In recent decades, reinforcement learning (RL) has been widely used in different research fields ranging from psychology to computer science. The unfeasibility of sampling all possibilities for continuous-state problems and the absence of an explicit teacher make RL algorithms preferable for supervised learning in the machine learning area, as the optimal control problem has become a popular subject of research. In this study, a system is proposed to solve mobile robot navigation by opting for the most popular two RL algorithms, Sarsa(λ) and Q(λ). The proposed system, developed in MATLAB, uses state and action sets, defined in a novel way, to increase performance. The system can guide the mobile robot to a desired goal by avoiding obstacles with a high success rate in both simulated and real environments. Additionally, it is possible to observe the effects of the initial parameters used by the RL methods, e.g., λ , on learning, and also to make comparisons between the performances of Sarsa(λ) and Q(λ) algorithms.

No abstract

Özetçe -Bu çalışmada çogunlukla iki boyutlu (2-B) görüntüler üzerinde kullanılan Marr-Hildreth yöntemi, üç boyutlu (3-B) görüntülerde çalışmak üzere genişletilmiştir. Aynı yöntemin 3-B, kesit bazında çalışan 2-B, ve hesaba ait karmaşıklıgı azaltan hızlandırılmış 3-B uyarlamalarının Osteoartrit Girişimi veri tabanından alınan diz MR görüntülerine uygulanmasıyla elde edilen sonuçlar karşılaştırılmış, 3-B Marr-Hildreth yöntemlerinin kesit bazında çalışan 2-B Marr-Hildreth yönteminin buldugu kenarları da tespit etme başarısı degerlendirilmiştir.Anahtar Kelimeler-3-B kenar tespiti, Marr-Hildreth yöntemi, LoG filtreleme, sıfır geçişleri, MR görüntüsü işleme.Abstract-In this study, Marr-Hildreth method applied on mostly two dimensional (2-D) images was extended in order to run on three dimensional (3-D) images. After the same method's 3-D version, the slicewise 2-D version, and the accelerated 3-D version reducing computational complexity were applied on knee MR images which were acquired from the Osteoarthritis Initiative database, the results obtained were compared, and the success of the 3-D Marr-Hildreth methods in detecting also the edges found by the slicewice 2-D Marr-Hildredth method was evaluated.

More effective detection of corner points in three dimensional (3-D) volumetric images can be possible through expansion of Harris corner detection algorithm, which run in two dimensional (2-D) images, into third dimension. In this study, the standard algorithm of Harris that detected corner points in 2-D slices and its 3-D version were implemented in the scale-space to determine the corner points of volumetric object images. The results obtained in sample object images with 2-D and 3-D methods that used different approaches for scale-space construction were qualitatively assessed.

This paper focuses on the land cover classification problem by employing a number of manifold learning algorithms in the feature extraction phase, then by running single and ensemble of classifiers in the modeling phase. Manifolds are learned on training samples selected randomly within available data, while the transformation of the remaining test samples is realized for linear and nonlinear methods via the learnt mappings and a radial-basis function neural network based interpolation method, respectively. The classification accuracies of the original data and the embedded manifolds are investigated with several classifiers. Experimental results on a 200-band hyperspectral image indicated that support vector machine was the best classifier for most of the methods, being nearly as accurate as the best classification rate of the original data. Furthermore, our modified version of random subspace classifier could even outperform the classification accuracy of the original data for local Fisher's discriminant analysis method despite of a considerable decrease in the extrinsic dimension.