Mean Absolute Error Research Articles

Prediction of vaults in eyes with vertical implantable collamer lens implantation.

To design formulas for predicting postoperative vaults in vertical Implantable Collamer Lens (ICL) implantation and to achieve more precise predictions using machine learning models. Retrospective observational study. XXXX (anonymized for review). We retrospectively reviewed the medical records of 720 eyes in 408 patients who underwent vertical ICL implantation. The data included age, sex, refractions, anterior segment biometric data, and surgical records. We designed three formulas (named V1-V3 formulas) using multiple linear regression analysis, and tested four machine learning models. Predicted vaults by V1-V3 formulas were 444.17 ± 93.83 μm, 444.08 ± 98.64 μm, and 444.27 ± 108.81 μm, with mean absolute error of 127.97 ± 107.92, 126.41 ± 105.86, and 122.90 ± 103.00 μm. There were no significant differences in error among the V1-V3 formulas, despite the fact that the V1 and V2 formulas referred to limited parameters (three and four, respectively), and the V3 formula referred to all 12 parameters. Two of four machine learning models, XGBoost and Random Forest Regressor, showed a better performance in predicted vaults: 444.52 ± 120.51 and 446.00 ± 102.55 μm and mean absolute error: 118.31 ± 100.55 and 118.63 ± 99.34 μm, respectively. This is the first study to design V1-V3 formulas for vertical ICL implantation. The V1 and V2 formulas exhibited good performance despite the limited parameters. In addition, two of the four machine learning models predicted more precise results.

Near Real‐Time Earthquake Monitoring in Texas Using the Highly Precise Deep Learning Phase Picker

AbstractArtificial intelligence (AI) seismology has witnessed enormous success in a variety of fields, especially in earthquake detection and P and S‐wave arrival picking. It has become widely accepted that DL techniques greatly help routine seismic monitoring by enabling more accurate picking than traditional pickers like STA/LTA. However, a completely automatic AI‐driven earthquake monitoring framework has not been reported due to the concerns of potential false positives using DL pickers. Here, we propose a novel AI‐facilitated near real‐time monitoring framework using a recently developed deep learning (DL) picker (EQCCT) that has been deployed in the Texas seismological network (TexNet). For the West Texas area, TexNet's seismic monitoring relies on the EQCCT picker to report earthquake events. For earthquakes with a magnitude above two, the picks are further validated by analysts to output the final TexNet catalog. Due to the fast‐increasing seismicity caused by continuing oil&gas production in West Texas, this AI‐facilitated framework significantly relieves the workload of TexNet analysts. We show the mean absolute error (MAE) of automatic magnitude estimation for the magnitude‐above‐two earthquakes is smaller than 0.15 in West Texas and MAEs of hypocenter locations within 2.6 km in both distance and depth estimates. This research provides more evidence that DL pickers can play a fundamental role in daily earthquake monitoring.

Enhancing protein aggregation prediction: a unified analysis leveraging graph convolutional networks and active learning.

Protein aggregation (PA) is a critical phenomenon associated with Alzheimer's and Parkinson's disease. Recent studies have suggested that factors like aggregation-prone regions (APRs) and β-strand interactions are crucial in understanding such behavior. While experimental methods have provided valuable insights, there has been a shift towards computational strategies, particularly machine learning, for their efficacy and speed. The challenge, however, lies in effectively incorporating structural information into these models. This study constructs a Graph Convolutional Network (GCN) to predict PA scores with the expanded and refined Protein Data Bank (PDB) and AlphaFold2.0 dataset. We employed AGGRESCAN3D 2.0 to calculate PA propensity and to enhance the dataset, we systematically separated multi polypeptide chains within PDB data into single polypeptide chains, removing redundancy. This effort resulted in a dataset comprising 302 032 unique PDB entries. Subsequently, we compared sequence similarity and obtained 22 774 Homo sapiens data from AlphaFold2.0. Using this expanded and refined dataset, the trained GCN model for PA prediction achieves a remarkable coefficient of determination (R 2) score of 0.9849 and a low mean absolute error (MAE) of 0.0381. Furthermore, the efficacy of the active learning process was demonstrated through its rapid identification of proteins with high PA propensity. Consequently, the active learning approach achieved an MAE of 0.0291 in expected improvement, surpassing other methods. It identified 99% of the target proteins by exploring merely 29% of the entire search space. This improved GCN model demonstrates promise in selecting proteins susceptible to PA, advancing protein science. This work contributes to the development of efficient computational tools for PA prediction, with potential applications in disease diagnosis and therapy.

