Next location prediction is a crucial task in human mobility modeling, and is pivotal for many downstream applications like location-based recommendation and transportation planning. Although there has been a large body of research tackling this problem, the usefulness of user preference and temporal regularity remains underrepresented. Specifically, previous studies usually neglect the explicit user preference information entailed from human trajectories and fall short in utilizing the arrival time of next location, as a key determinant on next location. To address these limitations, we propose a Multi-Context aware Location Prediction model (MCLP) to predict next locations for individuals, where it explicitly models user preference and the next arrival time as context. First, we utilize a topic model to extract user preferences for different types of locations from historical human trajectories. Second, we develop an arrival time estimator to construct a robust arrival time embedding based on the multi-head attention mechanism. The two components provide pivotal contextual information for the subsequent prediction. Finally, we utilize the Transformer architecture to mine sequential patterns and integrate multiple contextual information to predict the next locations. Experimental results on two real-world mobility datasets show that our proposed MCLP outperforms baseline methods.

Clustering-based active learning approaches take advantage of the structure of the data to select representative instances. However, some algorithms are either inefficient or only applicable to some data. In this paper, we propose an effective and adaptive algorithm that will be called active learning through two-stage clustering (ALTA). The first stage is data preprocessing using the two-round-clustering algorithm to obtain $\sqrt n $ small blocks, where n is the number of instances. For each block, the closest instance of the center is selected as the representative. The second stage is the active learning of representative instances through density clustering. This stage consists of a number of iterations of density clustering, labeling and classification. In general, data preprocessing reduces the size of the data and the complexity of the algorithm. The combination of distance vector clustering and density clustering makes the algorithm more adaptive. Experiments are performed in comparison against the state-of-the-art active learning algorithms on nine datasets. Results demonstrate that the new algorithm has higher classification accuracy with the same number of labeled data.

In this paper, the dynamic modelling and control design of a planar parallel manipulator used as a pick-and-place machine, is addressed. First, in a departure from standard modelling techniques utilized for planar parallel mechanisms, it is demonstrated that since the translational axes of the manipulator are driven by DC motors through industry standard ball screws, the nonlinear dynamics and coupling effects of the nonlinear dynamics of the manipulator are greatly reduced by a very large effective gear ratio factor, in this case, 1.097 xlO6. The dynamics of the driving motors thus become the dominant dynamics in the system. Hence, the dynamics of the entire system can be approximated as a set of three identical linear dynamic equations, each of which represents the dynamics of one kinematic chain, with constraints representing the coupling of these axes. Then a robust closed-loop controller designed with a Convex Integrated Design (CID) method is determined, such that multiple closed-loop performance specifications, together with a robustness specification, are simultaneously satisfied. The robustness of the closed-loop controller thus guarantees that the controller, although determined based on a simplified linear model, performs as expected on the practical system, i.e., the manipulator, hence results in satisfactory closed-loop performance. Both simulation and experiments conducted demonstrate that the multiple simultaneous closed-loop performance specifications are satisfied thus validating the simplified modeling strategy and verifying the effectiveness of the control design approach.

A high-speed, high-accuracy linear positioning system with application to electronic manufacturing is designed to satisfy four simultaneous closed-loop specifications by integrated design approach. Utilizing the three-stage convex integrated design (CID) method proposed here, the mechanical structure parameters of the linear positioning system, both the control gains and controller structure of a closed-loop controller, are uniquely determined, so that improved closed-loop system performance beyond that required by the n pre-specified closed-loop performance specifications, is acquired. The CID method is especially useful when the design problem has a small set of design variables. Experimental results show that all four performance specifications are simultaneously satisfied, which verify the effectiveness of this design.