Abstract: The increasing incorporation of Graphics Processing Units (GPUs) as accelerators has been one of the forefront High Performance Computing (HPC) trends and provides unprecedented performance; however, the prevalent adoption of the Single-Program Multiple-Data (SPMD) programming model brings with it challenges of resource underutilization. In other words, under SPMD, every CPU needs GPU capability available to it. However, since CPUs generally outnumber GPUs, the asymmetric resource distribution gives rise to overall computing resource underutilization. In this paper, we propose to efficiently share the GPU under SPMD and formally define a series of GPU sharing scenarios. We provide performance-modeling analysis for each sharing scenario with accurate experimentation validation. With the modeling basis, we further conduct experimental studies to explore potential GPU sharing efficiency improvements from multiple perspectives. Both further theoretical and experimental GPU sharing performance analysis and results are presented. Our results not only demonstrate the significant performance gain for SPMD programs with the proposed efficient GPU sharing, but also the further improved sharing efficiency with the optimization techniques based on our accurate modeling.
Abstract: A Wireless Sensor Network (WSN) is a collection of low-cost, low-power and large-scale wireless sensor nodes. Routing protocols are an important topic in WSN. Every sensor node should use a proper mechanism to transmit the generated packets to its destination, usually a base station. In previous works, routing protocols use the global information of the network that causes the redundant packets to be increased. Moreover, it leads to an increase in the network traffic, to a decrease in the delivery ratio of data packets, and to a reduction in network life. In this paper, we propose a new inferential routing protocol called SFRRP (Static Three-Dimensional Fuzzy Routing based on the Receiving Probability). The proposed protocol solves the above mentioned problems considerably. The data packets are transmitted by hop-to-hop delivery to the base station. It uses a fuzzy procedure to transmit the sensed data or the buffered data packets to one of the neighbors called selected node. In the proposed fuzzy system, the distance and number of neighbors are input variables, while the receiving probability is the output variable. SFRRP just uses the local neighborhood information to forward the packets and is not needed by any redundant packet for route discovery. The proposed protocol has some advantages such as a high delivery ratio, less delay time, high network life, and less network traffic. The performance of the proposed protocol surpasses the performance of the Flooding routing protocol in terms of delivery ratio, delay time and network lifetime.
Abstract: In this paper, we introduce the concept of a Large-Scale Intelligent Environment (LSIE) and provide an introduction to the use of bigraphs as a formal method for description and modelling. We then propose our MacroIE model as a solution to the LSIE problem and describe how that model may be implemented to achieve a continuity-of-experience to end users as they travel from place-to-place (a technology we call FollowMe). Our initial experiments with these implementations are presented, providing some valuable insights and promise for future refinement towards real-world deployment.
Abstract: This review article surveys extensively the current progresses made toward video-based human activity recognition. Three aspects for human activity recognition are addressed including core technology, human activity recognition systems, and applications from low-level to high-level representation. In the core technology, three critical processing stages are thoroughly discussed mainly: human object segmentation, feature extraction and representation, activity detection and classification algorithms. In the human activity recognition systems, three main types are mentioned, including single person activity recognition, multiple people interaction and crowd behavior, and abnormal activity recognition. Finally the domains of applications are discussed in detail, specifically, on surveillance environments, entertainment environments and healthcare systems. Our survey, which aims to provide a comprehensive state-of-the-art review of the field, also addresses several challenges associated with these systems and applications. Moreover, in this survey, various applications are discussed in great detail, specifically, a survey on the applications in healthcare monitoring systems.
Abstract: An artificial intelligence system, designed for operations in a real-world environment faces a nearly infinite set of possible performance scenarios. Designers and developers, thus, face the challenge of validating proper performance across both foreseen and unforeseen conditions, particularly when the artificial intelligence is controlling a robot that will be operating in close proximity, or may represent a danger, to humans. While the manual creation of test cases allows limited testing (perhaps ensuring that a set of foreseeable conditions trigger an appropriate response), this may be insufficient to fully characterize and validate safe system performance. An approach to validating the performance of an artificial intelligence system using a simple artificial intelligence test case producer (AITCP) is presented. The AITCP allows the creation and simulation of prospective operating scenarios at a rate far exceeding that possible by human testers. Four scenarios for testing an autonomous navigation control system are presented: single actor in two-dimensional space, multiple actors in two-dimensional space, single actor in three-dimensional space, and multiple actors in three-dimensional space. The utility of using the AITCP is compared to that of human testers in each of these scenarios.
Abstract: Dynamic and heterogeneous smart spaces cause challenges for security because it is impossible to anticipate all the possible changes at design-time. Self-adaptive security is an applicable solution for this challenge. This paper presents an architectural approach for security adaptation in smart spaces. The approach combines an adaptation loop, Information Security Measuring Ontology (ISMO) and a smart space security-control model. The adaptation loop includes phases to monitor, analyze, plan and execute changes in the smart space. The ISMO offers input knowledge for the adaptation loop and the security-control model enforces dynamic access control policies. The approach is novel because it defines the whole adaptation loop and knowledge required in each phase of the adaptation. The contributions are validated as a part of the smart space pilot implementation. The approach offers reusable and extensible means to achieve adaptive security in smart spaces and up-to-date access control for devices that appear in the space. Hence, the approach supports the work of smart space application developers.