Physical topology is a major determinant of the system performance of optical backbone networks, and it is important to understand the relationships between physical topology features and system performance for better...
详细信息
ISBN:
(纸本)9783903176447
Physical topology is a major determinant of the system performance of optical backbone networks, and it is important to understand the relationships between physical topology features and system performance for better system design. For application in elastic optical backbone network systems, we propose a framework of correlation analysis to examine these relationships comprehensively, and we use the framework to investigate the relationships between various physical topology features and system performance. The results of numerical experiments suggest that four important physical topology features are strongly correlated with the system performance. Specifically, the average number of hops and the algebraic connectivity are strongly correlated with only the communication capacity, whereas the average path length and the geodesic distance Laplacian spectral radius are strongly correlated with both the capacity and the cost. The geodesic distance Laplacian spectral radius is a newly defined quantity that is expected to expand the possibilities of physical topology design in the future. Through combinations of these features, we classify physical topology designs and examine the relationships between the classification, real networks, and graph generation algorithms.
This paper introduces a parametric design system for mortise and tenon structure based on Solid Works. Parametric design is utilized in the design of mortise and tenon structure models, and VB is used as a secondary d...
详细信息
Diffractive Deep Neural network refers to a neural network model constructed based on the principle of optical diffraction. It consists of multiple layers of diffractive surfaces and can perform various functions of n...
详细信息
One of the key performance metrics for opticalnetworks is the maximum achievable throughput. Determining it however, is an NP-hard optimisation problem, often solved via computationally expensive integer linear progr...
详细信息
ISBN:
(纸本)9783903176447
One of the key performance metrics for opticalnetworks is the maximum achievable throughput. Determining it however, is an NP-hard optimisation problem, often solved via computationally expensive integer linear programming (ILP) formulations. Heuristics, in conjunction with sequential loading, are scalable but non-exact. There is, thus, a need for ultra-fast performance evaluation of opticalnetworks. For the first time, we propose message passing neural networks (MPNN), to learn the relationship between the structure and the maximum achievable throughput of opticalnetworks. We demonstrate that MPNNs can accurately predict the maximum achievable throughput while reducing the computational time by 5-orders of magnitude compared to the ILP.
This study focuses on the problem of vehicle dynamics modeling within the framework of intelligent vehicles cyber-physical systems. Initially, a mechanistic analysis of vehicle dynamics is conducted, and, leveraging i...
详细信息
ISBN:
(纸本)9798350366105;9798350366099
This study focuses on the problem of vehicle dynamics modeling within the framework of intelligent vehicles cyber-physical systems. Initially, a mechanistic analysis of vehicle dynamics is conducted, and, leveraging its characteristics, we design a composite neural network that integrates Gated Recurrent Unit (GRU) and Feedforward Neural network (FNN), employing a data-driven modeling methodology. Subsequently, a novel neural network-based digital mapping proxy model for vehicle dynamics is formulated. Comparative experiments among various methods demonstrate that our proposed approach yields higher precision in both lateral and longitudinal dynamic models. The application of our model to the vehicle longitudinal speed tracking control system validates its suitability and real-time performance in control system simulation.
Focusing on the service access requirements of edge nodes, aiming at the problems of narrow network bandwidth, poor network quality and low transmission rate of the edge nodes, a node service dynamic demand prediction...
详细信息
In this work, we will give an overview of some of the most recent and successful applications of machine learning-based inverse system designs in photonic systems. Then, we will focus on our recent research on the Ram...
详细信息
ISBN:
(纸本)9783903176447
In this work, we will give an overview of some of the most recent and successful applications of machine learning-based inverse system designs in photonic systems. Then, we will focus on our recent research on the Raman amplifier inverse design. We will show how the machine learning framework is optimized to generate on-demand arbitrary Raman gain profiles in a controlled and fast way and how it can become a key feature for future optical communication systems.
This research proposes a microwave filter design method using convolutional neural network (CNN) based models trained on small data sets for parameter extraction in microwave filter optimization. The proposed method a...
详细信息
ISBN:
(纸本)9798350347401
This research proposes a microwave filter design method using convolutional neural network (CNN) based models trained on small data sets for parameter extraction in microwave filter optimization. The proposed method and CNN models are described with examples for 3-pole and 5-pole parallel coupled line microstrip filters. The proposed method uses CNN models trained on a pair of small data sets to design microwave filters with various center frequencies and bandwidths. As a result, the proposed method saves on computation time during parameter extraction at each space mapping iteration. Furthermore, the models provide fast, reliable, and robust parameter extraction across varying filter requirements.
The proceedings contain 141 papers. The topics discussed include: scattered light spot phase retrieval and beam quality calculation based on transport-of-intensity equation;terahertz spectral characterization of bitum...
ISBN:
(纸本)9781510686168
The proceedings contain 141 papers. The topics discussed include: scattered light spot phase retrieval and beam quality calculation based on transport-of-intensity equation;terahertz spectral characterization of bituminous coal treated with nitric acid under different conditions;design and analysis of Hermite-Gaussian mode multiplexer based on multi-plane light conversion (MPLC);improved convolutional neural network-based symbol synchronization scheme in MB-OFDM UWBoF system;silicon integrated broadband optical multi-beamformer combining both transmission and reception;accurate high-frequency measurement of electro-optic phase modulators based on optical spectrum analysis and microwave fixture de-embedding;and biophysical modeling of rod photoreceptors based on phototransduction and ionic channel.
In today's digital landscape, network security faces escalating challenges with the proliferation of cyber threats. Intrusion detection is a central defense mechanism against these threats, requiring constant inno...
详细信息
ISBN:
(纸本)9798350373301;9798350373295
In today's digital landscape, network security faces escalating challenges with the proliferation of cyber threats. Intrusion detection is a central defense mechanism against these threats, requiring constant innovation and refinement. This study presents a novel approach to modeling intrusion detection specifically tailored to Procreate, a landscape design software, with a focus on the data layer. Leveraging machine learning and deep learning techniques, proposed methodology encompasses comprehensive steps including feature selection, data processing, and model implementation. Through experimentation and comparison with the traditional methods, the proposed model demonstrates superior performance in terms of accuracy, error rate, recall rate, precision, F-measure, AUC, and computational efficiency. The results highlight the effectiveness of proposed approach in enhancing network security for Procreate users and provide valuable insights for future research directions.
暂无评论