检索结果-南通市图书馆

Lightweight Object Detection Networks for UAV Aerial Images Based on YOLO

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第4期33卷 997-1009页

作者： Yanshan LI Jiarong WANG Kunhua ZHANG Jiawei YI Miaomiao WEI Lirong ZHENG Weixin XIE ATR National key laboratory of Defense Technology Shenzhen University Guangdong key laboratory of intelligent {3. processing Shenzhen University

Existing high-precision object detection algorithms for UAV(unmanned aerial vehicle) aerial images often have a large number of parameters and heavy weight, which makes it difficult to be applied to mobile *** propose three YOLO-based lightweight object detection networks for UAVs, named YOLO-L, YOLO-S, and YOLO-M, respectively. In YOLO-L, we adopt a deconvolution approach to explore suitable upsampling rules during training to improve the detection accuracy. The convolution-batch normalization-Si LU activation function(CBS)structure is replaced with Ghost CBS to reduce the number of parameters and weight, meanwhile Maxpool maximum pooling operation is proposed to replace the CBS structure to avoid generating parameters and weight. YOLO-S greatly reduces the weight of the network by directly introducing CSPGhost Neck residual structures, so that the parameters and weight are respectively decreased by about 15% at the expense of 2.4% mAP. And YOLO-M adopts the CSPGhost Neck residual structure and deconvolution to reduce parameters by 5.6% and weight by 5.7%, while m AP only by 1.8%. The results show that the three lightweight detection networks proposed in this paper have good performance in UAV aerial image object detection task.

关键词： Training YOLO Deconvolution Accuracy Object detection Autonomous aerial vehicles Feature extraction

A Tabletop Nano-CT Image Noise Reduction Network Based on 3.Dimensional Axial Attention Mechanism

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 1711-1725页

作者： Huijuan Fu Linlin Zhu ChunhuiWang Xiaoqi Xi Yu Han Lei Li Yanmin Sun Bin Yan Henan key laboratory of Imaging and intelligent {3. PLA Strategic Support Force Information Engineering UniversityZhengzhou450000China

Nano-computed tomography(Nano-CT)is an emerging,high-resolution imaging ***,due to their low-light properties,tabletop Nano-CT has to be scanned under long exposure conditions,which the scanning process is *** 3. reconstruction data,this paper proposed a lightweight 3. noise reduction method for desktop-level Nano-CT called AAD-ResNet(Axial Attention DeNoise ResNet).The network is framed by theU-net *** encoder and decoder are incorporated with the proposed 3. axial attention mechanism and residual dense *** layer of the residual dense block can directly access the features of the previous layer,which reduces the redundancy of parameters and improves the efficiency of network *** 3. axial attention mechanism enhances the correlation between 3. information in the training process and captures the long-distance *** can improve the noise reduction effect and avoid the loss of image structure *** results show that the network can effectively improve the image quality of a 0.1-s exposure scan to a level close to a 3.s exposure,significantly shortening the sample scanning time.

关键词： Deep learning tabletop Nano-CT image denoising 3. axial attention mechanism

Multi-stream signals separation based on space-time-isomeric (SPATIO) array using metasurface antennas

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第2期67卷 181-200页

作者： Yangming LOU Liang JIN Huiming WANG Zhou ZHONG Junyan DAI PLA Strategic Support Force information Engineering University School of information and Communications Engineering Xi'an Jiaotong University 3. State Key Laboratory of Millimeter WavesSoutheast University

In spatial domain signal processing, it is necessary to equip more antennas at the receiver to improve spatial demultiplexing capability. However, increasing the number of antennas under restricted space will reduce antenna spacing and raise the channel correlation, making the number of signal streams spatially demultiplexed much smaller than that of antennas. This paper proposes a method to design a space-timeisomeric(SPATIO) array based on metasurface antennas under wireless multipath conditions. Each antenna in this array has a different pattern and varies independently with time, reducing the channel correlation by superposing multipath at distinct positions and moments. Based on the SPATIO array, we present an array parameter design scheme based on infinity norm minimization, which can maximize the received energy of each stream while separating multi-stream received signals. Simulation results illustrate the performance of the SPATIO array for multi-stream signal reception. Compared with conventional multiple-input multipleoutput arrays, the proposed array can reduce the bit error rate by one order of magnitude under the same simulation conditions.

