基于LVQ神经网络的水果图像分割研究

由于传统边沿检测算子在水果颜色多样、亮度不均匀时,难以分割得到完整、无噪声的二值图像且依赖优化的阈值,本研究提出了一种基于LVQ神经网络的水果图像分割方案。首先将彩色图像转变为灰度图像;然后对Canny算子获得的边沿图像随机选取一些像素作为网络的学习监督信号,仅以灰度图像中相同位置像素3×3邻域的Kirsch算子梯度值作为输入,训练权值;最后重新将原灰度图像的Kirsch算子梯度值输入到训练好的网络中,获得封闭的边沿并填充得到二值图像。考察了14幅像素为640×480的水果图像,结果表明:网络在很宽广的阈值范围内(0.001~0.99)分割得到完整、一致的二值图像;面积误差最小为0.9%,最大为8.83%,不依赖于优化的阈值,不需要对原始图像滤波预处理。与没有阈值及滤波的算法相比,本方案的误差和时间复杂度均更低;与设置了阈值和/或滤波的算法相比,本方案与之相当,甚至效果更优。

Activation Redistribution Based Hybrid Asymmetric Quantization Method of Neural Networks

The demand for adopting neural networks in resource-constrained embedded devices is continuously increasing.Quantization is one of the most promising solutions to reduce computational cost and memory storage on embedded devices.In order to reduce the complexity and overhead of deploying neural networks on Integeronly hardware,most current quantization methods use a symmetric quantization mapping strategy to quantize a floating-point neural network into an integer network.However,although symmetric quantization has the advantage of easier implementation,it is sub-optimal for cases where the range could be skewed and not symmetric.This often comes at the cost of lower accuracy.This paper proposed an activation redistribution-based hybrid asymmetric quantizationmethod for neural networks.The proposedmethod takes data distribution into consideration and can resolve the contradiction between the quantization accuracy and the ease of implementation,balance the trade-off between clipping range and quantization resolution,and thus improve the accuracy of the quantized neural network.The experimental results indicate that the accuracy of the proposed method is 2.02%and 5.52%higher than the traditional symmetric quantization method for classification and detection tasks,respectively.The proposed method paves the way for computationally intensive neural network models to be deployed on devices with limited computing resources.Codes will be available on https://github.com/ycjcy/Hybrid-Asymmetric-Quantization.

基于LVQ神经网络的青年女性胸部识别模型构建

为提高青年女性胸部形态分类的准确率,填补文胸号型分类体系存在的缺陷,结合青年女性胸部体型特征构建了一种基于LVQ神经网络的青年女性胸部识别模型。研究运用非接触式激光三维技术共采集216个青年女大学生胸部数据,将因子分析提取的9个胸部特征指标采用K-means聚类法,通过手肘图、轮廓系数图确定K值,最终将胸型分为4类。在此基础上构建LVQ神经网络胸型识别模型,以9项胸部特征指标为输入,4种胸型为输出,进行LVQ神经网络的训练。研究结果表明:模型经训练及测试后,识别精度达到95%,Kappa系数为0.932。与BP、PNN神经网络模型相比,在运算效率、模型精度和稳定性方面,LVQ神经网络模型的表现要明显优于其他两种神经网络。

Reinforcement Learning Based Quantization Strategy Optimal Assignment Algorithm for Mixed Precision

The quantization algorithm compresses the original network by reducing the numerical bit width of the model,which improves the computation speed. Because different layers have different redundancy and sensitivity to databit width. Reducing the data bit width will result in a loss of accuracy. Therefore, it is difficult to determinethe optimal bit width for different parts of the network with guaranteed accuracy. Mixed precision quantizationcan effectively reduce the amount of computation while keeping the model accuracy basically unchanged. In thispaper, a hardware-aware mixed precision quantization strategy optimal assignment algorithm adapted to low bitwidth is proposed, and reinforcement learning is used to automatically predict the mixed precision that meets theconstraints of hardware resources. In the state-space design, the standard deviation of weights is used to measurethe distribution difference of data, the execution speed feedback of simulated neural network accelerator inferenceis used as the environment to limit the action space of the agent, and the accuracy of the quantization model afterretraining is used as the reward function to guide the agent to carry out deep reinforcement learning training. Theexperimental results show that the proposed method obtains a suitable model layer-by-layer quantization strategyunder the condition that the computational resources are satisfied, and themodel accuracy is effectively improved.The proposed method has strong intelligence and certain universality and has strong application potential in thefield of mixed precision quantization and embedded neural network model deployment.

