Backtracking Search Algorithm

The development of artificial intelligence (AI) based techniques for electricity price forecasting (EPF) provides essential information to electricity market participants and managers because of its greater handling capability of complex input and output relationships. Therefore, this research investigates and analyzes the performance of different optimization methods in the training phase of artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) for the accuracy enhancement of EPF. In this work, a multi-objective optimization-based feature selection technique with the capability of eliminating non-linear and interacting features is implemented to create an efficient day-ahead price forecasting. In the beginning, the multi-objective binary backtracking search algorithm (MOBBSA)-based feature selection technique is used to examine various combinations of input variables to choose the suitable feature subsets, which minimizes, simultaneously, both the number of features and the estimation error. In the later phase, the selected features are transferred into the machine learning-based techniques to map the input variables to the output in order to forecast the electricity price. Furthermore, to increase the forecasting accuracy, a backtracking search algorithm (BSA) is applied as an efficient evolutionary search algorithm in the learning procedure of the ANFIS approach. The performance of the forecasting methods for the Queensland power market in the year 2018, which is well-known as the most competitive market in the world, is investigated and compared to show the superiority of the proposed methods over other selected methods.

This paper presents a study on the N-Queens Problem. Different approaches to its solution discussed in the scientific literature are analyzed. The implementation of an algorithm based on the backtracking method is also presented. The algorithm is optimized to find solutions in a specific subset of configurations among all possible ones. With this approach, the computational complexity of the algorithm is reduced from exponential to quadratic. In this way, the algorithm finds all possible solutions in a shorter time: fundamental and their symmetrical equivalents. The methodology for conducting the experiments is presented. The purpose of the study, the tasks to be performed, and the conditions for conducting the experiments are presented as well. In connection with the research, an application that implements the presented algorithm has been developed. This application generated all the results obtained in this study. The experimental results show that with a linear increase in the number of queens (equivalent to a quadratic increase in the number of fields on the board, the number of recursive calls made by the algorithm increases exponentially. Similarly, the number of possible solutions, as well as the execution time of the algorithm (in the different modes of the application -internal, interactive, and combined), also increases exponentially. However, the algorithm's execution time in the internal mode is significantly shorter than in the other two modes -interactive and combined. The future guidelines for the study are presented.

This paper introduces a technique for controlling a class of uncertain chaotic systems using an adaptive fuzzy Proportional-Integrator-Derivative (PID) controller with H∞ tracking performance. The purpose of this work is to achieve optimal tracking performance of the controller using Backtracking Search Algorithm (BSA). BSA, which is a novel heuristic algorithm, has an easy structure with single control parameter. In BSA, three basic genetic operators (selection, mutation and crossover) are utilized to generate trial individuals. To this reason, the control problem in hand is considered as an optimization problem by defining an appropriate objective function. Stability analysis of the control scheme is provided based on Lyapunov theory and modified Riccati-like equation, where the robustness of the closed-loop system is guaranteed by H∞ tracking performance for any predefined level. To evaluate the performance of the proposed control method, it is employed for tracking control of Duffing uncertain chaotic system. Simulation results show the capability of the proposed controller.

In this paper, a new method has been presented for the extraction of edge information by using Differential Search Optimization Algorithm. The proposed method is based on using a new heuristic image thresholding method for edge detection. The success of the proposed method has been examined on fusion of two remote sensed images. The applicability of the proposed method on edge detection and image fusion problems have been analysed in detail and the empirical results exposed that the proposed method is useful for solving the mentioned problems.

Change detection is one of the most important subjects of remote sensing discipline. In this paper, a new unsupervised change detection approach is proposed for multi-temporal remotely sensed optic imagery. This approach does not require any prior information about changed and unchanged pixels. The approach is based on Discrete Wavelet Transform (DWT) based image fusion and Backtracking Search Optimization Algorithm (BSA). In the first step of the approach, absolute-valued difference image and absolute-valued log-ratio image is calculated from co-registered and radiometrically corrected multi-temporal images. Then, these difference images are fused using DWT. The fused image is filtered by median filter for edge information preservation and by wiener filter for image smoothing. Then, a min-max normalization is applied to the filtered data. The normalized data is clustered into two groups with BSA as changed and unchanged pixels by minimizing an objective function, unlike classical methods using CVA, PCA, FCM or K-means techniques. To show effectiveness of proposed approach, two remote sensing data sets, Sardinia and Mexico, are used. False Alarm, Missed Alarm, Total Alarm and Total Error Rate are selected as performance criteria to evaluate the effectiveness of new approach using ground truth images. Experimental results show that proposed approach is effective for unsupervised change detection of optical remote sensing data.