Multispectral two-dimensional temperature field reconstruction using particle swarm optimization and the Broyden–Fletcher–Goldfarb–Shanno algorithm with multiple extreme value optimization

The flame temperature is a crucial parameter in combustion, indicating heat generation and transfer. However, determining the correct temperature becomes challenging when flame emissivity is unknown. This article presents a multispectral 2D temperature field reconstruction method using particle swarm optimization and the Broyden–Fletcher–Goldfarb–Shanno algorithm, combined with multivariate extreme-value optimization. This method establishes an objective function based on the correlation between the true temperature and spectral data. The objective function was minimized by adjusting the emissivity, enabling the reconstruction of 2D temperature and emissivity images without assuming an emissivity model. Calibration with a multispectral camera yielded the spectral response coefficients, and three-time spline interpolation was used to verify the calibration data. The reconstructed 2D temperature field showed a mean absolute error (MAE) of 4.61 and structural similarity (SSIM) of 0.995. The reconstructed emissivity image had an MAE range of 0.04 to 0.053 and an SSIM range of 0.897 to 0.915. The system, tested on a butane flame, showed a temperature range of 1001 K to 1356 K, with an average temperature of 1194 K and emissivity values ranging from 0.3166 to 0.8621. The results align with the expected combustion process and radiation characteristics distribution of the butane flame.

Exploiting the synergy of SARIMA and XGBoost for spatiotemporal earthquake time series forecasting

AbstractEarthquakes are vibrations that occur on the surface of earth, generating fires, ground shaking, tsunamis, landslides and cracks. These incidents can cause severe damage and loss of life. Accurate earthquake forecasts are critical for anticipating and mitigating these hazards, which can avoid damage to buildings and infrastructure and save lives. To address the challenges given by earthquakes probabilistic nature, this paper presents a hybrid SARIMA–XGBoost approach to earthquake magnitude prediction. The suggested technique consists of a two‐step process: an exploration phase that uses exploratory data analysis, which includes descriptive statistics and data visualisation, and a prediction phase that focusses on forecasting future earthquakes. Using a large significant earthquake dataset spanning 1965–2023, the study intends to gain insights and lessons for more effective earthquake prediction methods. Further, in a comparison analysis, the results of SARIMA‐XGBoost model are compared to those of traditional ARIMA and SARIMA models. The results highlight the superior performance of the hybrid SARIMA–XGBoost model, showcasing a mean absolute error (MAE) of 0.038, a mean squared error (MSE) of 0.0040, and a root mean squared error (RMSE) of 0.068. These metrics collectively underscore the model's enhanced accuracy in forecasting earthquake magnitudes. The notably low values of MAE, MSE and RMSE indicate that our hybrid approach significantly improves prediction accuracy compared to alternative models. By integrating SARIMA's time series (TS) analysis with XGBoost's machine learning (ML) capabilities, the hybrid model reduces forecasting errors more effectively, demonstrating its clear advantage in precision.

Hourly PM2.5 concentration prediction for dry bulk port clusters considering spatiotemporal correlation: A novel deep learning blending ensemble model

Accurate prediction of PM2.5 concentrations in ports is crucial for authorities to combat ambient air pollution effectively and protect the health of port staff. However, in port clusters formed by multiple neighboring ports, we encountered several challenges owing to the impact of unique meteorological conditions, potential correlation between PM2.5 levels in neighboring ports, and coupling influence of background pollutants in city zones. Therefore, considering the spatiotemporal correlation among the factors influencing PM2.5 concentration variations within the harbor cluster, we developed a novel blending ensemble deep learning model. The proposed model combined the strengths of four deep learning architectures: graph convolutional networks (GCN), long short-term memory networks (LSTM), residual neural networks (ResNet), and convolutional neural networks (CNN). GCN, LSTM, and ResNet served as the base models aimed at capturing the spatial correlation of PM2.5 concentrations in neighboring ports, the potential long-term dependence of meteorological factors and PM2.5 concentrations, and the effects of urban ambient air pollutants, respectively. Following the blending ensemble technique, the prediction outcomes of three base models were used as the input data for the meta-model CNN, which employs the blending ensemble technique to produce the final prediction results. Based on actual data obtained from 18 ports in Nanjing, the proposed model was compared and analyzed for its prediction performance against six state-of-the-art models. The findings revealed that the proposed model provided more accurate predictions. It reduced mean absolute error (MAE) by 10.59 %–20.00 %, reduced root mean square error (RMSE) by 13.22 %–17.11 %, improved coefficient of determination (R2) by 10 %–35.38 %, and improved accuracy (ACC) by 3.48 %–7.08 %. Additionally, the contribution of each component to the prediction performance of the proposed model was measured using a systematic ablation study. The results demonstrated that the GCN model exerted the most substantial influence on the prediction performance of the GCN-LSTM-ResNet model, followed by the LSTM model. The influence of urban background pollutants can significantly enhance the generalizability of the complete model. Moreover, a comparison with three blended ensemble models incorporating any two base models demonstrated that the GCN-LSTM-ResNet model exhibited superior prediction performance and was particularly excellent in predicting the occurrence of high-concentration events. Specifically, the GCN-LSTM-ResNet model improved MAE and RMSE by at least 12.3% and 9.2%, respectively, but reduced R2 and ACC by 26.1% and 6.8%, respectively. The proposed model provided reliable PM2.5 concentration prediction outcomes and decision support for air quality management strategies in dry bulk port clusters.

