基于卷积神经网络的列车检测算法研究

列车检测作为列车自动驾驶的核心技术,可以有效地降低列车追尾等事故造成的人身危险和财产损失。为实现精准的列车检测,选用改进的卷积神经网络(PVANET)对输入图像进行特征提取,在此基础上,采用候选区域网络,从生成的特征图里滑动搜索,判断出图像中可能为列车的区域位置,并进一步采用快速区域卷积神经网络对每个候选区域进行分类,计算出其所属类别的置信度,同时精确定位列车。经验证,该方法适应范围广、鲁棒性高,可以有效地检测不同环境光强及不同朝向的列车,保障列车安全,为列车自动驾驶及辅助驾驶提供安全保障。     

A hybrid machine learning model for forecasting a billing period’s peak electric load days

Many models have been studied for forecasting the peak electric load, but studies focusing on forecasting peak electric load days for a billing period are scarce. This focus is highly relevant to consumers, as their electricity costs are determined based not only on total consumption, but also on the peak load required during a period. Forecasting these peak days accurately allows demand response actions to be planned and executed efficiently in order to mitigate these peaks and their associated costs. We propose a hybrid model based on ARIMA, logistic regression and artificial neural networks models. This hybrid model evaluates the individual results of these statistical and machine learning models in order to forecast whether a given day will be a peak load day for the billing period. The proposed model predicted 70% (40/57) of actual peak load days accurately and revealed potential savings of approximately USD $80,000 for an American university during a one-year testing period.     

Modelling the iron ore price index: A new perspective from a hybrid data reconstructed EEMD-GORU model

As iron ore is the fundamental steel production resource, predicting its price is strategically important for risk management at related enterprises and projects. Based on a signal decomposition technology and an artificial neural network, this paper proposes a hybrid EEMD-GORU model and a novel data reconstruction method to explore the price risk and fluctuation correlations between China’s iron ore futures and spot markets, and to forecast the price index series of China’s and international iron ore spot markets from the futures market. The analysis found that the iron ore futures market in China better reflected the price fluctuations and risk factors in the imported and international iron ore spot markets. However, the forward price in China’s iron ore futures market was unable to adequately reflect the changes in the domestic iron ore market, and was therefore unable to fully disseminate domestic iron ore market information. The proposed model was found to provide better market risk perceptions and predictions through its combinations of the different volatility information in futures and spot markets. The results are valuable references for the early-warning and management of the related enterprise project risks.     

Observing viewers’ self-reported and neurophysiological responses to message appeal in social media advertisements

PurposeMarketing research mainly uses self-reported method to record respondents' perceptions of creativity, and while self-reported method has its own merits, there exists some critique, particularly in terms of its ability to adequately capture the influence of message appeal on creativity. This paper studies how viewers’ responses to message appeals in social media advertisement compare in terms of self-reported responses versus responses taken through a neurophysiological method of Electroencephalograph (EEG).MethodologyTwo social media advertisements are displayed through a laboratory experiment to 17 subjects observing the subjects' neurophysiological reactions as well as their self-reported responses with regard to the commercials’ emotional, informational, and brand-related content.FindingsResults show that neurophysiological method offers unique details about emotional appeal, which the self-reported method fails to reflect. Furthermore, the neurophysiological measure identifies differences across the two target commercials in the emotional content part, which again are not identified through the self-reported method.OriginalityThis paper advances advertising research in social media literature by comparing content evaluation within advertisement through neurophysiological and self-reported measure. These findings have implications for marketers to use and measure message appeals in advertisement on social media to influence consumer response.     

Opportunities to reduce road traffic injury: new insights from the study of urban areas

Abstract

Over the past four decades considerable efforts have been taken to mitigate the growing burden of road injury. With increasing urbanisation along with global mobility that demands not only safe but equitable, efficient and clean (reduced carbon footprint) transport, the responses to dealing with the burgeoning road traffic injury in low- and middle-income countries has become increasingly complex. In this paper, we apply unique methods to identify important strategies that could be implemented to reduce road traffic injury in the Asia-Pacific region; a region comprising large middle-income countries (China and India) that are currently in the throes of rapid motorisation. Using a convolutional neural network approach, we clustered countries containing a total of 1632 cities from around the world into groups based on urban characteristics related to road and public transport infrastructure. We then analysed 20 countries (containing 689 cities) from the Asia-Pacific region and assessed the global burden of disease attributed to road traffic injury and these various urban characteristics. This study demonstrates the utility of employing image recognition methods to discover new insights that afford urban and transport planning opportunities to mitigate road traffic injury at a regional and global scale.     