In this study, a new artificial intelligence optimization algorithm, Differential Search (DS), was proposed for Principal Component Analysis (PCA) based unsupervised change detection method for optic and SAR image data. The model firstly computes an eigenvector space using previously created k × k blocks. The change detection map is generated by clustering the feature vector as two clusters which are changed and unchanged using Differential Search Algorithm. For clustering, a cost function is used based on minimization of Euclidean distance between cluster centers and pixels. Experimental results of optic and SAR images proved that proposed approach is effective for unsupervised change detection of remote sensing image data.

In this study, a new artificial intelligence optimization algorithm, Differential Search (DS), was proposed for Principal Component Analysis (PCA) based unsupervised change detection method for optic and SAR image data. The model firstly computes an eigenvector space using previously created k × k blocks. The change detection map is generated by clustering the feature vector as two clusters which are changed and unchanged using Differential Search Algorithm. For clustering, a cost function is used based on minimization of Euclidean distance between cluster centers and pixels. Experimental results of optic and SAR images proved that proposed approach is effective for unsupervised change detection of remote sensing image data.

Change detection is one of the most important subjects of remote sensing discipline. In this paper, a new unsupervised change detection approach is proposed for multi-temporal remotely sensed optic imagery. This approach does not require any prior information about changed and unchanged pixels. The approach is based on Discrete Wavelet Transform (DWT) based image fusion and Backtracking Search Optimization Algorithm (BSA). In the first step of the approach, absolute-valued difference image and absolute-valued log-ratio image is calculated from co-registered and radiometrically corrected multi-temporal images. Then, these difference images are fused using DWT. The fused image is filtered by median filter for edge information preservation and by wiener filter for image smoothing. Then, a min-max normalization is applied to the filtered data. The normalized data is clustered into two groups with BSA as changed and unchanged pixels by minimizing an objective function, unlike classical methods using CVA, PCA, FCM or K-means techniques. To show effectiveness of proposed approach, two remote sensing data sets, Sardinia and Mexico, are used. False Alarm, Missed Alarm, Total Alarm and Total Error Rate are selected as performance criteria to evaluate the effectiveness of new approach using ground truth images. Experimental results show that proposed approach is effective for unsupervised change detection of optical remote sensing data.

Change detection is one of the most important subjects of remote sensing discipline. In this paper, a new unsupervised change detection approach is proposed for multi-temporal remotely sensed optic imagery. This approach does not require any prior information about changed and unchanged pixels. The approach is based on Discrete Wavelet Transform (DWT) based image fusion and Backtracking Search Optimization Algorithm (BSA). In the first step of the approach, absolute-valued difference image and absolute-valued log-ratio image is calculated from co-registered and radiometrically corrected multi-temporal images. Then, these difference images are fused using DWT. The fused image is filtered by median filter for edge information preservation and by wiener filter for image smoothing. Then, a min-max normalization is applied to the filtered data. The normalized data is clustered into two groups with BSA as changed and unchanged pixels by minimizing an objective function, unlike classical methods using CVA, PCA, FCM or K-means techniques. To show effectiveness of proposed approach, two remote sensing data sets, Sardinia and Mexico, are used. False Alarm, Missed Alarm, Total Alarm and Total Error Rate are selected as performance criteria to evaluate the effectiveness of new approach using ground truth images. Experimental results show that proposed approach is effective for unsupervised change detection of optical remote sensing data.

This paper presents a comparative analysis of two algorithms i.e: backtracking and genetic algorithm for the solution of N queen‟s problem. In this paper the N queens problem is solved using both the algorithms . Both the algorithms have their own advantages and drawbacks. Bothatheamethodsaofasolvinga N Queen problem area entirely different. The first one is general method and takes time in days, months and years as a Na increases. Ina this paper the time taken by the two methods for as given value of Na area compared.

