Using Cross Entropy as a Performance Metric for Quantifying Uncertainty in DNN Image Classifiers: An Application to Classification of Lung Cancer on CT Images

Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation metric for image classifier models and apply it to the CT image classification of lung cancer. A convolutional neural network is employed as the deep neural network (DNN) image classifier, with the residual network (ResNet) 50 chosen as the DNN archi-tecture. The image data used comprise a lung CT image set. Two classification models are built from datasets with varying amounts of data, and lung cancer is categorized into four classes using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic neighbor embedding to visually explain the data distribution after classification. Experimental results demonstrate that cross en-tropy is a highly useful metric for evaluating the reliability of image classifier models. It is noted that for a more comprehensive evaluation of model perfor-mance, combining with other evaluation metrics is considered essential. .

A Cross Entropy-Genetic Algorithm for m-Machines No-Wait Job-ShopScheduling Problem

No-wait job-shop scheduling (NWJSS) problem is one of the classical scheduling problems that exist on many kinds of industry with no-wait constraint, such as metal working, plastic, chemical, and food industries. Several methods have been proposed to solve this problem, both exact (i.e. integer programming) and metaheuristic methods. Cross entropy (CE), as a new metaheuristic, can be an alternative method to solve NWJSS problem. This method has been used in combinatorial optimization, as well as multi-external optimization and rare-event simulation. On these problems, CE implementation results an optimal value with less computational time in average. However, using original CE to solve large scale NWJSS requires high computational time. Considering this shortcoming, this paper proposed a hybrid of cross entropy with genetic algorithm (GA), called CEGA, on m-machines NWJSS. The results are compared with other metaheuritics: Genetic Algorithm-Simulated Annealing (GASA) and hybrid tabu search. The results showed that CEGA providing better or at least equal makespans in comparison with the other two methods.

Introduce a Novel PCA Method for Intuitionistic Fuzzy Sets Based on Cross Entropy

In this paper, a new method for Principal Component Analysis in intuitionistic fuzzy situations has been proposed. This approach is based on cross entropy as an information index. This new method is a useful method for data reduction for situations in which data are not exact. The inexactness in the situations assumed here is due to fuzziness and missing data information, so that we have two functions (membership and non-membership). Thus, method proposed here is suitable for Atanasov’s Intuitionistic Fuzzy Sets (A-IFSs) in which we have an uncertainty due to a mixture of fuzziness and missing data information. For the demonstration of the application of the method, we have used an example and have presented a conclusion.

An improved cross entropy algorithm for steelmaking-continuous casting production scheduling with complicated technological routes

In order to increase productivity and reduce energy consumption of steelmaking-continuous casting(SCC) production process, especially with complicated technological routes, the cross entropy(CE) method was adopted to optimize the SCC production scheduling(SCCPS) problem. Based on the CE method, a matrix encoding scheme was proposed and a backward decoding method was used to generate a reasonable schedule. To describe the distribution of the solution space, a probability distribution model was built and used to generate individuals. In addition, the probability updating mechanism of the probability distribution model was proposed which helps to find the optimal individual gradually. Because of the poor stability and premature convergence of the standard cross entropy(SCE) algorithm, the improved cross entropy(ICE) algorithm was proposed with the following improvements: individual generation mechanism combined with heuristic rules, retention mechanism of the optimal individual, local search mechanism and dynamic parameters of the algorithm. Simulation experiments validate that the CE method is effective in solving the SCCPS problem with complicated technological routes and the ICE algorithm proposed has superior performance to the SCE algorithm and the genetic algorithm(GA).

Time dependence of entropy flux and entropy production for a dynamical system driven by noises with coloured cross-correlation

This paper shows the Fokker-Planck equation of a dynamical system driven by coloured cross-correlated white noises in the absence and presence of a small external force. Based on the Fokker-Planck equation and the definition of Shannon＇s information entropy, the time dependence of entropy flux and entropy production can be calculated. The present results can be used to explain the extremal behaviour of time dependence of entropy flux and entropy production in view of the dissipative parameter γ of the system, coloured cross-correlation time τ and coloured cross-correlation strength λ.

