Lower RMSE Research Articles

Modeling the Thermal Inactivation of Monascus ruber Ascospores Isolated from Green Olive (Arauco Cultivar) Storage Brine: An Alternative Strategy to Reduce Antifungal Chemical Agents.

Monascus ruber is an important fungus that causes spoilage in table olives, resulting in the darkening of the brine, the softening of the fruit, increased pH, and apparent mycelial growth. This study aimed to evaluate this resistance, providing a model to determine the optimal processing conditions for mitigating fungal contamination and prolonging shelf life without antifungal agents while optimizing pasteurization to reduce energy consumption. The resistance in brine (3.5% NaCl; pH 3.5) from Arauco cultivar green olives imported from Argentina was assessed. Four predictive models (log linear, log linear + shoulder, log linear + tail, log linear + shoulder + tail) estimated kinetic parameters for each survival curve. Log linear + shoulder + tail provided the best fit for 70 °C and 75 °C, with low RMSE (0.171 and 0.112) and high R2 values (0.98 and 0.99), respectively, while the log linear model was used for 80 °C. Decimal reduction times at 70, 75, and 80 °C were 24.8, 5.4, and 1.6 min, respectively, with a z-value of 8.2 °C. The current regulatory processes are insufficient to eliminate M. ruber at requisite levels, considering reduced antifungal agents.

Multi-mode monitoring and energy management for photovoltaic-storage systems

The integration of photovoltaic generation systems and variable demand can cause instability in the distribution network, due to power fluctuations and the increase in reactants, particularly in the industrial sector. In response, photovoltaic units have been equipped with local storage systems, which eventually absorb power fluctuations and improve installation performance. However, during this procedure other functionalities that energy storage could provide are neglected. Consequently, this study provides a multi-mode energy monitoring and management model that enables voltage regulation, frequency regulation and reactive power compensation through the optimal operation of energy storage systems. With this objective, a smoothing control algorithm is developed that interacts with parameters of the electrical grid at the common connection point and also allows the compensation of reactive power based on an industrial demand profile. This strategy uses the Long short-term memory neural network of historical demand data prior to energy consumption with a relatively low RMSE of 1.2e-09. The results are previously validated in a development environment using a real-time OPAL-RT simulator and tests in the electrical Microgrid laboratory at the University of Cuenca. This configuration allows establishing a demand forecasting model that improves the supervision, automation and analysis of daily energy production. A series of results are provided and analyzed that demonstrate that the new tool allows taking advantage of the provision of multimode functionalities, achieving optimal voltage regulation and improving power quality by reducing the total harmonic distortion THD (V) and THD (I) indices by 0.5. % and 2 % respectively.

Predicting Cd(II) adsorption capacity of biochar materials using typical machine learning models for effective remediation of aquatic environments

The screening and design of “green” biochar materials with high adsorption capacity play a pivotal role in promoting the sustainable treatment of Cd(II)-containing wastewater. In this study, six typical machine learning (ML) models, namely Linear Regression, Random Forest, Gradient Boosting Decision Tree, CatBoost, K-Nearest Neighbors, and Backpropagation Neural Network, were employed to accurately predict the adsorption capacity of Cd(II) onto biochars. A large dataset with 1051 data points was generated using 21 input variables obtained from batch adsorption experiments, including preparation conditions for biochar (2 features), physical properties of biochar (4 features), chemical composition of biochar (9 features), and adsorption experiment conditions (6 features). The rigorous evaluation and comparison of the ML models revealed that the CatBoost model exhibited the highest test R2 value (0.971) and the lowest RMSE (20.54 mg/g), significantly outperforming all other models. The feature importance analysis using Shapley Additive Explanations (SHAP) indicated that biochar chemical compositions had the greatest impact on model predictions of adsorption capacity (42.2 %), followed by adsorption conditions (37.57 %), biochar physical characteristics (12.38 %), and preparation conditions (7.85 %). The optimal experimental conditions optimized by partial dependence plots (PDP) are as follows: as high Cd(II) concentration as possible, C(%) of 33 %, N(%) of 0.3 %, adsorption time of 600 min, pyrolysis time of 50 min, biochar dosage of less than 2 g/L, O(%) of 42 %, biochar pH value of 11.2, and DBE of 1.15. This study unveils novel insights into the adsorption of Cd(II) and provides a comprehensive reference for the sustainable engineering of biochars in Cd(II) wastewater treatment.

