A Trust Evaluation Model for Social Commerce Based on BP Neural Network

Recent years we have witnessed the rapid growth of social commerce in China, but many users are not willing to trust and use social commerce. So improving consumers’ trust and purchase intention has become a crucial factor in the success of social commerce. Business factors, environment factors and social factors including twelve secondary indexes build up a social commerce trust evaluation model. Questionnaires are handed out to collect twelve secondary indexes scores as input of BP neural network and composite score of trust as output. Model simulation shows that both training samples and test samples have low level of average error and standard deviation, which certify that the model has good stability and it is a good method for evaluating social commerce trust.

Neural Network Based Multi-level Fuzzy Evaluation Model for Mechanical Kinematic Scheme

To implement a quantificational evaluation for mechanical kinematic scheme more effectively,a multi-level and multi-objective evaluation model is presented using neural network and fuzzy theory. Firstly,the structure of evaluation model is constructed according to evaluation indicator system. Then evaluation samples are generated and provided to train this model. Thus it can reflect the relation between attributive value and evaluation result,as well as the weight of evaluation indicator. Once evaluation indicators of each candidate are fuzzily quantified and fed into the trained network model,the corresponding evaluation result is outputted and the best alternative can be selected. Under this model,expert knowledge can be effectively acquired and expressed,and the quantificational evaluation can be implemented for kinematic scheme with multi-level evaluation indicator system. Several key problems on this model are discussed and an illustration has demonstrated that this model is feasible and can be regarded as a new idea for solving kinematic scheme evaluation.

Prediction of constrained modulus for granular soil using 3D discrete element method and convolutional neural networks

To efficiently predict the mechanical parameters of granular soil based on its random micro-structure,this study proposed a novel approach combining numerical simulation and machine learning algorithms.Initially,3500 simulations of one-dimensional compression tests on coarse-grained sand using the three-dimensional(3D)discrete element method(DEM)were conducted to construct a database.In this process,the positions of the particles were randomly altered,and the particle assemblages changed.Interestingly,besides confirming the influence of particle size distribution parameters,the stress-strain curves differed despite an identical gradation size statistic when the particle position varied.Subsequently,the obtained data were partitioned into training,validation,and testing datasets at a 7:2:1 ratio.To convert the DEM model into a multi-dimensional matrix that computers can recognize,the 3D DEM models were first sliced to extract multi-layer two-dimensional(2D)cross-sectional data.Redundant information was then eliminated via gray processing,and the data were stacked to form a new 3D matrix representing the granular soil’s fabric.Subsequently,utilizing the Python language and Pytorch framework,a 3D convolutional neural networks(CNNs)model was developed to establish the relationship between the constrained modulus obtained from DEM simulations and the soil’s fabric.The mean squared error(MSE)function was utilized to assess the loss value during the training process.When the learning rate(LR)fell within the range of 10-5e10-1,and the batch sizes(BSs)were 4,8,16,32,and 64,the loss value stabilized after 100 training epochs in the training and validation dataset.For BS?32 and LR?10-3,the loss reached a minimum.In the testing set,a comparative evaluation of the predicted constrained modulus from the 3D CNNs versus the simulated modulus obtained via DEM reveals a minimum mean absolute percentage error(MAPE)of 4.43%under the optimized condition,demonstrating the accuracy of this approach.Thus,by combining DEM and CNNs,the variation of soil’s mechanical characteristics related to its random fabric would be efficiently evaluated by directly tracking the particle assemblages.

Simulation and optimization for synthetic technology of 2-chloro-4,6-dinitroresorcinol based on back-propagation neural network

Back-propagation neural network was applied to predict and optimize the synthetic technology of 2-chloro-4,6-dinitroresorcinol. A model was established based on back-propagation neural network using the experimental data of homogeneous design as the training sample set and the technological parameters were optimized by it. The optimal technological parameters are as follows： the reaction time is 4h, the reaction temperature is 80℃, the molar ratio of NaOH to 4,6-dinitro-1,2,3-trichlorobenzene is 5.5：1, the molar ratio of methanol to 4,6-dinitro-1,2,3- trichlorobenzene is 11：1, and the molar ratio of water to 4,6-dinitro-1,2,3-trichlorobenzene is 70：1. Under the optimal conditions, three groups of experiments were performed and the average yield of 2-chloro-4,6-dinitroresorcinol is 96.64%, the absolute error of it with the predicted value is -1.07%.

