Hefei University of Technology

About: Hefei University of Technology is a education organization based out in Hefei, China. It is known for research contribution in the topics: Computer science & Microstructure. The organization has 28093 authors who have published 24935 publications receiving 324989 citations.

Fuzzy Restricted Boltzmann Machine for the Enhancement of Deep Learning

Abstract: In recent years, deep learning caves out a research wave in machine learning. With outstanding performance, more and more applications of deep learning in pattern recognition, image recognition, speech recognition, and video processing have been developed. Restricted Boltzmann machine (RBM) plays an important role in current deep learning techniques, as most of existing deep networks are based on or related to it. For regular RBM, the relationships between visible units and hidden units are restricted to be constants. This restriction will certainly downgrade the representation capability of the RBM. To avoid this flaw and enhance deep learning capability, the fuzzy restricted Boltzmann machine (FRBM) and its learning algorithm are proposed in this paper, in which the parameters governing the model are replaced by fuzzy numbers. This way, the original RBM becomes a special case in the FRBM, when there is no fuzziness in the FRBM model. In the process of learning FRBM, the fuzzy free energy function is defuzzified before the probability is defined. The experimental results based on bar-and-stripe benchmark inpainting and MNIST handwritten digits classification problems show that the representation capability of FRBM model is significantly better than the traditional RBM. Additionally, the FRBM also reveals better robustness property compared with RBM when the training data are contaminated by noises.

Less is More: Efficient 3-D Object Retrieval With Query View Selection

Abstract: The explosively increasing 3-D objects make their efficient retrieval technology highly desired. Extensive research efforts have been dedicated to view-based 3-D object retrieval for its advantage of using 2-D views to represent 3-D objects. In this paradigm, typically the retrieval is accomplished by matching the views of the query object with the objects in database. However, using all the query views may not only introduce difficulty in rapid retrieval but also degrade retrieval accuracy when there is a mismatch between the query views and the object views in the database. In this work, we propose an interactive 3-D object retrieval scheme. Given a set of query views, we first perform clustering to obtain several candidates. We then incrementally select query views for object matching: in each round of relevance feedback, we only add the query view that is judged to be the most informative one based on the labeling information. In addition, we also propose an efficient approach to learn a distance metric for the newly selected query view and the weights for combining all of the selected query views. We conduct experiments on the National Taiwan University 3D Model database, ETH 3D object collection, and Shape Retrieval Content of Non-Rigid 3D Model, and results demonstrated that our approach not only significantly speeds up the retrieval process but also achieves encouraging retrieval performance.

Constacyclic Codes and Some New Quantum MDS Codes

Abstract: One central theme in quantum error-correction is to construct quantum codes that have a large minimum distance. Quantum maximal distance separable (MDS) codes are optimal in the sense they attain maximal minimum distance. Recently, constructing quantum MDS codes has received much attention and seems to become more and more difficult. In this paper, based on classical constacyclic codes, we construct some new quantum MDS codes by employing the Hermitian construction. Compared with the known quantum MDS codes, these quantum MDS codes have much larger minimum distance.

Fabrication of Fe3O4/SiO2 core/shell nanoparticles attached to graphene oxide and its use as an adsorbent

Abstract: Amino-functionalized Fe(3)O(4)/SiO(2) core/shell nanoparticles were synthesized by reacting Fe(3)O(4) nanoparticles with tetraethyl orthosilicate and (3-aminopropyl) triethoxysilane to introduce amino groups on the surface. The amino groups on the Fe(3)O(4)/SiO(2) were reacted with the carboxylic groups of graphene oxide (GO) with the aid of 1-ethyl-3-(3-dimethylaminopropyl)carbodiimide and N-hydroxysuccinnimide to form Fe(3)O(4)/SiO(2)GO nanoparticles. The structural, surface, and magnetic characteristics of the material were investigated by scanning and transmission electron microscopy, energy-dispersive X-ray spectrometry, powder X-ray diffraction, Fourier transform infrared spectroscopy, and thermogravimetric analysis. Adsorption equilibrium and kinetics of methylene blue on the Fe(3)O(4)/SiO(2)GO were studied in a batch system. The maximum adsorption capacities were found to be 97.0, 102.6, and 111.1 mg g(-1) at 25, 45, and 60°C, respectively. A second-order kinetic equation could best describe the sorption kinetics. Thermodynamic parameters indicated that the adsorption of methylene blue onto the material was thermodynamically feasible and could occur spontaneously.