In this paper, we introduced a novel image clustering method based on combination of the classical Fuzzy C-Means (FCM) algorithm and Backtracking Search optimization Algorithm (BSA). The image clustering was achieved by minimizing the objective function of FCM with BSA. In order to improve the local search ability of the new algorithm, an inertia weight parameter (w) was proposed for BSA. The improvement was accomplished by using w in the steps of the determination of the search-direction matrix of BSA and the new algorithm was named as w-BSAFCM. In order to show the effectiveness of the new algorithm, FCM was also combined with the general forms of BSA in the same manner and three benchmark images were clustered by utilizing these algorithms. The obtained results were analyzed according to the objective function and Davies-Bouldin index values to compare the performances of the algorithms. According to the results, it was shown that w-BSAFCM can be effectively be used for solving image clustering problem.

Impervious surface areas are artificial structures covered by materials such as asphalt, stone, brick, rooftops and concrete. Buildings, parking lots, roads, driveways and sidewalks are shown as impervious surfaces. They increase depending on the population growth. The spatial development of impervious surface expansion is necessary for better understanding of the urbanization status and its effect on environment. There are different impervious surface determining approaches met in literature. In this paper, it is aimed to extract the impervious surface areas of Kayseri city, Turkey by using remote sensing techniques. It is possible to group these techniques under a few main topics as V-IS (vegetation-impervious surface-soil) model, based on spectral mixture analysis or decision tree algorithms or impervious surface indices. According to these techniques, we proposed a new technique by using RUSBoost algorithm based on decision tree in this study. In this scope, Landsat 8 LDCM image belonging to July, 2013 was used. Determining of impervious surface areas accurately depends on accuracy of image classification methods. Therefore, satellite image was classified separately by using Classification Tree and RUSBoost boosting method which increases accuracy of the classification method based on decision tree. Classification accuracies of these supervised classification methods were compared and it was observed that the best overall accuracy was obtained with RUSBoost method. For this reason, RUSBoost method was preferred to determine impervious surface areas. The overall accuracies were obtained 95% with Classification Tree and 97% with RUSBoost boosting method.

In this paper, a new method has been presented for the extraction of edge information by using Differential Search Optimization Algorithm. The proposed method is based on using a new heuristic image thresholding method for edge detection. The success of the proposed method has been examined on fusion of two remote sensed images. The applicability of the proposed method on edge detection and image fusion problems have been analysed in detail and the empirical results exposed that the proposed method is useful for solving the mentioned problems.

In this paper, the performance of four optimization techniques i.e. Grey Wolf Optimizer (GWO), Backtracking Search Algorithm (BSA), Differential Evolution (DE), and Bat Algorithm (BA) have been investigated for optimizing the scaling factors of fuzzy proportional-integral controller (FPIC). Jacketed continuous stirred tank reactor (CSTR) has been considered for step set-point and trajectory tracking of reactor temperature. The present work has been simulated in LabVIEW ™. The performance of aforementioned algorithms has been evaluated by comparing the cost function Integral of Absolute Error for step set-point and trajectory tracking. On the basis of simulation results, it can be inferred that, GWO outperformed other optimization algorithms for all considered cases.

In this study, a new artificial intelligence optimization algorithm, Differential Search (DS), was proposed for Principal Component Analysis (PCA) based unsupervised change detection method for optic and SAR image data. The model firstly computes an eigenvector space using previously created k × k blocks. The change detection map is generated by clustering the feature vector as two clusters which are changed and unchanged using Differential Search Algorithm. For clustering, a cost function is used based on minimization of Euclidean distance between cluster centers and pixels. Experimental results of optic and SAR images proved that proposed approach is effective for unsupervised change detection of remote sensing image data.

