Game Theory Based Model for Predictive Analytics Using Distributed Position Function

This paper presents a game theory-based method for predicting the outcomes of negotiation and group decision-making problems. We propose an extension to the BDM model to address problems where actors’ positions are distributed over a position spectrum. We generalize the concept of position in the model to incorporate continuous positions for the actors, enabling them to have more flexibility in defining their targets. We explore different possible functions to study the role of the position function and discuss appropriate distance measures for computing the distance between the positions of actors. To validate the proposed extension, we demonstrate the trustworthiness of our model’s performance and interpretation by replicating the results based on data used in earlier studies.

Predictive Analytics for Project Risk Management Using Machine Learning

Risk management is relevant for every project that which seeks to avoid and suppress unanticipated costs, basically calling for pre-emptive action. The current work proposes a new approach for handling risks based on predictive analytics and machine learning (ML) that can work in real-time to help avoid risks and increase project adaptability. The main research aim of the study is to ascertain risk presence in projects by using historical data from previous projects, focusing on important aspects such as time, task time, resources and project results. t-SNE technique applies feature engineering in the reduction of the dimensionality while preserving important structural properties. This process is analysed using measures including recall, F1-score, accuracy and precision measurements. The results demonstrate that the Gradient Boosting Machine (GBM) achieves an impressive 85% accuracy, 82% precision, 85% recall, and 80% F1-score, surpassing previous models. Additionally, predictive analytics achieves a resource utilisation efficiency of 85%, compared to 70% for traditional allocation methods, and a project cost reduction of 10%, double the 5% achieved by traditional approaches. Furthermore, the study indicates that while GBM excels in overall accuracy, Logistic Regression (LR) offers more favourable precision-recall trade-offs, highlighting the importance of model selection in project risk management.

Leveraging Predictive Analytics for Strategic Corporate Communications: Enhancing Stakeholder Engagement and Crisis Management

This study explores the integration of predictive analytics in strategic corporate communications, with a specific focus on stakeholder engagement and crisis management. Our mixed-methods approach, which combines a comprehensive literature review with case studies of five multinational corporations, allows us to investigate the applications, challenges, and ethical implications of leveraging predictive models in communication strategies. While our findings reveal significant potential for enhancing personalized content delivery, real-time sentiment analysis, and proactive crisis management, we stress the need for careful consideration of challenges such as data privacy concerns and algorithmic bias. This emphasis on ethical implementation is crucial in navigating the complex landscape of predictive analytics in corporate communications. To address these issues, we propose a framework that prioritizes ethical considerations. Furthermore, we identify key areas for future research, thereby contributing to the evolving field of data-driven communication management.

A Weighted Multi-Layer Analytics Based Model for Emoji Recommendation

The developed system for eye and face detection using Convolutional Neural Networks(CNN)models,followed by eye classification and voice-based assistance,has shown promising potential in enhancing accessibility for individuals with visual impairments.The modular approach implemented in this research allows for a seamless flow of information and assistance between the different components of the system.This research significantly contributes to the field of accessibility technology by integrating computer vision,natural language processing,and voice technologies.By leveraging these advancements,the developed system offers a practical and efficient solution for assisting blind individuals.The modular design ensures flexibility,scalability,and ease of integration with existing assistive technologies.However,it is important to acknowledge that further research and improvements are necessary to enhance the system’s accuracy and usability.Fine-tuning the CNN models and expanding the training dataset can improve eye and face detection as well as eye classification capabilities.Additionally,incorporating real-time responses through sophisticated natural language understanding techniques and expanding the knowledge base of ChatGPT can enhance the system’s ability to provide comprehensive and accurate responses.Overall,this research paves the way for the development of more advanced and robust systems for assisting visually impaired individuals.By leveraging cutting-edge technologies and integrating them into amodular framework,this research contributes to creating a more inclusive and accessible society for individuals with visual impairments.Future work can focus on refining the system,addressing its limitations,and conducting user studies to evaluate its effectiveness and impact in real-world scenarios.

