人工智能:天使还是魔鬼?

随着大数据的兴起与计算资源的丰富,人工智能在诸多应用领域取得了显著突破,成为了世界各国竞相争先的战略制高点.与此同时,人工智能的社会影响日益突出,得到广泛关注的同时也备受争议.本文从宏观视角概览人工智能的基本概念、发展历程、发展现状和未来趋势,试图揭示人工智能的真实面貌和发展规律,致力于引导全社会对人工智能技术的正确认知,并倡议在人工智能发展中应未雨绸缪、形成合力,确保人工智能的正面效应与健康发展,保障人工智能始终造福于人类.

A survey on rough set theory and its applications

After probability theory, fuzzy set theory and evidence theory, rough set theory is a new mathematical tool for dealing with vague, imprecise, inconsistent and uncertain knowledge. In recent years, the research and applications on rough set theory have attracted more and more researchers＇ attention. And it is one of the hot issues in the artificial intelligence field. In this paper, the basic concepts, operations and characteristics on the rough set theory are introduced firstly, and then the extensions of rough set model, the situation of their applications, some application software and the key problems in applied research for the rough set theory are presented.

A study on key technologies of unmanned driving

Although the development of machine intelligence is far from simulating all the cognitive competence of our brains, still it is absolutely possible to peel the driving activity from people＇s cognitive activities and then make the machine finish some low-level, complicated and lasting driving cognition by simulating our brains. The goal of driving is to replace drivers and free them from boring driving activities. Based on some studies on unmanned driving, this paper summarizes and analyzes the background, significance, research status and key technology of unmanned driving and the research group also introduces some research on brain cognition of driving and sensor placement of intelligent vehicles, which offers more meaningful reference to push the study of unmanned driving.

Relative attribute based incremental learning for image recognition

In this study, we propose an incremental learning approach based on a machine-machine interaction via relative attribute feedbacks that exploit comparative relationships among top level image categories. One machine acts as ＇Student （S）＇ with initially limited information and it endeavors to capture the task domain gradually by questioning its mentor on a pool of unlabeled data. The other machine is ＇Teacher （T）＇ with the implicit knowledge for helping S on learning the class models. T initiates relative attributes as a communication channel by randomly sorting the classes on attribute space in an unsupervised manner. S starts modeling the categories in this intermediate level by using only a limited number of labeled data. Thereafter, it first selects an entropy-based sample from the pool of unlabeled data and triggers the conversation by propagating the selected image with its belief class in a query. Since T already knows the ground truth labels, it not only decides whether the belief is true or false, but it also provides an attribute-based feedback to S in each case without revealing the true label of the query sample if the belief is false. So the number of training data is increased virtually by dropping the falsely predicted sample back into the unlabeled pool. Next, S updates the attribute space which, in fact, has an impact on T＇s future responses, and then the category models are updated concurrently for the next run. We experience the weakly supervised algorithm on the real world datasets of faces and natural scenes in comparison with direct attribute prediction and semi-supervised learning approaches, and a noteworthy performance increase is achieved.

Online RGB-D person re-identification based on metric model update

Person re-identification （re-id） on robot platform is an important application for human-robot- interaction （HRI）, which aims at making the robot recognize the around persons in varying scenes. Although many effective methods have been proposed for surveillance re-id in recent years, re-id on robot platform is still a novel unsolved problem. Most existing methods adapt the supervised metric learning offline to improve the accuracy. However, these methods can not adapt to unknown scenes. To solve this problem, an online re-id framework is proposed. Considering that robotics can afford to use high-resolution RGB-D sensors and clear human face may be captured, face information is used to update the metric model. Firstly, the metric model is pre-trained offline using labeled data. Then during the online stage, we use face information to mine incorrect body matching pairs which are collected to update the metric model online. In addition, to make full use of both appearance and skeleton information provided by RGB-D sensors, a novel feature funnel model （FFM） is proposed. Comparison studies show our approach is more effective and adaptable to varying environments.

Density peaks clustering based integrate framework for multi-document summarization

We present a novel unsupervised integrated score framework to generate generic extractive multi- document summaries by ranking sentences based on dynamic programming （DP） strategy. Considering that cluster-based methods proposed by other researchers tend to ignore informativeness of words when they generate summaries, our proposed framework takes relevance, diversity, informativeness and length constraint of sentences into consideration comprehensively. We apply Density Peaks Clustering （DPC） to get relevance scores and diversity scores of sentences simultaneously. Our framework produces the best performance on DUC2004, 0.396 of ROUGE-1 score, 0.094 of ROUGE-2 score and 0.143 of ROUGE-SU4 which outperforms a series of popular baselines, such as DUC Best, FGB [7], and BSTM [10].

Exploiting structural similarity of log files in fault diagnosis for Web service composition

With increasing deployment of Web services, the research on the dependability and availability of Web service composition becomes more and more active. Since unexpected faults of Web service composition may occur in different levels at runtime, log analysis as a typical data- driven approach for fault diagnosis is more applicable and scalable in various architectures. Considering the trend that more and more service logs are represented using XML or JSON format which has good flexibility and interoperability, fault classification problem of semi-structured logs is considered as a challenging issue in this area. However, most existing approaches focus on the log content analysis but ignore the structural information and lead to poor performance. To improve the accuracy of fault classification, we exploit structural similarity of log files and propose a similarity based Bayesian learning approach for semi-structured logs in this paper. Our solution estimates degrees of similarity among structural elements from heterogeneous log data, constructs combined Bayesian network （CBN）, uses similarity based learning algorithm to compute probabilities in CBN, and classifies test log data into most probable fault categories based on the generated CBN. Experimental results show that our approach outperforms other learning approaches on structural log datasets.

