Northeastern University (China)

About: Northeastern University (China) is a education organization based out in Shenyang, China. It is known for research contribution in the topics: Microstructure & Control theory. The organization has 36087 authors who have published 36125 publications receiving 426807 citations. The organization is also known as: Dōngběi Dàxué & Northeastern University (东北大学).

Sentiment analysis using deep learning approaches: an overview

Abstract: Nowadays, with the increasing number of Web 2.0 tools, users generate huge amounts of data in an enormous and dynamic way. In this regard, the sentiment analysis appeared to be an important tool that allows the automation of getting insight from the user-generated data. Recently, deep learning approaches have been proposed for different sentiment analysis tasks and have achieved state-of-the-art results. Therefore, in order to help researchers to depict quickly the current progress as well as current issues to be addressed, in this paper, we review deep learning approaches that have been applied to various sentiment analysis tasks and their trends of development. This study also provides the performance analysis of different deep learning models on a particular dataset at the end of each sentiment analysis task. Toward the end, the review highlights current issues and hypothesized solutions to be taken into account in future work. Moreover, based on knowledge learned from previous studies, the future work subsection shows the suggestions that can be incorporated into new deep learning models to yield better performance. Suggestions include the use of bidirectional encoder representations from transformers (BERT), sentiment-specific word embedding models, cognition-based attention models, common sense knowledge, reinforcement learning, and generative adversarial networks.

A fast reconstruction algorithm for fluorescence molecular tomography with sparsity regularization

Abstract: Through the reconstruction of the fluorescent probe distributions, fluorescence molecular tomography (FMT) can three-dimensionally resolve the molecular processes in small animals in vivo. In this paper, we propose an FMT reconstruction algorithm based on the iterated shrinkage method. By incorporating a surrogate function, the original optimization problem can be decoupled, which enables us to use the general sparsity regularization. Due to the sparsity characteristic of the fluorescent sources, the performance of this method can be greatly enhanced, which leads to a fast reconstruction algorithm. Numerical simulations and physical experiments were conducted. Compared to Newton method with Tikhonov regularization, the iterated shrinkage based algorithm can obtain more accurate results, even with very limited measurement data.

A Novel Energy Function-Based Stability Evaluation and Nonlinear Control Approach for Energy Internet

Abstract: Unlike conventional interconnected power systems, energy Internet presents an unsolved and more challenging problem for the society including transfer impedance, damping, large penetration of distributed generation, and numerous hybrid integration of generators and converters. In this paper, a novel energy function designed for energy internet router is proposed to accurately evaluate its transfer stability. The reliability of the proposed energy function is confirmed through both theoretical analysis and empirical simulations. Furthermore, generalized methods to determine critical stable energy, stable domain, and critical clearing time are proposed. By updating stability criterion and evaluating system energy of post-disturbance system, fault energy-based impulsive feedback control method is specifically designed for energy Internet to stabilize the system. Simulation and experimental results are provided to validate the effectiveness of the proposed energy function and nonlinear control method.

Mixed H∞ /passive sampled-data synchronization control of complex dynamical networks with distributed coupling delay

Abstract: This paper investigates the problem of the mixed H ∞ / passive sampled-data synchronization control for complex dynamical networks (CDNs) with distributed coupling delay. The sampled interval is deemed as time-varying. The main purpose is to design a sampled-data controller so as to the synchronization error system (SES) is exponentially stable and satisfies a predefined H ∞ / passive performance index simultaneously. Some novel auxiliary function-based integral inequalities are applied to reduce the conservativeness of the presented results, and some effective synchronization criteria are addressed. The gains for the desired controller can be designed by settling an optimization issue in view of the proposed criteria. Three examples are employed to demonstrate the less conservativeness and superiority of the addressed method.