Employing a Backpropagation Neural Network for Predicting Fear of Cancer Recurrence among Non-Small Cell Lung Cancer Patients

Objective:Non-small cell lung cancer(NSCLC)patients often experience significant fear of recurrence.To facilitate precise identification and appropriate management of this fear,this study aimed to compare the efficacy and accuracy of a Backpropagation Neural Network(BPNN)against logistic regression in modeling fear of cancer recurrence prediction.Methods:Data from 596 NSCLC patients,collected between September 2023 and December 2023 at the Cancer Hospital of the Chinese Academy of Medical Sciences,were analyzed.Nine clinically and statistically significant variables,identified via univariate logistic regression,were inputted into both BPNN and logistic regression models developed on a training set(N=427)and validated on an independent set(N=169).Model performances were assessed using Area Under the Receiver Operating Characteristic(ROC)Curve and Decision Curve Analysis(DCA)in both sets.Results:The BPNN model,incorporating nine selected variables,demonstrated superior performance over logistic regression in the training set(AUC=0.842 vs.0.711,p<0.001)and validation set(0.7 vs.0.675,p<0.001).Conclusion:The BPNN model outperforms logistic regression in accurately predicting fear of cancer recurrence in NSCLC patients,offering an advanced approach for fear assessment.

Optimizing Healthcare Outcomes through Data-Driven Predictive Modeling

This study investigates the transformative potential of big data analytics in healthcare, focusing on its application for forecasting patient outcomes and enhancing clinical decision-making. The primary challenges addressed include data integration, quality, privacy issues, and the interpretability of complex machine-learning models. An extensive literature review evaluates the current state of big data analytics in healthcare, particularly predictive analytics. The research employs machine learning algorithms to develop predictive models aimed at specific patient outcomes, such as disease progression and treatment responses. The models are assessed based on three key metrics: accuracy, interpretability, and clinical relevance. The findings demonstrate that big data analytics can significantly revolutionize healthcare by providing data-driven insights that inform treatment decisions, anticipate complications, and identify high-risk patients. The predictive models developed show promise for enhancing clinical judgment and facilitating personalized treatment approaches. Moreover, the study underscores the importance of addressing data quality, integration, and privacy to ensure the ethical application of predictive analytics in clinical settings. The results contribute to the growing body of research on practical big data applications in healthcare, offering valuable recommendations for balancing patient privacy with the benefits of data-driven insights. Ultimately, this research has implications for policy-making, guiding the implementation of predictive models and fostering innovation aimed at improving healthcare outcomes.

基于模糊PA算法的微博信息传播分享预测研究

微博已经成为网民信息获取、分享的主要平台之一。对信息分享进行预测,是对微博信息传播进行监管控制的基础。微博用户和信息属性中包含着用户偏好、生理特征、内容类型等数据,基于这些数据可进行信息分享预测。分析了微博信息传播模式、分享预测理论方法,基于PA算法提出了信息分享预测模型,以新浪微博数据为例验证了预测模型。结果表明,该模型对信息分享具有较高的预测准确率。

孕妇孕晚期血浆t-PA和PAI-1对HND的预测价值

目的探讨孕妇孕晚期血浆组织纤溶酶原激活物(t-PA)和组织纤溶酶原抑制物(PAI-1)对新生儿溶血病(HND)的预测价值。方法以76例夫妇血型不合的O型RhD(+)孕妇及其新生儿为研究对象,依据溶血3项检查和临床表现诊断为NHD新生儿30例,健康新生儿46例。比较健康与NHD新生儿及其母亲孕晚期血浆中t-PA、PAI-1及t-PA/PAI-1水平,并分别以健康新生儿母亲组t-PA、PAI-1和t-PA/PAI-1均值的95%可信区间上限值7.48μmol/L、50.46μg/L和0.19μmol/μg为临界值,分析t-PA、PAI-1及t-PA/PAI-1对HND的预测灵敏度、特异度和准确度。结果 NHD新生儿及其母亲的t-PA、PAI-1和t-PA/PAI-1均高于健康新生儿及其母亲(P <0.05)。孕晚期母体t-PA、PAI-1和t-PA/PAI-1各单项指标对HND的预测灵敏度均低于50%,准确度均低于60%,特异度均>70%上;但三者联合检测的灵敏度(56.67%)、特异度(86.96%)和准确度(75.00%)均高于各单项指标(P <0.05)。结论孕妇孕晚期t-PA、PAI-1和t-PA/PAI-1的升高对于预测HND有一定的提示作用,但各单项指标及联合检测的预测灵敏度均较低,仍需借助其他指标做更准确的判断。