Heart is the vital organ of a Human Body, because of its involvement in various works and processes in the entire body such as blood pumping etc., so recording a heart function is also a great thing, it is done through ECG signals. ECG signal records the electrical signals and activity of a Human Heart based on the electrical signals released by the Heart. ECG signal consists of PQRST waves, which are the reference points on an ECG signal. But, recording them is much easy than extracting and analyzing them, so, as to extract them, we are applying an advanced adaptive multi-level thresholding (AAMT) along with a selective statistical false peak elimination for the detection of QRS peaks of an ECG signal. Initially, median and moving average filters are applied for removing noise as well as terms. After AAMT is implemented on the complete dataset of ECG signals. Then selective statistical false peak elimination (SSFPE) is implemented for removing noise terms that might be missed out during filtering. At last, a search back stage will be implemented to search for low amplitude useful peaks. We used MIT-BIH arrhythmia and fantasia databases and got a higher accuracy in detecting and sensitivity is increased to 99.3 for MIT-BIH arrhythmia and 99.7 for fantasia database compared to existing previous methods.

Arazi örtüsü/kullanımı değişiminin belirlenmesi gerek doğal çevrenin gerekse de insan yapısı alanların değişimin izlenmesi ve nedenlerinin gözlemlenerek gelecekteki değişimin yönetilmesi için oldukça önemlidir. Sayısal görüntü verilerinden arazi kullanımı/örtüsü bilgilerinin çıkarımı için sayısal hesaplamalara dayanan kantitatif analiz ve insana dayanan değerlendirmeyi içeren görsel yorumlama teknikleri kullanılmaktadır. Görsel yorumlamanın kalitesinin yüksekliği analistin değerlendirmesi kadar, görüntü zenginleştirme ile görüntüdeki yeryüzü özelliklerinin arasındaki farkın artırılmasına bağlıdır. Mekansal filtreleme, uydu görüntülerinden bilgi çıkarmak amacıyla kullanılanılan mekansal özellik manipülasyonlarından biridir ve görüntü karakteristiklerinin bazılarının bastırılması ya da öne çıkarılıp vurgulanmasını sağlar. Bu çalışmada Tekirdağ ili, Bıyıkali köyü ve civarında 2500 hektar alana sahip ve arazi örtüsü/arazi kullanım çeşitliliğinin fazla olduğu bir çalışma alanı belirlenmiş ve mekansal filtreleme yöntemleri kullanarak bilgi çıkarımı yapılmıştır. Çalışma iki aşamalı olarak gerçekleştirilmiştir. İlk aşamada, orta mekansal çözünürlüğe sahip Landsat-5 TM görüntüsü üzerinden, en iyi ayırtedilebilirliği sağlayan mekansal filtreleme yöntemini belirlemek, diğer filtreleme yöntemleriyle karşılaştırmak ve hedeflenen arazi kullanım sınıflarının tesbiti ve ayırtedilebilirliğini belirlemek amacıyla çeşitli mekansal filtreler kullanılmıştır. Çalışmada kullanılan filtreler; 3x3 boyutundaki yüksek geçirgenli filtre, kenar zenginleştirme filtresi, Laplacian kenar zenginleştirme filtresi ve yüksek frekanslı bileşenleri güçlendiren filtredir. Çalışmanın ikinci aşamasında ise yüksek mekansal çözünürlüklü Worldview-2 görüntüsü referans kabul edilerek, ilk aşamada zenginleştirilmesi yapılan Landsat-5 görüntüleri kullanılarak, arazi kullanım/örtülerini temsil eden belirli objeler ekran üzerinden alansal sayıllaştırma yapılmış ve bu alanlar referans görüntüyle karşılaştırılmıştır. Son olarak referans görüntü ve zenginleştirilmiş görüntüden elde edilen alanlar arasındaki farklar için bağıl karesel ortalama hatalar (k.o.h) hesaplanarak doğruluk değerlendirmesi gerçekleştirilmiş ve en iyi sonuç veren filtreleme yöntemi/yöntemleri belirlenmiştir.

