Mean Average Percentage Error Research Articles

Truck Parking Pattern Aggregation and Availability Prediction by Deep Learning

With the significant increase of e-commerce, freight transportation demand has surged significantly over the past decade. Most of the demand has been served by trucks in the United States. One major problem commonly identified across the country is the worsening truck parking availability because the increase of truck parking facilities has lagged behind the growth of trucking activities. The lack of parking spaces and real-time parking availability information greatly exacerbate the uncertainty of trips, and often results in illegal and potentially dangerous parking or overtime driving. This paper elaborates on pilot research on improving truck parking facilities cooperated with the Washington State Department of Transportation (WSDOT), building and testing the advanced Truck Parking Information and Management System (TPIMS) with the real-time user visualization and prediction function empowered by artificial intelligence. Furthermore, by analyzing the activities of truck drivers, the researchers aggregated the regularity of truck parking patterns by a customized sequential similarity methodology. A Truck Parking Occupancy Prediction (TPOP) neural network for time-variant occupancy prediction by deep learning and attributes embedding is proposed and integrated into the TPIMS. The TPOP achieves 5.82%, 5.07%, 4.84%, and 4.19% mean average percentage error (MAPE) for 16, 8, 4, and 2 minutes ahead of occupancy prediction respectively, significantly outperforms other state-of-the-art methods. Clearly, the proposed solutions can benefit both the truck drivers and government agencies by a more efficient and smart TPIMS.

Hybrid model in machine learning–robust regression applied for sustainability agriculture and food security

<span lang="EN-US">A dataset containing 1924 observations used in this study to evaluate the effect of 435 different independent variables on one dependent variable. Big data has some issues such as irrelevant variables and outliers. Therefore, this study focused on analysing and comparing the impact of three different variable selection based on machine learning techniques, including random forest (RF), support vector machines (SVM), and Boosting. Further, the M robust regression was applied to address the outliers using M–bi square, M–Hampel, and M–Huber. Random forest and M-Hampel results revealed the significant comparing from the other methods such as mean absolute error (MAE) 175.33995, mean square error (MSE) 31.8608, mean average percentage error (MAPE) 9.16091, sum of square error (SSE) 89270.45, R–square 0.829511, and R–square adjusted 0.82670. Also, these techniques indicated that the 8 selection criteria were lower than the other techniques including Akaike information criterion (AIC) 47.25915, generalized cross validation (GCV) 47.27169, hannan-quinn (HQ) 47.60351, RICE (47.2845), SCHWARZ 51.7099, sigma square (SGMASQ) 46.50605, SHIBATA 47.23489, and final prediction error (FPE) 47.25929. Therefore, the study recommended that the best random forest and M-Hampel models are helpful to show the minimum issues and efficient validation for analysing and comparing big data.</span>

Short-Term Aging Performance and Simulation of Modified Binders Using Adaptive Neuro-Fuzzy Inference System

The influence of polymer/nanocomposites (Acrylete-Styrene-Acrylonitrile (ASA)/ Nanosilica (Si)) asphalt binder aging and performance characteristics was investigated. ASA was used at 5% while nanosilcia was blended in 3, 5 and 7% concentrations by the weight of asphalt. Temperature sensitivity, aging resistance and viscoelastic properties of the asphalt binders were evaluated by conducting physical and dynamic shear rheometer (DSR) testing procedures. The tests were performed under unaged and short-term aged conditions by simulating the aging of asphalt in a Rolling thin film oven (RTFO). Additionally, the Adaptive Neuro-Fuzzy Inference System (ANFIS) modelling technique was adopted to predict the short-term aged behaviour of asphalt binders by using the viscoelastic properties of asphalt in an unaged state. The experimental outcomes from the DSR tests showed that the complex modulus (G*) was increased and the phase angle (δ) was reduced for the modified binders, indicating an improvement in the viscoelastic properties compared to the control asphalt binder. Furthermore, the considerably small difference in the G* and δ between the binders in unaged and RTFO aged states indicated that the modifiers had a positive effect in terms of improving the aging resistance of the asphalt binders. Moreover, the ANFIS model prediction capacity, which was assessed by the Coefficient of Determination (R2) and Mean Squared Error (MSE) and Mean Average Percentage Error (MAPE) was shown to be capable of accurately predicting the short term-aging behaviour of asphalt binders from the asphalt binder viscoelastic properties in an unaged state with an R2 value of 0.977, MSE of 0.00032 and MAPE of 0.286.