In situ calibrated angle between the quantization axis and the propagating direction of the light field for trapping neutral atoms

The recently developed magic-intensity trapping technique of neutral atoms efficiently mitigates the detrimental effect of light shifts on atomic qubits and substantially enhances the coherence time. This technique relies on applying a bias magnetic field precisely parallel to the wave vector of a circularly polarized trapping laser field. However, due to the presence of the vector light shift experienced by the trapped atoms, it is challenging to precisely define a parallel magnetic field, especially at a low bias magnetic field strength, for the magic-intensity trapping of85Rb qubits. In this work, we present a method to calibrate the angle between the bias magnetic field and the trapping laser field with the compensating magnetic fields in the other two directions orthogonal to the bias magnetic field direction. Experimentally, with a constantdepth trap and a fixed bias magnetic field, we measure the respective resonant frequencies of the atomic qubits in a linearly polarized trap and a circularly polarized one via the conventional microwave Rabi spectra with different compensating magnetic fields and obtain the corresponding total magnetic fields via the respective resonant frequencies using the Breit–Rabi formula. With known total magnetic fields, the angle is a function of the other two compensating magnetic fields.Finally, the projection value of the angle on either of the directions orthogonal to the bias magnetic field direction can be reduced to 0(4)° by applying specific compensating magnetic fields. The measurement error is mainly attributed to the fluctuation of atomic temperature. Moreover, it also demonstrates that, even for a small angle, the effect is strong enough to cause large decoherence of Rabi oscillation in a magic-intensity trap. Although the compensation method demonstrated here is explored for the magic-intensity trapping technique, it can be applied to a variety of similar precision measurements with trapped neutral atoms.

A Novel Quantization and Model Compression Approach for Hardware Accelerators in Edge Computing

Massive computational complexity and memory requirement of artificial intelligence models impede their deploy-ability on edge computing devices of the Internet of Things(IoT).While Power-of-Two(PoT)quantization is pro-posed to improve the efficiency for edge inference of Deep Neural Networks(DNNs),existing PoT schemes require a huge amount of bit-wise manipulation and have large memory overhead,and their efficiency is bounded by the bottleneck of computation latency and memory footprint.To tackle this challenge,we present an efficient inference approach on the basis of PoT quantization and model compression.An integer-only scalar PoT quantization(IOS-PoT)is designed jointly with a distribution loss regularizer,wherein the regularizer minimizes quantization errors and training disturbances.Additionally,two-stage model compression is developed to effectively reduce memory requirement,and alleviate bandwidth usage in communications of networked heterogenous learning systems.The product look-up table(P-LUT)inference scheme is leveraged to replace bit-shifting with only indexing and addition operations for achieving low-latency computation and implementing efficient edge accelerators.Finally,comprehensive experiments on Residual Networks(ResNets)and efficient architectures with Canadian Institute for Advanced Research(CIFAR),ImageNet,and Real-world Affective Faces Database(RAF-DB)datasets,indicate that our approach achieves 2×∼10×improvement in the reduction of both weight size and computation cost in comparison to state-of-the-art methods.A P-LUT accelerator prototype is implemented on the Xilinx KV260 Field Programmable Gate Array(FPGA)platform for accelerating convolution operations,with performance results showing that P-LUT reduces memory footprint by 1.45×,achieves more than 3×power efficiency and 2×resource efficiency,compared to the conventional bit-shifting scheme.

Image Steganography by Pixel-Value Differencing Using General Quantization Ranges

A new steganographic method by pixel-value differencing(PVD)using general quantization ranges of pixel pairs’difference values is proposed.The objective of this method is to provide a data embedding technique with a range table with range widths not limited to powers of 2,extending PVD-based methods to enhance their flexibility and data-embedding rates without changing their capabilities to resist security attacks.Specifically,the conventional PVD technique partitions a grayscale image into 1×2 non-overlapping blocks.The entire range[0,255]of all possible absolute values of the pixel pairs’grayscale differences in the blocks is divided into multiple quantization ranges.The width of each quantization range is a power of two to facilitate the direct embedding of the bit information with high embedding rates.Without using power-of-two range widths,the embedding rates can drop using conventional embedding techniques.In contrast,the proposed method uses general quantization range widths,and a multiple-based number conversion mechanism is employed skillfully to implement the use of nonpower-of-two range widths,with each pixel pair being employed to embed a digit in the multiple-based number.All the message bits are converted into a big multiple-based number whose digits can be embedded into the pixel pairs with a higher embedding rate.Good experimental results showed the feasibility of the proposed method and its resistance to security attacks.In addition,implementation examples are provided,where the proposed method adopts non-power-of-two range widths and employsmultiple-based number conversion to expand the data-hiding and steganalysis-resisting capabilities of other PVD methods.

