Harbin Institute of Technology

About: Harbin Institute of Technology is a education organization based out in Harbin, China. It is known for research contribution in the topics: Microstructure & Control theory. The organization has 88259 authors who have published 109297 publications receiving 1603393 citations. The organization is also known as: HIT.

Multi-view Response Selection for Human-Computer Conversation

Abstract: In this paper, we study the task of response selection for multi-turn human-computer conversation. Previous approaches take word as a unit and view context and response as sequences of words. This kind of approaches do not explicitly take each utterance as a unit, therefore it is difficult to catch utterancelevel discourse information and dependencies. In this paper, we propose a multi-view response selection model that integrates information from two different views, i.e., word sequence view and utterance sequence view. We jointly model the two views via deep neural networks. Experimental results on a public corpus for context-sensitive response selection demonstrate the effectiveness of the proposed multi-view model, which significantly outperforms other single-view baselines.

BioSeq-Analysis2.0: an updated platform for analyzing DNA, RNA and protein sequences at sequence level and residue level based on machine learning approaches.

Abstract: As the first web server to analyze various biological sequences at sequence level based on machine learning approaches, many powerful predictors in the field of computational biology have been developed with the assistance of the BioSeq-Analysis. However, the BioSeq-Analysis can be only applied to the sequence-level analysis tasks, preventing its applications to the residue-level analysis tasks, and an intelligent tool that is able to automatically generate various predictors for biological sequence analysis at both residue level and sequence level is highly desired. In this regard, we decided to publish an important updated server covering a total of 26 features at the residue level and 90 features at the sequence level called BioSeq-Analysis2.0 (http://bliulab.net/BioSeq-Analysis2.0/), by which the users only need to upload the benchmark dataset, and the BioSeq-Analysis2.0 can generate the predictors for both residue-level analysis and sequence-level analysis tasks. Furthermore, the corresponding stand-alone tool was also provided, which can be downloaded from http://bliulab.net/BioSeq-Analysis2.0/download/. To the best of our knowledge, the BioSeq-Analysis2.0 is the first tool for generating predictors for biological sequence analysis tasks at residue level. Specifically, the experimental results indicated that the predictors developed by BioSeq-Analysis2.0 can achieve comparable or even better performance than the existing state-of-the-art predictors.

A Secure Authentication Protocol for Internet of Vehicles

Abstract: An Internet of Vehicles (IoV) allows forming a self-organized network and broadcasting messages for the vehicles on roads. However, as the data are transmitted in an insecure network, it is essential to use an authentication mechanism to protect the privacy of vehicle users. Recently, Ying et al. proposed an authentication protocol for IoV and claimed that the protocol could resist various attacks. Unfortunately, we discovered that their protocol suffered from an offline identity guessing attack, location spoofing attack, and replay attack, and consumed a considerable amount of time for authentication. To resolve these shortcomings, we propose an improved protocol. In addition, we provide a formal proof to the proposed protocol to demonstrate that our protocol is indeed secure. Compared with previous methods, the proposed protocol performs better in terms of security and performance.

Weighted Schatten $p$ -Norm Minimization for Image Denoising and Background Subtraction

Abstract: Low rank matrix approximation (LRMA), which aims to recover the underlying low rank matrix from its degraded observation, has a wide range of applications in computer vision. The latest LRMA methods resort to using the nuclear norm minimization (NNM) as a convex relaxation of the nonconvex rank minimization. However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications. We propose a more flexible model, namely, the weighted Schatten $p$ -norm minimization (WSNM), to generalize the NNM to the Schatten $p$ -norm minimization with weights assigned to different singular values. The proposed WSNM not only gives better approximation to the original low-rank assumption, but also considers the importance of different rank components. We analyze the solution of WSNM and prove that, under certain weights permutation, WSNM can be equivalently transformed into independent non-convex $l_{p}$ -norm subproblems, whose global optimum can be efficiently solved by generalized iterated shrinkage algorithm. We apply WSNM to typical low-level vision problems, e.g., image denoising and background subtraction. Extensive experimental results show, both qualitatively and quantitatively, that the proposed WSNM can more effectively remove noise, and model the complex and dynamic scenes compared with state-of-the-art methods.

A review on ammonia, ammonia-hydrogen and ammonia-methane fuels

Abstract: Combustion of fuels to generate energy is integral to various human activities, both domestic and industrial. However, the predominance of hydrocarbon fuel usage produces emissions containing pollutants that cause multiple environmental complications and risks to human health. Therefore, replacement of conventional fuels to achieve zero carbon emission is of utmost importance. In terms of carbon-free fuel, ammonia offers several advantages over hydrogen. However, its low burning velocity and high fuel NOx emissions inhibit large-scale usage. Hence, hydrogen and methane have been studied in this review as possible secondary fuels to aid ammonia combustion and address the aforementioned issues. This review starts from the suitability of ammonia fuel as energy vector in terms of physicochemical and combustion characteristics, moving through the kinetics and mechanisms of ammonia-based and ammonia-fuel combustion. The impacts and limitations of each system are also addressed, thus providing a comparison on each system. Particularly, this review assesses and discusses the advantages and mechanisms involved with secondary fuel addition to the ammonia combustion, presenting the role of key reaction differences and the change in key reaction mechanism under different conditions at the level of reaction mechanisms. Finally, this review covers future perspectives and challenges on the usage and development of ammonia-based fuels, emphasizing the maturity of ammonia-based and ammonia-fuel combustion kinetics. Herein, this work summarizes the principles of the combustion reactions of ammonia-based and ammonia-fuel systematically and serves as a theoretical reference of ammonia-fuel combustion kinetics for transitioning into future practical applications where ammonia is an important energy vector.