Multiple clusterings of heterogeneous information networks

Machine Learning - Traditional clustering algorithms focus on a single clustering result; as such, they cannot explore potential diverse patterns of complex real world data. To deal with this...     

Looking ahead: Joint small group detection and tracking in crowd scenes

Small group detection and tracking in crowd scenes are basis for high level crowd analysis tasks. However, it suffers from the ambiguities in generating proper groups and in handling dynamic changes of group configurations. In this paper, we propose a novel delay decision-making based method for addressing the above problems, motivated by the idea that these ambiguities can be solved using rich temporal context. Specifically, given individual detections, small group hypotheses are generated. Then candidate group hypotheses across consecutive frames and their potential associations are built in a tree. By seeking for the best non-conflicting subset from the hypothesis tree, small groups are determined and simultaneously their trajectories are got. So this framework is called joint detection and tracking. This joint framework reduces the ambiguities in small group decision and tracking by looking ahead for several frames. However, it results in the unmanageable solution space because the number of track hypotheses grows exponentially over time. To solve this problem, effective pruning strategies are developed, which can keep the solution space manageable and also improve the credibility of small groups. Experiments on public datasets demonstrate the effectiveness of our method. The method achieves the state-of-the-art performance even in noisy crowd scenes.     

Output-relevant Variational autoencoder for Just-in-time soft sensor modeling with missing data

Main challenges for developing data-based models lie in the existence of high-dimensional and possibly missing observations that exist in stored data from industry process. Variational autoencoder (VAE) as one of the deep learning methods has been applied for extracting useful information or features from high-dimensional dataset. Considering that existing VAE is unsupervised, an output-relevant VAE is proposed for extracting output-relevant features in this work. By using correlation between process variables, different weight is correspondingly assigned to each input variable. With symmetric Kullback–Leibler (SKL) divergence, the similarity is evaluated between the stored samples and a query sample. According to the values of the SKL divergence, data relevant for modeling are selected. Subsequently, Gaussian process regression (GPR) is utilized to establish a model between the input and the corresponding output at the query sample. In addition, owing to the common existence of missing data in output data set, the parameters and missing data in the GPR are estimated simultaneously. A practical debutanizer industrial process is utilized to illustrate the effectiveness of the proposed method.     

An adaptive image steganographic scheme based on Noise Visibility Function and an optimal chaotic based encryption method

Steganography is the science of hiding secret message in an appropriate digital multimedia in such a way that the existence of the embedded message should be invisible to anyone apart from the sender or the intended recipient. This paper presents an irreversible scheme for hiding a secret image in the cover image that is able to improve both the visual quality and the security of the stego-image while still providing a large embedding capacity. This is achieved by a hybrid steganography scheme incorporates Noise Visibility Function (NVF) and an optimal chaotic based encryption scheme. In the embedding process, first to reduce the image distortion and to increase the embedding capacity, the payload of each region of the cover image is determined dynamically according to NVF. NVF analyzes the local image properties to identify the complex areas where more secret bits should be embedded. This ensures to maintain a high visual quality of the stego-image as well as a large embedding capacity. Second, the security of the secret image is brought about by an optimal chaotic based encryption scheme to transform the secret image into an encrypted image. Third, the optimal chaotic based encryption scheme is achieved by using a hybrid optimization of Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) which is allowing us to find an optimal secret key. The optimal secret key is able to encrypt the secret image so as the rate of changes after embedding process be decreased which results in increasing the quality of the stego-image. In the extracting process, the secret image can be extracted from the stego-image losslessly without referring to the original cover image. The experimental results confirm that the proposed scheme not only has the ability to achieve a good trade-off between the payload and the stego-image quality, but also can resist against the statistics and image processing attacks.     

Complexities of digital technology use and the teaching and learning of function

Many argue that digital technologies have the potential to enhance the teaching and learning of mathematics. However, the availability of technology is not sufficient to realise this potential. The study reported takes a detailed approach to investigate the utility of the particular offerings of the available technologies in the teaching and learning of a specific area of mathematics, functions. Sixteen affordances identified in the data are described. The complexity of the process involved in resolving a situation where particular affordances would be useful so as they are perceived and enacted is detailed. Finally, a grounded theory framework arising from the data analysis from this study that can be used to explain, predict and guide action in other digital environments is presented.     

