The penetration of embedded generation, including renewable power sources (wind and solar), is gradually increasing in power distribution networks. Also, the transition from conventional fossil fuel-based transportati...
详细信息
There is an evolution in cellular communication due to the high demand for better quality of service, data rates, capacity, and lower latency. To satisfy these expectations, cellular network design is being drasticall...
详细信息
ISBN:
(纸本)9781665483032
There is an evolution in cellular communication due to the high demand for better quality of service, data rates, capacity, and lower latency. To satisfy these expectations, cellular network design is being drastically improved. This paper provides a survey of cellular networkarchitectures, multiple access techniques, and emerging technologies from first generation (1G) to fifth generation (5G). The paper also includes a glimpse at what the forthcoming sixth generation (6G) might anticipate. The architecture of the cellular network from 1G to 5G is presented. Some of the important emerging technologies that enable the architecture to be improved and fulfill user needs are discussed. These emerging technologies include massive MIMO, software-defined networking, mm-Wave, etc. Moreover, multiple access techniques used from 1G to 5G are studied. Comparison among different generations of cellular communication is presented. There are challenges and open issues for 6G which are described.
As quantum computing continues to progress, there is an increasing need for standardized quantum network technology [I], pi to connect quantum computers together. Experimental testbeds are necessary in order to develo...
详细信息
ISBN:
(纸本)9798331541378
As quantum computing continues to progress, there is an increasing need for standardized quantum network technology [I], pi to connect quantum computers together. Experimental testbeds are necessary in order to develop quantum network software and hardware. Building a scalable testbed for data center-level quantum networks requires overcoming numerous engineering and technical challenges in quantum communications, quantum processing and quantum storage. In this work, we describe a software framework for use with an all-photonic quantum networking testbed. This framework is designed for rapid development and capable of automated execution of quantum experiments. We introduce PnPQ, an open-source, unified driver library for hardware commonly used in quantum optical experiments. On top of this low-level hardware control library, we present software modules for controlling and coordinating quantum network nodes using remote procedure calls (RPC). Finally, we describe high-level software for performing and analyzing quantum photonic experiments using these software modules. As a whole, these software components comprise the first version of a framework that will enable us to implement and test quantum networkarchitectures. This framework is intended to help us move forward from building simple experiments to complex quantum systems.
Monitoring road condition has been a strategic area of research in maintaining an extensive transportation infrastructure network. Although damages on road surfaces initially appear as slight cracks, the depth and dan...
详细信息
ISBN:
(纸本)9798350388978;9798350388961
Monitoring road condition has been a strategic area of research in maintaining an extensive transportation infrastructure network. Although damages on road surfaces initially appear as slight cracks, the depth and danger of these damages may increase over time and changing weather conditions. Cracks on the road surface are one of the main factors affecting the performance of the road. Automatic detection of road cracks is an important task in road maintenance. However, automatic crack detection is a challenging application area due to the inhomogeneity of the density of cracks and the complexity of the background (e.g. low contrast with the surrounding coating and possible shadows of similar intensity). Recently, deep learning-based object detection and segmentation methods have begun to be used effectively in detecting cracks on road surfaces. In this study, a comparative analysis was carried out for the detection of cracks on road surfaces using the current versions of You Only Look Once (YOLO), a popular single-step object detection algorithm. The open source dataset UAPD, consisting of unmanned aerial vehicle (UAV) images, was used in the analysis. In the application carried out to detect different types of cracks with YOLOv5x, 0.639 mean average precision (mAP) and 0.759 sensitivity metrics were obtained. Using the YOLOv5x algorithm, the highest accuracy was achieved compared to other algorithms.
Approximate computing along with quantized low-precision computing has gained significant interest in today's neural network (NN) implementation. This paper proposes a library of VLSI implementations of different ...