An empirical investigation of water consumption forecasting methods

Many regions on earth face daily limitations in the quantity and quality of the water resources available. As a result, it is necessary to implement reliable methodologies for water consumption forecasting that will enable the better management and planning of water resources. This research analyses, for the first time, a large database containing data from 2 million water meters in 274 unique postal codes, in one of the most densely populated areas of Europe, which faces issues of droughts and overconsumption in the hot summer months. Using the R programming language, we built and tested three alternative forecasting methodologies, employing univariate forecasting techniques including a machine-learning algorithm, with very promising results.     

Predicting bank insolvencies using machine learning techniques

Proactively monitoring and assessing the economic health of financial institutions has always been the cornerstone of supervisory authorities. In this work, we employ a series of modeling techniques to predict bank insolvencies on a sample of US-based financial institutions. Our empirical results indicate that the method of Random Forests (RF) has a superior out-of-sample and out-of-time predictive performance, with Neural Networks also performing almost equally well as RF in out-of-time samples. These conclusions are drawn not only by comparison with broadly used bank failure models, such as Logistic, but also by comparison with other advanced machine learning techniques. Furthermore, our results illustrate that in the CAMELS evaluation framework, metrics related to earnings and capital constitute the factors with higher marginal contribution to the prediction of bank failures. Finally, we assess the generalization of our model by providing a case study to a sample of major European banks.     

The effects of handling outliers on the performance of bankruptcy prediction models

Ratio type financial indicators are the most popular explanatory variables in bankruptcy prediction models. These measures often exhibit heavily skewed distribution because of the presence of outliers. In the absence of clear definition of outliers, ad hoc approaches can be found in the literature for identifying and handling extreme values. However, it is not clear how these different approaches can affect the predictive power of models. There seems to be consensus in the literature on the necessity of handling outliers, at the same time, it is not clear how to define extreme values to be handled in order to maximize the predictive power of models. There are two possible ways to reduce the bias originating from outliers: omission and winsorization. Since the first approach has been examined previously in the literature, we turn our attention to the latter. We applied the most popular classification methodologies in this field: discriminant analysis, logistic regression, decision trees (CHAID and CART) and neural networks (multilayer perceptron). We assessed the predictive power of models in the framework of tenfold stratified crossvalidation and area under the ROC curve. We analyzed the effect of winsorization at 1, 3 and 5% and at 2 and 3 standard deviations, furthermore we discretized the range of each variable by the CHAID method and used the ordinal measures so obtained instead of the original financial ratios. We found that this latter data preprocessing approach is the most effective in the case of our dataset. In order to check the robustness of our results, we carried out the same empirical research on the publicly available Polish bankruptcy dataset from the UCI Machine Learning Repository. We obtained very similar results on both datasets, which indicates that the CHAID-based categorization of financial ratios is an effective way of handling outliers with respect to the predictive performance of bankruptcy prediction models.     

央行和商业银行视角下存款准备金率的实证分析

本文分别从央行货币政策调控目标和商业银行对存款准备金率容忍度的视角出发,利用参数法和神经网络模型对存款准备金率进行实证分析。研究发现,央行近年来多次上调存款准备金率主要是为了对抗通货膨胀以及回收货币流动性。在不考虑银行容忍度下,参数模型给出的目标存款准备金率为23%,而在考虑了存款准备金率对银行的负面影响后,根据神经网络模型得出2011年上半年合理的存款准备金率应为21.34%,与当前21.5%的实际存款准备金率相符。说明央行在货币调控时考虑到了银行的容忍度,是符合宏观审慎性原则的。而模型的敏感性分析表明,未来存款准备金率仍旧存在上调的区间与上调的可能性。     

Economic corollaries of personalized recommendations

The impact of recommendation systems (RSs) on the diversity of consumption is not transparent or well understood. Available studies, whether experimental or theoretical, show inconsistent and even opposite results, which manifests as debate in the literature. In this paper, we investigate the impact of two main recommender systems, neural collaborative filtering and deep content filtering, on sales diversity via a randomized field experiment. Our results confirm the capability of recommender engines in increasing or decreasing aggregate sales diversity. Nonetheless, they amplify homogenization and reduce individual-level consumption diversity. In conclusion, our research reconciles seemingly contradict previous findings and illustrates that the design of the RS is the decisive factor in homogenizing or diversifying product sales.