Upper bound for the time derivative of entropy for a dynamical system driven by coloured cross-correlated white noises

It is shown how the cross-correlation time and strength of coloured cross-correlated white noises can set an upper bound for the time derivative of entropy in a nonequilibrium system. The value of upper bound can be calculated directly based on the Schwartz inequality principle and the Fokker-Planck equation of the dynamical system driven by coloured cross-correlated white noises. The present calculations can be used to interpret the interplay of the dissipative constant and cross-correlation time and strength of coloured cross-correlated white noises on the upper bound.

Improved Cross Entropy Algorithm for Steelmaking Continuous Casting Production Scheduling with Minimum Power Consumption

A matrix encoding scheme for the steelmaking continuous casting( SCC) production scheduling( SCCPS) problem and the corresponding decoding method are proposed. Based on it,a cross entropy( CE) method is adopted and an improved cross entropy( ICE) algorithm is proposed to solve the SCCPS problem to minimize total power consumption. To describe the distribution of the solution space of the CE method,a probability model is built and used to generate individuals by sampling and a probability updating mechanism is introduced to trace the promising samples. For the ICE algorithm,some samples are generated by the heuristic rules for the shortest makespan due to the relation between the makespan and the total power consumption,which can reduce the search space greatly. The optimal sample in each iteration is retained through a retention mechanism to ensure that the historical optimal sample is not lost so as to improve the efficiency and global convergence. A local search procedure is carried out on a part of better samples so as to improve the local exploitation capability of the ICE algorithm and get a better result. The parameter setting is investigated by the Taguchi method of design-of-experiment. A number of simulation experiments are implemented to validate the effectiveness of the ICE algorithm in solving the SCCPS problem and also the superiority of the ICE algorithm is verified through the comparison with the standard cross entropy( SCE) algorithm.

Cross Entropy Based Sparse Logistic Regression to Identify Phenotype-Related Mutations in Methicillin-Resistant <i>Staphylococcus aureus</i>

Emergence of drug resistant bacteria is one of the serious problems in today’s public health. However, the relationship between genomic mutation of bacteria and the phenotypic difference of them is still unclear. In this paper, based on the mutation information in whole genome sequences of 96 MRSA strains, two kinds of phenotypes (pathogenicity and drug resistance) were learnt and predicted by machine learning algorithms. As a result of effective feature selection by cross entropy based sparse logistic regression, these phenotypes could be predicted in sufficiently high accuracy (100% and 97.87%, respectively) with less than 10 features. It means that we could develop a novel rapid test method in the future for checking MRSA phenotypes.

Application of Weighted Cross-Entropy Loss Function in Intrusion Detection

The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence problem. Firstly, we utilize a network model architecture combining Gelu activation function and deep neural network;Secondly, the cross-entropy loss function is improved to a weighted cross entropy loss function, and at last it is applied to intrusion detection to improve the accuracy of intrusion detection. In order to compare the effect of the experiment, the KDDcup99 data set, which is commonly used in intrusion detection, is selected as the experimental data and use accuracy, precision, recall and F1-score as evaluation parameters. The experimental results show that the model using the weighted cross-entropy loss function combined with the Gelu activation function under the deep neural network architecture improves the evaluation parameters by about 2% compared with the ordinary cross-entropy loss function model. Experiments prove that the weighted cross-entropy loss function can enhance the model’s ability to discriminate samples.

Incremental clustering algorithm via crossentropy

A new incremental clustering method is presented, which partitions dynamic data sets by mapping data points in high dimension space into low dimension space based on （fuzzy） cross-entropy（CE）. This algorithm is divided into two parts： initial clustering process and incremental clustering process. The former calculates fuzzy cross-entropy or cross-entropy of one point relafive to others and a hierachical method based on cross-entropy is used for clustering static data sets. Moreover, it has the lower time complexity. The latter assigns new points to the suitable cluster by calculating membership of data point to existed centers based on the cross-entropy measure. Experimental compafisons show the proposed methood has lower time complexity than common methods in the large-scale data situations cr dynamic work environments.

