In semiconductor manufacturing, automated material handling systems (AMHSs) transport wafers through a complex re-entrant manufacturing process. In some systems, Overhead Hoist Transport (OHT) vehicles move throughout the facility on a ceiling-mounted track system, delivering wafers to machines and storage locations. To improve efficiency in such systems, this thesis proposes an adaptive dynamic routing approach that allows the system to self-regulate, reducing steady-state travel times by 4-6% and avoiding excessive congestion and deadlock. Our approach allows vehicles to be rerouted while in progress in response to changes in the location and severity of congestion as measured by edge traversal time estimates updated via exponential smoothing. Our proposed method is efficient enough to be used in a large system where several routing decisions are made each second. We also consider how the effectiveness of a AMHS layout differs between static and dynamic routing. We demonstrate that dynamic routing significantly reduces sensitivity to shortcut placement and allows an eight-fold increase in the number of shortcuts along the center loop. This reduces travel times by an additional 24%. To demonstrate the effectiveness of our proposed routing approach, we use a high-fidelity simulation of vehicle movement. To test the impact of routing methods on layout effectiveness, we developed an associated Excel-based automated layout generation tool that allows the efficient generation of thousands of candidate layouts. The user selects from among a set of modular templates to create a design and all simulation files are generated with the click of a button.

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / The Convolutional Neural Network (CNN) have shown a substantial improvement in the field of Machine Learning. But they do come with their own set of drawbacks. Capsule Networks have addressed the limitations of CNNs and have shown a great improvement by calculating the pose and transformation of the image. Deeper networks are more powerful than shallow networks but at the same time, more difficult to train. Residual Networks ease the training and have shown evidence that they can give good accuracy with considerable depth. Putting the best of Capsule Network and Residual Network together, we present Residual Capsule Network and 3-Level Residual Capsule Network, a framework that uses the best of Residual Networks and Capsule Networks. The conventional Convolutional layer in Capsule Network is replaced by skip connections like the Residual Networks to decrease the complexity of the Baseline Capsule Network and seven ensemble Capsule Network. We trained our models on MNIST and CIFAR-10 datasets and have seen a significant decrease in the number of parameters when compared to the Baseline models.

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / During recent years, the field of computer vision has evolved rapidly. Convolutional Neural Networks (CNNs) have become the chosen default for implementing computer vision tasks. The popularity is based on how the CNNs have successfully performed the well-known computer vision tasks such as image annotation, instance segmentation, and others with promising outcomes. However, CNNs have their caveats and need further research to turn them into reliable machine learning algorithms. The disadvantages of CNNs become more evident as the approach to breaking down an input image becomes apparent. Convolutional neural networks group blobs of pixels to identify objects in a given image. Such a technique makes CNNs incapable of breaking down the input images into sub-parts, which could distinguish the orientation and transformation of objects and their parts. The functions in a CNN are competent at learning only the shift-invariant features of the object in an image. The discussed limitations provides researchers and developers a purpose for further enhancing an effective algorithm for computer vision. The opportunity to improve is explored by several distinct approaches, each tackling a unique set of issues in the convolutional neural network’s architecture. The Capsule Network (CapsNet) which brings an innovative approach to resolve issues pertaining to affine transformations by sharing transformation matrices between the different levels of capsules. While, the Residual Network (ResNet) introduced skip connections which allows deeper networks to be more powerful and solves vanishing gradient problem. The motivation of these fusion of these advantageous ideas of CapsNet and ResNet with Squeeze and Excite (SE) Block from Squeeze and Excite Network, this research work presents SE-Residual Capsule Network (SE-RCN), an efficient neural network model. The proposed model, replaces the traditional convolutional layer of CapsNet with skip connections and SE Block to lower the complexity of the CapsNet. The performance of the model is demonstrated on the well known datasets like MNIST and CIFAR-10 and a substantial reduction in the number of training parameters is observed in comparison to similar neural networks. The proposed SE-RCN produces 6.37 Million parameters with an accuracy of 99.71% on the MNIST dataset and on CIFAR-10 dataset it produces 10.55 Million parameters with 83.86% accuracy.