Power system oscillation is a serious threat to the stability of multimachine power systems. The coordinated control of power system stabilizers (PSS) and thyristor-controlled series compensation (TCSC) damping controllers is a commonly used technique to provide the required damping over different modes of growing oscillations. However, their coordinated design is a complex multimodal optimization problem that is very hard to solve using traditional tuning techniques. In addition, several limitations of traditionally used techniques prevent the optimum design of coordinated controllers. In this paper, an alternate technique for robust damping over oscillation is presented using backtracking search algorithm (BSA). A 5-area 16-machine benchmark power system is considered to evaluate the design efficiency. The complete design process is conducted in a linear time-invariant (LTI) model of a power system. It includes the design formulation into a multi-objective function from the system eigenvalues. Later on, nonlinear time-domain simulations are used to compare the damping performances for different local and inter-area modes of power system oscillations. The performance of the BSA technique is compared against that of the popular particle swarm optimization (PSO) for coordinated design efficiency. Damping performances using different design techniques are compared in term of settling time and overshoot of oscillations. The results obtained verify that the BSA-based design improves the system stability significantly. The stability of the multimachine power system is improved by up to 74.47% and 79.93% for an inter-area mode and a local mode of oscillation, respectively. Thus, the proposed technique for coordinated design has great potential to improve power system stability and to maintain its secure operation.

This paper presents a study on the N-Queens Problem. Different approaches to its solution discussed in the scientific literature are analyzed. The implementation of an algorithm based on the backtracking method is also presented. The algorithm is optimized to find solutions in a specific subset of configurations among all possible ones. With this approach, the computational complexity of the algorithm is reduced from exponential to quadratic. In this way, the algorithm finds all possible solutions in a shorter time: fundamental and their symmetrical equivalents. The methodology for conducting the experiments is presented. The purpose of the study, the tasks to be performed, and the conditions for conducting the experiments are presented as well. In connection with the research, an application that implements the presented algorithm has been developed. This application generated all the results obtained in this study. The experimental results show that with a linear increase in the number of queens (equivalent to a quadratic increase in the number of fields on the board, the number of recursive calls made by the algorithm increases exponentially. Similarly, the number of possible solutions, as well as the execution time of the algorithm (in the different modes of the application-internal, interactive, and combined), also increases exponentially. However, the algorithm's execution time in the internal mode is significantly shorter than in the other two modes-interactive and combined. The future guidelines for the study are presented.

The use of graphs is widely applied in modeling and solving problems in the field of computer science and bioinformatics.Therefore, it is essential to develop and improve algorithms reducing their computational complexity and  increasing the precision of the solutions generated by them as well as the size of the input data.In this study two well-known algorithms for solving the problem for finding a minimum Hamiltonian cycle in weighted, undirected and complete graph (also known as Travelling Salesman Problem –- TSP) are analyzed.The first algorithm is based on the backtracking method and it always finds the optimal solution, while with the second one, the genetic algorithm (GA), finding the optimal solution is not always guaranteed.The aims of the study are to determine: (1)which of the algorithms can be used so that the resulting solution is optimal or near-optimal and the execution time be reasonable depending on the size of the input data; (2)the influence of GA parameter valu...

In this paper, a new method has been presented for the extraction of edge information by using Differential Search Optimization Algorithm. The proposed method is based on using a new heuristic image thresholding method for edge detection. The success of the proposed method has been examined on fusion of two remote sensed images. The applicability of the proposed method on edge detection and image fusion problems have been analysed in detail and the empirical results exposed that the proposed method is useful for solving the mentioned problems.

Bu çalışmada amaç, aynı alana ait ve iki farklı zamanda elde edilmiş uydu görüntüleri, ortofoto, tematik haritalar ve/veya dijital görüntüler için geliştirilen bir Matlab ara yüzü ile değişim haritalarının belirlenmesi, her bir sınıf için değişim haritalarının oluşturulması ve geliştirilen ara yüzün doğruluğunun uzaktan algılama alanında sıklıkla kullanılan ticari bir yazılım ile karşılaştırılmasıdır. Kullanılan uydu görüntüleri ile geliştirilen ara yüzün sınıf sayısından ve mekânsal çözünürlükten bağımsız olduğunu doğrulamak için üç farklı mekânsal çözünürlüğe ve spektral yansıma kümesine sahip uydu görüntüleri kullanılmıştır.