Fault prediction model on electrical power network using artificial neural network-based time series: A case study of Ayede-Eruwa/ Lanlate Feeder

Increase in size of electrical power network usually results in a rise in fault level and consequently in huge economic losses to energy providers and consumers in the distribution systems. Therefore, it is very important to be proactive in dealing with faults on distribution feeder systems not only to reduce financial havoc, but to save lives and improve the quality of life of the people. A case study of Ayede-Eruwa/Lanlate Oyo State, Nigeria 33kV line is considered. An Artificial Neural Network based Time Series (ANN-TS) fault predictive model is developed for forecasting of faults on the above chosen electrical power network. Daily forced outage readings of the substation’s feeders for three years were collected and modeled using a three-layer feed-forward network ANN-TS. The results in the frequency of fault prediction show that there is an overlap between the observed and predicted values. The annual Mean Average Percentage Error (MAPE) varies between 0.004% and 25%, and the feeders’ average MAPE ranges from 6% to 10%. The fault duration annual MAPE varies between 0.001% and 25.54% while the feeders’ average MAPE varies between 6% and 11%. The energy loss prediction follows the same trend with the annual MAPE alternating between 0.01% and 26.75%, andthe feeders’ average MAPE between 6% and 10%. The average overall MAPE of each feeder is between 6% and 10% which indicates that the developed model is about 90% to 94% accurate. Although, the model is designed for Ayede-Eruwa/Lanlate feeder, it could be utilized for effective prediction of faults in any power distribution network.

EURO-CORDEX: A Multi-Model Ensemble Fit for Assessing Future Hydrological Change?

Human-induced changes in climatic behavior and variations in future river flows has been at the fore-front of recent academic and political discourse. Future climate projections are a vital tool in tackling climate change and supporting future adaptation, however until recently models have been viewed individually with a lack of uncertainty quantification. A multi-model ensemble (MME) with a wide range of general circulation models, regional climate models and emissions scenarios, EURO-CORDEX provides climate projections as well as flow series projections across the European domain from 1950 to 2100. This paper explores the validity of the 68 chain MME flow projections by investigating its ability to match observed flow records in the UK over the period 1975–2004. The work explores magnitude through quantile matching and seasonality matching by time-series decomposition of trends. Two statistical tests [Mann-Whitney, and Mean Average Arctangent Percentage Error (MAAPE)] were used to compare EURO-CORDEX flow projections to observed river flows recorded by the National River Flow Archive (NRFA) across 1,436 UK river catchments. Results indicate a high degree of similarity justifying the application of this dataset for assessing future hydrological changes across a regional scale. Discretizing the flow projections into regional and hydrometric areas highlights the variability in performance between neighboring domains and the strong influence local features may have on climate model performance. The validation of EURO-CORDEX flow projection data regionally enables a wide range of applications including the exploration of future changes in local and national river flows.

The Effect of Walking on the Estimation of Breathing Pattern Parameters using Wearable Bioimpedance.

Wearable bioimpedance is a technique proposed to estimate breathing parameters such as respiratory rate (RR). However, its potential application lies in clinical investigation of daily-life activities like walking. This study evaluated the effect of the walking interference on the estimation of breathing parameters. 50 chronic obstructive pulmonary disease patients performed static and active measurements during thoracic bioimpedance acquisition. The static measurements included respiratory airflow for reference. The active measurements were used to estimate the walking interference from bioimpedance, and the obtained signals were added to static measurements for comparison with the reference. Afterward, we applied four different preprocessing methods to remove this walking interference and the resulting signals were used to detect the respiratory cycles and estimate breathing parameters (inspiratory time, expiratory time, duty cycle, and RR). The methods performed differently in terms of accuracy and mean average percentage error (MAPE), showing the need for specific preprocessing for active measurements. Furthermore, the MAPE values in the RR estimation were close to 3 % indicating that breathing parameters can be accurately estimated during walking. Accordingly, the present study reinforces the applicability of wearable bioimpedance for respiratory monitoring. Clinical relevance- This study exhibits the suitability of wearable bioimpedance to estimate accurate breathing param-eters during walking activities.