Sales Prediction and Product Recommendation Model Through User Behavior Analytics

The COVID-19 has brought us unprecedented difficulties and thousands of companies have closed down.The general public has responded to call of the government to stay at home.Offline retail stores have been severely affected.Therefore,in order to transform a traditional offline sales model to the B2C model and to improve the shopping experience,this study aims to utilize historical sales data for exploring,building sales prediction and recommendation models.A novel data science life-cycle and process model with Recency,Frequency,and Monetary(RFM)analysis method with the combination of various analytics algorithms are utilized in this study for sales prediction and product recommendation through user behavior analytics.RFM analysis method is utilized for segmenting customer levels in the company to identify the importance of each level.For the purchase prediction model,XGBoost and Random Forest machine learning algorithms are used to build prediction models and 5-fold Cross-Validation method is utilized to evaluate their.For the product recommendation model,the association rules theory and Apriori algorithm are used to complete basket analysis and recommend products according to the outcomes.Moreover,some suggestions are proposed for the marketing department according to the outcomes.Overall,the XGBoost model achieved better performance and better accuracy with F1-score around 0.789.The proposed recommendation model provides good recommendation results and sales combinations for improving sales and market responsiveness.Furthermore,it recommend specific products to new customers.This study offered a very practical and useful business transformation case that assists companies in similar situations to transform their business models.

Smart Healthcare Using Data-Driven Prediction of Immunization Defaulters in Expanded Program on Immunization (EPI)

Immunization is a noteworthy and proven tool for eliminating lifethreating infectious diseases,child mortality and morbidity.Expanded Program on Immunization(EPI)is a nation-wide program in Pakistan to implement immunization activities,however the coverage is quite low despite the accessibility of free vaccination.This study proposes a defaulter prediction model for accurate identification of defaulters.Our proposed framework classifies defaulters at five different stages:defaulter,partially high,partially medium,partially low,and unvaccinated to reinforce targeted interventions by accurately predicting children at high risk of defaulting from the immunization schedule.Different machine learning algorithms are applied on Pakistan Demographic and Health Survey(2017–18)dataset.Multilayer Perceptron yielded 98.5%accuracy for correctly identifying children who are likely to default from immunization series at different risk stages of being defaulter.In this paper,the proposed defaulters’prediction framework is a step forward towards a data-driven approach and provides a set of machine learning techniques to take advantage of predictive analytics.Hence,predictive analytics can reinforce immunization programs by expediting targeted action to reduce dropouts.Specially,the accurate predictions support targeted messages sent to at-risk parents’and caretakers’consumer devices(e.g.,smartphones)to maximize healthcare outcomes.

Intelligent Smart Grid Stability Predictive Model for Cyber-Physical Energy Systems

A cyber physical energy system(CPES)involves a combination of pro-cessing,network,and physical processes.The smart grid plays a vital role in the CPES model where information technology(IT)can be related to the physical system.At the same time,the machine learning(ML)modelsfind useful for the smart grids integrated into the CPES for effective decision making.Also,the smart grids using ML and deep learning(DL)models are anticipated to lessen the requirement of placing many power plants for electricity utilization.In this aspect,this study designs optimal multi-head attention based bidirectional long short term memory(OMHA-MBLSTM)technique for smart grid stability predic-tion in CPES.The proposed OMHA-MBLSTM technique involves three subpro-cesses such as pre-processing,prediction,and hyperparameter optimization.The OMHA-MBLSTM technique employs min-max normalization as a pre-proces-sing step.Besides,the MBLSTM model is applied for the prediction of stability level of the smart grids in CPES.At the same time,the moth swarm algorithm(MHA)is utilized for optimally modifying the hyperparameters involved in the MBLSTM model.To ensure the enhanced outcomes of the OMHA-MBLSTM technique,a series of simulations were carried out and the results are inspected under several aspects.The experimental results pointed out the better outcomes of the OMHA-MBLSTM technique over the recent models.

