Explore chapters and articles related to this topic
Case Studies
Published in Abhijit Pandit, Mathematical Modeling using Fuzzy Logic, 2021
In moving averages to generate predictions, predictors can experiment with moving averages of different lengths. The predictors separate the lengths that yield the highest truth about the predictions generated. The weighted moving-average method is a variation of the moving stereotype approach. In the moving-average method, each observation in the data is weighted equally. The weighted moving-average method stipulates variable weights for observations for the data used in the moving average. Again, suppose that the predictor wants to generate a moving average of three periods. In the weighted moving-average method, the three data points receive various weights that exceed the calculated stereotype. Typically, the most recent observation is weighted at its maximum, and the weight is decremented relative to the previous data value (Table 4.2).
Edge Analytics
Published in Chandrasekar Vuppalapati, Building Enterprise IoT Applications, 2019
Smoothing is a technique applied to time series in order to remove the fine-grained variation between time steps. The goal of smoothing is to remove noise and better expose the signal of the underlying causal processes. Moving averages are a simple and common type of smoothing used in time series analysis and time series forecasting. Calculating a moving average involves creating a new series where the values are comprised of the average of raw observations in the original time series. A moving average requires that you specify a window size called the window width. This defines the number of raw observations used to calculate the moving average value. The “moving” part in the moving average refers to the fact that the window defined by the window width is slid along the time series in order to calculate the average values in the new series.
Continuous structural health monitoring for short and medium span bridges
Published in Nigel Powers, Dan M. Frangopol, Riadh Al-Mahaidi, Colin Caprani, Maintenance, Safety, Risk, Management and Life-Cycle Performance of Bridges, 2018
For the purposes of this study, characteristic deflection, μa (Miyamoto & Yabe 2012) is defined as the estimated deflection obtained from Eq. (2) averaged in the bridge section of the road. Studies have shown that characteristic deflection can be made to converge to the extent that anomaly evaluation results are not affected by increasing the number of samples, N, by using the central limit theorem, in order to allow for the influence of various external disturbance factors, δx(t), including the operating conditions of the bus. In this study, the authors used the moving average method to process characteristic deflection data and see what happens. In the moving average method, averages are calculated for incrementally shifted data sections. Fig. 5 shows standard deviations of characteristic deflection values obtained by calculating characteristic deflection averages for incrementally shifted data sections. As shown in Fig. 5, as data sections become larger, standard deviations tend to decrease. It can also be seen that after data section size exceeds a certain limit, standard deviations do not change significantly thereafter. This indicates that by the moving average method mentioned above, the variability of characteristic deflection values decreased and converged so that anomalies can be detected by observing such changes.
Short term wind speed forecasting using time series techniques
Published in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2022
Shreya Sajid, Surender Reddy Salkuti, Praneetha c, Nisha k
Exponential Smoothing is very similar to a basic Moving Average model. The difference between the two is due to the model’s weighting of observations inside the moving frame. A moving average is calculated by establishing a new series whose values are the average of the observations in the initial time series. A moving average necessitates the specification of a window size known as the window width. The number of observations utilized to generate the moving average value is specified in the window width. The “moving” aspect of the moving average refers to how the window indicated by the window width is slid along the time series to calculate the new series’ average values. In this method, every observation in the sliding window is treated evenly. Conversely, in Exponential Smoothing, weights decrease exponentially as the observations get older. To put it another way, the larger the related weight, the more recent the observation (Taylor 2003). To generate a forecast, it directly adds the exponentially weighted sum of the previous values. The model can be portrayed mathematically as:
Zero defect manufacturing: state-of-the-art review, shortcomings and future directions in research
Published in International Journal of Production Research, 2020
Foivos Psarommatis, Gökan May, Paul-Arthur Dreyfus, Dimitris Kiritsis
Another fact to point out is that researchers in the field need closer collaboration with the industries, because as the trend in the chart in Figure 14 from our analysis illustrates, more research works are carried out in the laboratory environments year-by-year rather than the industrial plants itself. Figure 14 presents the number of papers per year in the form of 4 periods moving average and not the actual numbers revealed by our analysis. A moving average is a technique to get an overall idea of the trends in a data set. The technology readiness levels of developed technologies pertaining to certain strategies should be improved by ever closer collaboration between academia and industry thus leading to more and more implementation and demonstration in operational environments.
Applied sentiment analysis on a real estate advertisement recommendation model
Published in Enterprise Information Systems, 2023
Regina Fang-Ying Lin, Jiesheng Wu, Kuo-Kun Tseng, Yuk-Ming Tang, Lu Liu
The long-term trend is an essential component. There are two main methods to calculate its exact value: Moving average and the linear model. The moving average is a commonly used method that calculates the average in a specific interval and then moves to the next interval. The average calculated in the moving interval form new time series data, which can weaken the significant fluctuation of the original data. We assumed that the moving step is k. Equation (15) shows the calculation of the long-term trend by the moving average method: