Green consumption behavior prediction based on fan-shaped search mechanism fruit fly algorithm optimized neural network

Predicting consumption behavior is very important for adjusting supplier production plans and enterprise marketing activities. Conventional statistical methods are unable to accurately predict green consumption behavior because it is characterized by multivariate nonlinear interactions. The paper proposes an optimized fruit fly algorithm (FOA) and extreme learning machine (ELM) model for consumption behavior prediction. First, to address the problem of uneven search direction of FOA leading to insufficient search ability and low efficiency, the paper proposes a sector search mechanism instead of a random search mechanism to improve the global search ability and convergence speed of FOA. Second, to address the issue that the initial weights and hidden layer bias values of the ELM are randomly generated, which affects the learning efficiency and generalization of the ELM, the paper uses an improved FOA to optimize the weights and bias values of ELM for improving the prediction accuracy. Taking the green vegetable consumption behavior of Beijing residents as an example, the results show the optimization of the initial weight and threshold of ELM by the GA, PSO, FOA, and SFOA, the prediction accuracy of the GA-ELM, PSO-ELM, FOA-ELM, and SFOA-ELM models all surpass those of ELM. Compared with BPNN, GRNN, ELM, GA-ELM, PSO-ELM, and FOA-ELM models, the RMSE value of SFOA-ELM was decreased by 9.45%, 8.40%, 11.89%, 5.84%, 2.22%, and 2.69%, respectively. These findings demonstrate the effectiveness of the SFOA-ELM model in green consumption behavior prediction and provide new ideas for the accurate prediction of consumption behaviors of other green products with similar characteristics.     

Examining artificial intelligence (AI) technologies in marketing via a global lens: Current trends and future research opportunities

Artificial intelligence (AI) has captured substantial interest from a wide array of marketing scholars in recent years. Our research contributes to this emerging domain by examining AI technologies in marketing via a global lens. Specifically, our lens focuses on three levels of analysis: country, company, and consumer. Our country-level analysis emphasizes the heterogeneity in economic inequality across countries due to the considerable economic resources necessary for AI adoption. Our company-level analysis focuses on glocalization because while the hardware that underlies these technologies may be global in nature, their application necessitates adaptation to local cultures. Our consumer-level analysis examines consumer ethics and privacy concerns, as AI technologies often collect, store and process a cornucopia of personal data across our globe. Through the prism of these three lenses, we focus on two important dimensions of AI technologies in marketing: (1) human–machine interaction and (2) automated analysis of text, audio, images, and video. We then explore the interaction between these two key dimensions of AI across our three-part global lens to develop a set of research questions for future marketing scholarship in this increasingly important domain.     

iSDS: a self-configurable software-defined storage system for enterprise

ABSTRACT

Storage is one of the most important aspects of IT infrastructure for various enterprises. But, enterprises are interested in more than just data storage; they are interested in such things as more reliable data protection, higher performance and reduced resource consumption. Traditional enterprise-grade storage satisfies these requirements at high cost. It is because traditional enterprise-grade storage is usually designed and constructed by customised field-programmable gate array to achieve high-end functionality. However, in this ever-changing environment, enterprises request storage with more flexible deployment and at lower cost. Moreover, the rise of new application fields, such as social media, big data, video streaming service etc., makes operational tasks for administrators more complex. In this article, a new storage system called intelligent software-defined storage (iSDS), based on software-defined storage, is described. More specifically, this approach advocates using software to replace features provided by traditional customised chips. To alleviate the management burden, it also advocates applying machine learning to automatically configure storage to meet dynamic requirements of workloads running on storage. This article focuses on the analysis feature of iSDS cluster by detailing its architecture and design.     

Predicting credit card delinquencies: An application of deep neural networks

The objective of this paper is twofold. First, it develops a prediction system to help the credit card issuer model the credit card delinquency risk. Second, it seeks to explore the potential of deep learning (also called a deep neural network), an emerging artificial intelligence technology, in the credit risk domain. With real-life credit card data linked to 711,397 credit card holders from a large bank in Brazil, this study develops a deep neural network to evaluate the risk of credit card delinquency based on the client's personal characteristics and the spending behaviours. Compared with machine-learning algorithms of logistic regression, naive Bayes, traditional artificial neural networks, and decision trees, deep neural networks have a better overall predictive performance with the highest F scores and area under the receiver operating characteristic curve. The successful application of deep learning implies that artificial intelligence has great potential to support and automate credit risk assessment for financial institutions and credit bureaus.     

