Search results

This study aims to create an efficient approach to validate building energy simulation models amidst challenges from time-intensive data collection. Emphasizing precision in model calibration through strategic short-term data acquisition, the systematic framework targets critical adjustments using a strategically captured dataset. Leveraging metrics like Mean Bias Error (MBE) and Coefficient of Variation of Root Mean Square Error (CV(RMSE)), this methodology aims to heighten energy efficiency assessment accuracy without lengthy data collection periods.

A standalone school and a campus facility were selected as case studies. Field investigations enabled precise energy modeling, emphasizing user-dependent parameters and compliance with standards. Simulation outputs were compared to short-term actual measurements, utilizing MBE and CV(RMSE) metrics, focusing on internal temperature and CO₂ levels. Energy bills and consumption data were scrutinized to verify natural gas and electricity usage against uncertain parameters.

Discrepancies between initial simulations and measurements were observed. Following adjustments, the standalone school 1’s average internal temperature increased from 19.5 °C to 21.3 °C, with MBE and CV(RMSE) aiding validation. Campus facilities exhibited complex variations, addressed by accounting for CO₂ levels and occupancy patterns, with similar metrics aiding validation. Revisions in lighting and electrical equipment schedules improved electricity consumption predictions. Verification of natural gas usage and monthly error rate calculations refined the simulation model.

This paper tackles Building Energy Simulation validation challenges due to data scarcity and time constraints. It proposes a strategic, short-term data collection method. It uses MBE and CV(RMSE) metrics for a comprehensive evaluation to ensure reliable energy efficiency predictions without extensive data collection.

The purpose of this paper is to investigate the effect of residence time distribution in extruders along with the incorporation of nutraceuticals on the final quality of the products with respect to several pivotal responses.

Corn–rice flour blend fortified with isolated nutraceutical concentrates at two (low and high) levels was extruded at barrel temperature (110°C), screw speed (260 rpm) and feed moisture (17 percent). Extrudates were collected at an interval of 24 s followed by analysis for radial expansion (RE), bulk density (BD), water absorption index (WAI), sensory score (SS), textural hardness, colorimetric values (L*, a* and b*) and color difference (E).

The entire data were fitted to zero- and first-order kinetic models. There was a gradual decrease in RE, SS and L* value, whereas an increase in BD, textural hardness and a* value of extrudates fortified with the three nutraceutical concentrates was observed with the successive time interval of 24 s along with a more pronounced effect on color difference (E) observed during the last stages of extrusion time. The zero-order kinetic model was well fitted for BD and a* value, whereas the first-order kinetic model showed better results for RE, WAI, SS, textural hardness, L* value, a* value and b* value of fortified extrudates.

Nutraceuticals like β-glucans, lignans and γ oryzanol exhibit numerous health-beneficial effects. This study analyzes the kinetics of changes in various responses of extrudates fortified with these nutraceutical concentrates during extrusion.

This chapter analyzes the properties of an alternative least-squares based estimator for linear panel data models with general predetermined regressors. This approach uses backward means of regressors to approximate individual specific fixed effects (FE). The author analyzes sufficient conditions for this estimator to be asymptotically efficient, and argue that, in comparison with the FE estimator, the use of backward means leads to a non-trivial bias-variance tradeoff. The author complements theoretical analysis with an extensive Monte Carlo study, where the author finds that some of the currently available results for restricted AR(1) model cannot be easily generalized, and should be extrapolated with caution.

From the standpoint of a policy maker who has access to a number of expert forecasts, the uncertainty of a combined or ensemble forecast should be interpreted as that of a typical forecaster randomly drawn from the pool. This uncertainty formula should incorporate forecaster discord, as justified by (i) disagreement as a component of combined forecast uncertainty, (ii) the model averaging literature, and (iii) central banks’ communication of uncertainty via fan charts. Using new statistics to test for the homogeneity of idiosyncratic errors under the joint limits with both T and n approaching infinity simultaneously, the authors find that some previously used measures can significantly underestimate the conceptually correct benchmark forecast uncertainty.

Visible and near infrared spectroscopy have been applied widely in fruits quality assessment especially on the measurement of soluble solids content (SSC) measured in ^oBrix and acidity measured in pH. Spectroscopy technique has been applied on three botanically different categories of fruits, that is: imported Californian table grape, Mandarin lime and star fruit. The purpose is to examine the ability of spectroscopy technique to quantify internal quality parameters with very narrow variability due to the characteristics of the raw material analyzed. This work also presents comparative study on peak wavelengths that can best be used to calibrate SSC and pH of different types of fruits.