Learning Vector Quantization-Based Fuzzy Rules Oversampling Method

Imbalanced datasets are common in practical applications,and oversampling methods using fuzzy rules have been shown to enhance the classification performance of imbalanced data by taking into account the relationship between data attributes.However,the creation of fuzzy rules typically depends on expert knowledge,which may not fully leverage the label information in training data and may be subjective.To address this issue,a novel fuzzy rule oversampling approach is developed based on the learning vector quantization(LVQ)algorithm.In this method,the label information of the training data is utilized to determine the antecedent part of If-Then fuzzy rules by dynamically dividing attribute intervals using LVQ.Subsequently,fuzzy rules are generated and adjusted to calculate rule weights.The number of new samples to be synthesized for each rule is then computed,and samples from the minority class are synthesized based on the newly generated fuzzy rules.This results in the establishment of a fuzzy rule oversampling method based on LVQ.To evaluate the effectiveness of this method,comparative experiments are conducted on 12 publicly available imbalance datasets with five other sampling techniques in combination with the support function machine.The experimental results demonstrate that the proposed method can significantly enhance the classification algorithm across seven performance indicators,including a boost of 2.15%to 12.34%in Accuracy,6.11%to 27.06%in G-mean,and 4.69%to 18.78%in AUC.These show that the proposed method is capable of more efficiently improving the classification performance of imbalanced data.

Hierarchical Controller Synthesis Under Linear Temporal Logic Specifications Using Dynamic Quantization

Linear temporal logic(LTL)is an intuitive and expressive language to specify complex control tasks,and how to design an efficient control strategy for LTL specification is still a challenge.In this paper,we implement the dynamic quantization technique to propose a novel hierarchical control strategy for nonlinear control systems under LTL specifications.Based on the regions of interest involved in the LTL formula,an accepting path is derived first to provide a high-level solution for the controller synthesis problem.Second,we develop a dynamic quantization based approach to verify the realization of the accepting path.The realization verification results in the necessity of the controller design and a sequence of quantization regions for the controller design.Third,the techniques of dynamic quantization and abstraction-based control are combined together to establish the local-to-global control strategy.Both abstraction construction and controller design are local and dynamic,thereby resulting in the potential reduction of the computational complexity.Since each quantization region can be considered locally and individually,the proposed hierarchical mechanism is more efficient and can solve much larger problems than many existing methods.Finally,the proposed control strategy is illustrated via two examples from the path planning and tracking problems of mobile robots.

基于LVQ神经网络的电力网络智能风险预警方法

针对现有电力网络风险预警方法在实际应用中,存在无法找出全部异常数据,无法实现对电力网络安全的准确判别问题,引入LVQ神经网络,开展对电力网络智能风险预警方法的设计研究。从多个来源采集电力网络运行数据,并对其处理。利用LVQ神经网络,实现对异常数据的排查和定级。最后,应用全业务合规管理监控,实现对电力网络风险的智能化预警和对预警结果的可视化展现。通过对比实验证明,新的预警方法可以实现对电力网络中异常数据的全部查出,促进电力网络运行安全性提升。

Does There Exist the Applicability Limit of PDE to Describe Physical Phenomena?—A Personal Survey of Quantization, QED, Turbulence

What does it mean to study PDE (Partial Differential Equation)? How and what to do “to claim proudly that I’m studying a certain PDE”? Newton mechanic uses mainly ODE (Ordinary Differential Equation) and describes nicely movements of Sun, Moon and Earth etc. Now, so-called quantum phenomenum is described by, say Schrödinger equation, PDE which explains both wave and particle characters after quantization of ODE. The coupled Maxwell-Dirac equation is also “quantized” and QED (Quantum Electro-Dynamics) theory is invented by physicists. Though it is said this QED gives very good coincidence between theoretical1 and experimental observed quantities, but what is the equation corresponding to QED? Or, is it possible to describe QED by “equation” in naive sense?

