University of Macau

About: University of Macau is a education organization based out in Macao, Macau, China. It is known for research contribution in the topics: Population & Control theory. The organization has 6636 authors who have published 18324 publications receiving 327384 citations. The organization is also known as: UM & UMAC.

Unified Embedding Alignment with Missing Views Inferring for Incomplete Multi-View Clustering

Abstract: Multi-view clustering aims to partition data collected from diverse sources based on the assumption that all views are complete. However, such prior assumption is hardly satisfied in many real-world applications, resulting in the incomplete multi-view learning problem. The existing attempts on this problem still have the following limitations: 1) the underlying semantic information of the missing views is commonly ignored; 2) The local structure of data is not well explored; 3) The importance of different views is not effectively evaluated. To address these issues, this paper proposes a Unified Embedding Alignment Framework (UEAF) for robust incomplete multi-view clustering. In particular, a locality-preserved reconstruction term is introduced to infer the missing views such that all views can be naturally aligned. A consensus graph is adaptively learned and embedded via the reverse graph regularization to guarantee the common local structure of multiple views and in turn can further align the incomplete views and inferred views. Moreover, an adaptive weighting strategy is designed to capture the importance of different views. Extensive experimental results show that the proposed method can significantly improve the clustering performance in comparison with some state-of-the-art methods.

Design and Precision Position/Force Control of a Piezo-Driven Microinjection System

Abstract: This paper presents the design and development of a piezo-driven cell injection system with the fusion of force and position control. By integrating a polyvinylidene fluoride force sensor for detecting the penetration force of biological cells and a strain-gage sensor for measuring the micropipette relative position in real time, the entire cell micromanipulation system features low cost, convenient installation, and easy maintenance. The challenge of transition jerk between the force and position controller switching is reduced by introducing a weight coefficient method. An adaptive sliding mode control with parameter estimation scheme is implemented to compensate for the hysteresis nonlinearity and disturbance of the piezoelectric actuator. The injection force is controlled by realizing an incremental proportional-integral-derivative controller. The effectiveness of the developed cell injection system is experimentally verified by penetrating zebrafish embryos. The experimental results lay a foundation for the further biological manipulation research, such as the automatic batch injection of zebrafish embryos.