Evaluation of machine learning models for predicting TiO2 photocatalytic degradation of air contaminants

The escalation of global urbanization and industrial expansion has resulted in an increase in the emission of harmful substances into the atmosphere. Evaluating the effectiveness of titanium dioxide (TiO2) in photocatalytic degradation through traditional methods is resource-intensive and complex due to the detailed photocatalyst structures and the wide range of contaminants. Therefore in this study, recent advancements in machine learning (ML) are used to offer data-driven approach using thirteen machine learning techniques namely XG Boost (XGB), decision tree (DT), lasso Regression (LR2), support vector regression (SVR), adaBoost (AB), voting Regressor (VR), CatBoost (CB), K-Nearest Neighbors (KNN), gradient boost (GB), random Forest (RF), artificial neural network (ANN), ridge regression (RR), linear regression (LR1) to address the problem of estimation of TiO2 photocatalytic degradation rate of air contaminants. The models are developed using literature data and different methodical tools are used to evaluate the developed ML models. XGB, DT and LR2 models have high R2 values of 0.93, 0.926 and 0.926 in training and 0.936, 0.924 and 0.924 in test phase. While ANN, RR and LR models have lowest R2 values of 0.70, 0.56 and 0.40 in training and 0.62, 0.63 and 0.31 in test phase respectively. XGB, DT and LR2 have low MAE and RMSE values of 0.450 min-1/cm2, 0.494 min-1/cm2 and 0.49 min-1/cm2 for RMSE and 0.263 min-1/cm2, 0.285 min-1/cm2 and 0.29 min-1/cm2 for MAE in test stage. XGB, DT, and LR2 have 93% percent errors within 20% error range in training phase. XGB has 92% and DT, and LR2 have 94% errors with 20% range in test phase. XGB, DT, LR2 models remained the highest performing models and XGB is the most robust and effective in predictions. Feature importances reveal the role of input parameters in prediction made by developed ML models. Dosage, humidity, UV light intensity remain important experimental factors. This study will impact positively in providing efficient models to estimate photocatalytic degradation rate of air contaminants using TiO2.

Gaussian process regression coupled with mRMR to predict adulterant concentration in cocaine

Street cocaine is often mixed with various substances that intensify its harmful effects. This paper proposes a framework to identify attenuated total reflection Fourier transform infrared spectroscopy (ATR-FTIR) intervals that best predict the concentration of adulterants in cocaine samples. Wavelengths are ranked according to their relevance through ReliefF and mRMR feature selection approaches, and an iterative process removes less relevant wavelengths based on the ranking suggested by each approach. Gaussian Process (GP) regression models are constructed after each wavelength removal and the prediction performance is evaluated using RMSE. The subset balancing a low RMSE value and a small percentage of retained wavelengths is chosen. The proposed framework was validated using a dataset consisting of 345 samples of cocaine with different amounts of levamisole, caffeine, phenacetin, and lidocaine. Averaged over the four adulterants, the GP regression coupled with the mRMR retained 1.07 % of the 662 original wavelengths, outperforming PLS and SVR regarding prediction performance.

Can Unmanned Aerial Vehicle Images Be Used to Estimate Forage Production Parameters in Agroforestry Systems in the Caatinga?

The environmental changes in the Caatinga biome have already resulted in it reaching levels of approximately 50% of its original vegetation, making it the third most degraded biome in Brazil, due to inadequate grazing practices that are driven by the difficulty of monitoring and estimating the yield parameters of forage plants, especially in agroforestry systems (AFS) in this biome. This study aimed to compare the predictive ability of different indexes with regard to the biomass and leaf area index of forage crops (bushveld signal grass and buffel grass) in AFS in the Caatinga biome and to evaluate the influence of removing system components on model performance. The normalized green red difference index (NGRDI) and the visible atmospherically resistant index (VARI) showed higher correlations (p < 0.05) with the variables. In addition, removing trees from the orthomosaics was the approach that most favored the correlation values. The models based on classification and regression trees (CARTs) showed lower RMSE values, presenting values of 3020.86, 1201.75, and 0.20 for FB, DB, and LAI, respectively, as well as higher CCC values (0.94). Using NGRDI and VARI, removing trees from the images, and using CART are recommended in estimating biomass and leaf area index in agroforestry systems in the Caatinga biome.

