با سلام خدمت کاربران عزیز، به اطلاع می رساند ترجمه مقالاتی که سال انتشار آن ها زیر 2008 می باشد رایگان بوده و میتوانید با وارد شدن در صفحه جزییات مقاله به رایگان ترجمه را دانلود نمایید.
Forecasting third-party mobile payments with implications for customer flow prediction
پیش بینی پرداخت های تلفن همراه شخص ثالث با پیامدهای پیش بینی جریان مشتری-2020
Forecasting customer flow is key for retailers in making daily operational decisions, but small retailers often lack the resources to obtain such forecasts. Rather than forecasting stores’ total customer flows, this research utilizes emerging third-party mobile payment data to provide participating stores with a value-added service by forecasting their share of daily customer flows. These customer transactions using mobile payments can then be utilized further to derive retailers’ total customer flows indirectly, thereby overcoming the constraints that small retailers face. We propose a third-party mobile-paymentplatform centered daily mobile payments forecasting solution based on an extension of the newly-developed Gradient Boosting Regression Tree (GBRT) method which can generate multi-step forecasts for many stores concurrently. Using empirical forecasting experiments with thousands of time series, we show that GBRT, together with a strategy for multi-period-ahead forecasting, provides more accurate forecasts than established benchmarks. Pooling data from the platform across stores leads to benefits relative to analyzing the data individually, thus demonstrating the value of this machine learning application.
Keywords: Analytics | Big data | Customer flow forecasting | Machine learning | Forecasting many time series | Multi-step-ahead forecasting strategy
The effects of Chile’s 2005 traffic law reform and in-country socioeconomic differences on road traffic deaths among children aged 0-14 years: A 12-year interrupted time series analysis
اثرات اصلاح قانون راهنمایی و رانندگی در سال 2005 شیلی و اختلافات اقتصادی و اجتماعی درون کشور در مورد مرگ و میر در جاده های کودکان در سن 0-14 سال: تجزیه و تحلیل قطع 12 ساله سری های زمانی -2020
Objectives: This study assessed the effect of Chile’s 2005 traffic law reform (TLR) on the rates of road traffic deaths (RTD) in children aged 0–14 years, adjusting for socioeconomic differences among the regions of the country. Methods: Free-access sources of official and national information provided the data for every year of the study period (2002–2013) and for each of the country’s 13 upper administrative divisions with respect to RTD in child pedestrians and RTD in child passengers (dependent variables), and the following control variables: the number of road traffic tickets processed, investment in road infrastructure, poverty, income inequality, insufficient education, unemployment, population aged 0–14 years, and prevalence of alcohol consumption in the general population. Interrupted time series analyses (level and slope change impact model), using generalized estimating equation methods, were conducted to assess the impact of the TLR (independent variable) on the dependents variables. Results: There was a significant interaction between time and Chile’s 2005 TLR for a reduction in child pedestrians (incidence rate ratio [IRR] 0.87, 95% confidence interval [CI] 0.79-0.96) and passengers RTD (IRR for interaction 0.80, 95% CI 0.67-0.96) trends. In addition, in child pedestrians, RTD rates were affected by poverty (IRR 1.04, 95% CI 1.02–1.05), income inequality (IRR 1.02, 95% CI 1.00–1.04), and unemployment (IRR 0.94, 95% CI 0.90-0.98), whereas in the case of child passengers, poverty (IRR 1.05, 95% CI 1.01–1.08) and income inequality (IRR 0.93, 95% CI 0.91-0.95) were significant. Conclusions: Large-scale legislative actions can be effective road safety measures if they are aimed at promoting behavioral change in developing countries, improving the safety of children on the road. Additionally, regional socioeconomic differences are associated with higher RTD rates in this population, making this an argument in favor of road safety policies that consider these inequalities. The number of road traffic tickets processed and the investment in road infrastructure were not significant.
