Inverse design of complex nanophotonic devices is a very computation-consuming task. Deep-learning-based approaches can facilitate this process. However, due to the lack of solid knowledge about the underlying complex...
详细信息
Inverse design of complex nanophotonic devices is a very computation-consuming task. Deep-learning-based approaches can facilitate this process. However, due to the lack of solid knowledge about the underlying complexity of the input-output relation for a selected class of nanostructures, it is common to select an over-parameterized neural network (NN) for modeling this relation. We present a novel pruning method based on removing weak nodes and connections in the original NN to simplify the input-output relation without imposing significant error. In addition to reducing the model complexitycomputations, the pruned network can be used to find valuable insight into the physics of device operation. To show the efficacy of our approach, we use it for modeling and inverse design of two classes of nanostructures with different complexities.
FastSLAM algorithm is commonly used in Unmanned Ground Vehicles (UGVs) recently. One of the main problems under research is the computation cost of this probabilistic algorithm. Since the speed of the UGV is limited b...
详细信息
ISBN:
(纸本)9781728109336
FastSLAM algorithm is commonly used in Unmanned Ground Vehicles (UGVs) recently. One of the main problems under research is the computation cost of this probabilistic algorithm. Since the speed of the UGV is limited by the latency of the algorithm, the computation complexity and its effect on the step time of the FastSLAM needs to be investigated. The present work addresses the effects of the number of particles and number of map features on the computation complexity of the FastSLAM algorithm. The study included the prediction, the observation, data association and resampling phase's complexities. Also, the correlation between the uncertainty of the UGV location and the number of particles was addressed. The simulation study was validated experimentally using hardware in the loop (HIL) setup. The analysis showed that when there is a prior knowledge of the average number of map features, an optimum number of particle filters could be set for that UGV in the given environment while maintaining an improved performance of the algorithm.
The optimal order in fractional Fourier transform (FrFT) can be used to estimate chromatic dispersion (CD) and nonlinearity in an optical fiber transmission system. In this paper, we propose a novel method to estimate...
详细信息
ISBN:
(数字)9781510617469
ISBN:
(纸本)9781510617469;9781510617452
The optimal order in fractional Fourier transform (FrFT) can be used to estimate chromatic dispersion (CD) and nonlinearity in an optical fiber transmission system. In this paper, we propose a novel method to estimate CD with lower computation complexity in fractional domain. The computation complexity can be reduced by 10 3 times with the same measurement accuracy compared with one step method when the number of samples is 8192 and search step is 0.0001. The correctness of the novel method for optimal order searching is proved by chirp parameter estimation for linear frequency modulation (LFM) signals. The measurement relative error is only 0.02%. For CD estimation, the maximum estimation error ratio is 0.338% and 0.564% for 28GBaud quadrature phase-shift keying (QPSK) and 16 quadrature amplitude modulation (16QAM) optical fiber transmission systems over 100 km similar to 2000 km SSMF.
Animation scene generation (ASG) is the best digital media tool for lifelike scenes, particularly for movies. Traditional animation methods are laborious, computationally intensive, and scalable. Thus, this work addre...
详细信息
Animation scene generation (ASG) is the best digital media tool for lifelike scenes, particularly for movies. Traditional animation methods are laborious, computationally intensive, and scalable. Thus, this work addresses animation production issues using NFL-ASG. Combining fuzzy logic with a convolution neural network may create more realistic animated situations with less human interaction and better learning. Convolutional model training uses animation scenarios' complicated motion patterns, character interactions, and ambient factors. Deep learning and fuzzy logic might change animation by boosting production techniques and releasing digital media technological creativity. After testing the system on the Moana Island scene dataset, it achieved a perception analysis success rate of 0.981% and a minimal processing complexity of (n logn).
This work demonstrates the application of deep neural networks (DNN) to alleviate the computational complexity associated with Model Predictive Control (MPC), which has always been an obstacle hindering the practical ...
详细信息
This work demonstrates the application of deep neural networks (DNN) to alleviate the computational complexity associated with Model Predictive Control (MPC), which has always been an obstacle hindering the practical adoption of MPC. This challenge is particularly critical in applications for autonomous vehicles where achieving multiple objectives while enforcing a certain number of system constraints is essential. We first revisit and design a control algorithm tailored to the Adaptive Cruise Control (ACC) problem. The developed algorithm consists of two distinct implicit MPCs, each addressing a specific control mode, namely velocity and space control. Multiple control objectives and constraints are integrated into the algorithm synthesis to ensure satisfactory control performance. We further adopt supervised learning with deep neural networks to reduce the computational cost of MPC, thereby making MPC more accessible for practical use. Simulation results affirm that the DNN-based approximated policy can match the control performance in terms of both tracking precision and constraint satisfaction of state-of-the-art solvers dedicated to optimization problems. Remarkably, the execution time of the approximated policy is approximately one order of magnitude lower than that of implicit MPCs, while its memory footprint is significantly lower than those of its counterparts, thereby emphasizing its distinct advantages.
