The Experts below are selected from a list of 438102 Experts worldwide ranked by ideXlab platform
James S Albus - One of the best experts on this subject based on the ideXlab platform.
-
4d rcs a reference Model Architecture for intelligent unmanned ground vehicles
Proceedings of SPIE, 2002Co-Authors: James S AlbusAbstract:4D/RCS consists of a multi-layered multi-resolutional hierarchy of computational nodes each containing elements of sensory processing (SP), world Modeling (WM), value judgment (VJ), and behavior generation (BG). At the lower levels, these elements generate goal-seeking reactive behavior. At higher levels, they enable goal-defining deliberative behavior. At low levels, range in space and time is short and resolution is high. At high levels, distance and time are long and resolution is low. This enables high-precision fast-action response over short intervals of time and space at low levels, while long-range plans and abstract concepts are being formulated over broad regions of time and space at high levels. 4D/RCS closes feedback loops at every level. SP processes focus attention (i.e., window regions of space or time), group (i.e., segment regions into entities), compute entity attributes, estimate entity state, and assign entities to classes at every level. WM processes maintain a rich and dynamic database of knowledge about the world in the form of images, maps, entities, events, and relationships at every level. Other WM processes use that knowledge to generate estimates and predictions that support perception, reasoning, and planning at every level. 4D/RCS was developed for the Army Research Laboratory Demo III program. To date, only the lower levels of the 4D/RCS Architecture have been fully implemented, but the results have been extremely positive. It seems clear that the theoretical basis of 4D/RCS is sound and the Architecture is capable of being extended to support much higher levels of performance.
-
4 d rcs reference Model Architecture for unmanned ground vehicles
International Conference on Robotics and Automation, 2000Co-Authors: James S AlbusAbstract:4D/RCS is the reference Model Architecture currently being developed for the Demo III Experimental Unmanned Vehicle program. 4D/RCS integrates the NIST (National Institute of Standards and Technology) RCS (real-time control system) with the German (Universitat der Bundeswehr Munchen) VaMoRs 4D approach (3 dimensions+time) to dynamic machine vision. The 4D/RCS Architecture consists of a hierarchy of computational nodes each of which contains behavior generation (BG), world Modeling (WM), sensory processing (SP), and value judgement (VJ) processes. Each node also contains a knowledge database (KD) and an operator interface. These computational nodes are arranged such that the BG processes represent organizational units within a command and control hierarchy.
-
4-D/RCS Reference Model Architecture for Unmanned Ground Vehicles
1999Co-Authors: James S AlbusAbstract:4-D/RCS is the reference Model Architecture currently being developed for the Demo m Experimental Unmanned Vehicle program. 4-D/RCS integrates the NIST (National Institute of Standards and Technology) RCS (Real-time Control System) with the German (Universitat der Bundeswehr Munchen) VaMoRs 4-D approach to dynamic machine vision. The 4-D/RCS Architecture consists of a hierarchy of computational nodes each of which contains behavior generation (BG), world Modeling (WM), sensory processing (SP), and value judgment (VJ) processes. Each node also contains a knowledge database (KD) and an operator interface. These computational nodes are arranged such that the BG processes represent organizational units within a command and control hierarchy.
Andrew Harrison - One of the best experts on this subject based on the ideXlab platform.
-
a super simple life cycle cost estimation Model with minimum data requirement
Social Science Research Network, 2020Co-Authors: Maryam Farsi, John Ahmet Erkoyuncu, Andrew HarrisonAbstract:Life-cycle costing is a practical approach to estimate the total cost of ownership in product-service systems. In high-value manufacturing sectors, due to the complication of overhaul invoices, shop visits, repair and maintenance interventions, identifying service cost reduction opportunities can be complex. Moreover, quantifying the impact of key cost drivers on the total cost is challenging due to the lack of complete historical data and high level of uncertainties within the service cost data. To address these challenges, a super simple life-cycle cost Model Architecture is presented. A set of minimum data requirements is identified for the development of the presented cost Model. The Model Architecture comprises of life-cycle cost breakdown structure and work breakdown structure to specify the cost drivers, unit costs and their frequencies. A bottom-up activity-based cost estimation approach is implemented to calculate the total life-cycle cost of a product. The way that the minimum data requirement is applied to the cost estimation structure is explained. In addition, the minimum data is employed to perform a deterministic sensitivity analysis to compare the relative impact of the Model input on the total cost. The Monte-Carlo simulation is performed for estimating the uncertainty propagation on the total life-cycle cost. The presented Model Architecture simplifies life-cycle cost estimations and service control decisions for maintenance, repair, and overhaul actions. A case study of life-cycle cost estimation in the machine tool industry is considered for testing the validity of the cost Model Architecture.
Radoslaw Martin Cichy - One of the best experts on this subject based on the ideXlab platform.
-
comparison of deep neural networks to spatio temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence
Scientific Reports, 2016Co-Authors: Radoslaw Martin Cichy, Aditya Khosla, Dimitrios Pantazis, Antonio Torralba, Aude OlivaAbstract:The complex multi-stage Architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while Model Architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain.
Maryam Farsi - One of the best experts on this subject based on the ideXlab platform.
-
a super simple life cycle cost estimation Model with minimum data requirement
Social Science Research Network, 2020Co-Authors: Maryam Farsi, John Ahmet Erkoyuncu, Andrew HarrisonAbstract:Life-cycle costing is a practical approach to estimate the total cost of ownership in product-service systems. In high-value manufacturing sectors, due to the complication of overhaul invoices, shop visits, repair and maintenance interventions, identifying service cost reduction opportunities can be complex. Moreover, quantifying the impact of key cost drivers on the total cost is challenging due to the lack of complete historical data and high level of uncertainties within the service cost data. To address these challenges, a super simple life-cycle cost Model Architecture is presented. A set of minimum data requirements is identified for the development of the presented cost Model. The Model Architecture comprises of life-cycle cost breakdown structure and work breakdown structure to specify the cost drivers, unit costs and their frequencies. A bottom-up activity-based cost estimation approach is implemented to calculate the total life-cycle cost of a product. The way that the minimum data requirement is applied to the cost estimation structure is explained. In addition, the minimum data is employed to perform a deterministic sensitivity analysis to compare the relative impact of the Model input on the total cost. The Monte-Carlo simulation is performed for estimating the uncertainty propagation on the total life-cycle cost. The presented Model Architecture simplifies life-cycle cost estimations and service control decisions for maintenance, repair, and overhaul actions. A case study of life-cycle cost estimation in the machine tool industry is considered for testing the validity of the cost Model Architecture.
Jiawei Zhang - One of the best experts on this subject based on the ideXlab platform.
-
get rid of suspended animation problem deep diffusive neural network on graph semi supervised classification
arXiv: Learning, 2020Co-Authors: Jiawei ZhangAbstract:Existing graph neural networks may suffer from the "suspended animation problem" when the Model Architecture goes deep. Meanwhile, for some graph learning scenarios, e.g., nodes with text/image attributes or graphs with long-distance node correlations, deep graph neural networks will be necessary for effective graph representation learning. In this paper, we propose a new graph neural network, namely DIFNET (Graph Diffusive Neural Network), for graph representation learning and node classification. DIFNET utilizes both neural gates and graph residual learning for node hidden state Modeling, and includes an attention mechanism for node neighborhood information diffusion. Extensive experiments will be done in this paper to compare DIFNET against several state-of-the-art graph neural network Models. The experimental results can illustrate both the learning performance advantages and effectiveness of DIFNET, especially in addressing the "suspended animation problem".