Mining citizen emotions to estimate the urgency of urban issues

Crowdsourcing technology offers exciting possibilities for local governments. Specifically, citizens are increasingly taking part in reporting and discussing issues related to their neighborhood and problems they encounter on a daily basis, such as overflowing trash-bins, broken footpaths and lifts, illegal graffiti, and potholes. Pervasive citizen participation enables local governments to respond more efficiently to these urban issues. This interaction between citizens and municipalities is largely promoted by civic engagement platforms, such as See-Click-Fix, FixMyStreet, CitySourced, and OpenIDEO, which allow citizens to report urban issues by entering free text describing what needs to be done, fixed or changed. In order to develop appropriate action plans and priorities, government officials need to figure out how urgent are the reported issues. In this paper we propose to estimate the urgency of urban issues by mining different emotions that are implicit in the text describing the issue. More specifically, a reported issue is first categorized according to the emotions expressed in it, and then the corresponding emotion scores are combined in order to produce a final urgency level for the reported issue. Our experiments use the SeeClickFix hackathon data and diverse emotion classification algorithms. They indicate that (i) emotions can be categorized efficiently with supervised learning algorithms, and (ii) the use of citizen emotions leads to accurate urgency estimates. Further, using additional features such as the type of issue or its author leads to no further accuracy gains.     

ECG heart beat classification method based on modified ABC algorithm

Electrocardiogram is the most commonly used tool for the diagnosis of cardiologic diseases. In order to help cardiologists to diagnose the arrhythmias automatically, new methods for automated, computer aided ECG analysis are being developed. In this paper, a Modified Artificial Bee Colony (MABC) algorithm for ECG heart beat classification is introduced. It is applied to ECG data set which is obtained from MITBIH database and the result of MABC is compared with seventeen other classifier's accuracy.In classification problem, some features have higher distinctiveness than others. In this study, in order to find higher distinctive features, a detailed analysis has been done on time domain features. By using the right features in MABC algorithm, high classification success rate (99.30%) is obtained. Other methods generally have high classification accuracy on examined data set, but they have relatively low or even poor sensitivities for some beat types. Different data sets, unbalanced sample numbers in different classes have effect on classification result. When a balanced data set is used, MABC provided the best result as 97.96% among all classifiers.Not only part of the records from examined MITBIH database, but also all data from selected records are used to be able to use developed algorithm on a real time system in the future by using additional software modules and making adaptation on a specific hardware.     

增强现实光照方向估计方法评述与展望

光照一致性是增强现实中实现虚实融合的重要方面,实时地估计出户外场景中的光照方向,对实现户外场景光照一致性和增强真实感具有重要意义.针对光照方向估计问题,首先归纳了户外场景光照方向估计的特点,把现有的光照方向估计方法分为借助光测球等特殊标定物的估算方法、立体视觉法和人工智能法3类方法.然后总结了各类方法的基本原理和有代表性的研究工作,并且比较了各类方法的优缺点和适用范围.最后,根据实际应用中存在的问题和挑战,展望了户外增强现实系统光照方向估计的研究方向.     

Bayesian network based general correspondence retrieval method for depth sensing with single-shot structured light

This study reinvestigated one of the most fundamental problems in structure light depth sensing field: correspondence retrieval of features between patterns and images. We formulate the global optimum correspondence retrieval by maximizing a conditional probability of correspondence given observed features, which is depicted by a Bayesian network. Different from traditional “code-only” based correspondence retrieval methods, the proposed Bayesian network based method exploits the positional correlations of correspondences of neighboring features, namely, the correspondences of poorly detected features are estimated with the aid of the correspondences of well detected features. The method performs especially well on challenging scenes with rich depth variations, abrupt depth changes, edges, etc. Experiments show that the proposed method increase the correspondence accuracy by about 40% on challenging scenes, compared with traditional “code-only” based correspondence retrieval methods.