The issues of spectral redundancy and limited training samples hinder the widespread application and development of hyperspectral images. In this letter, a novel active deep feature extraction scheme is proposed by incorporating both representative and informative measurement. Firstly, an adversarial autoencoder is modified to suit the classification task with deep feature extraction. Dictionary learning and a multi-variance and distributional distance (MVDD) measure are then introduced to choose the most valuable candidate training samples, where we use the limited labeled samples to obtain a high classification accuracy. Comparative experiments with the proposed querying strategy were carried out with two hyperspectral datasets. The experimental results obtained with the two datasets demonstrate that the proposed scheme is superior to the others. With this method, the unstable increase in accuracy is eliminated by incorporating both informative and representative measurement.

The highly correlated spectral features and the limited training samples pose challenges in hyperspectral image classification. In this article, to tackle the issues of end-to-end feature learning and transfer learning with limited labeled samples, we propose a unified multiscale learning (UML) framework, which is based on a fully convolutional network. A multiscale spatial-channel attention mechanism and a multiscale shuffle block are proposed in the UML framework to improve the problem of land-cover map distortion. The contextual information and the spectral feature are enhanced before the last classification layer based on three strategies in this work: 1) the channel shuffle operation, which was employed to learn the more effective spectral characteristics by disordering the channels of the feature map; 2) multiscale block, which considered the contextual information in multiple ranges; and 3) spatiospectral attention, which enhanced the expression of the important characteristic among all pixels. Three hyperspectral datasets, including two airborne hyperspectral images and one spaceborne hyperspectral image, were used to demonstrate the performance of the UML framework in both classification and transfer learning. The experimental results confirmed that the proposed method outperforms most of the state-of-the-art hyperspectral image classification methods. The source code is released athttps://github.com/Hyper-NN/UML.

Online monitoring user cardinalities in graph streams is fundamental for many applications such as anomaly detection. These graph streams may contain edge duplicates and have a large number of user-item pairs, which makes it infeasible to exactly compute user cardinalities due to limited computational and memory resources. Existing methods are designed to approximately estimate user cardinalities, but their accuracy highly depends on complex parameters and they cannot provide anytime-available estimation. To address these problems, we develop novel bit/register sharing algorithms, which use a bit/register array to build a compact sketch of all users’ connected items. Our algorithms exploit the dynamic properties of the bit/register arrays (e.g., the fraction of zero bits in the bit array) to significantly improve the estimation accuracy, and have low time complexity$O(1)$to update the estimations for a new user-item pair. In addition, our algorithms are simple and easy to use, without requirements to tune any parameter. Furthermore, we extend our methods to detect super spreaders with large cardinalities in real-time. We evaluate the performance of our methods on real-world datasets. The experimental results demonstrate that our methods are several times more accurate and faster than state-of-the-art methods using the same amount of memory.

The challenges of generic visual tracking have attracted great attentions. However, it is still difficult for most of the existing trackers to track objects accurately on real-time occasion. We propose a framework which integrate a verifying mechanism and a correcting mechanism to improve the accuracy of real-time tracking. Under online learning, both target location and sample model update in parallel. Validations are carried out in every frame according to spatial-temporal convolution response. Furthermore, a correcting mechanism would be activated when the current tracking results considered to be unreliable. Synchronously, an online target model updating strategy is constructed to filter the contributive samples, which makes the sample model update confidently. The proposed tracker is evaluated on four popular benchmarks, achieving a state-of-the-art performance while runs at real-time speed.

An implicit assumption in many generic object trackers is that the videos are blur free. However, motion blur is very common in real videos. The performance of a generic object tracker may drop significantly when it is applied to videos with severe motion blur. In this paper, we propose a new Tracking-Learning-Data approach to transfer a generic object tracker to a blur-invariant object tracker without deblurring image sequences. Before object tracking, a large set of unlabeled images is used to learn objects' visual prior knowledge, which is then transferred to the appearance model of a specific target. During object tracking, online training samples are collected from the tracking results and the context information. Different blur kernels are involved with the training samples to increase the robustness of the appearance model to severe blur, and the motion parameters of the object are estimated in the particle filter framework. Extensive experimental results demonstrate that the proposed algorithm can robustly track objects not only in severely blurred videos but also in other challenging scenes.

The recent years witness the rapid development of the Internet of Things (IoT). Increasing numbers of conventional manufacturing enterprises face the challenge of using current data management systems to collect and analyze the massive volume of monitor data generated by sensors and equipments to improve the design, manufacture and maintenance of products. Hence, Map Reduce technique has gained a lot of attention for its applicability in large parallel monitor data analyses. In this paper, we apply a series of metrics implemented based on Map Reduce framework to depict a large collection of monitor data. With the help of these proposed metrics, domain experts can quickly analyze monitor data and feedback the analysis results to improve the design, manufacture and maintenance of products. Furthermore, we conduct a series of experiments on the real-world data sets and experimental results show that when facing a large amount of monitor data, these proposed Map Reduce implemented metrics outperform the conventional structured databases implemented metrics. Moreover, these Map Reduce implemented metrics have been successfully applied to a construction machinery manufacturer's condition monitoring system.

While many process mining algorithms have been proposed recently, there does not exist a widely accepted benchmark to evaluate and compare these process mining algorithms. As a result, it can be difficult to choose a suitable process mining algorithm for a given enterprise or application domain. Some recent benchmark systems have been developed and proposed to address this issue. However, evaluating available process mining algorithms against a large set of business models (e.g., in a large enterprise) can be computationally expensive, tedious, and time-consuming. This paper investigates a scalable solution that can evaluate, compare, and rank these process mining algorithms efficiently, and hence proposes a novel framework that can efficiently select the process mining algorithms that are most suitable for a given model set. In particular, using our framework, only a portion of process models need empirical evaluation and others can be recommended directly via a regression model. As a further optimization, this paper also proposes a metric and technique to select high-quality reference models to derive an effective regression model. Experiments using artificial and real data sets show that our approach is practical and outperforms the traditional approach.

Motion blur is very common in the low quality of image sequences and videos captured by low speed of cameras. Object tracking without accounting for the motion blur would easily fail in these kinds of videos. We propose a new data-driven tracker in the particle filter framework to address this problem without deblurring the image sequences. The motion blur is detected by exploring the property of the blurred input image through Fourier analysis. The appearance model is integrated with a set of motion blur kernels which could reflect different blur effects in real scenes. The motion model is improved to be more robust to sudden motion of the target object. To evaluate the proposed algorithm, several challenging videos with significant motion blur are used in the experiments. The experimental results demonstrate the robustness and accuracy of our algorithm.

While many process mining algorithms have been proposed recently, there does not exist a widely-accepted benchmark to evaluate and compare these process mining algorithms. As a result, it can be difficult to choose a suitable process mining algorithm for a given enterprise or application domain. Some recent benchmark systems have been developed and proposed to address this issue. However, evaluating available process mining algorithms against a large set of business models (e.g., in a large enterprise) can be computationally expensive, tedious and time-consuming. This paper proposes a novel framework that can efficiently select the process mining algorithms that are most suitable for a given model set. In particular, it attemptsto investigate how we can avoid evaluating numerous process mining algorithms on all given process models.