详细信息
ISBN:
(数字)9781665461863
ISBN:
(纸本)9781665461863
Approximate computing along with quantized low-precision computing has gained significant interest in today's neural network (NN) implementation. This paper proposes a library of VLSI implementations of different activation functions, aimed towards designing hardware-efficient NN accelerators. Cartesian genetic programming (CGP), an evolutionary algorithm was employed to generate gate-level designs of approximate and exact representations of activation functions. We open-source the hardware library of 9444 circuits containing a majority of the activation functions employed in NN architectures, including Sigmoid, Hyperbolic-Tangent, Gaussian, ReLU, GeLU, Softplus, and Binary-Step. The library also presents the error characteristics and hardware metrics of the designs which will aid in the usage of the library in future research. Additionally a hardware comparison of the proposed circuits against existing implementations including piecewise-linear (PWL), memory-based, hls4ml, DNNweaver implementations to realize activation functions on FPGA and ASIC flow is presented. The CGP evolved hardware library shows minimal silicon space requirement, least power consumption when investigated for ASIC flow, and the least LUT utilization's in FPGA flow. Besides, SOMALib designs are purely combinatorial, allowing various synthesis stage optimizations towards the target Power-Performance-Area budget, which is not possible in standard memory block implementations.
We propose a machine learning method to solve a mean-field game price formation model with common noise. This involves determining the price of a commodity traded among rational agents subject to a market clearing con...
详细信息
ISBN:
(纸本)9798350301243
We propose a machine learning method to solve a mean-field game price formation model with common noise. This involves determining the price of a commodity traded among rational agents subject to a market clearing condition imposed by random supply, which presents additional challenges compared to the deterministic counterpart. Our approach uses a dual recurrent neural network encoding noise dependence and a particle approximation of the mean-field model with a single loss function optimized by adversarial training. We provide a posteriori estimates for convergence and illustrate our method through numerical experiments.
Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i.e., models with more MACs typically achieve better accuracies, such as EfficientNet and RegNet. These works try ...
详细信息
ISBN:
(数字)9781665487399
ISBN:
(纸本)9781665487399
Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i.e., models with more MACs typically achieve better accuracies, such as EfficientNet and RegNet. These works try to enlarge the network architecture with one unified rule by sampling and statistical methods. However, the rule is not prospective to the design of large networks because it is obtained from the experience of researchers on small networkarchitectures. In this paper, we propose to enlarge the capacity of CNN models by fine-grained MACs allocation for the width, depth and resolution on the stage level. In particular, starting from a base small model, we gradually add extra channels, layers or resolution by using a dynamic programming manner. With step-by-step modifying the computations on different stages, the enlarged network will be equipped with optimal allocation and utilization of MACs. On EfficientNet, our method consistently outperforms the performance of the original scaling method. In particular, the proposed method is used to enlarge models sourced by GhostNet, we achieve state-of-the-art 80.9% and 84.3% ImageNet top-1 accuracies under the setting of 600M and 4.4B MACs, respectively.
In-memory database in the data center plays an indispensable role in many fields. B+tree is the most recognized index in in-memory database, but its indexing latency has become the bottleneck that prevents the databas...
详细信息
The relevance of the study is related to the increased needs of medical personnel in qualitative solution of image data analysis tasks, in particular lung scans during the period of controlling the consequences of cor...
详细信息
Lipschitz constants for linear MPC are useful for certifying inherent robustness against unmodeled disturbances or robustness for neural network-based approximations of the control law. In both cases, knowing the mini...
详细信息
ISBN:
(纸本)9798350301243
Lipschitz constants for linear MPC are useful for certifying inherent robustness against unmodeled disturbances or robustness for neural network-based approximations of the control law. In both cases, knowing the minimum Lipschitz constant leads to less conservative certifications. Computing this minimum Lipschitz constant is trivial given the explicit MPC. However, the computation of the explicit MPC may be intractable for complex systems. The paper discusses a method for efficiently computing the minimum Lipschitz constant without using the explicit control law. The proposed method simplifies a recently presented mixed-integer linear program (MILP) that computes the minimum Lipschitz constant. The simplification is obtained by exploiting saturation and symmetries of the control law and irrelevant constraints of the optimal control problem.
暂无评论