China 
Africa 
Explore chapters and articles related to this topic
Energy Efficiency in Smart Street Lighting System for ITU
Published in Tugrul Daim, Marina Dabić, Yu-Shan Su, The Routledge Companion to Technology Management, 2023
Eren Deliaslan, M. Özgür Kayalica, Gülgün Kayakutlu
As mentioned earlier, the total energy demand forecast for the lighting of a smart campus will be realized using a generally accepted method and a machine learning method. Concisely, a hybridized model of SARIMA and a LSTM has been evaluated for this implementation. Autoregressive Integrated Moving Average (ARIMA) is one of the most widely used forecasting methods for time series data forecasting. An extension to ARIMA that supports the direct modeling of the seasonal component of the series is called SARIMA (Hyndman & Athanasopoulos, 2013). A SARIMA model has been commonly used for energy consumption forecasting. However, in the existing studies, it is generally assumed that there is a linear correlation structure among the time series values. Because of the nonlinear structure of real-world problems, this linear relationship is not realistic. Hence, this nonlinear relationship needs to be ascertained as the approximation of linear models in complex real-world problems has not always provided satisfactory results (Chaudhry et al. 2000).
Time series features and models
Published in Elizabeth Ann Maharaj, Pierpaolo D'Urso, Jorge Caiado, Time Series Clustering and Classification, 2019
Elizabeth Ann Maharaj, Pierpaolo D'Urso, Jorge Caiado
Many time series encountered in various fields exhibit non-stationary behaviour and in particular they do not fluctuate about a fixed level. Although the level about which the series fluctuates may be different at different times, when differences in levels are taken, they may be similar. This is referred to as homogeneous non-stationary behaviour (Box et al., 1994) and the series can be represented by a model that requires the d-th difference of the process to be stationary. In practice, d is usually no more than 2. Hence, an ARMA model can be extended to what is known as an autoregressive, integrated moving average (ARIMA) model, Autoregressive, integrated moving average (ARIMA) model or ARIMA(p,d,q) to represent a homogeneous non-stationary time series. This model is expressed as ϕ(B)(1−B)dZt=θ(B)εt.
Machine Learning for Multi-UAV Mobility Prediction
Published in Fei Hu, Xin-Lin Huang, DongXiu Ou, UAV Swarm Networks, 2020
Viprav Raju, ShiZe Huang, DongXiu Ou
The different tools used in some popularly cited literature for state prediction include: Historical average (HA): This predicts the demand using average values of previous demands at the location given in the same relative time interval (i.e., the same time of the day).Autoregressive integrated moving average (ARIMA): This is a well-known model for forecasting time series that combines moving average and autoregressive components for modeling time series.Linear regression (LR): This could be ordinary least-squares regression (OLSR), Ridge regression (i.e., with L2-norm regularization) and Lasso (i.e., with L1-norm regularization).Multiple layer perceptron (MLP): This neural network could have different numbers of fully connected layers (such as 128, 128, 64 and 64).XGBoost: This is a powerful boosting tree-based method and is widely used in data mining applications.ST-ResNet: This is a deep learning–based approach for traffic prediction. The method constructs a city's traffic density map at different times as images. CNN is used to extract features from historical images.
Comparative analysis of deep learning and classical time series methods to forecast natural gas demand during COVID-19 pandemic
Published in Energy Sources, Part B: Economics, Planning, and Policy, 2023
Autoregressive Integrated Moving Average (ARIMA) is one of the popular classical time series methods used to predict the future value from its past values (Ceylan, Bulkan, and Elevli 2020). This approach, developed by George Box and Gwilym Jenkins, is also called the Box-Jenkins method (Box 1970). The model is denoted as ARIMA (p, d, q) where parameters and are non-negative integers. Here, and are the order of autoregressive (AR) and moving average (MA), respectively, and is the degree of difference. The general expression of an ARIMA (p, d, q) model can be explained using Eq. (1):
Traffic violation analysis using time series, clustering and panel zero-truncated one-inflated mixed model
Published in International Journal of Injury Control and Safety Promotion, 2022
Zahra Rezaei Ghahroodi, Samaneh Eftekhari Mahabadi, Sara Bourbour, Helia Safarkhanloo, Shokoufa Zeynali
ARIMA (Autoregressive Integrated Moving Average) family of models are mathematical models of the autocorrelation in a time series which describe the behaviour of a variable in terms of its past values. These models are widely used in almost all fields of transportation with marked success; examples of such applications are Lau et al. (2009), Masten (2007), and Smith et al. (2002). Lau et al. (2009) investigated the effectiveness of hourly carbon monoxide concentrations on the traffic pattern. In this study, hourly, monthly and seasonal mean carbon monoxide concentration data are collected from a roadside air monitoring station in Hong Kong over 7-years. Using a SARIMA (Seasonal Autoregressive Integrated Moving Average) model shows that the daily traffic cycle strongly influences concentrations and the hourly carbon monoxide concentrations resemble the traffic pattern of the area and tend to be lower in the summer. In Masten (2007), time series analyses were used to determine whether six states which upgraded to primary enforcement laws experienced changes in night-time and daytime safety belt use based on proxy estimates from fatal crash-involved vehicle occupants.
Time series: a data analysis approach using R
Published in Journal of Quality Technology, 2021
As the authors point out, two separate, but not mutually exclusive, approaches to time series analysis exist: the time domain approach and the frequency domain approach. The second part, Chapter 4 and Chapter 5, focuses on the time domain approaches. Chapter 4 covers the AR (autoregressive), MA (moving average), and in general, ARMA (autoregressive moving average) modeling for a stationary time series. Another important concept of partial autocorrelation function (PACF) is defined in this chapter and the typical ACF and PACF patterns are summarized to help identify an appropriate time series model. Chapter 5 extends the ARMA model to the ARIMA (autoregressive integrated moving average) model to deal with non-stationarity and SARIMA (seasonal ARIMA) model to account for seasonal behavior. I would recommend Section 5.2 specifically as it provides a step-by-step guideline for building an ARIMA model, from data visualization to model diagnostics and model selection.