Keywords: Safety management | Child | Traffic accidents | Mortality | Socioeconomic factors
Effectiveness of implementing the criminal administrative punishment law of drunk driving in China: An interrupted time series analysis, 2004-2017
اثربخشی اجرای قانون مجازات اداری کیفری رانندگی مست در چین: تجزیه و تحلیل سری های زمانی قطع شده ، 2004-2017-2020
In 2011, a more severe drunk driving law was implemented in China, which criminalized driving under the influence of alcohol for the first time and increased penalties for drunk driving. The present study aimed to assess effectiveness of the drunk driving law in China in reducing traffic crashes, injuries, and mortality. Data used in this study was obtained from the Traffic Management Bureau of the Ministry of Public Security of the People’s Republic of China. An interrupted time series analysis was conducted to analyze annual data from 2004 to 2017, including the number of road traffic crashes, deaths, and injuries caused by drunk driving in China. The average annual incidences of crashes, mortality, and injuries have decreased after the promulgation of drunk driving law in 2011. In the post-intervention period, the increased slope for crashes, mortality and injury rates were, respectively, -0.140 to -0.006, -0.052 to -0.005 and -0.150 to -0.008, indicating a weaker downward trend of dependent variables. The more stringent drunk driving law is not as effective as expected. Drunk driving is still a severe traffic safety problem to be addressed in China. Both legislation and other prevention programs should be adopted to reduce road traffic injuries caused by drunk driving in China.
Keywords: Drunk driving | Interrupted time series analysis | Road traffic law | Injury | Evaluation | China
Refined composite multivariate multiscale symbolic dynamic entropy and its application to fault diagnosis of rotating machine
آنتروپی پویای نمادین چند متغیره کامپوزیت تصفیه شده و کاربرد آن در تشخیص خطای ماشین چرخشی-2020
Accurate and efficient identification of various fault categories, especially for the big data and multisensory system, is a challenge in rotating machinery fault diagnosis. For the diagnosis problems with massive multivariate data, extracting discriminative and stable features with high efficiency is the significant step. This paper proposes a novel feature extraction method, called Refined Composite multivariate Multiscale Symbolic Dynamic Entropy (RCmvMSDE), based on the refined composite analysis and multivariate multiscale symbolic dynamic entropy. Specifically, multivariate multiscale symbolic dynamic entropy can capture more identification information from multiple sensors with superior computational efficiency, while refine composite analysis guarantees its stability. The abilities of the proposed method to measure the complexity of multivariate time series and identify the signals with different components are discussed based on adequate simulation analysis. Further, to verify the effectiveness of the proposed method on fault diagnosis tasks, a centrifugal pump dataset under constant speed condition and a ball bearing dataset under time-varying speed condition are applied. Compared with the existing methods, the proposed method improves the classification accuracy and F-score to 99.81% and 0.9981, respectively. Meanwhile, the proposed method saves at least half of the computational time. The result shows that the proposed method is effective to improve the efficiency and classification accuracy dealing with the massive multivariate signals.
Keywords: Multivariate multiscale symbolic dynamic | entropy | Random forest | Time-varying speed conditions | Fault diagnosis
Complementarity modeling of monthly streamflow and wind speed regimes based on a copula-entropy approach: A Brazilian case study
مدل سازی مکمل رژیم های ماهانه جریان و سرعت باد بر اساس یک رویکرد کوپل-آنتروپی: یک مطالعه موردی برزیل-2020
Wind power energy has been showing significant growth in installed capacity around the world. This opportunity presents big challenges to operate power systems with high wind power penetration levels, considering the variability and intermittent behavior of this type of power source. To reduce uncertainties associated with this kind of power systems, researchers have explored the integration of wind power energy with other renewable energy sources, like solar and hydropower. For instance, the integration of wind and hydro systems can deal with the spatial and temporal complementarity of hydrological and wind regimes to produce energy. Therefore, it is necessary to consider the stochastic behavior and the dependence structures between these variables to define better operational policies. This study explores the spatial correlation of hydrological and wind regimes in different regions of Brazil and defines an entropy-copula-based model for the joint simulation of monthly streamflow and wind speed time series to evaluate the potential integration of hydro and wind energy sources. The proposed model showed a good adherence to the periodic behavior for both variables, and the results indicate that simulated scenarios preserved statistical features of historical data
Keywords: Hydro-wind complementary | Renewable energy | Stochastic modeling
