Search By Subject

We focus on the key task of semantic type discovery over a set of heterogeneous sources, an important data preparation task. We consider the challenging setting of multiple Web data sources in a vertical domain, which present sparsity of data and ...

Causal inference is capable of estimating the treatment effect (i.e., the causal effect of treatment on the outcome) to benefit the decision making in various domains. One fundamental challenge in this research is that the treatment assignment ...

Database fragmentation has been used as a protection mechanism of database’s privacy by allocating attributes with sensitive associations into separate data fragments. A typical relational database consists of multiple relations. Thus, ...

Data corruption is an impediment to modern machine learning deployments. Corrupted data can severely bias the learned model and can also lead to invalid inferences. We present, Picket, a simple framework to safeguard against data corruptions ...

Graph simulation is one of the most fundamental problems in graph processing and analytics. It can help users to generate new graphs on different scales to mimic observed real-life graphs in many applications such as social networks, biology ...

A correction to this paper has been published: https://doi.org/10.1007/s00778-021-00678-1

We study the problem of utilizing human intelligence to categorize a large number of objects. In this problem, given a category hierarchy and a set of objects, we can ask humans to check whether an object belongs to a category, and our goal is to ...

Because of its flexibility, intuitiveness, and expressivity, the graph edit distance (GED) is one of the most widely used distance measures for labeled graphs. Since exactly computing GED is NP-hard, over the past years, various heuristics have ...

Since the learning ability of adaptive control (including multi-model adaptive control) is actually very limited and the persistent excitation (PE) condition is also not satisfied in the design of uncertain nonlinear system controllers, an improved ...

This work introduces a novel convolutional feature for the task of human pose estimation, which is a framework of fusing a convolutional neural network into a multi-level graph structure model so as to improve the pose estimation results from body-part ...

The brain-computer interface technology interprets the EEG signals displayed by the human brain's neurological thinking activities through computers and instruments, and directly uses the interpreted information to manipulate the outside world, thereby ...

Since the contextual information has an important impact on the speaker's emotional state, how to use emotion-related context information to conduct feature learning is a key problem. The existing speech emotion recognition algorithms achieve the ...

Aiming at the disadvantages of the traditional machine-based facial expression recognition method that eliminates the feature of manual selection, a feature extraction method based on deep convolutional neural network to learn expression features is ...

The monitoring system is a critical function in modern underground mine gas accidents prevention. As a complex dynamic critical system, its fault diagnosis is generally based on the traditional two-state fault tree. In order to solve the problem that ...

In view of the nonlinearity and uncertainty of safety accident risk assessment, firstly, based on the deep neural network, the training criterion of the network is changed, and the triplet convolutional neural network with the similarity measure as the ...

Since the initial weight matrix between the last hidden layer of the network and the classification layer is usually generated randomly, the weight matrix does not have the discrimination ability to accurately classify the facial expression recognition, ...

Combining image information fusion theory with machine learning for biometric recognition is an important field in computer vision research in recent years. Based on this, a gesture recognition algorithm based on image information fusion in virtual ...

Scale-invariant feature transform (SIFT) is one of the widely used interest point features. It has been successfully applied in various computer vision algorithms like object detection, object tracking, robotic mapping, and large-scale image retrieval. ...

Based on the self-balance of free-floating two-wheel self-balancing pendulum robot system, an optimal path planning of two-wheel self-balancing pendulum robot is proposed. Firstly, the corner trajectory of the two-wheel self-balancing pendulum robot is ...