Search

Deep subspace clustering methods are now prominent in clustering, typically using fully connected networks and a self-representation loss function. However, these methods often struggle with overfitting and lack interpretability. In this paper, we explore an alternative clustering approach based on deep unfolding. By unfolding iterative optimization methods into neural networks, this approach offers enhanced interpretability and reliability compared to data-driven deep learning methods, and greater adaptability and generalization than model-based approaches. Hence, unfolding has become widely used in inverse imaging problems, such as image restoration, reconstruction, and super-resolution, but has not been sufficiently explored yet in the context of clustering. In this work, we introduce an innovative clustering architecture for hyperspectral images (HSI) by unfolding an iterative solver based on the Alternating Direction Method of Multipliers (ADMM) for sparse subspace clustering. To our knowledge, this is the first attempt to apply unfolding ADMM for computing the self-representation matrix in subspace clustering. Moreover, our approach captures well the structural characteristics of HSI data by employing the K nearest neighbors algorithm as part of a structure preservation module. Experimental evaluation of three established HSI datasets shows clearly the potential of the unfolding approach in HSI clustering and even demonstrates superior performance compared to state-of-the-art techniques.

In dissertation a problem of reconstruction of images from undersampled measurements is considered which has direct application in creation of magnetic resonance images. The topic of the research is proposition of new regularization based methods for image reconstruction which are based on statistical Markov random field models and theory of compressive sensing. With the proposed signal model which follows the statistics of images, a new regularization functions are defined and four methods for reconstruction of magnetic resonance images are derived., U doktorskoj disertaciji razmatran je problem rekonstrukcije signala slike iz nepotpunih merenja koji ima direktnu primenu u kreiranju slika magnetne reznonace. Predmet istraživanja je vezan za predlog novih regularizacionih metoda rekonstrukcije korišćenjem statističkih modela Markovljevog slučajnog polja i teorije retke reprezentacije signala. Na osnovu predloženog modela koji na verodostojan način reprezentuje statistiku signala slike predložene su regularizacione funkcije i kreirana četiri algoritma za rekonstrukciju slike magnetne rezonance.

Prečišćavanje gradskih otpadnih voda u Subotici vrši se više od četiri decenije. Od 2010. godine osavremenjena je tehnologija biološkog prečišćavanja otpadnih voda u cilju otklanjanja nutrijenata. Efektivno se smanjuje koncentracija fosfora, koji po ekološkim načelima predstavlja jedan od najbitnijih eutrofikacijskih faktora opterećenja vodnog tela recipijenta. U radu će se analizirati kretanje koncentracije fosfora od ulaznih (influent) do izlaznih parametara (effluent) u preseku procenta uklanjanja.

The third edition of the "international - Traveling Workshop on Interactions between Sparse models and Technology" (iTWIST) took place in Aalborg, the 4th largest city in Denmark situated beautifully in the northern part of the country, from the 24th to 26th of August 2016. The workshop venue was at the Aalborg University campus. One implicit objective of this biennial workshop is to foster collaboration between international scientific teams by disseminating ideas through both specific oral/poster presentations and free discussions. For this third edition, iTWIST'16 gathered about 50 international participants and features 8 invited talks, 12 oral presentations, and 12 posters on the following themes, all related to the theory, application and generalization of the "sparsity paradigm": Sparsity-driven data sensing and processing (e.g., optics, computer vision, genomics, biomedical, digital communication, channel estimation, astronomy); Application of sparse models in non-convex/non-linear inverse problems (e.g., phase retrieval, blind deconvolution, self calibration); Approximate probabilistic inference for sparse problems; Sparse machine learning and inference; "Blind" inverse problems and dictionary learning; Optimization for sparse modelling; Information theory, geometry and randomness; Sparsity? What's next? (Discrete-valued signals; Union of low-dimensional spaces, Cosparsity, mixed/group norm, model-based, low-complexity models, ...); Matrix/manifold sensing/processing (graph, low-rank approximation, ...); Complexity/accuracy tradeoffs in numerical methods/optimization; Electronic/optical compressive sensors (hardware)., Comment: 69 pages, 22 extended abstracts, iTWIST'16 website: http://www.itwist16.es.aau.dk

Dummy.

Crvene kokošije grinje (Dermanyssus gallinae) uzročnik su dermanisoze značajnog zdrastvenog i ekonomskog problema živine, mane koja može da bude skrivena. Kokošije grinje su problem i ambijenta i jata. Način unošenja bolesti u jato može da bude pojedinačan ili višestruk. Rad sugeriše pristup problemu, dajući neophodne instrukcije kako bi se bolest otkrivala na vreme kada je moguće da se uspostave uzročno-posledične veze. Metoda za rano otkrivanje crvenih kokošijih grinja skraćuje period apsolutne skrivenosti bolesti u naseljenim živinarnicima i, sa ostalim savetovanim merama, pomaže da se otkriju grinje u transportima kokošaka. Ispravan pristup tekara veterinarske medicine i proizvođača prema dermanisozi (Dermanyssosis) preduslov su ispravnoj forenzičkoj praćen/. U suprotnom, omogućava se dalje širenje kokošijih grinja u jatima i između jata, nastanak i dalje povećavanje šteta., Red chicken mites (Dermanyssus gallinae) are the cause of dermanyssosis, a major health and economic problem in poultry that is not necessarily evident. Chicken mites are a problem of both the environment and the flock. The manner in which the disease infiltrates a flock can be individual or multiple. The paper suggests an approach to this problem, giving the necessary instructions to detect the disease on time, when it is still possible to establish the cause-and-effect links. The method for the early detection of red chicken mites shortens the period when the disease is absolutely unrecognizable in the flock, and, in addition to other recommended measures, helps detect mites in chicken transports. A correct approach by doctors of veterinary medicine and manufacturers toward dermanyssosis is a precondition for its correct forensic evaluation. Unless this is done, chicken mites will continue to spread within a flock and among flocks, to occur and result in ever greater damages.

The developments in the use of unmanned aerial vehicles (UAVs) and advanced imaging sensors provide new opportunities for ultra-high resolution (e.g., less than a 10 cm ground sampling distance (GSD)) crop field monitoring and mapping in precision agriculture applications. In this study, we developed a strategy for inter- and intra-row weed detection in early season maize fields from aerial visual imagery. More specifically, the Hough transform algorithm (HT) was applied to the orthomosaicked images for inter-row weed detection. A semi-automatic Object-Based Image Analysis (OBIA) procedure was developed with Random Forests (RF) combined with feature selection techniques to classify soil, weeds and maize. Furthermore, the two binary weed masks generated from HT and OBIA were fused for accurate binary weed image. The developed RF classifier was evaluated by 5-fold cross validation, and it obtained an overall accuracy of 0.945, and Kappa value of 0.912. Finally, the relationship of detected weeds and their ground truth densities was quantified by a fitted linear model with a coefficient of determination of 0.895 and a root mean square error of 0.026. Besides, the importance of input features was evaluated, and it was found that the ratio of vegetation length and width was the most significant feature for the classification model. Overall, our approach can yield a satisfactory weed map, and we expect that the obtained accurate and timely weed map from UAV imagery will be applicable to realize site-specific weed management (SSWM) in early season crop fields for reducing spraying non-selective herbicides and costs.