关键词： multiple-input multiple-output metasurface antenna space-time-isomeric array multipath channel degree of freedom

L_(1)-Smooth SVM with Distributed Adaptive Proximal Stochastic Gradient Descent with Momentum for Fast Brain Tumor Detection

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 1975-1994页

作者： Chuandong Qin Yu Cao Liqun Meng School of Mathematics and information Science North Minzu UniversityYinchuan750021China Ningxia key laboratory of intelligent {3. and Big Data processing Yinchuan750021China

Brain tumors come in various types,each with distinct characteristics and treatment approaches,making manual detection a time-consuming and potentially ambiguous *** tumor detection is a valuable tool for gaining a deeper understanding of tumors and improving treatment *** learning models have become key players in automating brain tumor *** descent methods are the mainstream algorithms for solving machine learning *** this paper,we propose a novel distributed proximal stochastic gradient descent approach to solve the L_(1)-Smooth Support Vector Machine(SVM)classifier for brain tumor ***,the smooth hinge loss is introduced to be used as the loss function of *** avoids the issue of nondifferentiability at the zero point encountered by the traditional hinge loss function during gradient descent ***,the L_(1) regularization method is employed to sparsify features and enhance the robustness of the ***,adaptive proximal stochastic gradient descent(PGD)with momentum,and distributed adaptive PGDwithmomentum(DPGD)are proposed and applied to the L_(1)-Smooth *** computing is crucial in large-scale data analysis,with its value manifested in extending algorithms to distributed clusters,thus enabling more efficient processing ofmassive amounts of *** DPGD algorithm leverages Spark,enabling full utilization of the computer’s multi-core *** to its sparsity induced by L_(1) regularization on parameters,it exhibits significantly accelerated convergence *** the perspective of loss reduction,DPGD converges faster than *** experimental results show that adaptive PGD withmomentumand its variants have achieved cutting-edge accuracy and efficiency in brain tumor ***-trained models,both the PGD andDPGD outperform other models,boasting an accuracy of 95.21%.

关键词： Support vector machine proximal stochastic gradient descent brain tumor detection distributed computing

A Heuristic Radiomics Feature Selection Method Based on Frequency Iteration and Multi-Supervised Training Mode

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2277-2293页

作者： Zhigao Zeng Aoting Tang Shengqiu Yi Xinpan Yuan Yanhui Zhu School of Computer Hunan University of TechnologyZhuzhou412007China Hunan key laboratory of intelligent {3. Perception and processing Technology Zhuzhou412007China

Radiomics is a non-invasive method for extracting quantitative and higher-dimensional features from medical images for *** has received great attention due to its huge application prospects in recent *** can know that the number of features selected by the existing radiomics feature selectionmethods is basically about *** this paper,a heuristic feature selection method based on frequency iteration and multiple supervised training mode is *** on the combination between features,it decomposes all features layer by layer to select the optimal features for each layer,then fuses the optimal features to form a local optimal group layer by layer and iterates to the global optimal combination *** with the currentmethod with the best prediction performance in the three data sets,thismethod proposed in this paper can reduce the number of features fromabout ten to about three without losing classification accuracy and even significantly improving classification *** proposed method has better interpretability and generalization ability,which gives it great potential in the feature selection of radiomics.

关键词： Radiomics feature selection machine learning metaheuristic

Experimental demonstration of a photonic spiking neuron based on a DFB laser subject to side-mode optical pulse injection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第3期67卷 271-280页

作者： Shuiying XIANG Shuang GAO Yuechun SHI Yuna ZHANG Ziwei SONG Xingxing GUO Yahui ZHANG Yuxin MA Xiangfei CHEN State key laboratory of Integrated Service Networks Xidian University Yongjiang laboratory 3. College of Engineering and Applied Sciences Nanjing University

We proposed and experimentally demonstrated a simple and novel photonic spiking neuron based on a distributed feedback(DFB) laser subject to side-mode optical pulse injection(SMOPI). The DFB laser chip is designed and fabricated based on asymmetric equivalent π phase shift(π-EPS) with the reconstruction-equivalent-chirp(REC) technique. Under side-mode continuous-wave(CW) optical injection,excitability pulse was experimentally observed during the dominant mode switching process due to the injection-locked effect. Based on the transition between the excitability regime and the side-mode injection locking effect, the controllable and repeatable neuron-like spiking response can be realized when external stimulus pulses are electro-optically modulated on the CW optical carrier. The experimental results show that the spike threshold, temporal integration, and refractory period, which are important spike processing mechanisms in biological neurons, can all be achieved in the optically-injected DFB laser. The experimental findings are also verified numerically with a rate equation model that considers the SMOPI. To the best of our knowledge, this is the first experimental demonstration of a photonic spiking neuron based on a DFB laser subject to SMOPI, which holds promise for realizing large-scale photonic spiking neuron arrays for hardware photonic spiking neural network chips.