MACHINE LEARNING APPROACHES FOR DEMAND FORECASTING: THE IMPACT OF CUSTOMER SATISFACTION ON PREDICTION ACCURACY

This study investigates the effectiveness of various machine learning models in predicting product demand based on customer satisfaction data. Four models—Linear Regression, Random Forest, Gradient Boosting, and Support Vector Machine (SVM)—were evaluated using performance metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R² score. The results indicate that Gradient Boosting achieved the highest accuracy, with an MAE of 2.56, MSE of 12.75, RMSE of 3.57, and R² score of 0.82, effectively capturing the complex, non-linear relationships inherent in customer satisfaction factors. Random Forest also demonstrated strong performance, while Linear Regression and SVM showed limitations in handling intricate datasets. These findings underscore the importance of utilizing advanced machine learning techniques for accurate demand forecasting, highlighting the critical role of customer satisfaction data in enhancing predictive capabilities. The insights gained from this research can guide organizations in optimizing inventory management and improving customer satisfaction in a rapidly evolving market.

NASPrecision: Neural Architecture Search-Driven Multi-Stage Learning for surface roughness prediction in ultra-precision machining

Accurate surface roughness prediction is critical for ensuring high product quality, especially in sectors such as manufacturing, aerospace, and medical devices, where the smallest imperfections can compromise performance or safety. However, this is very challenging due to complex, non-linear interactions among variables, which is further exacerbated when working with limited and imbalanced datasets. Existing methods leveraging traditional machine learning algorithms require extensive domain knowledge for feature engineering and substantial human intervention for model selection. To address these issues, we propose a Neural Architecture Search (NAS)-Driven Multi-Stage Learning Framework, named NASPrecision. This innovative approach autonomously identifies the most suitable features and models for various surface roughness prediction tasks and significantly enhances the performance by multi-stage learning. Our framework operates in three stages: (1) architecture search stage, employing NAS to automatically identify the most effective model architecture; (2) initial training stage, where we train the neural network for initial predictions; (3) refinement stage, where a subsequent model is appended to refine and capture subtle variations overlooked by the initial training stage. In light of limited and imbalanced datasets, we adopt a generative data augmentation technique to balance and generate new data by learning the underlying data distribution. We perform extensive experiments on three distinct real-world datasets, each associated with a different machining technique, and compare with various machine learning algorithms. The experimental results underscore the superiority of our framework, which achieves an average improvement of 25.7%, 22.7%, and 39.1% in terms of Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Standard Deviation of Residuals (STDR), respectively. This significant performance enhancement not only confirms the robustness of our framework but also establishes it as a generic solution for accurate surface roughness prediction. The success of this approach can lead to improved production efficiency and product quality in critical industries while also reducing the need for extensive domain knowledge and human intervention.