Multi-dimensional data-based medium- and long-term power-load forecasting using double-layer CatBoost

In this study, a medium- and long-term power load prediction method is proposed based on the two-layer categorical boosting (CatBoost) algorithm with multi-dimensional feature considerations. Simultaneously, the influences of economic fluctuation, power generation disruption, and meteorological data on power load are considered, whereby the dimension of power-load forecasting data characteristics is broadened. A randomised search cross-validation (CV) regression model is also applied to model parameter optimisation. Real data from a province in northeast China were used for the training and test sets. Compared with nine advanced load prediction models, including eXtreme gradient boosting and adaptive boosting, the coefficient of determination (R2) of the proposed method was 0.925, mean average percentage error (MAPE) was 0.0158, and root-mean-square error (RMSE) was 274.2036. In this study, a popular, viable artificial intelligence technology, two-layer CatBoost, was explored, and multi-dimensional external variables of power generation were added for the first time for load prediction. Finally, a higher accuracy load forecasting tree model is presented. The method has good potential for use in medium- and long-term power-load forecasting applications.

Time series forecasting for tuberculosis incidence employing neural network models

Every effort aimed at stopping the expansion of Tuberculosis is important to national programs' struggle to combat this disease. Different computational tools have been proposed in order to design new strategies that allow managing potential patients and thus providing the correct treatment. In this work, artificial neural networks were used for time series forecasting, which were trained with information on reported cases obtained from the national vigilance institution in Colombia. Three neural models were proposed in order to determine the best one according to their forecasting performance. The first approach employed a nonlinear autoregressive model, the second proposal used a recurrent neural network, and the third proposal was based on radial basis functions. The results are presented in terms of the mean average percentage error, which indicates that the models based on traditional methods show better performance compared to connectionist ones. These models contribute to obtaining dynamic information about incidence, thus providing extra-help for health authorities to propose more strategies to control the disease's spread.

Geometric Brownian Motion-Based Time Series Modeling Methodology for Statistical Autocorrelated Process Control: Logarithmic Return Model

Fitting a time series model to the process data before applying a control chart to the residuals is essential to fulfill the basic assumptions of statistical process control (SPC). Autoregressive integrated moving average (ARIMA) model has been one of the well-established time series modeling approaches that is extensively used for this purpose and is widely recognized for its accuracy and efficiency. Nevertheless, the research community commented that its iterative stages are laborious and time-consuming. In addressing this gap, a novel time series modeling technique with its conceptual assumptions of attributes that was derived from the geometric Brownian motion (GBM) law was developed in this study. It was termed as the logarithmic return (LR) model. Then, the model was employed and tested on a real-world autocorrelated data, whereby the results were assessed and benchmarked with the ARIMA model. The findings for LR model reported a mean average percentage error that ranged between 1.5851% and 3.3793% (less than 10%), which were as accurate as the ARIMA model. The running time (in second of CPU time) taken by the LR model was at least 96.2% faster than the ARIMA model. Interestingly, the corresponding multivariate control chart constructed from the LR model also portrayed a similar general conclusion as that of its counterpart. The LR model was obviously parsimonious and easier to compute and took a shorter running time than the ARIMA model. Therefore, it possessed the potential as an alternative time series modeling methodology for the ARIMA model in the procedures of SPC.

Transformer‐based time series prediction of the maximum power point for solar photovoltaic cells

AbstractThis paper proposes an improved deep learning‐based maximum power point tracking (MPPT) in solar photovoltaic cells considering various time series‐based environmental inputs. Generally, artificial neural network‐based MPPT algorithms use basic neural network architectures and inputs which do not represent the ambient conditions in a comprehensive manner. In this article, the ambient conditions of a location are represented through a comprehensive set of environmental features. Furthermore, the inclusion of time‐based features in the input data is considered to model cyclic patterns temporally within the atmospheric conditions leading to robust modeling of the MPPT algorithm. A transformer‐based deep learning architecture is trained as a time series prediction model using multidimensional time series input features. The model is trained on a dataset containing typical meteorological‐year data points of ambient weather conditions from 50 locations. The attention mechanism in the transformer modules allows the model to learn temporal patterns in the data efficiently. The proposed model achieves a 0.47% mean average percentage error of prediction on non‐zero operating voltage points in a test dataset consisting of data collected over a period of 200 consecutive hours; resulting in the average power efficiency of 99.54% and peak power efficiency of 99.98%. The proposed model is validated through real‐time simulations. The proposed model performs power point tracking in a robust, dynamic, and nonlatent manner, over a wide range of atmospheric conditions.