The effective wavelengths chosen for calibration development are compared with those selected by other researchers in similar experiments. NIR wavelengths 910 nm (C−H band) and 950 nm (O−H band) are the most important wavelengths for the prediction of SSC for all examined fruits while wavelengths 922‐923 nm and 990‐995 nm for pH. Visible wavelength 605, 675 and 654 nm can efficiently improve the SSC and pH prediction for grape, lime and star fruit, respectively.

The best prediction for SSC has been achieved with R²=0.953 and RMSE=0.182 for grape, R²=0.918 and RMSE=0.109 for lime and R²=0.957 and RMSE=0.354 for star fruit. The best prediction for pH has been achieved with R²=0.763 and RMSE=0.110 for grape, R²=0.841 and RMSE=0.073 for lime and R²=0.862 and RMSE=0.261 for star fruit.

Currently, the spectroscopy research conducted for the measurement of fruits qualities is conducted through wide range spectrometer. However, the peak responses are only located at specific wavelengths. Hence, the selection of wavelengths related to SSC and pH will allow the design of low cost instruments for the prediction of these internal quality parameters.

Cartosat‐1 is the first Indian Remote Sensing satellite, developed for topographic mapping, able to collect in‐track high‐resolution stereo images with a 2.5 m pixel size. In the framework of the Cartosat‐1 Scientific Assessment Programme (C‐SAP), the Politecnico di Milano University (Italy) evaluated the performances of the Cartosat‐1 satellite in the generation of digital terrain models (DTMs) from stereo‐couples. The purpose of this paper is to describe in detail the outcomes for the Salon de Provence (France) test site, with respect to existing standards and products actually used in France and also to provide a comparison with the global Shuttle Radar Topography Mission's DTM freely available from by NASA.

The Cartosat‐1 data processing was done using the commercial off‐the‐shelf software ENVI®, selected for investigating the capabilities and limits of the system using standard image processing tools, so from the point of view of a typical remote sensing user. The data processing involved the following aspects: data pre‐processing; optimization of the DTM's extraction procedure; analysis of the influence of ground control points' (GCPs) in the generated DTMs; analysis of the influence of the DTM's resolution in the elevation accuracy; and post‐processing refinement.

When generating relative DTMs an error was observed in elevation of some hundreds of meters. After georeferencing, the root mean square error (RMSE) was between 9.0 and 14.2 m and the LE90 between 16.1 and 19.0 m. When generating absolute DTMs, the optimum number of GCPs was found to be 9, with a regular geometric distribution (4.6 m RMSE and 6.5 m LE90 for 10 m grid cell size). Post‐processing may be applied to enhance results (1.6 m RMSE and 2.0 m LE90 for 10 m grid cell size). In this case, the absolute DTMs fulfilled and also overcame the standards required for the IGNs and Spot Image's Reference 3D®.

This paper describes the outcomes of the C‐SAP led by the International Society for Photogrammetry and Remote Sensing and the Indian Space Research Organisation for evaluating the capabilities of the last Cartosat‐1 satellite. The aim is to provide remote sensing users a comprehensive study about the potentialities and limits of the Cartosat‐1 images for multi‐resolution DTM generation (from 5 to 90 m grid cell size).

This study aims to assess support vector machine (SVM) models' predictive ability to estimate half-cell potential (HCP) values from input parameters by using Bayesian optimization, grid search and random search.

A data set with 1,134 rows and 6 columns is used for principal component analysis (PCA) to minimize dimensionality and preserve 95% of explained variance. HCP is output from temperature, age, relative humidity, X and Y lengths. Root mean square error (RMSE), R-squared, mean squared error (MSE), mean absolute error, prediction speed and training time are used to measure model effectiveness. SHAPLEY analysis is also executed.

The study reveals variations in predictive performance across different optimization methods, with RMSE values ranging from 18.365 to 30.205 and R-squared values spanning from 0.88 to 0.96. Additionally, differences in training times, prediction speeds and model complexities are observed, highlighting the trade-offs between model accuracy and computational efficiency.

This study contributes to the understanding of SVM model efficacy in HCP prediction, emphasizing the importance of optimization techniques, model complexity and dimensionality reduction methods such as PCA.

