Embedded wireless networks have largely focused on open-loop sensing and monitoring. To address actuation in closed-loop wireless control systems there is a strong need to re-think the communication architectures and ...
详细信息
ISBN:
(纸本)9781424444465
Embedded wireless networks have largely focused on open-loop sensing and monitoring. To address actuation in closed-loop wireless control systems there is a strong need to re-think the communication architectures and protocols for reliability, coordination and control. As the links, nodes and topology of wireless systems are inherently unreliable, such time-critical and safety-critical applications require programming abstractions where the tasks are assigned to the sensors, actuators and controllers as a single component rather than statically mapping a set of tasks to a specific physical node at design time. To this end, we introduce the Embedded Virtual Machine (EVM), a powerful and flexible programming abstraction where virtual components and their properties are maintained across node boundaries. In the context of process and discrete control, an EVM is the distributed runtime system that dynamically selects primary-backup sets of controllers to guarantee QoS given spatial and temporal constraints of the underlying wireless network. The EVM architecture defines explicit mechanisms for control, data and fault communication within the virtual component. EVM-based algorithms introduce new capabilities such as predictable outcomes and provably minimal graceful degradation during sensor/actuator failure, adaptation to mode changes and runtime optimization of resource consumption. Through the design of a natural gas process plant hardware-in-loop simulation we aim to demonstrate the preliminary capabilities of EVM-based wireless networks.
A signal processing approach is proposed to jointly filter and fuse spatially-indexed measurements captured from many vehicles. It is assumed that these measurements are corrupted by both sensor noise and GPS position...
详细信息
Human beings do not have well defined shapes neither well defined behaviors. In dense outdoor environments, they are as a consequence hard to detect and algorithms based on a single sensor tend to produce lot of wrong...
详细信息
Human beings do not have well defined shapes neither well defined behaviors. In dense outdoor environments, they are as a consequence hard to detect and algorithms based on a single sensor tend to produce lot of wrong detections. Moreover, many applications require algorithms that work very fast on CPU limited mobile architectures while remaining able to detect, track and classify objects as people with a very high precision. We present an algorithm based on the contribution of a range finder and a vision based algorithm that addresses these three constraints: efficiency, velocity and robustness and that we believe is scalable to a large variety of applications.
Distributed information fusion is an active area of research; however, fusion in the large, dynamic, unpredictable, and power-scarce setting of wireless sensor network (WSN) requires more than just distributed fusion ...
详细信息
Distributed information fusion is an active area of research; however, fusion in the large, dynamic, unpredictable, and power-scarce setting of wireless sensor network (WSN) requires more than just distributed fusion algorithms. Some of the important questions that need to be addressed are dynamic mapping of inference responsibilities to sensor nodes in a distributed manner and cost-effective, fault-tolerant exchange of fusion information. Graphical models provide compact representation of joint probability distributions; they help in drawing inference more efficiently. We propose two graphical models called inference cost network (ICN) and dynamic inference cost network (DICN) that generalize Bayesian networks and dynamic Bayesian networks for truly distributed implementation. We also propose distributed inference algorithms for ICN/DICN that address the unique requirements of information fusion in WSN. We prove correctness of the model and the algorithms and demonstrate that the algorithms are lightweight in terms of computational complexity.
sensor-based smart spaces have been developed to help caring of the elderly. Selection of sensors, layout of smart space, design of fusion algorithms, and knowledge of domain experts are critical to the development of...
详细信息
sensor-based smart spaces have been developed to help caring of the elderly. Selection of sensors, layout of smart space, design of fusion algorithms, and knowledge of domain experts are critical to the development of a useful ICT system for caring the elderly in the institutional facilities. We apply multi-modal sensorfusion technique to improve the confidence level of our system, and leverage the knowledge of domain experts, which is stored in ontology database, to detect the sequence of events that can lead to dangerous situations.
Vehicle classification is an important task for various traffic monitoring applications. This paper investigates the capabilities of acoustic feature generation for vehicle classification. Six temporal and spectral fe...