Short Time Series Forecasting: Recommended Methods and Techniques

This paper tackles the problem of forecasting real-life crime. However, the recollected data only produced thirty-five short-sized crime time series for three urban areas. We present a comparative analysis of four simple and four machine-learning-based ensemble forecasting methods. Additionally, we propose five forecasting techniques that manage the seasonal component of the time series. Furthermore, we used the symmetric mean average percentage error and a Friedman test to compare the performance of the forecasting methods and proposed techniques. The results showed that simple moving average with seasonal removal techniques produce the best performance for these series. It is important to highlight that a high percentage of the time series has no auto-correlation and a high level of symmetry, which is deemed as white noise and, therefore, difficult to forecast.

Machine learning methods for the prediction of milk fatty acid content

Random forest, extreme gradient boosting and artificial neural network machine learning methods were used to predict the content of myristic acid (C14:0) and conjugated linoleic acid (CLA) based on the milk fatty acids (FA) obtained through Fourier transform infrared spectroscopy. The methods had similar prediction performance for C14:0 (mean average percentage error < 7%). The low prediction accuracy for CLA was probably due to the poor association between the CLA and the input variables. Therefore, machine learning can be used to predict C14:0 and other saturated FA fromed from similar metabolic pathways

COMPARISON OF AUTOREGRESSIVE MODEL WITH MISSING DATA TREATED USING ORDINARY LEAST SQUARES AND INTERPOLATION WITH WEIGHTING METHOD

Bandung is committed to contributing to the achievement of the Sustainable Development Goals (SDGs) in Indonesia. One of the efforts that can be made to support the 13th pillar of SDGS regarding climate change is to forecast the air temperature of Bandung City in the future. One of the models that can be used for forecasting air temperature data in Bandung is the Autoregressive (AR) model. Based on BMKG data, often the time series data obtained has missing data. Therefore, in order to do a good time series analysis, it is necessary to make an effort to correct the missing data. The purpose of this research was to examine the procedure for overcoming missing data in the AR model using the Ordinary Least Squares (OLS) method and Interpolation with Weighting, which was applied to forecasting the average air temperature data in the city of Bandung. The research methodology followed the Box-Jenkins 3-step procedure. The first-order AR estimation parameter model was estimated using the OLS method and then used to overcome missing data using both methods with weighting using R software. Both methods resulted in an estimated value of 0.9991 and the same Mean Average Percentage Error (MAPE) value of 2,459% with very accurate criteria. Therefore, to overcome the missing data on the average air temperature data in the city of Bandung with a parameter estimator close to one, we got the same result for both methods.

Stock Indices Forecasting: A Comparison of Holt-Winters Seasonality and Dynamic Harmonic Regression

This research aims to investigate the performance of various time-series forecasting approaches in predicting stock indices in Indonesia. This research compared the performance of additive Holt-Winters seasonality, multiplicative Holt-Winters seasonality, and Dynamic Harmonic regression. The stock indices being forecast are SRI-KEHATI, LQ45, and IHSG. Forecasting SRI-KEHATI index is the novelty in this research. SRI-KEHATI index contains all the companies that comply with the requirements regarding sustainability and concerns for the environmental impact of the companies operations. Decompositions of SRI-KEHATI, LQ45, and IHSG reveal that the trend and seasonality components are all existent within all indices. The results showed that Holt-Winters models are superior to Dynamic Harmonic Regression. Multiplicative Holt-Winters seasonality forecast best for SRI-KEHATI and LQ45. Additive Holt-Winters excelled at predicting IHSG. Although Dynamic Harmonic Regression had less accuracy, its performance was still very outstanding since its mean average percentage errors never exceeded 8%. The result signifies the excellence of the Holt-Winters model for predicting stock indices and also shows that Dynamic Harmonic Regression also scores high in accuracy. Both models validate the time variance notion of the stock market proposed by Boudreaux (1995). The practical benefit for Investors is that this research enables investors to forecast the stock indices in the future and make adjustments in their trading strategy thereof.

