Publications

To respond to the rapid growth of shipping container throughput, terminals urgently need to improve the efficiency of thier operations and reduce operational costs through automation and intellectualization upgrades, thereby improving service levels and enhancing market competitiveness. Due to the advantages of reliable transportation, efficient operation, and environmental friendliness, AGV-based automated container terminal (ACT) has become the development trend of container terminals. To help ACT improve its operational management capabilities, plenty of scholars have explored the transportation system of ACT. Through the analysis of operational management issues, the paper defines the four main research topics in vehicle transportation of the ACT including equipment scheduling, path planning, exception handling, and vehicle management. Then, in each topic, the works in the recent 25 years are summarized and several research opportunities for possible follow-up research directions in different fields are proposed. We expect our survey could not only provide references for more scholars on the research of operation and management of terminals, but also provide guidance for system evaluation and improvement for terminal system engineers and operation managers.

Abstract Flexible strain monitoring of hand and joint muscle movement is recognized as an effective method for the diagnosis and rehabilitation of neurological diseases such as stroke and Parkinson's disease. However, balancing high sensitivity and large strain, improving wearing comfort, and solving the separation of diagnosis and treatment are important challenges for further building tele‐healthcare systems. Herein, a hydrogel‐based optical waveguide stretchable (HOWS) sensor is proposed in this paper. A double network structure is adopted to allow the HOWS sensor to exhibit high stretchability of the tensile strain up to 600% and sensitivity of 0.685 mV % −1 . Additionally, the flexible smart bionic fabric embedding the HOWS sensor, produced through the warp and weft knitting, significantly enhances wearing comfort. A small circuit board is prepared to enable wireless signal transmission of the designed sensor, thereby improving the daily portability. A speech recognition and human‐machine interaction system, based on sensor signal acquisition, is constructed, and the convolutional neural network algorithm is integrated for disease assessment. By integrating sensing, wireless transmission, and artificial intelligence (AI), a smart tele‐healthcare system based on HOWS sensors is demonstrated to hold great potential for early warning and rehabilitation monitoring of neurological diseases.

Cable-driven systems are widely used in robotics due to their lightweight, low inertia, and high adaptability. However, existing actuation methods face challenges in compactness, safety, and modularity. This article presents the development and evaluation of a safety-enhanced modular magnetorheological (MR) actuation module for cable-driven systems. The proposed module employs MR fluid to achieve inherent safety by decoupling input and output inertia while enabling controllable torque transmission. The unit design supports dual-cable output and allows rapid reconfiguration via belt coupling for different application requirements. The principle of module driving and the optimization process of magnetorheological actuator is introduced in detail. Experimental results demonstrate that the actuation module provides reliable torque output and decoupling protection.

During the past decade, human activity recognition ( HAR ) using wearable sensors has become a new research hot spot due to its extensive use in various application domains such as healthcare, fitness, smart homes, and eldercare. Deep neural networks, especially convolutional neural networks ( CNNs ), have gained a lot of attention in HAR scenario. Despite exceptional performance, CNNs with heavy overhead is not the best option for HAR task due to the limitation of computing resource on embedded devices. As far as we know, there are many invalid filters in CNN that contribute very little to output. Simply pruning these invalid filters could effectively accelerate CNNs , but it inevitably hurts performance. In this article, we first propose a novel CNN for HAR that uses filter activation. In comparison with filter pruning that is motivated for efficient consideration, filter activation aims to activate these invalid filters from an accuracy boosting perspective. We perform extensive experiments on several public HAR datasets, namely, UCI-HAR ( UCI ), OPPORTUNITY ( OPPO ), UniMiB-SHAR ( Uni ), PAMAP2 ( PAM2 ), WISDM ( WIS ), and USC-HAD ( USC ), which show the superiority of the proposed method against existing state-of-the-art ( SOTA ) approaches. Ablation studies are conducted to analyze its internal mechanism. Finally, the inference speed and power consumption are evaluated on an embedded Raspberry Pi Model 3 B plus platform.