Machine Learning and Hybrid Model Building Mechanism for Forecasting Agricultural Market Behaviour: A Case Study of Vegetable Crops

A strategic market intelligence mechanism is essential for stakeholders to make well-informed decisions on production, pricing, and marketing strategies; however, the complex behaviour of agricultural markets, coupled with the presence of non-stationarity, non-normality, and non-linearity in the arrivals and prices of perishable agricultural commodities pose challenges for traditional statistical models in modelling and forecasting. This study sought to overcome these challenges by employing machine learning and hybrid models for vegetable crops. Machine learning techniques, known for their flexibility with non-stationary, non-normal, and non-linear data, were showcased in the empirical illustration, highlighting their effectiveness. The trends of arrivals and prices were found to be significantly positive (p<0.01) for tomato and capsicum. Time delay neural network (TDNN) and hybrid models outperformed the seasonal ARIMA models based on lower RMSE and MAPE for the modelling and forecasting. Utilizing the best-fit models, the prices of tomato and capsicum were forecasted to be highest during June 2024 with ?2267 and 2623 per q. This study contributed to the growing body of applications of machine learning in agricultural systems. It will help develop a robust market intelligence mechanism to address uncertainties in agricultural markets.

Intensification of bio-actives extraction from pomegranate peel via microwave irradiation: Effect of factors, optimization, kinetics, and bioactive profiling

Pomegranate (Punica granatum L.) peel is an appealing agri-food byproduct due to its high content of health-beneficial phytochemicals. However, the extraction processes may alter their bioactivity. A microwave irradiation treatment was applied to enhance the extraction efficiency. Extraction time, microwave power, and temperature were examined and optimized numerically using polynomial model and genetic algorithm. Time and temperature were the most influential factors in intensifying bioactives extraction. The optimal variables were 620 W microwave power at 74 °C for 18 min (RSM), and 685 W power at 75 °C for 24 min (ANN-GA). The obtained yields of total polyphenols, flavonoids, punicalagin, ellagic acid, and total hydrolyzable tannins contents were 165.53 mg GAE/g, 40.78 mg QE/g, 91.05 mg/g, 4.28 mg/g, and 130.82 mg TAE/g of pomegranate peel, respectively. The extract showed significant antioxidant capacities, with 65.74 % DPPH inhibition and 71.26 % ABTS inhibition. Several kinetic models were studied to define the extraction kinetics, with Peleg's model being the best fitting with the highest R2 (0.963–0.987) and lowest RMSE (0.95–5.08). LCMS analysis confirms the presence of 15 hydrolyzable tannins, with punicalagin and ellagic acid being the most abundant. These findings demonstrated the significant potential of microwave irradiation for extracting bioactives from fruit byproducts.

Enhancing prediction accuracy of Remaining Useful Life in lithium-ion batteries: A deep learning approach with Bat optimizer

Remaining Useful Life (RUL) prediction in lithium-ion batteries is crucial for assessing battery performance. Despite the popularity of deep learning methods for RUL prediction, their complex architectures often pose challenges in interpretation and resource consumption. We propose a novel approach that combines the interpretability of a convolutional neural network (CNN) with the efficiency of a bat-based optimizer. CNN extracts battery data features and characterizes degradation kinetics, while the optimizer refines CNN parameters. Tested on NASA PCoE data, our method achieves exceptional results with minimal computational burden and fewer parameters. It outperforms traditional approaches, yielding an R2-score of 0.9987120, an MAE of 0.004397067 Ah, and a low RMSE of 0.00656 Ah. The proposed model outperforms traditional deep learning models, as confirmed by comparative analysis.

