Master Degree / Yüksek Lisans Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/11147/3008

Browse

Filters

2010 - 20112

Settings

Department: search.filters.department.Thesis (Master)--İzmir Institute of Technology, Electrical and Electronics EngineeringSubject: search.filters.subject.Supervised learning (Machine learning)

Search Results

Now showing 1 - 2 of 2
  • Master Thesis
    Separation of Stimulus-Specific Patterns in Electroencephalography Data Using Quasi-Supervised Learning
    (Izmir Institute of Technology, 2011) Köktürk, Başak Esin; Karaçalı, Bilge; Karaçalı, Bilge; 03.05. Department of Electrical and Electronics Engineering; 03. Faculty of Engineering; 01. Izmir Institute of Technology
    In this study separation of the electroencephalography data recorded under different visual stimuli is investigated using the quasi-supervised learning algorithm. The quasi-supervised learning algorithm estimates the posterior probabilities associated with the different stimuli, thus identifying the EEG data samples that are exclusively specific to their respective stimuli directly and automatically from the data. The data used in this study contains 32 channels EEG recording under six different visual stimuli in random successive order. In our study, we have first constructed EEG profiles to represent instantaneous brain activity from the EEG data by various combinations of independent component analysis and the wavelet transform following data preprocessing. Then, we have applied the binary and M-ary quasi-supervised learning to identify condition-specific EEG profiles in different comparison scenarios. The results reveal that the quasi-supervised learning algorithm is successful in capturing the distinction between the samples. In addition, feature extraction using independent component analysis increased the performance of the quasi-supervised learning and the wavelet decomposition revealed the different frequency bands of the features, making more explicit the separation of the samples. The best results we obtained by combining the wavelet decomposition and the independent component analysis before the quasisupervised learning algorithm.
  • Master Thesis
    Detection of Man-Made Structures in Aerial Imagery Using Quasi-Supervised Learning and Texture Features
    (Izmir Institute of Technology, 2010) Güven, Mesut; Karaçalı, Bilge; Karaçali, Bilge; 03.05. Department of Electrical and Electronics Engineering; 03. Faculty of Engineering; 01. Izmir Institute of Technology
    In this thesis, the quasi-supervised statistical learning algorithm has been applied for texture recognitioning analysis. The main objective of the proposed method is to detect man-made objects or differences on the terrain as a result of habitating. From this point of view, gaining information about human presence in a region of interest using aerial imagery is of vital importance. This task is adressed using a machine learning paradigm in a quasi-supervised learning. Eigthteen different sized aerial images were used in all computations and analysis. The available data was divided into a reference control set which consist of normalcy condition samples with no human presence, and a mixed testing data set which consisting images of habitate and cultivated terrain. Grey level co-occurrence matrices were then computed for each block and .Haralick Features. were extracted and organized into a texture vector. The quasi-supervised learning was then applied to the collection of texture vectors to identify those image blocks which show human presence in the test data set. In the performance evaluatian part, detected abnormal areas were compared with manually labeled data to determine the corresponding reciever operating characteristic curve. The results showed that the quasi-supervised learning algorithm is able to identify the indicators of human presence in a region such as houses, roads and objects that are not likely to be observed in areas free from human habitation.