District heating load prediction algorithm based on bidirectional long short-term memory network model

Heating load prediction based on machine learning algorithms has received increasing attention, especially the Long Short Term Memory (LSTM) network, have been shown to have a superior performance in predicting the heat load consumption. However, most of the current research reports on load prediction models using LSTM models are focused on the unidirectional (Uni-LSTM) network. In this paper, a bidirectional (Bi-LSTM) network for heat load prediction is proposed to make full use of the model hyperparameters to obtain the optimal model and to fully compare with the Uni-LSTM model, and the Bi-LSTM model can improve the prediction accuracy of heat load in a district heating system by using both past and future weather information. In addition, the two types of models are set up with different depth-stacked layers, and for each of the proposed models, a hyperparametric optimization tool has been used to obtain the best model. The results indicate that the increase in depth-stacked LSTM layers has no significant improvement in the prediction accuracy. The input time series length reflects the inertia influence duration of the district heating system, and the optimal model can be obtained for different settings of input time series length. The best optimally configured models were compared, and the single-layer Bi-LSTM model outperformed the single-layer Uni-LSTM model by 19.56%, 16.43%, 14.16%, and 20.69% in terms of the Root Mean Square Error (RMSE), Mean Average Percentage Error (MAPE), Mean Absolute Error (MAE), and the coefficient of variation of the RMSE (CV-RMSE), respectively.

An Improved Two-states Cyclical Dynamic Model for Plastic Waste Management

The panacea to the global challenge of plastic waste management is the transition towards plastic circular economy, which can be sustained through tailor-made management strategies. However, cutting-edge strategic solutions are constrained by inadequate data due to inadequate plastic-based predictive models. This paper presents an improved version of an existing two-state cyclical dynamic closed (CDC) model. The CDC model was formulated using a homogeneous linear system of ordinary differential equations (ODEs) and was modified by introducing a separation target which plays an essential role in determining both quantity and quality of recycled plastics. The Laplace transforms technique was the main analytic solution technique used. Values of the parameters were computed using the global plastic data applied for the existing CDC model, and with a technique termed the nth-order product derivative proximity, alternating pairs of initial values were selected each for the global annual plastic production and the global annual plastic waste generation. The validation process of the new CDC model was accomplished using the root mean squared error (RMSE) and the mean average percentage error (MAPE), which are measures of the model’s predictive power. Comparatively, RMSEs of the new CDC model were smaller than the RMSEs of the existing CDC model. MAPEs for the new CDC model were 6.5% and 7% (as against 13% and 18% in the existing model) respectively for the global annual plastic: production and waste generation, indicating that the new model predicts with 93.5% and 93% degrees of accuracy respectively for the global annual plastic: production and waste generation. Therefore, the new CDC model has outperformed the existing CDC model in terms of predictive power, and thus, establishing the new CDC model as an improved version of the existing one. The model can therefore make impactful policy decisions for sustainable plastic waste management thereby aiding to achieve the transition towards circular economy in plastic waste management.

Asian stock markets closing index forecast based on secondary decomposition, multi-factor analysis and attention-based LSTM model

The analysis and prediction of stock markets in Asian is an important issue which can help to promote the integration and globalization of financial cooperation. However, owning to the non-stationary and complexity of the stock market fluctuation, it is challenging to predict the stock price accurately. Especially after the decomposition of the original series, how to solve the problem of pseudo information and filter the exogenous variables is often certain challenging. This paper presents a hybrid model based on secondary decomposition (SD), multi-factor analysis (MFA) and attention-based long short-term memory (ALSTM) to predict the stock market price trends of four major Asian countries. The original stock price series is preprocessed by two decomposition algorithms so as to capture further non-linear feature and better filter the noise. Multi-factor analysis is introduced as a supplement to the original data information. In the prediction stage, attention layer is added in long short-term memory model to increase the weights of effective information. Finally, four datasets about Asian stock markets and nine compared models were used to verify the performance of the proposed model. The empirical analysis results show that compared to the general long short-term memory, our proposed model can obtain higher 30% accuracy at least. The mean average percentage errors of the system were also the lowest among all models mentioned in this paper (0.612%, 0.903%, 0.606% and 0.402% respectively), which proves the effectiveness of the hybrid model.