Impervious surface areas are artificial structures covered by materials such as asphalt, stone, brick, rooftops and concrete. Buildings, parking lots, roads, driveways and sidewalks are shown as impervious surfaces. They increase depending on the population growth. The spatial development of impervious surface expansion is necessary for better understanding of the urbanization status and its effect on environment. There are different impervious surface determining approaches met in literature. In this paper, it is aimed to extract the impervious surface areas of Kayseri city, Turkey by using remote sensing techniques. It is possible to group these techniques under a few main topics as V-I-S (vegetation-impervious surface-soil) model, based on spectral mixture analysis or decision tree algorithms or impervious surface indices. According to these techniques, we proposed a new technique by using RUSBoost algorithm based on decision tree in this study. In this scope, Landsat 8 LDCM imag...

This paper introduces a technique for controlling a class of uncertain chaotic systems using an adaptive fuzzy Proportional-Integrator-Derivative (PID) controller with H∞ tracking performance. The purpose of this work is to achieve optimal tracking performance of the controller using Backtracking Search Algorithm (BSA). BSA, which is a novel heuristic algorithm, has an easy structure with single control parameter. In BSA, three basic genetic operators (selection, mutation and crossover) are utilized to generate trial individuals. To this reason, the control problem in hand is considered as an optimization problem by defining an appropriate objective function. Stability analysis of the control scheme is provided based on Lyapunov theory and modified Riccati-like equation, where the robustness of the closed-loop system is guaranteed by H∞ tracking performance for any predefined level. To evaluate the performance of the proposed control method, it is employed for tracking control of Du...

Change detection is one of the most important subjects of remote sensing discipline. In this paper, a new unsupervised change detection approach is proposed for multi-temporal remotely sensed optic imagery. This approach does not require any prior information about changed and unchanged pixels. The approach is based on Discrete Wavelet Transform (DWT) based image fusion and Backtracking Search Optimization Algorithm (BSA). In the first step of the approach, absolute-valued difference image and absolute-valued log-ratio image is calculated from co-registered and radiometrically corrected multi-temporal images. Then, these difference images are fused using DWT. The fused image is filtered by median filter for edge information preservation and by wiener filter for image smoothing. Then, a min-max normalization is applied to the filtered data. The normalized data is clustered into two groups with BSA as changed and unchanged pixels by minimizing an objective function, unlike classical methods using CVA, PCA, FCM or K-means techniques. To show effectiveness of proposed approach, two remote sensing data sets, Sardinia and Mexico, are used. False Alarm, Missed Alarm, Total Alarm and Total Error Rate are selected as performance criteria to evaluate the effectiveness of new approach using ground truth images. Experimental results show that proposed approach is effective for unsupervised change detection of optical remote sensing data.

This paper presents a study on the N-Queens Problem. Different approaches to its solution discussed in the scientific literature are analyzed. The implementation of an algorithm based on the backtracking method is also presented. The algorithm is optimized to find solutions in a specific subset of configurations among all possible ones. With this approach, the computational complexity of the algorithm is reduced from exponential to quadratic. In this way, the algorithm finds all possible solutions in a shorter time: fundamental and their symmetrical equivalents. The methodology for conducting the experiments is presented. The purpose of the study, the tasks to be performed, and the conditions for conducting the experiments are presented as well. In connection with the research, an application that implements the presented algorithm has been developed. This application generated all the results obtained in this study. The experimental results show that with a linear increase in the number of queens (equivalent to a quadratic increase in the number of fields on the board, the number of recursive calls made by the algorithm increases exponentially. Similarly, the number of possible solutions, as well as the execution time of the algorithm (in the different modes of the application - internal, interactive, and combined), also increases exponentially. However, the algorithm's execution time in the internal mode is significantly shorter than in the other two modes - interactive and combined. The future guidelines for the study are presented.

In this paper, a new method has been presented for the extraction of edge information by using Differential Search Optimization Algorithm. The proposed method is based on using a new heuristic image thresholding method for edge detection. The success of the proposed method has been examined on fusion of two remote sensed images. The applicability of the proposed method on edge detection and image fusion problems have been analysed in detail and the empirical results exposed that the proposed method is useful for solving the mentioned problems.

