The ability to perceive and comprehend a traffic situation and to estimate the state of the vehicles and road-users in the surrounding of the ego-vehicle is known as situational awareness. Situational awareness for a ...
详细信息
Neuroimaging plays an significant role in diagnosing and pathological study of brain diseases. Considering that both functional and structural abnormalities may lead to brain dis-eases and disorders, single modal neur...
详细信息
ISBN:
(数字)9781665468190
ISBN:
(纸本)9781665468206
Neuroimaging plays an significant role in diagnosing and pathological study of brain diseases. Considering that both functional and structural abnormalities may lead to brain dis-eases and disorders, single modal neuroimaging approach may not fully characterize brain activities and working modes. Fusion of multimodal neuroimaging data is expected to provide more comprehensive characterization of brain diseases, given that the different modalities contain more complementary information. Recently, Graph Convolutional Networks (GCNs) is shown to have powerful capacity in representation learning for graph-structure data, which is considered to integrate both graph se-mantic structure and node information. Therefore, in this paper, we propose the Weighted Graph AutoEncoder (WGAE), a GCN- driven multimodal fusion model, to learn the combinational latent node representation of fMRI and DTI neuroimaging data, which are used as node features and graph structure respectively in the graph in unsupervised manner. Experimental results on two real-world datasets show the superiority of the proposed model over other existing single-modal or multi-modal methods in learning representations for disease prediction as the downstream task. Furthermore, ablation experiments also show the collaborative contribution of multimodal neuroimaging fusion in the proposed model, and also show the feasibility of assessing the respective importance of the two modalities during the disease prediction.
This paper studies the distributed bandit convex optimization problem with time-varying inequality constraints, where the goal is to minimize network regret and cumulative constraint violation. To calculate network cu...
详细信息
Abstract We apply nonparametric techniques to identify nonlinear dynamic block-oriented systems of Hammerstein type. Hammerstein system consists of a memoryless nonlinear system followed by a dynamic, linear system. W...
Abstract We apply nonparametric techniques to identify nonlinear dynamic block-oriented systems of Hammerstein type. Hammerstein system consists of a memoryless nonlinear system followed by a dynamic, linear system. We introduce identification algorithms based on input-output observations for both systems and study their convergence and the rates. The performance of identification algorithms is validated in simulation studies. We apply Hammerstein system identification algorithms to identification of nonlinearities in a flexible robot manipulator.
This paper presents a new real-time architecture for motion control of industrial robots. The new control system obtained has two main advantages: first it provides a total open control architecture and the second adv...
详细信息
This paper presents a new real-time architecture for motion control of industrial robots. The new control system obtained has two main advantages: first it provides a total open control architecture and the second advantage is the simplicity and the interactivity of the platform developed. Experimental evaluation of a passivity-based control scheme shows the benefits of the architecture which is unique in the sense that open and advanced control can be combined with built-in safety logic as required in industrial applications.
One of challenges in GIS Web service is mass GIS data storage and processing. There are at least three obstacles that oppose dealing with this challenge: the mismatch between the frequent requirement of concurrent tas...
详细信息
One of challenges in GIS Web service is mass GIS data storage and processing. There are at least three obstacles that oppose dealing with this challenge: the mismatch between the frequent requirement of concurrent tasks for accessing data in GIS Web service and the poor performance of conventional storage mechanism such as relational databases;the insufficiency of relational databases to manage complex data types in GIS Web service;the horizontal scalability of storage for non-stop GIS Web service evolution. This paper proposes a distributed cached storage solution, as the mixture of MongoDB storage and Memcached cache, for GIS Web service. Both techniques are closely related to NoSQL that is a class of database management system identified by its non-adherence to the widely used relational database management system (RDBMS) model. A concise case that facilitates a better understanding of this work indicates its feasibility.
This study proposes a virtual-metrology-based control system for conjecturing machining states and suggesting controller operating modes. The two machining state conjecture models were integrated to validate the virtu...
详细信息
This study proposes a virtual-metrology-based control system for conjecturing machining states and suggesting controller operating modes. The two machining state conjecture models were integrated to validate the virtual metrology results using a dual-stage featuring scheme and a two-phase modeling procedure. The featuring scheme is to extract significant features from collecting data for modeling and to minimize the modeling features by using a genetic algorithm. The modeling procedure adopts two quality indicators to evaluate model effectiveness. Two case studies indicate that the system achieves a mean MAPE of precision estimation less than 8.5% and suggests the controller with operating modes in 1 s.
Automatic generation control (AGC) is one of the most profitable ancillary services of power systems. The main goal of AGC is to maintain zero steady state errors for frequency deviation and good tracking of load dema...
详细信息
Automatic generation control (AGC) is one of the most profitable ancillary services of power systems. The main goal of AGC is to maintain zero steady state errors for frequency deviation and good tracking of load demands in a power system. However, the system performance is often constrained by governor dead band nonlinearity. This paper addresses a sliding mode controller for a single area power system with governor dead band. Two RBF neural networks are employed in this presented method, where one network is designed to compensate the dead band and the other network is designed to approximate the output of the dead band. The weight update formulas of the two RBF networks are derived from Lyapunov direct method. Finally, simulation results show the feasibility of the presented method for the AGC problem of a single area power system.
Every year the fire disaster always causes a lot of casualties and property damage. Many researchers are involved in the study of related disaster prevention. Early warning systems and stable fire can significantly re...
详细信息
Every year the fire disaster always causes a lot of casualties and property damage. Many researchers are involved in the study of related disaster prevention. Early warning systems and stable fire can significantly reduce the damage caused by fire. Many existing image-based early warning systems can perform well in a particular field. In this paper, we propose a general framework that can be applied in most realistic environments. The proposed system is based on a block-based feature extraction method, which analyses local information in separate regions leading to a reduction in computing data. Local features of fire block are extracted from the detailed characteristics of fire objects, which include fire color, fire source immobility, and disorder. Each local feature has high detection rate and filter out different false-positive cases. Global analysis with fire texture and non-moving properties are applied to further reduce false alarm rate. The proposed system is composed of algorithms with low computation. Through a series of experiments, it can be observed that Experimental results show that the proposed system has higher detection rate and low false alarm rate under various environment.
暂无评论