Design of a high speed router for NOC

The complexity of System on Chip (SoC) is increasing with the scale of ICs, and Network on Chip (NoC) has become one of the most important solutions for SoC communication. As a significant point of NoC, research of routers and routing algorithms is receiving more and more attention from researchers and research institutes. This paper proposes a high-speed router on-chip router, which adopts wormhole switching mechanism, output queuing caching strategy, Credit-based flow control mechanism and Round-Robin arbitration mechanism, and the entire operation of the router is a two-stage flow. The selection of adaptive and deterministic routing algorithms can be done automatically, and finally, the performance parameters are evaluated.

Robust Data-Driven Vehicle Routing with Time Windows

On-time delivery is of utmost importance in today’s urban logistics. However, travel times are uncertain and classical deterministic routing solutions often fail to ensure timely delivery. In this paper, a robust solution that exploits travel times data to determine the best routes for maximal timely delivery is proposed. A new decision criterion is introduced, the service fulfillment risk index (sri), which accounts for both the late arrival probability and its magnitude. Together with Wasserstein distance–based ambiguity in travel times, sri can be evaluated efficiently in closed form. In addition, an exact branch-and-cut approach and a meta-heuristic algorithm are developed to minimize sri with a given travel cost. Simulation studies demonstrate that handling uncertainty improves service punctuality, and that incorporating ambiguity prevents overfitting. Most importantly, sri outperforms the canonical decision criteria of lateness probability and expected lateness duration.

A Framework for Automated Acquisition and Processing of As-Built Data with Autonomous Unmanned Aerial Vehicles

Planning and scheduling in construction heavily depend on current information about the state of construction processes. However, the acquisition process for visual data requires human personnel to take photographs of construction objects. We propose using unmanned aerial vehicle (UAVs) for automated creation of images and point cloud data of particular construction objects. The method extracts locations of objects that require inspection from Four Dimensional Building Information Modelling (4D-BIM). With this information at hand viable flight missions around the known structures of the construction site are computed. During flight, the UAV uses stereo cameras to detect and avoid any obstacles that are not known to the model, for example moving humans or machinery. The combination of pre-computed waypoint missions and reactive avoidance ensures deterministic routing from takeoff to landing and operational safety for humans and machines. During flight, an additional software component compares the captured point cloud data with the model data, enabling automatic per-object completion checking or reconstruction. The prototype is developed in the Robot Operating System (ROS) and evaluated in Software-In-The-Loop (SITL) simulations for the sake of being executable on real UAVs.

An IoT-based Smart Orchard Monitoring System by Employing Wireless Sensor Networks

In this study, an IoT-based smart orchard monitoring is proposed to gather and transmit environment data from a sensor node to a central node for necessary and relevant actuation in order to have good produce at the soonest amount of time. Wireless sensor motes are deployed based on a simple linear pattern across a square farm and only require the minimum set of specifications to monitor its surrounding. On the other hand, the central nodes will require more processing power, memory and power requirements. Sensor and central nodes communicate in a line-of-sight method and follows a deterministic routing table based on the sensor node’s four neighbors. Throughput, latency, and energy consumption results are presented to allow designers and farmers consideration and freedom on how to select which routing protocol can be used to achieve their target objectives

Deterministic Routing between Layout Abstractions for Multi-Scale Classification of Visually Rich Documents

Classifying heterogeneous visually rich documents is a challenging task. Difficulty of this task increases even more if the maximum allowed inference turnaround time is constrained by a threshold. The increased overhead in inference cost, compared to the limited gain in classification capabilities make current multi-scale approaches infeasible in such scenarios. There are two major contributions of this work. First, we propose a spatial pyramid model to extract highly discriminative multi-scale feature descriptors from a visually rich document by leveraging the inherent hierarchy of its layout. Second, we propose a deterministic routing scheme for accelerating end-to-end inference by utilizing the spatial pyramid model. A depth-wise separable multi-column convolutional network is developed to enable our method. We evaluated the proposed approach on four publicly available, benchmark datasets of visually rich documents. Results suggest that our proposed approach demonstrates robust performance compared to the state-of-the-art methods in both classification accuracy and total inference turnaround.