Quantization of Action for Elementary Particles and the Principle of Least Action

The uncertainty principle is a fundamental principle of quantum mechanics, but its exact mathematical expression cannot obtain correct results when used to solve theoretical problems such as the energy levels of hydrogen atoms, one-dimensional deep potential wells, one-dimensional harmonic oscillators, and double-slit experiments. Even after approximate treatment, the results obtained are not completely consistent with those obtained by solving Schrödinger’s equation. This indicates that further research on the uncertainty principle is necessary. Therefore, using the de Broglie matter wave hypothesis, we quantize the action of an elementary particle in natural coordinates and obtain the quantization condition and a new deterministic relation. Using this quantization condition, we obtain the energy level formulas of an elementary particle in different conditions in a classical way that is completely consistent with the results obtained by solving Schrödinger’s equation. A new physical interpretation is given for the particle eigenfunction independence of probability for an elementary particle: an elementary particle is in a particle state at the space-time point where the action is quantized, and in a wave state in the rest of the space-time region. The space-time points of particle nature and the wave regions of particle motion constitute the continuous trajectory of particle motion. When an elementary particle is in a particle state, it is localized, whereas in the wave state region, it is nonlocalized.

基于相空间重构与GSA-LVQ的有载调压变压器分接开关机械故障诊断

针对有载调压变压器分接开关机械故障诊断准确率不高以及潜在机械故障不能及时被发现的问题,提出了一种基于互补集合经验模态分解(CEEMD)、相空间重构结合万有引力搜索法(GSA)改进学习矢量量化神经网络(LVQ)的有载分接开关机械故障诊断新方法。采用CEEMD对振动信号进行时频域分解,然后通过C-C算法确定延迟时间和嵌入维数,对反映不同频率特征的固有模态函数(IMF)进行相空间重构,并提取反映混沌特征的两个特征量李雅普诺夫指数和关联维数构成特征向量。利用GSA优化LVQ,解决网络对初始连接权值敏感的问题,增强网络对有载分接开关机械故障分类识别性能。通过对有载分接开关机械状态的实验分析,证明了相空间重构结合GSA-LVQ算法的可行性和有效性。

基于LVQ神经网络的雷达杂波抑制方法

针对雷达目标检测后的剩余杂波影响雷达航迹起始和航迹跟踪的问题,提出基于学习向量量化(learning vector quantization,LVQ)神经网络的雷达杂波抑制方法。从雷达回波点迹的特征入手,通过分析目标点迹和杂波点迹的特征分布,通过人工提取特征的方式选取具有差异化的特征。根据特征数量和点迹类别数量构建LVQ神经网络分类模型,并对模型进行训练。利用训练好的LVQ神经网络分类模型对雷达回波点迹进行分类,区分目标点迹和杂波点迹,保留判别为目标的点迹,滤除判别为杂波的点迹,从而实现杂波抑制功能。通过对某型航管雷达的实测数据进行测试表明:该方法能够有效区分目标点迹和杂波点迹,杂波抑制能力比BP神经网络算法更好。

Finite-time H_(∞) filtering for Markov jump systems with uniform quantization

This paper is concerned with finite-time H_(∞) filtering for Markov jump systems with uniform quantization. The objective is to design quantized mode-dependent filters to ensure that the filtering error system is not only mean-square finite-time bounded but also has a prescribed finite-time H_(∞) performance. First, the case where the switching modes of the filter align with those of the MJS is considered. A numerically tractable filter design approach is proposed utilizing a mode-dependent Lyapunov function, Schur’s complement, and Dynkin’s formula. Then, the study is extended to a scenario where the switching modes of the filter can differ from those of the MJS. To address this situation, a mode-mismatched filter design approach is developed by leveraging a hidden Markov model to describe the asynchronous mode switching and the double expectation formula. Finally, a spring system model subject to a Markov chain is employed to validate the effectiveness of the quantized filter design approaches.

Quantization of Time Independent Damping Systems Using WKB Approximation

In this work time independent damping systems are studied using Lagrangian and Hamiltonian for time independent damping, which are present through the factor eλq. The Hamilton Jacobi equation is formulated to find the Hamilton Jacobi function S using separation of variables technique. We can form this function in compact form of two parts the first part as a function of coordinate q, and the second part as a function of time t. Finally, we find the ability of these systems to quantize through an illustrative example.

Path Integral Quantization of Non-Natural Lagrangian

Path integral technique is discussed using Hamilton Jacobi method. The Hamilton Jacobi function of non-natural Lagrangian is obtained using separation of variables method. This function makes an important role in path integral quantization. The path integral is obtained as integration over the canonical phase space coordinates, which contains the generalized coordinate q and the generalized momentum p. One illustrative example is considered to explain the application of our formalism.