详细信息
Vehicle classification is an important task for various traffic monitoring applications. This paper investigates the capabilities of acoustic feature generation for vehicle classification. Six temporal and spectral features are extracted from the audio recordings. Six different classification algorithms are compared using the extracted features. We focus on a single sensor setting to keep the computational effort low and evaluate its classification accuracy and real-time performance. The experimental evaluation is performed on our embedded platform using recorded data of about 150 vehicles. The results are applied in our ongoing research on fusing video, laser and acoustic data for real-time traffic monitoring.
Recent advancement in sensor networks provides a platform for applications that requires in-network data fusion and parallel algorithms. However, processing data in parallel while propagating at low latency is very ch...
详细信息
Recent advancement in sensor networks provides a platform for applications that requires in-network data fusion and parallel algorithms. However, processing data in parallel while propagating at low latency is very challenging. Also, implementation of these algorithms is limited by various constraints including energy, computation costs and complex network topology. In this paper, a statistical graphical model based algorithm is developed for in-network processing, which can be applied to tracking problems in the sensor networks. This algorithm represents the complex topology of a sensor network with a simple clique tree. It further utilizes the message passing algorithms to effectively make accurate inferences about the target location. The simulation shows that the algorithm can accurately track the target in a large scale random distributed sensor field with low complexity and low cost. The algorithm is also proved to be robust, as the simulation random disabled some sensors during the tracking phase.
Artificial neural networks (ANNs), support vector machines (SVMs) and naive Bayes classifiers (NBCs) are common tools for multisensor data fusionapplications. In this paper ANN, SVM and NBC are applied to embedded re...
详细信息
Artificial neural networks (ANNs), support vector machines (SVMs) and naive Bayes classifiers (NBCs) are common tools for multisensor data fusionapplications. In this paper ANN, SVM and NBC are applied to embedded realtime feature fusion and compared to different algorithms concerning classification execution time as well as classification rate. These algorithms are implemented on our three-layered multisensor data fusion architecture and applied to traffic monitoring where we are focusing on fusing data originating from distributed acoustic, image and laser sensors for vehicle classification and tracking. The evaluation of the algorithms is performed on our embedded platform and has shown promising results concerning realtime classification execution time and classification rate.
The proceedings contain 44 papers. The special focus in this conference is on General Problems of H-CSI, Disabled Persons Helping, Medical H-CSI applications, Psychological and Linguistic Aspects of H-CSI, Robots, Tra...
ISBN:
(纸本)9783642032011
The proceedings contain 44 papers. The special focus in this conference is on General Problems of H-CSI, Disabled Persons Helping, Medical H-CSI applications, Psychological and Linguistic Aspects of H-CSI, Robots, Training Systems and Various H-CSI applications. The topics include: From research on the decision-making in ill-structured situation control and the problem of risks;emulating the perceptual system of the brain for the purpose of sensorfusion;knowledge acquisition in conceptual ontological artificial intelligence system;a dialogue-based interaction system for human-computer interfaces;image annotation based on semantic rules;eye-mouse for disabled;eye-blink controlled human-computer interface for the disabled;machine learning of melanocytic skin lesion images;an application of detection function for the eye blinking detection;emotion recognition from facial expression using neural networks;emotion eliciting and decision making by psychodynamic appraisal mechanism;toward daydreaming machines;VoiceXML platform for minority languages;a web-oriented Java3D talking head;from research on the virtual reality installation;biologically reasoned point-of-interest image compression for mobile robots;graphical human-machine interface for QB systems;visualization of two parameters in a three-dimensional environment;enterprsise ontology for knowledge-based system;a new and improved skin detection method using mixed color space;a formal model for supporting the adaptive access to virtual museums;3D molecular interactive modeling and diagnosis based on fuzzy IF-THEN rules and genetic algorithms.
algorithms to perform distributed command and control functions in ground based air defense systems of systems are presented and analyzed. In previous research we presented the benefits of using swarm architectures fo...
详细信息
algorithms to perform distributed command and control functions in ground based air defense systems of systems are presented and analyzed. In previous research we presented the benefits of using swarm architectures for this type of application in terms of no single point of failure, lower detectability and higher scalability. Here we propose some free market distributed algorithms based on the principles of negotiation and competition among the swarm of agents performing air defense missions. In our research, parameter optimization as well as experimental results in tactical scenarios are obtained through simulation.
暂无评论