基于组合赋权-DEA的跨境铁路外部环境风险评价

研究目的:跨境铁路大多穿越不同国家,铁路沿线的自然、社会环境条件复杂多变,给跨境铁路外部环境安全带来巨大威胁。为保障跨境铁路平稳运行,采用组合赋权-DEA方法在全面识别跨境铁路沿线风险的基础上进行风险评价,旨在为跨境铁路风险管理工作提供借鉴。研究结论:(1)全面识别跨境铁路沿线外部环境风险,从自然环境与社会环境方面共选取30个风险指标构建跨境铁路外部环境风险评价指标体系,结合AHP-熵权法对各风险指标组合赋权;(2)应用基于DEA的风险评价方法,以各风险指标发生的概率和后果为变量,对跨境铁路外部环境风险进行评价和排序;(3)研究结果显示,跨境铁路侵限风险应予以重点关注,安保区内违法生产经营次之;(4)本文研究可为跨境铁路沿线外部环境安全管理工作提供新的思路,保障跨境铁路运输更加平稳高效运行。

融合残差连接的图像语义分割方法

由于传统SegNet模型在采样过程中产生了大量信息损失,导致图像语义分割精度较低,为此提出了一种融合残差连接的新型编-解码器网络结构:文中引入了多残差连接策略,更为全面地保留了多尺度图像中包含的大量细节信息,降低还原降采样所带来的信息损失;为进一步加速网络训练的收敛效率,改善样本的不平衡问题,设计了一种带平衡因子的交叉熵损失函数,对正负样本不平衡现象予以针对性的优化,使得模型的训练更加高效;实验表明该方法较好地解决了语义分割中信息损失以及分割不准确的问题,与SegNet相比,本网络在Cityscapes数据集上进行精细标注的mIoU值提高了约13%。

基于区间毕达哥拉斯犹豫模糊熵和交叉熵的ELECTRE II决策方法

针对属性权重完全未知或部分已知,属性值为区间毕达哥拉斯犹豫模糊数的多属性决策问题,提出了基于区间毕达哥拉斯犹豫模糊熵和交叉熵的ELECTRE II法。首先给出区间毕达哥拉斯犹豫模糊数的区间形式的得分函数和精度函数,定义新的距离测度。然后基于区间毕达哥拉斯犹豫模糊数的模糊因子、直觉因子和幅度因子,给出熵和交叉熵公式,并证明其性质,提出了基于熵和交叉熵确定属性权重的方法。最后提出了区间毕达哥拉斯犹豫模糊环境下的改进的ELECTRE II法,利用综合优势值对方案进行排序,并通过算例和比较分析验证了该方法的可行性和有效性。

考虑对称交互熵的对偶犹豫模糊企业环境行为决策模型分析

顺应绿色新发展理念,建设高质量生态文明,提升企业环境治理能力现代化水平,企业环境行为指标已逐渐被纳入投资者考量范围。本文针对第三方国际环境审计平台对企业环境行为评价的问题,研究面向对偶犹豫模糊评价信息的聚类方法。首先,定义对偶犹豫模糊相对熵与对称交互熵,并基于信息论角度提出一个新的对偶犹豫模糊相似度公式;然后,构造相似系数矩阵,并基于编网聚类方法对对偶犹豫模糊集进行聚类。最后,以不同指标权重下评价企业环境行为优劣程度为例进行计算,并与使用传统相关系数聚类方法所得结果进行对比,说明在考虑决策者提供的信息量较大的情况下,本文方法概念清晰、计算简单、分辨率高,是一种更加灵活、全面的多层次评价方法,为完善企业环境评价系统的构建提供了一种新思路。

