REV Journal on Electronics and Communications
Not a member yet
230 research outputs found
Sort by
Fisher information estimation using neural networks
Get PDFIn estimation theory, the Fisher information matrix (FIM) is a fundamental concept from which we can infer the well-known Cramér-Rao bound. A closed-form expression of the FIM is often intractable due to the lack or sophistication of statistical models. In this paper, we propose a Fisher Information Neural Estimator (FINE) based on neural networks and a relation between the f-divergence and the Fisher information. The proposed method produces an estimate of the FIM directly from observed data. It does not require knowledge or an estimate of the probability density function (pdf), and is therefore universally applicable. The proposed FINE is applicable for not only deterministic parameters but also random parameters. We show via numerical results that the proposed FINE can provide a highly-accurate FIM estimate with a low-computational complexity. Furthermore, we also propose an accelerated FINE version which can be used for scenarios with a high parameter dimension. Finally, we develop an algorithm to choose an appropriate size of the employed neural networks
Security for Multi-hop Communication of Two-tier Wireless Networks with Different Trust Degrees
Get PDFMany effective strategies for enhancing network performance have been put forth for wireless communications’ physical-layer security. Up until now, wireless communications security and privacy have been optimized based on a set assumption on the reliability or network tiers of certain wireless nodes. Eavesdroppers, unreliable relays, and trustworthy cooperative nodes are just a few examples of the various sorts of nodes that are frequently categorized. When working or sharing information for one another, wireless nodes in various networks may not always have perfect trust in one another. Modern wireless networks’ security and privacy may be enhanced in large part by optimizing the network based on trust levels. To determine the path with the shortest total transmission time between the source and the destination while still ensuring that the private messages are not routed through the untrusted network tier, we put forth a novel approach. Toexamine the effects of the transmit SNR, node density, and the percentage of the illegitimate nodes on various network performance components, simulation results are provided
Fast Resource Allocation for Resilient Service Coordination in an NFV-Enabled Internet-of-Things System
Get PDFNetwork Functions Virtualization (NFV) is a new way of leveraging an Internet-of-Things (IoT) system to provide real-time and highly flexible service creation. In an NFV-enabled Internet-of-Things (NIoT) system, several IoT functions implemented as Virtual Network Functions can be linked as a service function chain to build a customized IoT service quickly. It is important for an IoT service to be able to recover from a failure. However, the supply of a resilient IoT service in an NIoT system is challenging due to the coordination of distributed VNF instances. In this paper, we formulate the problem of resilient service coordination in an NIoT system as a mixed-integer linear programming model, namely RSOd. The model offers the optimal resource allocation for minimizing service disruption when a failure happens at a node of an NIoT system. We also develop two modified versions of RSOd for different use cases required by an IoT provider. Further, two approximation algorithms are proposed to provide a resilient service for a large-scale NIoT system. The evaluation results show that RSOd and its modified versions produce the optimal resource allocation in significantly reduced time compared to previous work. The results suggest that an IoT provider should carefully select an appropriate resource allocation strategy as it has to pay a resource cost to minimize the service disruption. The results also show that our proposed priority-based heuristic algorithm outperforms an approximation algorithm based on Simulated Annealingin terms of the service disruption and computation time
Impact of Image Denoising Techniques on CNN-based Liver Vessel Segmentation using Synthesis Low-dose Contrast Enhanced CT Images