Researches On The Network Security Evaluation Method Based Bn BP Neural Network

This paper first describes the basic theory of BP neural network algorithm, defects and improved methods, establishes a computer network security evaluation index system, explores the computer network security evaluation method based on BP neural network, and has designed to build the evaluation model, and shows that the method is feasible through the MATLAB simulation experiments.

Fuzzy Neural Network-based Evaluation Model on Chinese Area＇s Macroscopical Credit

Traditional credit evaluation models failed to produce partial results due to their ignorance of the whole risks of credit environment. An excellent evaluating model on credit should take into account the credit environment impersonally and comprehensively. In this paper, a novel area＇s macroscopical credit evaluation model based on Fuzzy Neural Network is constructed. A set of scientific and reasonable evaluating indexes are extracted from feature space of macroscopical credit, then based on these indexes a Fuzzy Neural Network （FNN） model on credit evaluation is constructed and applied into the practical credit evaluation of some Chinese provinces randomly selected for the first time. Results show our model is both practical and capable.

Evaluating Synthetic Economic Benefit of Introducing Projects Based on BP Neural Network Model

A new method for the evaluation of synthetic economic benefit of introducing projects based on BP neural network is introduced. A specific and careful study on how to set up the BP neural network model for evaluating economic benefit of introducing projects is focused. The gained results compared with those regular methods show that the method makes a new way to solve the problem.

Study on Sex Ratio of Lampreys Based on Simulated Ecosystem-Food Web Model

Lampreys, as an important participant in the ecosystem, play an irreplaceable role in the stability of nature. A variety of models were used to simulate ecosystems and food webs, and the dynamic evolution of multiple populations was solved. The temporal changes of the biomass and the health of the ecosystem affected by the population of Lampreys in other ecological niches were solved. For problem 1, Firstly, a simple natural ecosystem is simulated based on the threshold model and BP neural network model. The dynamic change of the sex ratio of lampreys population and the fluctuation of ecosystem health value were found to generate time series maps. Lampreys overprey on low-niche animals, which damages the overall stability of the ecosystem. For problem 2, We used the Lotka-Volterra model to construct ecological competition between lampreys and primary consumers and predators. Then, the Lotka-Volterra equations were solved, and a control group without gender shift function was set up, which reflected the advantages and disadvantages of the sex-regulated characteristics of lampreys in the natural environment. For problem 3, The ecosystem model established in question 1 was further deepened, and the food web was simulated by the Beverton-Holt model and the Logistic time-dependent differential equations model. The parameters of the food web model were input into the neurons of the ecosystem model, and the two models were integrated to form an overall biosphere model. The output layer of the ecosystem neural network was input into the food web Beverton-Holt and Logistic differential equations, and finally, the three-dimensional analytical solution was obtained by numerical simulation. Then Euler method is used to obtain the exact value of the solution surface. The Random forest model was used to predict the future development of lampreys and other ecological niches. For problem 4, By investigating relevant literature, we normalized the populations of lampreys and a variety of fish as well as other ecological niche animals, plants and microorganisms in the same water area, set different impact weights of lampreys, constructed weight evaluation matrix, and obtained positive and negative ideal solution vectors and negative correlation proximity by using TOPSIS comprehensive evaluation method. It is concluded that many kinds of fish are greatly affected by the sex regulation of lampreys.

Genetic Algorithm Based on New Evaluation Function and Mutation Model for Training of BPNN

A local minimum is frequently encountered in the training of back propagation neural networks (BPNN), which sharply slows the training process. In this paper, an analysis of the formation of local minima is presented, and an improved genetic algorithm (GA) is introduced to overcome local minima. The Sigmoid function is generally used as the activation function of BPNN nodes. It is the flat characteristic of the Sigmoid function that results in the formation of local minima. In the improved GA, pertinent modifications are made to the evaluation function and the mutation model. The evaluation of the solution is associated with both the training error and gradient. The sensitivity of the error function to network parameters is used to form a self adapting mutation model. An example of industrial application shows the advantage of the improved GA to overcome local minima.

A Web-Based Integrated Intelligent System for Sensory Fabric Hand Evaluation

This paper presents a web-based integrated system for on-line sensory fabric hand evaluation. The methods of fuzzy techniques, neural networks, classical factorial analysis and other data analysis are used in the system to analyze the objective and subjective data, and to build the relationship between them. Given the objective data of a new fabric sample, the system can provide its sensory hand data and its total hand grade. In meantime, the total hand grade can be obtained directly from the sensory fabric hand data if provided. The sensory evaluation system is developed in Internet environment using Java language and SQL server database management system.