Application of CANFIS for modelling and predicting multiple output performances for different materials in µEDM

Micro Electrical Discharge Machining (µEDM) is one of the most demanding manufacturing processes available today. The selection of EDM parameters remains a challenge since it is frequently based on machinist intuition and heuristic approaches. Artificial intelligence algorithms have been used to model and predict the µEDM machining process in recent years. However, artificial intelligence has not been established for predicting µEDM performances based on material properties. Therefore, this paper has proposed a model that considers the material properties, such as thermal conductivity, melting point, and electrical resistivity. Since µEDM is a non-linear and stochastic process, Coactive Neuro-Fuzzy Inference Systems (CANFIS) was proposed to model and predict the multiple µEDM performances on various materials. The material properties, feed rate, capacitance, and gap voltage are input parameters in a three-level design based on a full factorial experiment. The CANFIS model can accurately predict the material removal rate (MRR), total discharge pulse, overcut, and taperness in a single model. The mean average percentage error (MAPE) of various outputs (predicted by the model) for test dataset such as MRR, total discharge pulse, overcut, and taper angle were found to be 4.5% (95.4% accuracy), 6.8% (93.2% accuracy), 15.4% (84.6% accuracy) and 15.2% (84.8% accuracy) respectively.

The transferability and validity of a population-level simulation model for the economic evaluation of interventions in diabetes: the MICADO model

AimsValid health economic models are essential to inform the adoption and reimbursement of therapies for diabetes mellitus. Often existing health economic models are applied in other countries and settings than those where they were developed. This practice requires assessing the transferability of a model developed from one setting to another. We evaluate the transferability of the MICADO model, developed for the Dutch 2007 setting, in two different settings using a range of adjustment steps. MICADO predicts micro- and macrovascular events at the population level.MethodsMICADO simulation results were compared to observed events in an Italian 2000–2015 cohort (Casale Monferrato Survey [CMS]) and in a Dutch 2008–2019 (Hoorn Diabetes Care Center [DCS]) cohort after adjusting the demographic characteristics. Additional adjustments were performed to: (1) risk factors prevalence at baseline, (2) prevalence of complications, and (3) all-cause mortality risks by age and sex. Model validity was assessed by mean average percentage error (MAPE) of cumulative incidences over 10 years of follow-up, where lower values mean better accuracy.ResultsFor mortality, MAPE was lower for CMS compared to DCS (0.38 vs. 0.70 following demographic adjustment) and adjustment step 3 improved it to 0.20 in CMS, whereas step 2 showed best results in DCS (0.65). MAPE for heart failure and stroke in DCS were 0.11 and 0.22, respectively, while for CMS was 0.42 and 0.41.ConclusionsThe transferability of the MICADO model varied by event and per cohort. Additional adjustments improved prediction of events for MICADO. To ensure a valid model in a new setting it is imperative to assess the impact of adjustments in terms of model accuracy, even when this involves the same country, but a new time period.

Artificial neural networks application on friction factor and heat transfer coefficients prediction in tubes with inner helical-finning

A study presents new model of the artificial neural network to predict friction factor and heat transfer coefficients for the turbulent flow in tubes with inner helical-finning. A fin geometry differs in its form, shape and fabrication method. The generalized equations, correlating thermal performance in such tube, available in earlier works by other authors primarily apply to a single type of inner helical-finning. In present work, we compile experimental results of other authors to an extended database that has been used further for artificial neural network training procedure. The presented model of artificial neural network applies to all types of inner helical tube finning. The mean average percent error values of 11.8% for friction factor and 16.3% for Nusselt number values for the ANN model over the whole database have been achieved. The performance validation of the obtained model was based on a comparison of predicted data with the independent experimental results obtained by authors, yielding excellent accuracy. • Extended database of Nusselt number and friction factor in helicallyfinned tubes. • Novel generalization model of artificial neural network. • Systematic analysis and validation of obtained artificial neural network model.