University of Electronic Science and Technology of China

About: University of Electronic Science and Technology of China is a education organization based out in Chengdu, China. It is known for research contribution in the topics: Computer science & Antenna (radio). The organization has 50594 authors who have published 58502 publications receiving 711188 citations. The organization is also known as: UESTC.

Combining conflicting evidence using the DEMATEL method

Abstract: Dempster–Shafer evidence theory is widely used in the information fusion field for its effectivity in representing and handling uncertain information. However, applications of Dempster rule in combining multiple conflicting evidence often cause counterintuitive results. One of the existing researches on conflict is based on the similarity of evidence. However, due to the fact that computational complexity of the existing methods is large, it is difficult to meet the real-time requirements of systems. Therefore, new effective methods with acceptable expense should be explored. In this article, following the idea of modifying the source model of evidence, a new method based on DEMATEL is proposed to take the weight of each evidence into consideration. First, the total-relation matrix is determined by the similarity among evidence. Second, prominence and importance are calculated. Finally, the weighted average combination result can be obtained based on Dempster’s rule of combination. Numerical examples are used to demonstrate that the proposed model is efficient to both deals with conflicting evidence and reduce computational complexity.

Predicting Subcellular Localization of Mycobacterial Proteins by Using Chous Pseudo Amino Acid Composition

Abstract: The successful prediction of protein subcellular localization directly from protein primary sequence is useful to protein function prediction and drug discovery. In this paper, by using the concept of pseudo amino acid composition (PseAAC), the mycobacterial proteins are studied and predicted by support vector machine (SVM) and increment of diversity combined with modified Mahalanobis Discriminant (IDQD). The results of jackknife cross-validation for 450 non-redundant proteins show that the overall predicted successful rates of SVM and IDQD are 82.2% and 79.1%, respectively. Compared with other existing methods, SVM combined with PseAAC display higher accuracies.

Video Captioning by Adversarial LSTM

Abstract: In this paper, we propose a novel approach to video captioning based on adversarial learning and long short-term memory (LSTM). With this solution concept, we aim at compensating for the deficiencies of LSTM-based video captioning methods that generally show potential to effectively handle temporal nature of video data when generating captions but also typically suffer from exponential error accumulation. Specifically, we adopt a standard generative adversarial network (GAN) architecture, characterized by an interplay of two competing processes: a “generator” that generates textual sentences given the visual content of a video and a “discriminator” that controls the accuracy of the generated sentences. The discriminator acts as an “adversary” toward the generator, and with its controlling mechanism, it helps the generator to become more accurate. For the generator module, we take an existing video captioning concept using LSTM network. For the discriminator, we propose a novel realization specifically tuned for the video captioning problem and taking both the sentences and video features as input. This leads to our proposed LSTM–GAN system architecture, for which we show experimentally to significantly outperform the existing methods on standard public datasets.