Çelik kemerli tonoz sistemler, geniş açıklı alanların çok az kolon ile kaplanmasında kullanılan en popüler yapı sistemlerinden birisidir. Kemerli tonoz sistemler bir yönde eğriliği olan boyuna, enine ve çapraz elemanlardan oluşan basit bir yapıya sahiptirler. Tonozun konfigürasyonu, diğer bir deyişle, yapı elemanlarının boyutları tonozun yapısal performansı, estetiği ve maliyeti üzerinde büyük bir etkiye sahiptir. Bu makalede, dayanıklı, uzun ömürlü, güvenli ve estetik olmalarının yanında neredeyse tamamen geri dönüştürülebilmeleri sebebiyle sürdürülebilir çevre dostu olan yeni nesil yapı elemanları grubunda yer alan soğukta şekillendirilmiş çelik profiller kullanılarak yapılan tonoz sistemlerin optimal tasarımını yapmak için geliştirilmiş suni arı kolonisi algoritması ve uygulama programlama arayüzü (UPA) sunulmaktadır. Uygulama programlama arayüzü, yapısal analiz süreci için, analiz yazılımını suni arı kolonisi algoritması ile programlama dili aracılığıyla bağlamak için kullanılır. Sonuçlar, çelik kemerli tonoz sistemler gibi büyük ölçekli yapıların analizi için güçlü bir arayüz aracı olarak uygulama programlama arayüzünün etkinliğini ve aynı zamanda suni arı kolonisi algoritmasının hızlı yakınsama performansı ile optimum sonuçları elde etmedeki kararlılığını göstermektedir.

Bu çalışmada, optik görüntüler için oldukça basit ve etkin bir kontrolsüz değişim saptama yaklaşımı sunulmuştur. Yaklaşımın
temelinde fark görüntülerinin kombinasyonu ve Geri-İzleme Arama Algoritması (BSA)ile değişim haritasının hesaplanması
bulunmaktadır. İlk olarak standart fark alma ve logaritmik oran operatörleri kullanılarak fark görüntüleri elde edilir. Ardından
bir kombinasyon fonksiyonu kullanılarak fark görüntülerinden tek boyutlu özellik uzayı hesaplanır. Üçüncü adım olarak özellik
uzayına sırasıyla görüntünün yumuşatılması için wiener filtre ve kenar bilgilerinin muhafaza edilmesi için medyan filtre
uygulanır. Filtreleme ile yerel tutarlılık ve kenar bilgisi muhafaza edilmiş olur. Daha sonra filtrelenmiş veriye min-maks
normalizasyonu uygulanır. Son olarak normalize edilmiş veri, BSA kullanılarak değişim olan ve değişim olmayan pikseller
olarak iki gruba ayrılır. Sunulan yaklaşımın etkinliği göstermek için, değişim saptama tekniklerinin başarısını belirlemek
amacıyla sıkça tercih edilen Meksika ve Sardinia veri setleri kullanılmıştır. Deneysel sonuçlar ile yaklaşımın optik görüntülerden kontrolsüz değişim belirleme için etkin bir metot olduğu ispatlanmıştır.

Change detection is one of the most important subjects of remote sensing discipline. In this paper, a new unsupervised change
detection approach is proposed for multi-temporal remotely sensed optic imagery. This approach does not require any prior
information about changed and unchanged pixels. The approach is based on Discrete Wavelet Transform (DWT) based image fusion
and Backtracking Search Optimization Algorithm (BSA). In the first step of the approach, absolute-valued difference image and
absolute-valued log-ratio image is calculated from co-registered and radiometrically corrected multi-temporal images. Then, these
difference images are fused using DWT. The fused image is filtered by median filter for edge information preservation and by wiener
filter for image smoothing. Then, a min-max normalization is applied to the filtered data. The normalized data is clustered into two
groups with BSA as changed and unchanged pixels by minimizing an objective function, unlike classical methods using CVA, PCA,
FCM or K-means techniques. To show effectiveness of proposed approach, two remote sensing data sets, Sardinia and Mexico, are
used. False Alarm, Missed Alarm, Total Alarm and Total Error Rate are selected as performance criteria to evaluate the effectiveness
of new approach using ground truth images. Experimental results show that proposed approach is effective for unsupervised change
detection of optical remote sensing data.