基于延迟线组合调相的高能效自适应混合预编码方案

针对毫米波大规模多输入多输出系统采用混合预编码技术所带来的高功耗影响,基于延迟线组合调相器件设计了一种间接全连接型混合预编码系统结构,并提出一种自适应连接的混合预编码方案,可大幅减少与天线直连的调相器数量从而降低硬件造成的功耗损失。方案将编码矩阵的求解分为数字编码矩阵、模拟编码矩阵和开关组成的连接交换矩阵3个部分进行交替优化;提出一种基于互补正交投影矩阵的算法来解决模拟编码矩阵的优化;利用功率约束条件和最小二乘算法简化数字编码矩阵的求解;针对连接交换矩阵的离散组合优化问题,利用低复杂度的交叉熵算法进行优化。仿真结果表明,所提方案可以保证系统性能在接近纯数字预编码方案的同时有效提高系统的能量效率。

基于复杂纹理特征融合的材料图像分割方法

为解决材料图像分割中存在小样本、纹理复杂和数据分布不平衡的问题,抓住材料图像同相像素具有高度相似性的特性,提出一种基于复杂纹理特征融合的材料图像分割方法。在编码阶段,使用全卷积神经网络(FCN)作为基础网络,VGG16作为骨干网络;将改进的FCN的每层的特征图放入设计的级联的特征融合模块(CFF block),融合高低层语义信息;将融合的特征图放入多尺度学习模块(multi-scale block)进一步提取纹理特征。在解码阶段,对特征图施加注意力机制(Attention block),保留关键的特征图;针对材料图像中数据不平衡问题,采用并改进Dice损失,优化分割结果。通过对比实验和消融实验验证该方法的mIoU在多个数据集上均优于经典的深度学习方法。

基于模糊交叉熵与TOPSIS的碳审计风险评估

审计在促进“双碳”目标实现的过程中发挥着重要的监督与评价作用,有效规范了企业的碳排放行为,推动了企业生产方式的绿色转型。当前,我国的碳审计发展尚处起步阶段,存在着诸如制度不健全、碳数据核算困难、碳审计人才缺乏等一系列问题,多种因素的叠加使得碳审计工作面临着极大的风险与挑战。在文献梳理的基础上,本文依托传统风险导向审计理论,首先从环境风险、固有风险、控制风险、检查风险四个层面建立碳审计风险评估指标体系;其次,借助模糊交叉熵和TOPSIS算法构架新型的碳审计风险评估模型,探索碳审计风险评估模型的运行步骤,明晰风险评估模型中的决策方案排序策略;再次,通过对特定案例的深入分析,阐释模糊交叉熵和TOPSIS风险评估模型在碳审计风险评估中的具体应用流程,全方位探究风险评估模型中各类运算结果的分析方法;最后,针对碳审计所面临的各种风险,相应地从碳审计模式设计、双碳大数据中心构建、人才队伍建设三个方面提出管理碳审计检查风险的措施与建议。有关研究思路和结论能够为审计组织如何发现碳审计存在的关键风险因素、衡量碳审计风险水平、评价和控制碳审计风险提供理论支持。

中国城市群突破性创新能力分析——基于环长株潭城市群的实证

为助推以长沙为核心的环长株潭城市群全球研发中心城市建设,选取环长株潭城市群2010—2021年的发展数据,从突破性创新支持、创新管理、创新投入、创新产出和创新环境等5个维度构建城市群突破性创新能力SMIOE评价模型,采用信息贡献率分析法,遴选确定17个核心评价指标,使用“交叉熵权-TOPSIS”法测算环长株潭城市群的突破性创新能力指数。研究结果发现,SMIOE评价模型能客观反映城市群突破性创新能力的真实水平,环长株潭城市群突破性创新能力总体不均匀、发展水平较低,除长沙、株洲、衡阳外,2010—2021年间,其他5个城市指数分别呈“M”型和倒“V”型下降;突破性创新能力较高的城市主要集中于湖南东北部。最后基于研究结论,从树立全域创新、协同创新和重点创新等3个方面理念,提出环长株潭城市群突破性创新能力的发展建议,为促进环长株潭城市群创新群落早日提供参考。