Estimation of the shear strength of UHPC beams via interpretable deep learning models: Comparison of different optimization techniques

In this article, optimized deep learning (DL) models with different algorithms are adopted to estimate the shear strength of rectangular ultra-high performance concrete beams (UHPC-Bs) in order to overcome the challenges in traditional mechanics-based approaches. Long short-term memory (LSTM) and gated recurrent unit (GRU) are chosen as the DL models, whereas the recent popular optimization algorithms are phasor particle swarm optimization (PPSO), dwarf mongoose optimization (DMO), mountain gazelle optimizer (MGO), and atom search optimization (ASO). A thorough and reliable dataset of 244 UHPC-Bs test results with ten input features has been used to construct the hybrid DL models. The performance of the optimized hybrid LSTM and GRU models with different algorithms is extensively assessed and compared based on various statistical metrics, error, and score analyses. Then, the model with the best estimation performance is determined and compared with the mechanics-based formulas in the current international design codes. Additionally, Shapley additive explanations (SHAP) analysis is used to assist in the interpretability of DL models and to reveal the effects of input features that contribute to the model's estimation. According to the results of the present work, all DL models successfully estimate the shear strength of UHPC-Bs. Among these models, the MGO-LSTM model stands out compared to the other models in terms of several performance measures for both the training and testing phases, like a higher R2 value, lower RMSE, MAPE, and MAE values, as well as a smaller error ratio and a higher final score. The performance of the algorithms applied to optimize the hyper-parameters of the LSTM and GRU models can be ranked as follows: MGO > DMO > PPSO > ASO. Moreover, a graphical user interface (GUI) was constructed based on the best estimation model that was built so that the shear strength of UHPC-Bs could be estimated in real-world situations without the need for any extra software or tools. This enables more users to quickly and easily estimate the shear strength of UHPC-Bs, optimize design processes, and decrease experimental testing costs.

Coupling the PROSAIL Model and Machine Learning Approach for Canopy Parameter Estimation of Moso Bamboo Forests from UAV Hyperspectral Data

Parameters such as the leaf area index (LAI), canopy chlorophyll content (CCH), and canopy carotenoid content (CCA) are important indicators for evaluating the ecological functions of forests. Currently, rapidly developing unmanned aerial vehicles (UAV) equipped with hyperspectral technology provide advanced technical means for the real-time dynamic acquisition of regional vegetation canopy parameters. In this study, a hyperspectral sensor mounted on a UAV was used to acquire the data in the study area, and the canopy parameter estimation model of moso bamboo forests (MBF) was developed by combining the PROSAIL radiative transfer model and the machine learning regression algorithm (MLRA), inverted the canopy parameters such as LAI, CCH, and CCA. The method first utilized the extended Fourier amplitude sensitivity test (EFAST) method to optimize the global sensitivity analysis and parameters of the PROSAIL model, and the successive projections algorithm (SPA) was used to screen the characteristic wavebands for the inversion of MBF canopy parameter inversion. Then, the optimized PROSAIL model was used to construct the ‘LAI-CCH-CCA-canopy reflectance’ simulation dataset for the MBF; multilayer perceptron regressor (MLPR), extra tree regressor (ETR), and extreme gradient boosting regressor (XGBR) employed used to construct PROSAIL_MLPR, PROSAIL_ETR, and PROSAIL_XGBR, respectively, as the three hybrid models. Finally, the best hybrid model was selected and used to invert the spatial distribution of the MBF canopy parameters. The following results were obtained: Waveband sensitivity analysis reveals 400–490 and 710–1000 nm as critical for LAI, 540–650 nm for chlorophyll, and 490–540 nm for carotenoids. SPA narrows down the feature bands to 43 for LAI, 19 for CCH, and 9 for CCA. The three constructed hybrid models were able to achieve high-precision inversion of the three parameters of the MBF, the model fitting accuracy of PROSAIL_MLRA reached more than 95%, with lower RMSE values, and the PROSAIL_XGBR model yielded the best fitting results. Our study provides a novel method for the inversion of forest canopy parameters based on UAV hyperspectral data.

Individual random effects model for differences in trait distribution among respondents

The homogeneity hypothesis is a common assumption in classic measurement. However, the item response theory model assumes that different respondents with same ability have the same option probabilities, which may not hold. The aim of this study is to propose a new individual random effect model that accounts for the differences in option probabilities among respondents with same latent traits by using within-person variance. The performance of the new model is evaluated through simulation studies and real data using the PRESUPP scale of PISA. The model parameters are estimated by the MCMC method. The results show that the individual random effect model can provide more accurate parameter estimates and obtain a scale parameter to describe the distribution of respondents’ abilities, under different within-person variances. The new model has lower RMSE and better model fit than the classic IRT model.

