Abstract: Supernumerary robotic limbs (SRLs) are a new type of wearable human auxiliary equipment, which is currently a hot research topic in the world. SRLs have broad applications in many fields, and will provide a reference and technical support for the realization of human-robot collaboration and integration, while playing an important role in improving social security and public services. In this paper, representative SRLs are summarized from the aspects of related literature analysis, research status, ontology structure design, control and driving, sensing and perception, and application fields. This paper also analyzes and summarizes the current technical challenges faced by SRLs, and reviews development progress and key technologies, thus giving a prospect of future technical development trends.
Abstract: The supervisory control problem for discrete event system (DES) under control involves identifying the supervisor, if one exists, which, when synchronously composed with the DES, results in a system that conforms to the control specification. In this context, we consider a non-deterministic DES under complete observation and control specification expressed in action-based propositional μ-calculus. The key to our solution is the process of quotienting the control specification against the plan resulting in a new μ-calculus formula such that a model for the formula is the supervisor. Thus the task of control synthesis is reduced a problem of μ-calculus satisfiability. In contrast to the existing μ-calculus quotienting-based techniques that are developed in deterministic setting, our quotienting rules can handle nondeterminism in the plant models. Another distinguishing feature of our technique is that while existing techniques use a separate μ-calculus formula to describe the controllability constraint (that uncontrollable events of plants are never disabled by a supervisor), we absorb this constraint as part of quotienting which allows us to directly capture more general state-dependent controllability constraints. Finally, we develop a tableau-based technique for verifying satisfiability of quotiented formula and model generation. The runtime for the technique is exponential in terms of the size of the plan and the control specification. A better complexity result that is polynomial to plant size and exponential to specification size is obtained when the controllability property is state-independent. A prototype implementation in a tabled logic programming language as well as some experimental results are presented.
Abstract: This paper addresses the co-design problem of decentralized dynamic event-triggered communication and active suspension control for an in-wheel motor driven electric vehicle equipped with a dynamic damper. The main objective is to simultaneously improve the desired suspension performance caused by various road disturbances and alleviate the network resource utilization for the concerned in-vehicle networked suspension system. First, a T-S fuzzy active suspension model of an electric vehicle under dynamic damping is established. Second, a novel decentralized dynamic event-triggered communication mechanism is developed to regulate each sensor’s data transmissions such that sampled data packets on each sensor are scheduled in an independent manner. In contrast to the traditional static triggering mechanisms, a key feature of the proposed mechanism is that the threshold parameter in the event trigger is adjusted adaptively over time to reduce the network resources occupancy. Third, co-design criteria for the desired event-triggered fuzzy controller and dynamic triggering mechanisms are derived. Finally, comprehensive comparative simulation studies of a 3-degrees-of-freedom quarter suspension model are provided under both bump road disturbance and ISO-2631 classified random road disturbance to validate the effectiveness of the proposed co-design approach. It is shown that ride comfort can be greatly improved in either road disturbance case and the suspension deflection, dynamic tyre load and actuator control input are all kept below the prescribed maximum allowable limits, while simultaneously maintaining desirable communication efficiency.
Abstract: Energy consumption prediction of a CNC machin- ing process is important for energy efficiency optimization strategies. To improve the generalization abilities, more and more parameters are acquired for energy prediction modeling. While the data collected from workshops may be incomplete because of misoperation, unstable network connections, and frequent transfers, etc. This work proposes a framework for energy modeling based on incomplete data to address this issue. First, some necessary preliminary operations are used for incomplete data sets. Then, missing values are estimated to generate a new complete data set based on generative adversarial imputation nets (GAIN). Next, the gene expression programming (GEP) algorithm is utilized to train the energy model based on the generated data sets. Finally, we test the predictive accuracy of the obtained model. Computational experiments are designed to investigate the performance of the proposed framework with different rates of missing data. Experimental results demonstrate that even when the missing data rate increases to 30%, the proposed framework can still make efficient predictions, with the corresponding RMSE and MAE 0.903 kJ and 0.739 kJ, respectively.