This study aims to critically evaluate the competitiveness of Transformer-based models in financial forecasting, specifically in the context of stock realized volatility forecasting. It seeks to challenge and extend upon the assertions of Zeng et al. (2023) regarding the purported limitations of these models in handling temporal information in financial time series.

Employing a robust methodological framework, the study systematically compares a range of Transformer models, including first-generation and advanced iterations like Informer, Autoformer, and PatchTST, against benchmark models (HAR, NBEATSx, NHITS, and TimesNet). The evaluation encompasses 80 different stocks, four error metrics, four statistical tests, and three robustness tests designed to reflect diverse market conditions and data availability scenarios.

The research uncovers that while first-generation Transformer models, like TFT, underperform in financial forecasting, second-generation models like Informer, Autoformer, and PatchTST demonstrate remarkable efficacy, especially in scenarios characterized by limited historical data and market volatility. The study also highlights the nuanced performance of these models across different forecasting horizons and error metrics, showcasing their potential as robust tools in financial forecasting, which contradicts the findings of Zeng et al. (2023)

This paper contributes to the financial forecasting literature by providing a comprehensive analysis of the applicability of Transformer-based models in this domain. It offers new insights into the capabilities of these models, especially their adaptability to different market conditions and forecasting requirements, challenging the existing skepticism created by Zeng et al. (2023) about their utility in financial forecasting.

This paper aims to clarify the efficient process of the machine learning algorithms implemented in the ready-mix concrete (RMC) onsite. It proposes innovative machine learning algorithms in terms of preciseness and computation time for the RMC strength prediction.

This paper presents an investigation of five different machine learning algorithms, namely, multilinear regression, support vector regression, k-nearest neighbors, extreme gradient boosting (XGBOOST) and deep neural network (DNN), that can be used to predict the 28- and 56-day compressive strengths of nine mix designs and four mixing conditions. Two algorithms were designated for fitting the actual and predicted 28- and 56-day compressive strength data. Moreover, the 28-day compressive strength data were implemented to predict 56-day compressive strength.

The efficacy of the compressive strength data was predicted by DNN and XGBOOST algorithms. The computation time of the XGBOOST algorithm was apparently faster than the DNN, offering it to be the most suitable strength prediction tool for RMC.

Since none has been practically adopted the machine learning for strength prediction for RMC, the scope of this work focuses on the commercially available algorithms. The adoption of the modified methods to fit with the RMC data should be determined thereafter.

The selected algorithms offer efficient prediction for promoting sustainability to the RMC industries. The standard adopting such algorithms can be established, excluding the traditional labor testing. The manufacturers can implement research to introduce machine learning in the quality controcl process of their plants.

Regarding literature review, machine learning has been assessed regarding the laboratory concrete mix design and concrete performance. A study conducted based on the on-site production and prolonged mixing parameters is lacking.

The purpose of this study is to propose a systematic model selection procedure for long-term load forecasting (LTLF) for ex-ante and ex-post cases considering uncertainty in exogenous predictors.

The different variants of regression models, namely, Polynomial Regression (PR), Generalised Additive Model (GAM), Quantile Polynomial Regression (QPR) and Quantile Spline Regression (QSR), incorporating uncertainty in exogenous predictors like population, Real Gross State Product (RGSP) and Real Per Capita Income (RPCI), temperature and indicators of breakpoints and calendar effects, are considered for LTLF. Initially, the Backward Feature Elimination procedure is used to identify the optimal set of predictors for LTLF. Then, the consistency in model accuracies is evaluated using point and probabilistic forecast error metrics for ex-ante and ex-post cases.

From this study, it is found PR model outperformed in ex-ante condition, while QPR model outperformed in ex-post condition. Further, QPR model performed consistently across validation and testing periods. Overall, QPR model excelled in capturing uncertainty in exogenous predictors, thereby reducing over-forecast error and risk of overinvestment.

These findings can help utilities to align model selection strategies with their risk tolerance.

To propose the systematic model selection procedure in this study, the consistent performance of PR, GAM, QPR and QSR models are evaluated using point forecast accuracy metrics Mean Absolute Percentage Error, Root Mean Squared Error and probabilistic forecast accuracy metric Pinball Score for ex-ante and ex-post cases considering uncertainty in the considered exogenous predictors such as RGSP, RPCI, population and temperature.