Dünyada birçok uygulamada, yeryüzüne ait yüksek doğruluklu, hassas veri ve bilgilere ihtiyaç duyulmaktadır. Bu bilgiler
çevresel değişimlerin izlenmesi, arazi kullanımının belirlenmesi ve farklı tematik haritalama amaçları için kullanılmaktadır.
Uzaktan algılama sistemleri sinoptik görüş kabiliyeti, farklı konumsal, zamansal ve spektral çözünürlüğe sahip olmaları
nedeniyle tematik bilgi çıkartımı için en önemli araçlardan biri olmuştur. Uydu görüntülerinden tematik bilgi çıkarımındaki en
önemli aşama şüphesiz sınıflandırma işlemidir. Sınıflandırma işleminin doğruluğu, kullanılan yöntem ve yönteme ait
parametreler ile doğrudan ilişkilidir. Bu sebepten ötürü problemin ve kullanılan görüntünün niteliğine göre uygun sınıflandırma
yönteminin seçilmesi büyük önem arz etmektedir. Dünyada yapılan birçok çalışmada parametrik bir yöntem olan En Çok
Olabilirlik ve herhangi bir istatistiksel bilgiye ihtiyaç duymayan Yapay Sinir Ağları kullanılmıştır. Bu çalışmada bu yöntemlere
ek olarak çok hızlı bir sınıflandırma yöntemi olan Karar Ağaçları ve sınıflandırma yöntemlerinin doğruluğunu arttırmakta
kullanılan torbalama (Bagging) metodu kullanılarak çok kanallı Landsat verisinin sınıflandırılmasındaki başarısı araştırılmış ve
temel sınıflandırma yöntemleri ile başarıları kıyaslanmıştır.

Fen bilimlerinde karşılaşılan birçok problem doğrusal veya doğrusal olmayan bir optimizasyon problemi ile temsil edilir.
Doğrusal olan optimizasyon problemlerinin çözümünde klasik deterministik yöntemler kullanılmasına rağmen, doğrusal
olmayan problemlerin çözümünde artan değişken sayısı, kullanılan veri tipi gibi birtakım zorluklarla karşılaşılmaktadır. Bu
bağlamda, doğrusal olmayan optimizasyon problemlerinin çözümü için günümüzde Diferansiyel Gelişim Algoritması,
Genetik Algoritma, Yapay Arı Kolonisi gibi birçok sezgisel algoritma geliştirilmiştir.
Bu çalışmada Aster, Landsat ve Ikonos verileri, kullanımı son yıllarda giderek artan yapay zeka optimizasyon
algoritmalarından popülasyon tabanlı sezgisel bir algoritma olan Diferansiyel Gelişim Algoritması(DEA) ile
sınıflandırılmıştır. Yöntemin uydu görüntü verilerinin sınıflandırılmasındaki etkinliğinin değerlendirimi için klasik kontrolsüz sınıflandırma yöntemlerinden K-means ve Fuzzy C-means yöntemleriyle karşılaştırma yapılmıştır.

In this paper, we propose a context-sensitive technique for unsupervised change detection in multitemporal remote sensing images. The technique is based on fuzzy clustering approach and takes care of spatial correlation between neighboring pixels of the difference image produced by comparing two images acquired on the same geographical area at different times. Since the ranges of pixel values of the difference image belonging to the two clusters (changed and unchanged) generally have overlap, fuzzy clustering techniques seem to be an appropriate and realistic choice to identify them (as we already know from pattern recognition literatures that fuzzy set can handle this type of situation very well). Two fuzzy clustering algorithms, namely fuzzy c-means (FCM) and Gustafson-Kessel clustering (GKC) algorithms have been used for this task in the proposed work. For clustering purpose various image features are extracted using the neighborhood information of pixels. Hybridization of FCM and GKC with two other optimization techniques, genetic algorithm (GA) and simulated annealing (SA), is made to further enhance the performance. To show the effectiveness of the proposed technique, experiments are conducted on two multispectral and multitemporal remote sensing images. A fuzzy cluster validity index (Xie-Beni) is used to quantitatively evaluate the performance. Results are compared with those of existing Markov random field (MRF) and neural network based algorithms and found to be superior. The proposed technique is less time consuming and unlike MRF does not require any a priori knowledge of distributions of changed and unchanged pixels.