Deep image hiding is a challenging image processing task that aims to hide a secret image into a cover image of equal size perfectly. How to improve the imperceptibility of deep image hiding while ensuring high comput...
详细信息
Deep image hiding is a challenging image processing task that aims to hide a secret image into a cover image of equal size perfectly. How to improve the imperceptibility of deep image hiding while ensuring high computational efficiency is a primary challenge. Where imperceptibility means not being visually perceived while not being perceived by the steganalysis model. In this paper, we propose a novel deep image hiding framework called DIH-OAIN (Deep Image Hiding based on One-way Adversarial Invertible Networks) to address it. Firstly, an image cascade framework is introduced to extract image semantics and details with dual-resolution branches, and reduces computation complexity by balancing image resolution and model complexity. Secondly, a hidden probability guided module is designed to constrain the secret image to be hidden in the texture region, utilizing the image texture complexity as prior knowledge. The above two points can effectively improve visual imperceptibility. Finally, a one-way adversarial training strategy is proposed to enhance the model imperceptibility. A series of experimental results show that the proposed method is significantly improved in imperceptibility comparing to state-of-the-art deep image hiding algorithms, while maintaining a low computation complexity.
The use of the Internet of Things(IoT)is expanding at an unprecedented scale in many critical applications due to the ability to interconnect and utilize a plethora of wide range of *** critical infrastructure domains...
详细信息
The use of the Internet of Things(IoT)is expanding at an unprecedented scale in many critical applications due to the ability to interconnect and utilize a plethora of wide range of *** critical infrastructure domains like oil and gas supply,intelligent transportation,power grids,and autonomous agriculture,it is essential to guarantee the confidentiality,integrity,and authenticity of data collected and ***,the limited resources coupled with the heterogeneity of IoT devices make it inefficient or sometimes infeasible to achieve secure data transmission using traditional cryptographic ***,designing a lightweight secure data transmission scheme is becoming *** this article,we propose lightweight secure data transmission(LSDT)scheme for IoT *** consists of three phases and utilizes an effective combination of symmetric keys and the Elliptic Curve Menezes-Qu-Vanstone asymmetric key agreement *** design the simulation environment and experiments to evaluate the performance of the LSDT scheme in terms of communication and computation *** and performance analysis indicates that the LSDT scheme is secure,suitable for IoT applications,and performs better in comparison to other related security schemes.
Image Super-Resolution(SR)research has achieved great success with powerful neural *** deeper networks with more parameters improve the restoration quality but add the computation complexity,which means more inference...
详细信息
Image Super-Resolution(SR)research has achieved great success with powerful neural *** deeper networks with more parameters improve the restoration quality but add the computation complexity,which means more inference time would be cost,hindering image SR from practical *** the spatial distribution of the objects or things in images,a twostage local objects SR system is proposed,which consists of two modules,the object detection module and the SR ***,You Only Look Once(YOLO),which is efficient in generic object detection tasks,is selected to detect the input images for obtaining objects of interest,then put them into the SR module and output corresponding High-Resolution(HR)*** computational power consumption of image SR is optimized by reducing the resolution of input *** addition,we establish a dataset,TrafficSign500,for our ***,the performance of the proposed system is evaluated under several State-Of-The-Art(SOTA)YOLOv5 and SISR *** show that our system can achieve a tremendous computation improvement in image SR.
Replacing multiplication with addition can effectively reduce the computational complexity. Based on this idea, adder neural networks (AdderNets) are proposed. Thereafter, AdderNets are applied to super-resolution (SR...
详细信息
Replacing multiplication with addition can effectively reduce the computational complexity. Based on this idea, adder neural networks (AdderNets) are proposed. Thereafter, AdderNets are applied to super-resolution (SR) task to obtain AdderSR, which significantly reduces the energy consumption caused by SR models. However, the weak fitting ability of AdderNets makes AdderSR only applicable to the low-complexity pixel-wise loss, and the performance of the model drops sharply when the high-complexity perceptual loss is used. Enhanced AdderSR (EAdderSR) is proposed to overcome the limitations of AdderSR in SR tasks. Specifically, current adder networks have serious gradient precision loss problem, which affects the training stability. The normalization layer is adjusted to normalize the output of the adder layer to a reasonably narrow range, which can reduce the amount of precision loss. Then, a coarse-grained knowledge distillation (CGKD) method is developed to give adder networks an efficient guidance to reduce the fitting burden. The experimental results show that the proposed method not only further improves the performance of adder networks, but also ensures the quality of the output results when the complexity of the loss function increases.
The article considers a distributed divide-and-conquer method to test the mutual independence between components of massive multivariate data. In particular, a new test statistic based on U-statistics by dividing the ...
详细信息
The article considers a distributed divide-and-conquer method to test the mutual independence between components of massive multivariate data. In particular, a new test statistic based on U-statistics by dividing the full data samples into disjoint blocks will be established. Some numerical simulations and real data analysis demonstrate that the proposed method is effective, and it can significantly reduce the computational complexity and save the running time of the test procedure on massive data inference.
暂无评论