高校大学生实验室安全意识评价模型的构建

为减少实验室安全事故的发生和提高大学生的实验室安全意识,设计了实验室安全意识影响因素调查问卷和大学生实验室安全意识评价调查问卷,利用层次分析法—熵权法(AHP-EWM)主客观相结合的方法建立高校大学生实验室安全意识评价体系。通过主成分分析法(PCA)处理,再选取累计贡献率超过95%的评价指标进行布谷鸟搜索(Cuckoo Search, CS),最后结合混合优化支持向量机(SVM)建立PCA-CS-SVM大学生实验室安全意识评价模型。验证结果表明,与PCA-LS-SVM和PCA-GA-SVM模型相比,PCA-CS-SVM模型的预测值与实际值的误差较小且评价等级与实际值保持一致,具有较高的准确性和可靠性,可用于高校大学生实验室安全意识评价。

扰动引力场中机动突防导弹落点精确预报方法

针对弹道导弹大机动突防后精确制导面临的落点预测需求,提出了一种考虑高阶扰动引力影响的导弹落点解析预报模型。将落点预报问题分解为标准落点预报和落点偏差预报两部分,标准落点预报由二体椭圆轨道理论解析求解,落点偏差预报通过构建的状态空间摄动模型进行求解。基于球谐函数换极法建立高阶扰动引力矢量在轨道柱坐标系中的表达式,并推导得到由F函数和G函数等两类核函数组成的落点偏差预报解析模型以及F函数和G函数的递推公式。该模型无需射前准备工作,相对已有方法具有使用灵活、鲁棒性好等特点。数值仿真结果表明本文提出的落点预测模型残差均值为11.2 m,相对误差小于0.1%,预测耗时小于100 ms,能够为制导算法设计提供支撑,具有一定的工程应用价值。

基于可达区在线预测的GPI中制导协同拦截策略

针对临近空间高超声速滑翔目标防御中存在目标机动能力强、机动意图不明确的问题,提出一种基于可达区在线预测的滑翔段拦截器(GPI)中制导协同拦截策略。基于滑翔弹道解析解给出针对目标横程机动的可达区在线预测方法。利用多项式拟合和反向传播(BP)神经网络给出GPI标控弹道的纵程可达区在线预测方法,并利用弹道解析解进一步给出拦截弹的横程可达区在线预测方法。通过对目标和拦截弹可达区在线预测,引入多弹协同思想,实现拦截弹可达区对目标可达区的覆盖,完成协同拦截策略的设计。拦截仿真分析表明:所提协同拦截策略可有效应对目标的倾侧反转机动。

间接矩阵变换器-双异步电机调速系统的模型预测控制权重因数整定

间接矩阵变换器-双异步电机调速系统结构复杂,传统模型预测电压控制中权重因数整定困难。该文提出一种基于层次分析评估的权重因数整定方法,通过对物理量纲、双电机、网侧与电机侧统合将权重因数数量减少至1个,并引入层次分析评估法来实时调整权重因数以满足各种工况的要求,使系统在宽运行范围、多功率流模态下均具有良好的网侧电能质量与电机调速性能。通过仿真和实验证明,采用该文提出的方法,可保证在多种工况下网侧功率因数接近1,网侧电流正弦,电机定子电流畸变小、电机动态调速性能良好。而且,相比于传统的简化模型预测电压控制方法,该文所提出的方法权重因数整定简单易实现,网侧电流质量更好。

预测分析与人工智能在软件用例预测的应用研究

深入探讨了预测分析与人工智能在软件用例预测领域的应用。首先,概述了软件用例预测的重要性,并分析了预测分析与人工智能技术的发展背景及其在不同行业中的应用情况;其次,提出了一种创新的技术框架——智能预测分析模型,并详细地描述了该框架的构建与实施过程,包括数据收集与处理、模型构建、算法选择和性能评估与优化等关键步骤;然后,通过模拟实验,展示了该智能预测分析框架在预测软件在不同用户群体中的使用频率方面的有效性。实验结果表明,利用该智能预测分析模型框架可以有效地提高软件用例预测的准确性和效率;最后,讨论了在实际应用中面临的挑战和未来发展方向,指出预测分析和人工智能在软件用例预测领域的应用前景和研究价值。