Abstract: This paper aims to solve the robust iterative learning control (ILC) problems for nonlinear time-varying systems in the presence of nonrepetitive uncertainties. A new optimization-based method is proposed to design and analyze adaptive ILC, for which robust convergence analysis via a contraction mapping approach is realized by leveraging properties of substochastic matrices. It is shown that robust tracking tasks can be realized for optimization-based adaptive ILC, where the boundedness of system trajectories and estimated parameters can be ensured, regardless of unknown time-varying nonlinearities and nonrepetitive uncertainties. Two simulation tests, especially implemented for an injection molding process, demonstrate the effectiveness of our robust optimization-based ILC results.
Abstract: Stocks that are fundamentally connected with each other tend to move together. Considering such common trends is believed to benefit stock movement forecasting tasks. However, such signals are not trivial to model because the connections among stocks are not physically presented and need to be estimated from volatile data. Motivated by this observation, we propose a framework that incorporates the inter-connection of firms to forecast stock prices. To effectively utilize a large set of fundamental features, we further design a novel pipeline. First, we use variational autoencoder (VAE) to reduce the dimension of stock fundamental information and then cluster stocks into a graph structure (fundamentally clustering). Second, a hybrid model of graph convolutional network and long-short term memory network (GCN-LSTM) with an adjacency graph matrix (learnt from VAE) is proposed for graph-structured stock market forecasting. Experiments on minute-level U.S. stock market data demonstrate that our model effectively captures both spatial and temporal signals and achieves superior improvement over baseline methods. The proposed model is promising for other applications in which there is a possible but hidden spatial dependency to improve time-series prediction.
Abstract: This paper presents a novel medical image registration algorithm named total variation constrained graph-regularization for non-negative matrix factorization (TV-GNMF). The method utilizes non-negative matrix factorization by total variation constraint and graph regularization. The main contributions of our work are the following. First, total variation is incorporated into NMF to control the diffusion speed. The purpose is to denoise in smooth regions and preserve features or details of the data in edge regions by using a diffusion coefficient based on gradient information. Second, we add graph regularization into NMF to reveal intrinsic geometry and structure information of features to enhance the discrimination power. Third, the multiplicative update rules and proof of convergence of the TV-GNMF algorithm are given. Experiments conducted on datasets show that the proposed TV-GNMF method outperforms other state-of-the-art algorithms.
Abstract: For a large-scale palmprint identification system, it is necessary to speed up the identification process to reduce the response time and also to have a high rate of identification accuracy. In this paper, we propose a novel hashing-based technique called orientation field code hashing for fast palmprint identification. By investigating hashing-based algorithms, we first propose a double-orientation encoding method to eliminate the instability of orientation codes and make the orientation codes more reasonable. Secondly, we propose a window-based feature measurement for rapid searching of the target. We explore the influence of parameters related to hashing-based palmprint identification. We have carried out a number of experiments on the Hong Kong PolyU large-scale database and the CASIA palmprint database plus a synthetic database. The results show that on the Hong Kong PolyU large-scale database, the proposed method is about 1.5 times faster than the state-of-the-art ones, while achieves the comparable identification accuracy. On the CASIA database plus the synthetic database, the proposed method also achieves a better performance on identification speed.
Abstract: This paper proposes a novel sampled-data asynchronous fuzzy output feedback control approach for active suspension systems in restricted frequency domain. In order to better investigate uncertain suspension dynamics, the sampled-data Takagi-Sugeno (T-S) fuzzy half-car active suspension (HCAS) system is considered, which is further modelled as a continuous system with an input delay. Firstly, considering that the fuzzy system and the fuzzy controller cannot share the identical premises due to the existence of input delay, a reconstructed method is employed to synchronize the time scales of membership functions between the fuzzy controller and the fuzzy system. Secondly, since external disturbances often belong to a restricted frequency range, a finite frequency control criterion is presented for control synthesis to reduce conservatism. Thirdly, given a full information of state variables is hardly available in practical suspension systems, a two-stage method is proposed to calculate the static output feedback control gains. Moreover, an iterative algorithm is proposed to compute the optimum solution. Finally, numerical simulations verify the effectiveness of the proposed controllers.