This paper presents the design and implementation of a wireless-controllable power outlet system for home automation networks. The proposed power outlet module integrates a ZigBee radio into its architecture. It acts as an actuator node in the home automation networks for remote control operations. A prototype of the power outlet module following the proposed architecture has been implemented. A testbed of a simple home automation network for validating the basic functions of the power outlet module has also been created. Results of the demonstration experiment show that the proposed power outlet module enables easy and flexible control of various home appliances with little infrastructure. It helps us add more intelligence into the home environments rapidly.

ABSTRACT Electrical percolation of carbon black (CB) and carbon nanotubes (CNTs) filled into silicone rubber (SR) is analyzed by the three‐dimensional (3D) Monte Carlo simulation. First, the 3D models and simulation parameters of CB and CNTs are researched to narrow the deviation between simulation and experimental results of CB/SR and CNTs/SR. The degree of agglomeration is the most important parameter in simulation for CB. The 3D model of CNTs is the most important factor in simulation for CNTs. Then, the 3D Monte Carlo simulation for CB/CNTs/SR is developed based on the optimized 3D models and parameters of CB and CNTs. The results yielded by the simulation with optimized parameters are similar to the experiments and synergistic conductive effect of two hybrid fillers in nanocomposites exists. This work has demonstrated that the quantification of the electrical percolation of two hybrid fillers in nanocomposites by Monte Carlo simulation is feasible. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2019 , 136 , 48222.

Imbalanced data is a major challenge in classification tasks. Most classification algorithms tend to be biased toward the samples in the majority class but fail to classify the samples in the minority class. Recently, ensemble learning, as a promising method, has been rapidly developed in solving highly imbalanced classification. However, the design of the base classifier for the ensemble is still an open question because the optimization problem of the base classifier is gradientless. In this study, the evolutionary algorithm (EA) technique is adopted to solve a wide range of optimization design problems in highly imbalanced classification without gradient information. A novel EA-based classifier optimization design method is proposed to optimize the design of multiple base classifiers automatically for the ensemble. In particular, an EA method with a neural network (NN) as the base classifier termed NN ensemble with EA (NNEAE) is developed for highly imbalanced classification. To verify the performance of NNEAE, extensive experiments are designed for testing. Results illustrate that NNEAE outperforms other compared methods.

Federated learning has recently been an emerging learning paradigm for training deep neural networks for activity recognition on resource-limited portable devices such as smartphones. However, prior most works typically focus on training a single global model while ignoring potential intrinsic relationship between clients, which cannot generalize well in heterogeneous federated human activity recognition (HAR) scenario. To address this issue, this article proposes an alternative via attention-based pairwise collaborations, where each client can collaborate with other similar clients to generate a stronger personalized model per client-specific objectives. Different from previous most works, instead of aggregating a single model, we adopt an attention method to calculate an optimal weighted model combination for each client, based on figuring out to what extent a client could benefit from other clients. Extensive experiments on four public HAR benchmark datasets with non-IID data setting show that our method significantly outperforms several popular state-of-the-art federated learning baselines in terms of overall accuracy while saves more than 50% communication overhead. Several ablation analyses are conducted to provide a deeper insight into the proposed algorithm in federated learning scenario. In particular, we analyze how the pairwise collaborations iteratively encourage similar clients to have stronger collaboration than inconsistent clients with heterogeneous activity data. An actual implementation is evaluated in a network of resource-limited Internet-of-Things (IoT) devices.

To ensure the performance of the dexterous manipulation, this paper presents the design of a mechanical-sensor integrated finger for prosthetic hand. The grab force and the contact position between the object and the prosthetic hand's finger can be captured by the designed finger. First, the mechanism design and analysis of the measurement theory are described in detail. Then, we introduce the measurement circuit and analyze the measurement error. Based on the analysis of the measurement theory and measurement error, the method of least-square is employed to calibrate the output of the designed finger. Prosthetic hand grasping is also conducted to verify the validity of the designed finger. The experimental result shows that the root-mean-square(RMS) of the force measurement error is 0.18N, and the RMS of the contact position measurement error is 0.91mm.