隧道涌水量预测计算方法综述

预测隧道涌水量对于保障隧道施工安全、进度、洞室稳定和人身安全问题至关重要。国内外学者已提出多种预测方法,但是存在不同适用条件,根据隧道的水文地质条件选取恰当的方法能有效提高预测精度。对解析公式法、经验公式法、数值法、随机性数学模型预测法等多种涌水量预测方法进行了系统梳理和分析,通过对这些方法的基本原理及适用条件进行综合分析,讨论了当前涌水量预测方法存在的不足之处,并提出改进方向。结果表明:解析公式法应用简单,但结果偏差较大;经验公式法源于工程案例总结,适用于相似条件下隧道涌水量预测;数值法通过数学模型模拟,可以解决复杂水文地质条件下的涌水量预测,但对勘察设计阶段获取的水文地质参数提出更高的要求;随机性数学模型方法需要大量数据来保证结果的准确性;其他方法主要依赖于地理信息系统(GIS)技术、同位素分析法等手段,通过科学分析来识别并判断地下水量及其流动通道的地质特征,需要充分的数据支持和详尽的地下勘探结果作为依据。研究成果可为实际工程中选择合适的涌水量预测方法提供参考。

基于改进LSTM神经网络的电动汽车充电负荷预测

当前对电动汽车(EV)充电负荷预测的研究缺少真实的数据支撑,并且模型考虑场景过于简单,影响因素考虑不到位,预测结果缺乏说服力。基于此,提出一种考虑多种电动汽车充电负荷影响因素的电动汽车充电负荷预测方法。首先,考虑天气、季节、温度、工作日、节假日等因素对电动汽车充电负荷的影响,采用三标度层次分析法分析各影响因素权重;其次,建立LSTM神经网络预测模型,通过真实数据训练得到用于预测的LSTM神经网络模型,结合影响因素权重分析结果对预测模型进行修正,得到最终的改进LSTM神经网络负荷预测模型;最后,采用常州某小区的真实数据对所提预测方法进行试验验证。结果表明,所提方法可以实现电动汽车充电负荷的精确预测,且负荷预测结果可为有序充电策略研究提供参考。

基于GIS的煤矿冲击地压危险区域预测

为了精准预测煤矿冲击地压危险区域,从自然地质、开采技术和防治措施等条件出发,采用层次分析法实现权重计算,应用模糊数学算法进行模糊评判,并基于ArcGIS网格法,将研究区划分为50 m×50 m的网格单元进行网格赋参和空间插值,分别以0.25、0.50、0.75作为冲击危险性临界值,对峻德矿的煤层和工作面进行冲击危险性预测,确定冲击危险区域。结果表明:峻德矿17煤层的无、弱、中等和强冲击危险区分别占32%、52%、15%、1%;工作面分单元概率预测结果为0.48~0.96,其中弱冲击区占34%,中等冲击区占48%,强冲击区占18%。当采掘工作推进至不同网格单元时,可确定工程所处位置的冲击危险性,以提前制订采取冲击防治措施。

胡家河煤矿综放工作面矿压显现规律预测及主控因素研究

现有工作面矿压显现规律预测方法中,基于数值模拟与统计回归的方法无法实现对工作面矿压显现规律的实时精准预测,深度学习方法存在超参数较多且难以设置、模型训练速度慢等问题。针对上述问题,以胡家河煤矿402102回采工作面采动过程中监测到的煤体内部应力变化时序数据为基础,将基于粒子群优化的门控循环单元(PSO-GRU)应用到回采工作面矿压显现规律预测中。采用PSO算法对GRU进行优化,构建PSO-GRU模型,实现对超参数的自动寻优,从而提高GRU的训练速度和预测精度。以预测结果为依据,采用层次分析法建立402102回采工作面矿压主控因素评价指标体系,将顶板条件、回采工艺、煤层赋存、地质构造确定为影响工作面矿压的一级指标,进一步细分出具有代表性的14个二级指标。测试结果表明:(1)与未经优化的GRU模型相比,PSO-GRU模型的均方误差(MSE)降低了83.9%,均方根误差(RMSE)降低了59.8%,平均绝对误差(MAE)降低了59.0%,决定系数R2提升了28.9%。(2)PSO-GRU模型对矿压数据预测的拟合度达0.980以上,具有良好的非线性拟合能力和泛化能力。(3)地质条件中的煤层赋存因素对回采工作面矿压的影响最大,权重为0.47;可人为干预的影响因素中工作面推进速度对矿压的影响最大,权重为0.13。