Assessment of mutual fund performance based on Ensemble Empirical Mode Decomposition
ارزیابی عملکرد صندوق های متقابل بر اساس تجزیه و تحلیل حالت تجربی گروه-2020
This study analyzes mutual fund performance in three different time scales. The mutual fund return time series is decomposed by ensemble empirical model decomposition method, which is a data analysis method, especially for processing nonstationary and nonlinear time series, into three time-scales, namely, short cycle, long cycle and trend, which have different meaning on mutual fund management. Short cycle represents the temporary volatility of the market and long cycle represents the operation circle of the mutual fund and trend represents the development tendency of the fund. The mutual funds are also divided into equity, bond, and mixture funds according to portfolio types. The performances of the three fund types are analyzed. The data set, having 2600 mutual funds, in this study is relatively large compared with that in other researches. Result shows that the bond and mixture funds have different management strategies from that of the equity fund, which means that, to seek excess profit, the equity fund focuses on short-cycle management and tends to ignore the long-cycle management, whereas the bond and mixture funds focus on long-cycle management and take less care on short-cycle management. In short cycle, all three sorts of funds are making excess profit through taking market system risk and have no significant performance on α return; in long cycle and trend, they seek excess profit through acquiring more α return. The assessment indices used to assess fund performance confirm the differences in the three fund’s management strategies.
Keywords: Capital asset pricing model | Ensemble Empirical Model Decomposition | Mutual fund performance | Fund management strategy
Electricity demand forecasting for decentralised energy management
پیش بینی تقاضای برق برای مدیریت انرژی غیر متمرکز-2020
The world is experiencing a fourth industrial revolution. Rapid development of technologies is advancing smart infrastructure opportunities. Experts observe decarbonisation, digitalisation and decentralisation as the main drivers for change. In electrical power systems a downturn of centralised conventional fossil fuel fired power plants and increased proportion of distributed power generation adds to the already troublesome outlook for op- erators of low-inertia energy systems. In the absence of reliable real-time demand forecasting measures, effective decentralised demand-side energy planning is often problematic. In this work we formulate a simple yet highly effective lumped model for forecasting the rate at which electricity is consumed. The methodology presented focuses on the potential adoption by a regional electricity network operator with inadequate real-time energy data who requires knowledge of the wider aggregated future rate of energy consumption. Thus, contributing to a reduction in the demand of state-owned generation power plants. The forecasting session is constructed initially through analysis of a chronological sequence of discrete observations. Historical demand data shows behaviour that allows the use of dimensionality reduction techniques. Combined with piecewise interpolation an electricity demand forecasting methodology is formulated. Solutions of short-term forecasting problems provide credible predictions for energy demand. Calculations for medium-term forecasts that extend beyond 6-months are also very promising. The forecasting method provides a way to advance a novel decentralised informatics, optimisa- tion and control framework for small island power systems or distributed grid-edge systems as part of an evolving demand response service.
Keywords: Demand response | Decentralised | Grid edge | Time series forecasting
An echo state network architecture based on quantum logic gate and its optimization
معماری شبکه ای حالت اکو مبتنی بر دروازه منطق کوانتومی و بهینه سازی آن-2020
Quantum neural network (QNN) is developed based on two classical theories of quantum computation and artificial neural networks. It has been proved that quantum computing is an important candidate for improving the performance of traditional neural networks. In this work, inspired by the QNN, the quantum computation method is combined with the echo state networks (ESNs), and a hybrid model namely quantum echo state network (QESN) is proposed. Firstly, the input training data is converted to quantum state, and the internal neurons in the dynamic reservoir of ESN are replaced by qubit neurons. Then in order to maintain the stability of QESN, the particle swarm optimization (PSO) is applied to the model for the parameter optimizations. The synthetic time series and real financial application datasets (Standard & Poor’s 500 index and foreign exchange) are used for performance evaluations, where the ESN, autoregressive integrated moving average (ARIMAX) are used as the benchmarks. Results show that the proposed PSO-QESN model achieves a good performance for the time series predication tasks and is better than the benchmarking algorithms. Thus, it is feasible to apply quantum computing to the ESN model, which provides a novel method to improve the ESN performance.