摩托车单向器自动装配机气动系统设计

针对当前摩托车单向器组件主要采用手工装配、装配效率低、随机性大、无法对装配过程实现有效管理控制的情况,为了易于对零件装配过程进行实时监测和提高生产效率,开发了一种智能摩托车单向器自动装配机。介绍了摩托车单向器自动装配机的上料系统、装配系统、检测系统和落料系统的机械结构,重点阐述了设备的气动系统设计,并进行了实验研究。结果表明,该设备可实现组成单向器的5种零件自动上料和装配,同时降低了操作人员的劳动强度,生产效率提高约50%。其气动系统噪音小、工作可靠,可应用于摩托车单向器的大批量生产。研究结果可为其他相似异形零件自动装配机的开发提供参考。     

Protecting Innovation Through Patents and Trade Secrets: Evidence for Firms with a Single Innovation

Abstract

This paper analyzes the use and effectiveness of patents and trade secrets designed to protect innovation. While previous studies have usually considered patents and trade secrets as substitutes for one another, we investigate to what extent and in what situations the two protection methods are used jointly. We identify protection strategies for single innovation firms and hence overcome the assignment problem of existing empirical studies, that is, whether firms using both protection methods do so for the same innovation or for different innovations. Employing firm panel data from Germany, we find fairly few differences between the determinants for choosing secrecy and patenting. Single innovators that combine both strategies, 39% of the group, tend to aim at a higher level of innovation and act in a more uncertain technological environment. Firms combining both protection methods yield significantly higher sales with new-to-market innovations, providing some evidence for a complementarity of the two protection methods.     

单频网多播系统中的开环半动态功率分配算法

在单频网多播传输中，传统的全反馈动态功率分配数算法需要根据每个时隙反馈的用户瞬时信道信息进行实时的调整，所以造成了资源分配频率快、上行反馈开销大的缺点。为了克服这个缺点，提出了一个低复杂度、没有用户反馈的单频网多播开环半动态功率分配算法。首先在各小区等功率分配的假设下，根据单频网的形状信息算出各小区等价信道增益，然后再根据这个增益值，实现满足速率需求情况下的各小区功率分配。仿真结果显示，与全反馈的动态功率分配算法相比，该算法以一小部分性能损失为代价，大大减少了单频网的上行反馈和资源分配的开销，因此更适用于实际的单频网多播系统。     

A multivariate distance nonlinear causality test based on partial distance correlation: a machine learning application to energy futures

This paper proposes a multivariate distance nonlinear causality test (MDNC) using the partial distance correlation in a time series framework. Partial distance correlation as an extension of the Brownian distance correlation calculates the distance correlation between random vectors X and Y controlling for a random vector Z. Our test can detect nonlinear lagged relationships between time series, and when integrated with machine learning methods it can improve the forecasting power. We apply our method as a feature selection procedure and combine it with the support vector machine and random forests algorithms to study the forecast of the main energy financial time series (oil, coal, and natural gas futures). It shows substantial improvement in forecasting the fuel energy time series in comparison to the classical Granger causality method in time series.     

Flexibility in the gig economy: managing time on three online piecework platforms

Gig economy platforms seem to provide extreme temporal flexibility to workers, giving them full control over how to spend each hour and minute of the day. What constraints do workers face when attempting to exercise this flexibility? We use 30 worker interviews and other data to compare three online piecework platforms with different histories and worker demographics: Mechanical Turk, MobileWorks, and CloudFactory. We find that structural constraints (availability of work and degree of worker dependence on the work) as well as cultural‐cognitive constraints (procrastination and presenteeism) limit worker control over scheduling in practice. The severity of these constraints varies significantly between platforms, the formally freest platform presenting the greatest structural and cultural‐cognitive constraints. We also find that workers have developed informal practices, tools, and communities to address these constraints. We conclude that focusing on outcomes rather than on worker control is a more fruitful way to assess flexible working arrangements.     

Nowcasting South African gross domestic product using a suite of statistical models

Given lags in the release of data, a central bank must ‘nowcast’ current gross domestic product (GDP) using available quarterly or higher frequency data to understand the current state of economic activity. This paper uses various statistical modelling techniques to draw on a large number of series to nowcast South African GDP. We also show that GDP volatility has increased markedly over the last 5 years, making GDP forecasting more difficult. We show that all the models developed, as well as the Reserve Bank's official forecasts, have tended to overestimate GDP growth over this period. However, several of the statistical nowcasting models we present in this paper provide competitive nowcasts relative to the official Reserve Bank and market analysts' nowcasts.