Abstract: Predictive models for assessing the risk of developing lung cancers can help identify high-risk individuals with the aim of recommending further screening and early intervention. To facilitate pre-hospital self-assessments, some studies have exploited predictive models trained on non-clinical data (e.g., smoking status and family history). The performance of these models is limited due to not considering clinical data (e.g., blood test and medical imaging results). Deep learning has shown the potential in processing complex data that combine both clinical and non-clinical information. However, predicting lung cancers remains difficult due to the severe lack of positive samples among follow-ups. To tackle this problem, this paper presents a generative-discriminative framework for improving the ability of deep learning models to generalize. According to the proposed framework, two nonlinear generative models, one based on the generative adversarial network and another on the variational autoencoder, are used to synthesize auxiliary positive samples for the training set. Then, several discriminative models, including a deep neural network (DNN), are used to assess the lung cancer risk based on a comprehensive list of risk factors. The framework was evaluated on over 55 000 subjects questioned between January 2014 and December 2017, with 699 subjects being clinically diagnosed with lung cancer between January 2014 and August 2019. According to the results, the best performing predictive model built using the proposed framework was based on DNN. It achieved an average sensitivity of 76.54% and an area under the curve of 69.24% in distinguishing between the cases of lung cancer and normal cases on test sets.
Abstract: Workflow scheduling is a key issue and remains a challenging problem in cloud computing. Faced with the large number of virtual machine (VM) types offered by cloud providers, cloud users need to choose the most appropriate VM type for each task. Multiple task scheduling sequences exist in a workflow application. Different task scheduling sequences have a significant impact on the scheduling performance. It is not easy to determine the most appropriate set of VM types for tasks and the best task scheduling sequence. Besides, the idle time slots on VM instances should be used fully to increase resources’ utilization and save the execution cost of a workflow. This paper considers these three aspects simultaneously and proposes a cloud workflow scheduling approach which combines particle swarm optimization (PSO) and idle time slot-aware rules, to minimize the execution cost of a workflow application under a deadline constraint. A new particle encoding is devised to represent the VM type required by each task and the scheduling sequence of tasks. An idle time slot-aware decoding procedure is proposed to decode a particle into a scheduling solution. To handle tasks’ invalid priorities caused by the randomness of PSO, a repair method is used to repair those priorities to produce valid task scheduling sequences. The proposed approach is compared with state-of-the-art cloud workflow scheduling algorithms. Experiments show that the proposed approach outperforms the comparative algorithms in terms of both of the execution cost and the success rate in meeting the deadline.
Abstract: Robotic intra-operative ultrasound has the potential to improve the conventional practice of diagnosis and procedure guidance that are currently performed manually. Working towards automatic or semi-automatic ultrasound, being able to define ultrasound views and the corresponding probe poses via intelligent approaches become crucial. Based on the concept of parallel system which incorporates the ingredients of artificial systems, computational experiments, and parallel execution, this paper utilized a recent developed robotic trans-esophageal ultrasound system as the study object to explore the method for developing the corresponding virtual environments and present the potential applications of such systems. The proposed virtual system includes the use of 3D slicer as the main workspace and graphic user interface (GUI), Matlab engine to provide robotic control algorithms and customized functions, and PLUS (Public software Library for UltraSound imaging research) toolkit to generate simulated ultrasound images. Detailed implementation methods were presented and the proposed features of the system were explained. Based on this virtual system, example uses and case studies were presented to demonstrate its capabilities when used together with the physical TEE robot. This includes standard view definition and customized view optimization for pre-planning and navigation, as well as robotic control algorithm evaluations to facilitate real-time automatic probe pose adjustments. To conclude, the proposed virtual system would be a powerful tool to facilitate the further developments and clinical uses of the robotic intra-operative ultrasound systems.
IEEE/CAA Journal of Automatica Sinica
JCR Impact Factor 2020: 6.171 Rank：Top 11% (7/93), Category of Automation & Control Systems Quantile: The 1st (SCI Q1)
CiteScore 2020 : 11.2 Rank： Top 5% (Category of Computer Science: Information System) , Top 6% (Category of Control and Systems Engineering), Top 7% (Category of Artificial Intelligence)Quantile: The 1st (Q1)