Estimating Forest Aboveground Biomass Using a Combination of Geographical Random Forest and Empirical Bayesian Kriging Models

Accurately estimating forest aboveground biomass (AGB) is imperative for comprehending carbon cycling, calculating carbon budgets, and formulating sustainable forest management plans. Currently, random forest (RF) and other machine learning models are widely used to estimate forest AGB, as they can effectively handle nonlinear relationships. However, by constructing a global model using all the samples collected from a study area, these models fail to account for the spatial heterogeneity in the AGB and cannot correct the prediction biases, thereby constraining the estimation accuracy. To overcome these limitations, we proposed a novel approach termed geographical random forest and empirical Bayesian kriging (GRFEBK). This hybrid model combines the localized modeling capability of geographical random forest (GRF) with the bias correction strength of empirical Bayesian kriging (EBK). GRF adapts RF to account for the spatial heterogeneity of the AGB, while EBK utilizes the spatial autocorrelation of residuals to correct the prediction deviations. This study was conducted in Hainan Island, utilizing spectral bands, vegetation indices, tasseled cap components derived from Landsat-8 imagery, backscattering coefficients from ALOS-2 synthetic aperture radar, topographic features, and the forest canopy height as the explanatory variables. A total of 195 forest aboveground biomass (AGB) samples were collected for modeling and assessing the predictive accuracy. The results demonstrate that, among the tested models, including GRFEBK, RF, support vector machine (SVM), k-nearest neighbor (KNN), geographically weighted regression (GWR), GRF, and EBK, GRFEBK attains the highest R2 (0.78) and the lowest RMSE (36.04 Mg/ha) and RRMSE (22.87%), significantly outperforming the conventional models and using GRF or EBK alone. These results demonstrate that by accounting for local non-stationarity in AGB and correcting prediction biases, GRFEBK achieves significantly higher accuracy than conventional RF and other models. While the results are promising, the computational cost of GRFEBK and its performance under varying geographical conditions warrant further investigation at larger scales to assess its broader applicability. Nevertheless, GRFEBK provides an innovative and more reliable approach for accurate forest AGB estimation with great potential to support global forest resource monitoring.

Multi-sequence generative adversarial network: better generation for enhanced magnetic resonance imaging images.

MRI is one of the commonly used diagnostic methods in clinical practice, especially in brain diseases. There are many sequences in MRI, but T1CE images can only be obtained by using contrast agents. Many patients (such as cancer patients) must undergo alignment of multiple MRI sequences for diagnosis, especially the contrast-enhanced magnetic resonance sequence. However, some patients such as pregnant women, children, etc. find it difficult to use contrast agents to obtain enhanced sequences, and contrast agents have many adverse reactions, which can pose a significant risk. With the continuous development of deep learning, the emergence of generative adversarial networks makes it possible to extract features from one type of image to generate another type of image. We propose a generative adversarial network model with multimodal inputs and end-to-end decoding based on the pix2pix model. For the pix2pix model, we used four evaluation metrics: NMSE, RMSE, SSIM, and PNSR to assess the effectiveness of our generated model. Through statistical analysis, we compared our proposed new model with pix2pix and found significant differences between the two. Our model outperformed pix2pix, with higher SSIM and PNSR, lower NMSE and RMSE. We also found that the input of T1W images and T2W images had better effects than other combinations, providing new ideas for subsequent work on generating magnetic resonance enhancement sequence images. By using our model, it is possible to generate magnetic resonance enhanced sequence images based on magnetic resonance non-enhanced sequence images. This has significant implications as it can greatly reduce the use of contrast agents to protect populations such as pregnant women and children who are contraindicated for contrast agents. Additionally, contrast agents are relatively expensive, and this generation method may bring about substantial economic benefits.