Salient pairwise spatio-temporal interest points for real-time activity recognition

Real-time Human action classification in complex scenes has applications in various domains such as visual surveillance, video retrieval and human robot interaction. While, the task is challenging due to computation efficiency, cluttered backgrounds and intro-variability among same type of actions. Spatio-temporal interest point （STIP） based methods have shown promising results to tackle human action classification in complex scenes efficiently. However, the state-of-the-art works typically utilize bag-of-visual words （BoVW） model which only focuses on the word distribution of STIPs and ignore the distinctive character of word structure. In this paper, the distribution of STIPs is organized into a salient directed graph, which reflects salient motions and can be divided into a time salient directed graph and a space salient directed graph, aiming at adding spatio-temporal discriminant to BoVW. Generally speaking, both salient directed graphs are constructed by labeled STIPs in pairs. In detail, the ＂directional co-occurrence＂ property of different labeled pairwise STIPs in same frame is utilized to represent the time saliency, and the space saliency is reflected by the ＂geometric relationships＂ between same labeled pairwise STIPs across different frames. Then, new statistical features namely the Time Salient Pairwise feature （TSP） and the Space Salient Pairwise feature （SSP） are designed to describe two salient directed graphs, respectively. Experiments are carried out with a homogeneous kernel SVM classifier, on four challenging datasets KTH, ADL and UT-Interaction. Final results confirm the complementary of TSP and SSP, and our multi-cue representation TSP ＋ SSP ＋ BoVW can properly describe human actions with large intro-variability in real-time.

RPK-table based efficient algorithm for join-aggregate query on MapReduce

Join-aggregate is an important and widely used operation in database system. However, it is time-consuming to process join-aggregate query in big data environment, especially on MapReduce framework. The main bottlenecks contain two aspects： lots of I/O caused by temporary data and heavy communication overhead between different data nodes during query processing. To overcome such disadvantages, we design a data structure called Reference Primary Key table （RPK-table） which stores the relationship of primary key and foreign key between tables. Based on this structure, we propose an improved algorithm on MapReduce framework for join-aggregate query. Experi-ments on TPC-H dataset demonstrate that our algorithm outperforms existing methods in terms of communication cost and query response time.

Cognitive-affective regulation process for micro-expressions based on Gaussian cloud distribution

In this paper, we explore the process of emotional state transition. And the process is impacted by emotional state of interaction objects. First of all, the cognitive reasoning process and the micro-expressions recognition is the basis of affective computing adjustment process. Secondly, the threshold function and attenuation function are proposed to quantify the emotional changes. In the actual environment, the emotional state of the robot and external stimulus are also quantified as the transferring probability. Finally, the Gaussian cloud distribution is introduced to the Gross model to calculate the emotional transitional probabilities. The experimental results show that the model in human-computer interaction can effectively regulate the emotional states, and can significantly improve the humanoid and intelligent ability of the robot. This model is consistent with experimental and emulational significance of the psychology, and allows the robot to get rid of the mechanical emotional transfer process.

Frame interpolation with pixel-level motion vector field and mesh based hole filling

Most of the traditional methods are based on block motion compensation tending to involve heavy blocking artifacts in the interpolated frames. In this paper, a new frame interpolation method with pixel-level motion vector field （MVF） is proposed. Our method consists of the following four steps： （i） applying the pixel-level motion vectors （MVs） estimated by optical flow algorithm to eliminate blocking artifacts （ii） motion post-processing and super-sampling anti-aliasing to solve the problems caused by pixel-level MVs （iii） robust warping method to address collisions and holes caused by occlusions （iv） a new holes filling method using triangular mesh （HFTM） to reduce the artifacts caused by holes. Experimental results show that the proposed method can effectively alleviate the holes and blocking artifacts in interpolated frames, and outperforms existing methods both in terms of objective and subjective performances, especially for sequences with complex motions.

Research progress of artificial psychology and artificial emotion in China

Since the concept of artificial psychology and artificial emotion was first presented, it has become a topic of interest in academic circles and enterprises. In this article, we first briefly introduce the basic concepts and principles of artificial psychology and artificial emotion, analyzing the unified macro-model of the cross-disciplinary system architecture against the need-motivation-behavior framework. Second, we discuss the origin of artificial psychology and artificial emotion, its course of development, and its present situation in China. We also present a review of the published papers and research endeavors of Chinese universities and research institutions and the technical engineering applications of artificial psychology and artificial emotion. Finally, we summarize the challenges to the further development of artificial psychology and artificial emotion and our recommendations for improving the cognitive computing model of psychological states and developing reliable and accurate humanoid interaction and cooperation technology, robot platforms with emotions and humanoid interaction and cooperation capabilities, and humanoid robots for the elderly and the disabled in smart homes. We believe that, with intensive research, artificial psychology and artificial emotion may be developed further and may eventually reach maturity.