大数据与计算模型

当前,人工智能持续升温,大语言模型吸引了众多人士的关注,并在全球范围内掀起了一股热潮。人工智能的成功本质上不是大算力“出奇迹”,而是改变了计算模型。首先,肯定了数据对于人工智能的基础性作用,指出合成数据将是未来数据的主要来源。然后,回顾了计算模型的发展历程,重点介绍了神经网络模型与图灵模型的历史性竞争;指出了大模型的重要标志是机器涌现智能,强调大模型的本质是“压缩”;分析了大模型产生“幻觉”的原因。最后,呼吁科技界在智能化科研中要重视大科学模型。

基于BP神经网络的高校教师精准教学能力评价模型构建

通过精准教学以促进学生个性化成长是教育理想和国家政策的不懈追求.高校教师是实施精准教学的“基”,现有关于其教学能力的评价体系中普遍存在概念不清和多采用主观构建评价指标的问题.为此,开展了基于BP神经网络的高校教师精准教学能力评价模型研究.首先,以理论研究为基础,对精准教学能力进行等级划分并构建评价指标框架,运用层级分析法建立指标权重;其次,利用BP神经网络智能学习的特性,以不同数据类型的指标值为输入,对应能力综合值为输出,检验精准教学能力分级及指标权重的合理性,进而生成较为客观的评价模型;最后,利用开发的评价系统和调查问卷进行样本数据采集和模型检验,从神经网络对数据的分类、拟合及仿真结果来看,模型能够对高校教师的精准教学能力进行客观评价,教师对模型测量结果的准确性也具有较高认可度.

基于LDA-BP神经网络的高校思政课教师数据驱动决策力评价研究

数据驱动决策力为高校思政课教师提供科学合理的教学判断,对数据驱动决策力进行评价研究,有助于提高高校思政课教师的数据决策水平,进而提升思想政治教育教学质量。鉴于传统评测方法缺乏客观性与可重复性,运用LDA-BP神经网络技术构建高校思政课数据驱动决策力的指标体系与评价模型。首先,运用LDA方法对高校思想政治教育相关的政策文本与研究文献进行主题提取,并将主题信息作为指标构建基础;其次,通过研读文献与政策文本,并结合主题分析结果构建高校思政课教师数据驱动决策力评价指标体系;最后,通过对BP神经网络的训练及测试来生成高校思政课教师数据驱动决策力的评价模型。研究表明,高校思政课教师的专业知识、教学水平以及数据分析与解读能力是影响数据驱动决策能力的关键因素,据此,理应从素养提升、文化培育、管理革新、政府支持等方面入手增强数据驱动决策力。

不同农业生产托管模式综合性能评价及影响因素分析

农业生产托管是推进服务规模经营、加速小农户与现代农业生产有机衔接的有效途径,因此,探究何种农业生产托管模式更具优势具有重要意义。基于单环节、多环节及全程托管等生产托管模式,以黑龙江农业生产托管情况为数据基础,运用BP神经网络和障碍度模型,综合评价不同农业生产托管模式并探讨其影响因素。结果表明,全程托管模式综合性能更好。引起不同模式差异的共性因素表现在经济性准则层中,说明经济性是农业生产托管综合性能提升的关键,而全程农业生产托管主要受公顷收入影响,受其他因素影响较小。据此,提出适度推广农业生产全程托管模式等对策建议。

一种基于深度神经网络的多阶段PUF抗建模能力评估方法

针对现有评估方法均无法全面评估物理不可克隆函数(PUF)抗建模能力的问题,定义PUF面临的3级建模威胁模型,分别阐明3类攻击的目的、对手的知识能力、攻击策略和攻击模式。基于此,设计一种基于深度神经网络的PUF抗建模能力评估方法,使用前馈神经网络建模攻击和侧信道建模攻击作为评估工具,分3个阶段依次评估目标PUF抵御机器学习建模攻击、可靠性侧信道攻击和功耗/电磁侧信道攻击的能力,解决传统方法无法评估PUF抗侧信道建模能力的问题。评估结果表明,被测PUF中仅有少部分拥有抗机器学习建模和抗可靠性建模能力,但均不具备抗功耗侧信道建模能力。