Keywords: Quantum computation | Echo state network | Particle swarm optimization | Time series | Financial applications
Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach
پیش بینی پیش بینی پایگاه داده های سری زمانی با استفاده از شبکه های عصبی مکرر در گروه های مشابه سری: یک روش خوشه بندی-2020
With the advent of Big Data, nowadays in many applications databases containing large quantities of sim- ilar time series are available. Forecasting time series in these domains with traditional univariate fore- casting procedures leaves great potentials for producing accurate forecasts untapped. Recurrent neural networks (RNNs), and in particular Long Short Term Memory (LSTM) networks, have proven recently that they are able to outperform state-of-the-art univariate time series forecasting methods in this context, when trained across all available time series. However, if the time series database is heterogeneous, ac- curacy may degenerate, so that on the way towards fully automatic forecasting methods in this space, a notion of similarity between the time series needs to be built into the methods. To this end, we present a prediction model that can be used with different types of RNN models on subgroups of similar time series, which are identified by time series clustering techniques. We assess our proposed methodology using LSTM networks, a widely popular RNN variant, together with various clustering algorithms, such as kMeans, DBScan, Partition Around Medoids (PAM), and Snob. Our method achieves competitive results on benchmarking datasets under competition evaluation procedures. In particular, in terms of mean sMAPE accuracy it consistently outperforms the baseline LSTM model, and outperforms all other methods on the CIF2016 forecasting competition dataset.
Keywords: Big data forecasting | RNN | LSTM | Time series clustering | Neural networks
The forgotten land use class: Mapping of fallow fields across the Sahel using Sentinel-2
کلاس استفاده از اراضی فراموش شده: نقشه برداری از مزارع مزرعه در ساحل با استفاده از سنتینل-2-2020
Remote sensing-derived cropland products have depicted the location and extent of agricultural lands with an ever increasing accuracy. However, limited attention has been devoted to distinguishing between actively cropped fields and fallowed fields within agricultural lands, and in particular so in grass fallow systems of semiarid areas. In the Sahel, one of the largest dryland regions worldwide, crop-fallow rotation practices are widely used for soil fertility regeneration. Yet, little is known about the extent of fallow fields since fallow is not explicitly differentiated within the cropland class in any existing remote sensing-based land use/cover maps, regardless of the spatial scale. With a 10 m spatial resolution and a 5-day revisit frequency, Sentinel-2 satellite imagery made it possible to disentangle agricultural land into cropped and fallow fields, facilitated by Google Earth Engine (GEE) for big data handling. Here we produce the first Sahelian fallow field map at a 10 m resolution for the baseline year 2017, accomplished by designing a remote sensing driven protocol for generating reference data for mapping over large areas. Based on the 2015 Copernicus Dynamic Land Cover map at 100 m resolution, the extent of fallow fields in the cropland class is estimated to be 63% (403,617 km2) for the Sahel in 2017. Similar results are obtained for five contemporary cropland products, with fallow fields occupying 57–62% of the cropland area. Yet, it is noted that the total estimated area coverage depends on the quality of the different cropland products. The share of cropped fields within the Copernicus cropland area is found to be higher in the arid regions (200–300 mm rainfall) as compared to the semi-arid regions (300–600 mm rainfall). The woody cover fraction within cropped and fallow fields is found to have a reversed pattern between arid (higher woody cover in cropped fields) and semi-arid (higher woody cover in fallow fields) regions. The method developed, using cloud-based Earth Observation (EO) data and computation on the GEE platform, is expected to be reproducible for mapping the extent of fallow fields across global croplands. Future applications based on multi-year time series is expected to improve our understanding of crop-fallow rotation dynamics in grass fallow systems being key in teasing apart how cropland intensification and expansion affect environmental variables, such as soil fertility, crop yields and local livelihoods in low-income regions such as the Sahel. The mapping result can be visualized via a web viewer (https://buwuyou.users.earthengine.app/view/fallowinsahel).
Keywords: Fallow fields | Cropland | Satellite image time series | Land use/cover mapping | Sentinel-2 | Drylands | Sahel