Assessing Solar Radiation Forecasting: a WRF-Solar Model Evaluation in Kupang, Indonesia

In response to the challenges faced by solar power plants in Kupang, Indonesia – particularly during the peak of the rainy season – this study aims to enhance the WRF-Solar (Weather Research and Forecasting–Solar) numerical weather prediction model. Accurate short-term solar radiation forecasting is crucial for managing electricity supply disruptions and controlling operational costs in the City of Kupang and its surroundings. The unpredictable weather patterns – characterized by intense cloud activity during these seasons – pose significant challenges for reliable solar energy generation, thereby making precise weather modeling an essential tool for effective power plant management. Spanning 2020–2022, the research focused on the peak rainy seasons, utilizing a specifically configured WRF-Solar model to simulate solar radiation. Validation of the WRF-Solar model using observational data from the Automatic Solar Radiation Stations at the Kupang Climatological Station showed correlation values consistently above 0.50. However, the model exhibited a tendency to overestimate radiation intensity for GHI and DNI parameters (correlation 0.78 and 0.54) and underestimate for DHI (correlation 0.80), with RMSE values ranging from 47–320 W/m² and MBE values from –41.84 to 116.34 W/m². The model's accuracy was notably higher under clear conditions, with lower RMSE and MBE values but decreased significantly under overcast conditions, hence indicating sensitivity to cloud cover. This study highlights the WRF-Solar model's capability in capturing the diurnal pattern and hourly fluctuations of solar radiation while also underscoring the need for improved cloud representation to enhance accuracy under diverse climatic conditions.

Wheat Yield Estimation Study Using Hyperspectral Vegetation Indices

Wheat is the main grain crop in our country, and the traditional wheat yield estimation method is time-consuming and laborious. By estimating wheat yield efficiently, quickly and non-destructively, agricultural producers can quickly obtain information about wheat yield, manage wheat fields more scientifically and accurately, and ensure national food security. Taking the Xinxiang Experimental Base of the Crop Science Research Institute, Chinese Academy of Agricultural Sciences as an example, hyperspectral data for the critical growth stages of wheat were pre-processed. A total of 27 vegetation indices were calculated from the experimental plots. These indices were then subjected to correlation analysis with measured wheat yield. Vegetation indices with Pearson correlation coefficients greater than 0.5 were selected. Five methods, including multiple linear regression, stepwise regression, principal component regression, neural networks and random forests, were used to construct wheat yield estimation models. Among the methods used, multiple linear regression, stepwise regression and the models developed using principal component analysis showed a lower modelling accuracy and validation precision. However, the neural network and random forest methods both achieved a modelling accuracy R2 greater than 0.6, with validation accuracy R2 values of 0.729 and 0.946, respectively. In addition, the random forest method had a lower cross-validation RMSE value, with values of 869.8 kg/hm−2, indicating a higher model accuracy. In summary, the random forest method provided the optimal estimation for wheat yield, enabling the timely and accurate pre-harvest wheat yield prediction, which has significant value for precision agriculture management and decision making.

Using predictive models unravel the potential of titanium oxide-loaded activated carbon for the removal of leachate ammoniacal nitrogen.

The TiO2 nanocomposite efficiency was determined under optimized conditions with activated carbon to remove ammoniacal nitrogen (NH3-N) from the leachate sample. In this work, the facile impregnation and pyrolysis synthesis method was employed to prepare the nanocomposite, and their formation was confirmed using the FESEM, FTIR, XRD, and Raman studies. In contrast, Raman phonon mode intensity ratio ID/IG increases from 2.094 to 2.311, indicating the increase of electronic conductivity and defects with the loading of TiO2 nanoparticles. The experimental optimal conditions for achieving maximum NH3-N removal of 75.8% were found to be a pH of 7, an adsorbent mass of 1.75mg/L, and a temperature of 30°C, with a corresponding time of 160min. The experimental data were effectively fitted with several isotherms (Freundlich, Hill, Khan, Redlich-Peterson, Toth, and Koble-Corrigan). The notably elevated R2 value of 0.99 and a lower ARE % of 14.61 strongly support the assertion that the pseudo-second-order model compromises a superior depiction of the NH3-N reduction process. Furthermore, an effective central composite design (CCD) of response surface methodology (RSM) was employed, and the lower RMSE value, precisely 0.45, demonstrated minimal disparity between the experimentally determined NH3-N removal percentages and those predicted by the model. The subsequent utilization of the desirability function allowed us to attain actual variable experimental conditions.