DNA Computing with Water Strider Based Vector Quantization for Data Storage Systems

The exponential growth of data necessitates an effective data storage scheme,which helps to effectively manage the large quantity of data.To accomplish this,Deoxyribonucleic Acid(DNA)digital data storage process can be employed,which encodes and decodes binary data to and from synthesized strands of DNA.Vector quantization(VQ)is a commonly employed scheme for image compression and the optimal codebook generation is an effective process to reach maximum compression efficiency.This article introduces a newDNAComputingwithWater StriderAlgorithm based Vector Quantization(DNAC-WSAVQ)technique for Data Storage Systems.The proposed DNAC-WSAVQ technique enables encoding data using DNA computing and then compresses it for effective data storage.Besides,the DNAC-WSAVQ model initially performsDNA encoding on the input images to generate a binary encoded form.In addition,aWater Strider algorithm with Linde-Buzo-Gray(WSA-LBG)model is applied for the compression process and thereby storage area can be considerably minimized.In order to generate optimal codebook for LBG,the WSA is applied to it.The performance validation of the DNAC-WSAVQ model is carried out and the results are inspected under several measures.The comparative study highlighted the improved outcomes of the DNAC-WSAVQ model over the existing methods.

UCAV situation assessment method based on C-LSHADE-Means and SAE-LVQ

The unmanned combat aerial vehicle(UCAV)is a research hot issue in the world,and the situation assessment is an important part of it.To overcome shortcomings of the existing situation assessment methods,such as low accuracy and strong dependence on prior knowledge,a datadriven situation assessment method is proposed.The clustering and classification are combined,the former is used to mine situational knowledge,and the latter is used to realize rapid assessment.Angle evaluation factor and distance evaluation factor are proposed to transform multi-dimensional air combat information into two-dimensional features.A convolution success-history based adaptive differential evolution with linear population size reduc-tion-means(C-LSHADE-Means)algorithm is proposed.The convolutional pooling layer is used to compress the size of data and preserve the distribution characteristics.The LSHADE algorithm is used to initialize the center of the mean clustering,which over-comes the defect of initialization sensitivity.Comparing experi-ment with the seven clustering algorithms is done on the UCI data set,through four clustering indexes,and it proves that the method proposed in this paper has better clustering performance.A situation assessment model based on stacked autoen-coder and learning vector quantization(SAE-LVQ)network is constructed,and it uses SAE to reconstruct air combat data fea-tures,and uses the self-competition layer of the LVQ to achieve efficient classification.Compared with the five kinds of assess-ments models,the SAE-LVQ model has the highest accuracy.Finally,three kinds of confrontation processes from air combat maneuvering instrumentation(ACMI)are selected,and the model in this paper is used for situation assessment.The assessment results are in line with the actual situation.

A Secure and Effective Energy-Aware Fixed-Point Quantization Scheme for Asynchronous Federated Learning

Asynchronous federated learning(AsynFL)can effectivelymitigate the impact of heterogeneity of edge nodes on joint training while satisfying participant user privacy protection and data security.However,the frequent exchange of massive data can lead to excess communication overhead between edge and central nodes regardless of whether the federated learning(FL)algorithm uses synchronous or asynchronous aggregation.Therefore,there is an urgent need for a method that can simultaneously take into account device heterogeneity and edge node energy consumption reduction.This paper proposes a novel Fixed-point Asynchronous Federated Learning(FixedAsynFL)algorithm,which could mitigate the resource consumption caused by frequent data communication while alleviating the effect of device heterogeneity.FixedAsynFL uses fixed-point quantization to compress the local and global models in AsynFL.In order to balance energy consumption and learning accuracy,this paper proposed a quantization scale selection mechanism.This paper examines the mathematical relationship between the quantization scale and energy consumption of the computation/communication process in the FixedAsynFL.Based on considering the upper bound of quantization noise,this paper optimizes the quantization scale by minimizing communication and computation consumption.This paper performs pertinent experiments on the MNIST dataset with several edge nodes of different computing efficiency.The results show that the FixedAsynFL algorithm with an 8-bit quantization can significantly reduce the communication data size by 81.3%and save the computation energy in the training phase by 74.9%without significant loss of accuracy.According to the experimental results,we can see that the proposed AsynFixedFL algorithm can effectively solve the problem of device heterogeneity and energy consumption limitation of edge nodes.