公立医院床位利用效率及配置合理性评估研究

目的分析上海市某三级甲等公立医院各科室床位利用效率,为评估床位资源配置合理性提供方法学依据。方法以上海市某三级甲等医院2023年的医疗运营数据为基础,利用床位利用模型进行可视化呈现,评价床位资源的利用效率。运用床位评价指标测算各科室床位的合理区间,得出床位调整方案。采用多层感知器神经网络模型评估床位调整方案的准确性、合理性、可行性。结果床位利用模型显示,11个(25.00%)科室属于床位效率型,11个(25.00%)科室属于床位周转型,16个(36.36%)科室属于床位闲置型,6个(13.64%)科室属于压床型。床位评价指标显示,8个科室床位数不需改变,16个科室床位数需要适当减少,20个科室床位数需要结合实际情况增加。利用多层感知器神经网络搭建床位不变、床位减少、床位增加模型。床位不变模型的受试者工作特征曲线下面积(area under curve,AUC)=0.719,灵敏度为100.00%,特异度为40.63%。床位减少模型的AUC=0.875,灵敏度为83.33%,特异度为85.00%。床位增加模型的AUC=0.913,灵敏度为100.00%,特异度为72.22%。结论医院整体床位利用效率较低且不同科室间床位的利用效率存在差异,通过多层感知器神经网络建立的床位增加模型评估结果与床位利用模型和床位评价指标的结果具有较好的一致性,能够为医院床位资源配置管理提供方法学依据,进而实现医院床位精细化管理。

高山峡谷地区地质灾害易发性评价——以怒江州为例

高山峡谷地区地质灾害频发,目的为探究地质灾害易发性空间分布状况,方法以怒江州为研究区,综合地质条件、气象水文、植被覆盖等因素,筛选高程、坡度、坡向、曲率、起伏度等12个共线性低的评价因子,构建区域易发性评价指标体系,并基于栅格单元采用信息量(information value,IV)模型、信息量-BP神经网络(information value-back propagation neural networks,IV-BPNN)耦合模型和信息量-支持向量机(information value-support vector machine,IV-SVM)耦合模型进行地质灾害易发性评价。结果结果表明:(1)用实际地质灾害点验证易发性结果,灾害点与3种易发性结果在空间分布上具有较好的一致性;(2)将易发性指数划分为低、中、高和极高易发4个等级,其中IV模型、IV-BPNN耦合模型与IV-SVM耦合模型的高+极高易发区面积占比分别为37.12%,32.36%,23.08%,高与极高易发区呈线状分布,主要集中在怒江、澜沧江、独龙江等水系沿岸地区、道路附近和地质构造活跃的区域;(3)IV模型、IV-BPNN耦合模型与IV-SVM耦合模型的受试者曲线(receiver operating characteristic curve,ROC)的曲线下面积(area under the curve,AUC)分别为0.884,0.889,0.901。结论3种地质灾害易发性评价模型均有较高的预测精度,其中IV-SVM耦合模型准确率最高,分区结果较可靠,可为当地政府制定地质灾害防治措施提供参考。

图神经网络节点分类任务基准测试及分析

图神经网络(Graph Neural Network,GNN)模型由于采用端到端的模型架构,在训练过程中能够更好地将节点隐藏特征的学习和分类目标协同起来,相比图嵌入(Graph Embedding)的方法,其在节点分类等任务上得到了较大的性能提升。但是,已有图神经网络模型实验对比阶段普遍存在的数据集类型单一、样本量不足、数据集切分不规范、对比模型规模及范围有限、评价指标单一、缺乏模型训练耗时对比等问题。为此,文中选取了包括cora,citeseer,pubmed,deezer等在内的来自不同领域(引文网络、社交网络及协作网络等)的共计20种数据集,以准确率、精确率、召回率、F-score值及模型训练耗时为多维评价指标,在FastGCN,PPNP,ChebyNet,DAGNN等17种主流图神经网络模型上,进行了全面且公平的节点分类任务基准测评,进而为真实业务场景下的模型选择提供了决策参考。通过基准测试实验发现,一方面,影响模型训练速度的因素排名依次是节点属性维度、图节点规模及图边的规模;另一方面,并不存在赢者通吃的模型,即不存在在所有数据集下全都表现优异的模型,特别是在公平的基准测试配置环境下,结构简洁的模型反而比复杂的GNN模型有着更好的性能表现。

面向人眼宽视场视觉成像质量的评价方法

为考虑边缘视觉的影响,实现对人眼宽视场条件下视觉成像质量的量化,提出一种基于孪生神经网络的多视域成像质量评价方法。构建个性化眼模型,根据波前像差值获得不同视场处的成像图;利用色彩差异分割成像图中的不同区域,将其作为子图像以样本对的形式输入到孪生神经网络中,提取图像的多维特征;模拟人眼对色彩的差异化感知,对区域图像质量评价值进行加权,得到对整幅图像的质量评价。为验证算法的有效性,在TID2013、LIVE和CSIQ这3个图像数据库上进行实验,其结果表明,该方法对多视场处成像质量的量化评估有良好的性能。