Optimizing reverse osmosis desalination from brackish waters: Predictive approach employing response surface methodology and artificial neural network models

A mathematical model frame has been developed to optimize the performance of reverse osmosis (RO) desalination in brackish waters with medium to high salt concentrations using response surface methodology (RSM) and artificial neural network (ANN), specifically catered towards efficiently operating RO desalination systems. The RSM model aims at predicting RO performance with second-order polynomials based on 15 experimental datasets. Inputs for RSM model include feed TDS concentration, feed water flow rate, and concentration-to-desalination ratio, while the outputs consider rejection, membrane flux, performance index, and specific energy consumption. The Genetic Algorithm optimized back-propagation Neural Network was employed to update network weights and biases, leading to an optimal ANN network structure of 3–10-4. A ratio of 70 % training, 15 % validation, and 15 % test data was chosen to establish an ANN model that predicts the performance of RO desalination. The ANN model demonstrated significantly higher prediction accuracy than the RSM model, with impressive correlation coefficients of 0.9936 for the performance index and 0.9932 for SEC prediction, and low RMSE of 0.85 for rejection. To maximize the performance index and minimize specific energy consumption, a two-step optimization method was further set up by applying the RSM model to initially determine optimal process conditions followed by the ANN model to enhance the accuracy of performance forecasts. Optimal process conditions were proposed for specific feed TDS scenarios, which involved setting a feed TDS concentration limit to meet drinking water standards.

Train-induced vibration response reconstruction for bridge damage detection with a deep learning methodology

Sensor malfunctions in bridge structural health monitoring system (BSHMS) could cause the missing of measured data, reducing the accuracy of damage detection. It is of great significance to reconstruct the data of faulty sensors with measured data of well-functioning sensors for bridge structural state assessment. In this paper, a train-induced vibration response reconstruction approach for bridge damage detection is proposed. An enhanced deep densely connected neural network (ED-DCNN) introducing a multi-head self-attention mechanism and a skip connection is designed to reconstruct the missing bridge responses, aiming to improve the vibration correlation between the faulty sensors and good sensors and benefit the learning of temporal and spatial features of responses. Then to further validate the accuracy and reliability of the ED-DCNN, an alternate down-sampling residual network (AD-ResNet) is built to identify bridge damage with the complete responses, including the reconstructed ones and the measured, which extracts the structural damage features at different scales utilizing different types of residual blocks in an alternating manner. The efficiency and robustness of the two networks are comprehensively studied using the collected acceleration data from a heavy-haul railway bridge, considering different noise levels. The results demonstrate that under various conditions, the reconstructed responses match the real responses well in time domain, with a low RMSE below 0.4% and a high correlation coefficient of 0.9744, which indicates that the incorporation of a multi-head self-attention module effectively improves the construction of correlations between responses. Additionally, the natural frequencies of bridge are accurately identified from the reconstructed responses. In terms of bridge damage detection, taking both the measured and reconstructed responses as inputs, the identification accuracy obviously improves by 33.57% compared to cases without the reconstructed responses, further emphasizing an excellent reconstruction capability of the ED-DCNN.

Utilize the Prediction Results from the Neural Network Gate Recurrent Unit (GRU) Model to Optimize Reactive Power Usage in High-Rise Buildings

The growing urbanization and the construction sector, efficient use of electric energy becomes important, especially the use of reactive power. If excessive use causes decreased efficiency and increased operational costs. Decreased efficiency contributes to increasing exhaust gas volumes and greenhouse emissions. Efficient energy can achieved if planning and predictions are correct. This research applies the GRU neural network method with grid search initialization as a novelty predictive model for energy-use high-rise buildings in form fast training without multiple iterations because optimal hyperparameters are obtained. Experimental show the MAE and RMSE performance metrics of the GRU better than LSTM in predicting energy consumption data peak loads, off-peak loads and reactive power. The accuracy of GRU predictions can optimize the use of energy to contribute to saving the environment from exhaust emissions and the greenhouse effect in urban systems. Experimental results demonstrate the superiority of GRU over LSTM, proof of the much lower MAE and RMSE values. This metric shows the accuracy of GRU in generalizing data both during peak and off-peak hours, as well as in reactive power usage. By Utilizing GRU's capabilities, building management can manage reactive power usage effectively, allocate reactive power resources appropriately, and mitigate peak load times and the power factor within the threshold, thus avoiding additional costs and electrical system efficiency and contributing to reducing the carbon footprint and gas emissions greenhouse. Research on GRU is widely open in the high-rise building sector, including its integration with sensors to automatically control energy use.