As hardware applications become increasingly complex, the supporting technology needs to evolve and adapt to the demands. Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit, General Purpose Processor, and System on Chip are the preferred devices for solving computational problems. Each of these platforms has its own specific advantages and disadvantages, which need to be accounted for during application development. Flexible radio communications has been dominated by Software Defined Radios. However, research in industry and universities has successfully developed run-time reconfiguration tools to make FPGA designs more flexible and thus vastly reducing configuration times. Developers now have a more powerful platform with dense Digital Signal Processor resources and the flexibility of SDR. Xilinx offers tools such as partial reconfiguration, which is a special modification of the standard tool-flow that supports configuration of the selected partial regions on an FPGA. The AgileHW project improves on the Xilinx tools resource allocation and routing scheme to increase the design agility and productivity. This thesis advances the AgileHW reconfigurable platform so developers can use the newer technology to build enhanced designs. / Master of Science

Mobile Ad hoc Networks (MANETs) are becoming increasingly important because of their unique characteristics of connectivity. Several delay sensitive applications are starting to appear in these kinds of networks. Therefore, an issue in concern is to guarantee Quality of Service (QoS) in such constantly changing communication environment. The classical QoS aware solutions that have been used till now in the wired and infrastructure wireless networks are unable to achieve the necessary performance in the MANETs. The specialized protocols designed for multihop ad hoc networks offer basic connectivity with limited delay awareness and the mobility factor in the MANETs makes them even more unsuitable for use. Several protocols and solutions have been emerging in almost every layer in the protocol stack. The majority of the research efforts agree on the fact that in such dynamic environment in order to optimize the performance of the protocols, there is the need for additional information about the status of the network to be available. Hence, many cross layer design approaches appeared in the scene. Cross layer design has major advantages and the necessity to utilize such a design is definite. However, cross layer design conceals risks like architecture instability and design inflexibility. The aggressive use of cross layer design results in excessive increase of the cost of deployment and complicates both maintenance and upgrade of the network. The use of autonomous protocols like bio-inspired mechanisms and algorithms that are resilient on cross layer information unavailability, are able to reduce the dependence on cross layer design. In addition, properties like the prediction of the dynamic conditions and the adaptation to them are quite important characteristics. The design of a routing decision algorithm based on Bayesian Inference for the prediction of the path quality is proposed here. The accurate prediction capabilities and the efficient use of the plethora of cross layer information are presented. Furthermore, an adaptive mechanism based on the Genetic Algorithm (GA) is used to control the flow of the data in the transport layer. The aforementioned flow control mechanism inherits GA’s optimization capabilities without the need of knowing any details about the network conditions, thus, reducing the cross layer information dependence. Finally, is illustrated how Bayesian Inference can be used to suggest configuration parameter values to the other protocols in different layers in order to improve their performance.

In this thesis, a feedback-based contention avoidance technique based on weighted Dijkstra algorithm is proposed to address the contention avoidance problem for Optical Burst Switching networks. Optical Burst Switching (OBS) has been proposed as a promising technique to support high-bandwidth, bursty data traffic in the next-generation optical Internet. Nevertheless, there are still some challenging issues that need to be solved to achieve an effective implementation of OBS. Contention problem occurs when two or more bursts are destined for the same wavelength. To solve this problem, various reactive contention resolution methods have been proposed in the literature. However, many of them are very vulnerable to network load and may suffer severe loss in case of heavy traffic. By proactively controlling the overall traffic, network is able to update itself in case of high congestion and by means of this method / contention avoidance can be achieved efficiently. The performance analysis of the proposed algorithm is presented through network simulation results provided by OMNET++ simulation environment. The simulation results show that the proposed contention avoidance technique significantly reduces the burst loss probability as compared to networks without any contention avoidance techniques.

Capsule Networks are an alternative to the conventional CNN structure for object recognition. They replace max pooling with a dynamic routing of capsule activation. The goal is to better exploit the spatial relationships of the learned features, not only to increase recognition performance, but also improve generalization capability and sample-efficiency. Recently, two algorithms for dynamic routing of capsules have been proposed. Although they received a lot of interest and they are from the same group, an experimental comparison of both is still missing. In this work we compare these two routing algorithms and provide experimental results on data efficiency and generalization to increased input images. Although the experiments are limited to variants of the MNIST dataset, they indicate that the approach of Sabour et al. (2017) is better at learning from few training samples and the EM routing of Hinton et al. (2018) is better at generalizing to changed image sizes.

Future spacecrafts will require more computational and processing power to keep up with the growing demand in requirements and complexity. ScOSA is the next generation on-board computer developed by the German Aerospace Centre (DLR). The main motivation behind ScOSA is to replace the conventional on-board computer with distributed and reconfigurable computing nodes which provides higher performance, reliability, availability and stability by using a combination of the COTS components and reliable computing processors that are space qualified. In the current ScOSA system reconfiguration and routing of data between nodes are based on a static decision graph. SpaceWire protocol is used to communicate between nodes to provide reliability. The focus of the thesis is to design and implement a dynamic routing protocol for ScOSA which can be used in future for not only communicating between the nodes but also for reconfiguration. SpaceWire IPC is a customized protocol developed by DLR to provide communication between the nodes in a distributed network and to support monitoring, management and reconfiguration services. The dynamic routing protocol proposed in this thesis is primarily derived from the monitoring mechanism used in the SpaceWire IPC. PULL type monitoring mechanism is modelled and simulated using OMNeT++. The results obtained provide a qualitative outlook of the dynamic routing protocol implemented.