Get PDFLiver vessel segmentation in contrast-enhanced CT (CECT) images has a significant role in the planning stage for liver cancer treatment, such as radiofrequency ablation (RFA). Lowering the radiation dose in CECT imaging to reduce radiation risk to the patient degrades the quality of the image and potentially affects the liver vessel segmentation. In recent years, the convolutional neural network (CNN) has shown significant achievement in medical image analysis, including segmentation and denoising tasks. This paper presents a study on a new framework consisting of three well-known denoising techniques, including vessel enhancing diffusion (VED), RED-CNN, and MAP-NN, along with the state-of-theart segmentation method (nnU-Net) to segment the liver vessels in CECT images. We quantitatively evaluate the impacts of denoising techniques on the vessel segmentation on multi-level simulated low-dose CECT images of the liver. The performances of the liver vessel segmentation method combined with the denoising techniques are evaluated using Dice score, sensitivity metric, and processing time. In addition, the effect of denoising on the surface roughness of the segmented liver vessel is also investigated. The experiments show that the image denoising techniques improve the quality of liver vessel segmentation on high noisy CECT images while also reducing the segmentation accuracy on low-noise-level CECT images
Deep Reinforcement Learning-based Bitrate Adaptations in Dynamic Adaptive Streaming over HTTP
Get PDFDynamic adaptive streaming over HTTP (DASH) has been a superior video streaming technology in recent years. Bitrate adaptation function at video player plays a vital role in guaranteeing a high quality-of-experience for the users. This work evaluates the performance of several advanced deep reinforcement learning algorithms, i.e., deep Q-learning, actor-critic, and proximal policy optimization, applied in bitrate adaptations and compares them with other rate adaptation methods with real-trace datasets
Multitasking Correlation Network for Depth Information Reconstruction
Get PDFIn this paper, we propose a novel multi-tasking network for stereo matching. The proposed network is trained to approximate similarity functions in statistics and linear algebra such as correlation coefficient, distance correlation and cosine similarity. By doing this, the proposed method decreases the amount of time needed to calculate the disparity map by using CNN's ability to calculate multiple pairs of image patches at the same time. We then compare the execution time and overall accuracy between the traditional method using functions and our method. The results show the model's ability to mimic the traditional method's performance while taking considerably less time to perform the task
A 4-Term Exponential-Quadratic Approximation for Gaussian Q or Error Functions Accurate to
Get PDFIntegrals on [0, ∞) where the integrand is of the form Qn(a√x) p(x), where Q is the Gaussian Q function, p(·) a Gamma PDF, n a positive integer and a > 0; or of the form erfn(ax + b) xr exp(-c2x2 + 2dx), where erf(x) is the error function, with integers r ≥ 0, n > 0, arise in performance modelling of communication and machine learning systems. Such integrals cannot be evaluated analytically in general, but they are reducible to a set of key integrals whose integrand is erfn(ax + b) N(x; m, s) where N() is a Gaussian PDF with mean m and variance s. Seeking an efficient and accurate evaluation method, we develop a new 4-term exponential quadratic approximator (EQA) for the error function that includes both linear and quadratic terms in its exponents. The EQA minimises a sum-of-squares cost function with two “spline-type” constraints, i.e., constraints on the function value and its first derivative. This constrained optimisation problem is reduced to an unconstrained one by inverting a 4-D linear system, then solved by gradient descent. The resulting approximator has a maximum absolute error of 1.65 × 10-4 on the real line, and outperforms many other exponential sum approximators for erf(x) on x ∈ [0, 1.5] and for Q(x) on x ∈ [0, 2]. Moreover, due to its functional form, the EQA leads to an analytical formula for the set of key integrals, which, in the n = 1 case, is accurate to 3 to 4 significant figures while being orders of magnitude more efficient than Monte Carlo integration. The EQA can equally be used to obtain closed forms for the average symbol error probability of various modulation schemes on Rayleigh fading channels
A Design of Similar High-gain and Dual-band Frequency/Polarization Reconfigurable Antenna for ISM Band Applications
Get PDFThis paper proposes a frequency/polarization reconfigurable antenna (RA) incorporating Frequency Selective Surface (FSS) to achieve dual-band and similar high-gain characteristics. The proposed RA-FSS design using 4 PIN Diodes can produce reconfigurability between circular polarization (CP) at 1.8 GHz and linear polarization (LP) at 2.45 GHz. The fabricated prototype shows good CP performance at 1.8 GHz while the measured peak broadside gains are about 7.2 dBi at 1.8 GHz and 8.5 dBi at 2.45 GHz when PIN diode ON and OFF, respectively