Machine (ELM), Support Vector Machine (SVM) and K-Nearest Neighbor (k-NN). Dataset used were taken from UCI library. In this dataset age, body mass index (BMI), glucose, insulin, homeostasis model assessment (HOMA), leptin, adiponectin, resistin and chemokine monocyte chemoattractant protein 1 (MCP1)   attributes were used. Parameters that have the best accuracy values were found by using four different Machine Learning techniques. For this purpose, hyperparameter optimization method was used. In the end, the results were compared and discussed.]]>
<![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.]]>