关键词： neuromorphic photonics photonic spiking neuron DFB laser side-mode optical pulse injections

Towards human-leveled vision systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第8期67卷 2331-2349页

作者： DING JianHao HUANG TieJun State key laboratory of Multimedia information {3. School of Computer SciencePeking UniversityBeijing 100871China

The human visual system is a complex and interconnected network comprising billions of neurons. It plays an essential role in translating environmental light stimuli into information that guides and shapes human perception and action. Research on the visual system aims to uncover the underlying neural structure principles of human visual perception and their possible ***, there are two main approaches: biological system analysis and simulation, artificial intelligence models based on deep learning. Here we aim to discuss the two approaches to human-level vision systems. Deep learning has significantly impacted the field of vision with achievements in representation, modeling, and hardware design. However, there is still a significant gap between deep learning models and the human visual system in terms of scalability, transferability, and sustainability. The progress of the biological visual system can help fill the gap by further understanding the properties and functions of different components of the system. We take the efforts of reconstructing the retina as an example to illustrate that even if we are unable to replicate the visual system on a computer right now, we can still learn a lot by combining existing research outcomes in neuroscience. At the end of the paper, we suggest tracing back to gradually build visual systems from the computational counterpart of biological structures to achieve a human-level vision system in the future.

关键词： human-leveled vision system deep learning biological visual system

维普期刊数据库

SFGA-CPA: A Novel Screening Correlation Power Analysis Framework Based on Genetic Algorithm

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4641-4657页

作者： Jiahui Liu Lang Li Di Li Yu Ou College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial key laboratory of intelligent {3. processing and Application Hengyang Normal UniversityHengyang421002China

Correlation power analysis(CPA)combined with genetic algorithms(GA)now achieves greater attack efficiency and can recover all subkeys ***,two issues in GA-based CPA still need to be addressed:key degeneration and slow evolution within *** challenges significantly hinder key recovery *** paper proposes a screening correlation power analysis framework combined with a genetic algorithm,named SFGA-CPA,to address these ***-CPA introduces three operations designed to exploit CPA characteris-tics:propagative operation,constrained crossover,and constrained ***,the propagative operation accelerates population evolution by maximizing the number of correct bytes in each ***,the constrained crossover and mutation operations effectively address key degeneration by preventing the compromise of correct ***,an intelligent search method is proposed to identify optimal parameters,further improving attack *** were conducted on both simulated environments and real power traces collected from the SAKURA-G *** the case of simulation,SFGA-CPA reduces the number of traces by 27.3.and 60%compared to CPA based on multiple screening methods(MS-CPA)and CPA based on simple GA method(SGA-CPA)when the success rate reaches 90%.Moreover,real experimental results on the SAKURA-G platform demonstrate that our approach outperforms other methods.

关键词： Side-channel analysis correlation power analysis genetic algorithm crossover mutation

Side-Channel Leakage Analysis of Inner Product Masking

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 1245-1262页

作者： Yuyuan Li Lang Li Yu Ou College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial key laboratory of intelligent {3. processing and Application Hengyang Normal UniversityHengyang421002China

The Inner Product Masking(IPM)scheme has been shown to provide higher theoretical security guarantees than the BooleanMasking(BM).This scheme aims to increase the algebraic complexity of the coding to achieve a higher level of *** previous work unfolds when certain(adversarial and implementation)conditions are met,and we seek to complement these investigations by understanding what happens when these conditions deviate from their expected *** this paper,we investigate the security characteristics of IPM under different *** adversarial condition,the security properties of first-order IPMs obtained through parametric characterization are preserved in the face of univariate and bivariate *** implementation condition,we construct two new polynomial leakage functions to observe the nonlinear leakage of the IPM and connect the security order amplification to the nonlinear *** observe that the security of IPMis affected by the degree and the linear component in the leakage *** addition,the comparison experiments from the coefficients,signal-to-noise ratio(SNR)and the public parameter show that the security properties of the IPM are highly implementation-dependent.

关键词： Side-channel analysis inner product masking mutual information nonlinear leakage