Co-Kriging model-based multi-fidelity regression for refining milling stability predictions of variable tool overhang length using limited experimental data

Determining chatter-free machining parameters is critical in process planning since chatter vibrations significantly affect machining quality and production efficiency. Stability lobe diagram is essential in selecting chatter-free machining parameters, but its predictions confront challenges in both theoretical accuracy and experimental efficiency. To address this, the Co-Kriging modelling is introduced to predict the tool overhang length-dependent stability limits with limited experiments. First, tool tip dynamics and cutting force coefficients of a source overhang length are roughly identified to obtain sufficient low-fidelity (LF) theoretical stability limits. The entropy-based sampling and affine transformation are used to sequentially obtain high-fidelity (HF) experimental stability limits and update LF stability limits. HF and updated LF datasets are combined to train a multi-fidelity (MF) Co-Kriging model. For a target overhang length, MF stability limits of the source overhang length serve as LF data, and a minimum mean absolute percentage error (MAPE)-based sampling guides the acquisition of HF stability limits. Combining HF data and LF data processed by affine transformation to train a target Co-Kriging model. Case studies reveal that the proposed method exhibits lower MAPE values and significantly outperforms other comparison methods in predicting experimental stability limits, particularly when confronted with limited experimental data.

Performance evaluation of machine learning algorithms in predicting machining responses of superalloys

This study explores the application of machine learning algorithms—gene expression programming (GEP), adaptive neuro-fuzzy inference system (ANFIS), and artificial neural networks (ANN)—to predict machining responses during the milling of Inconel 690, a superalloy known for its exceptional mechanical properties and oxidation resistance. Machining Inconel 690 presents significant challenges due to its toughness and work-hardening tendencies, which can lead to rapid tool wear and poor surface finish. Traditional optimization methods often rely on empirical models and trial-and-error approaches, which are time-consuming and costly. In contrast, machine learning techniques can effectively model complex, nonlinear relationships between machining parameters and performance outcomes, such as surface roughness, cutting force, and cutting temperature. This study employs statistical metrics, including Root mean square error (RMSE), coefficient of determination (R2), and mean absolute percentage error (MAPE), to determine the predictive performance of the models. The results show that the GEP model achieved an R2 ranging from 0.944 572 to 0.992 999, with an RMSE between 0.015 527% and 0.694 523% and a MAPE ranging from 1.452 397% to 4.947 892%. ANFIS and ANN also demonstrated strong predictive capabilities, although GEP outperformed them. The importance of this study lies in its demonstration of advanced AI techniques as effective tools for optimizing machining processes, ultimately contributing to improved efficiency and quality in manufacturing superalloys.

Optimization of temperature prediction algorithms and simulation of future neighborhood-scale thermal environments in Chongqing

With climate change and urbanization, predicting the outdoor thermal environment of residential areas has become increasingly crucial, particularly during extreme weather conditions. Existing studies lack a comprehensive approach to optimizing temperature prediction algorithms for Chongqing and simulating extreme thermal environments at the neighborhood scale for future decades. This study employed various algorithms, including Levenberg-Marquardt optimization, Monte Carlo simulation, ARIMA modeling, and SARIMA prediction, to simulate and forecast temperature data for the central urban area of Chongqing from 2014 to 2023. By assessing metrics such as root mean square error (RMSE), R-squared (R2), and mean absolute percentage error (MAPE), the most effective prediction algorithm was identified. Results indicate that the Levenberg-Marquardt optimization algorithm, known for its nonlinear curve fitting capabilities, demonstrated superior performance in both the test and training sets, achieving an RMSE of 0.82 °C, MAPE of 1.81 %, and R2 of 0.75. This algorithm was subsequently used to forecast the outdoor temperature trend in Chongqing from 2024 to 2050, while also simulating the outdoor wind field, temperature distribution, building surface temperatures, and wind speeds in a residential district at neighborhood scale for 2030, 2040, and 2050 at a building density of 40 %. Findings reveal that peak pedestrian-level temperatures could reach 45.62 °C, and peak roof surface temperatures could reach 93.93 °C under extreme conditions. Furthermore, the study proposes practical recommendations for building layouts and cooling strategies. These findings are expected to improve residential planning in Chongqing, enhance residents' quality of life, and provide insights for other regions facing future temperature changes.

Efficiency of the decision support system for determining the severity of scoliotic spinal deformity by the analysis of radiographs

BACKGROUND: In 2020, a decision support system was developed at expense of grant from Innovation Promotion Fund and integrated into medical base of prosthetic and orthopedic center “Sсoliologic.ru.” It is the first computer program for determining severity of scoliotic spinal deformity in analysis of radiographs. AIM: To evaluate performance of a computer program for determining Cobb angle by comparing obtained automated data with manual measurement data by various specialists. MATERIALS AND METHODS: From medical base of prosthetic and orthopedic center “Sсoliologic.ru,” 411 digital radiographs of spine of children and adolescents were selected, which were drawn by a radiologist (BP-etalon), an orthopedic traumatologist with 5 years of experience and experience in vertebrology (OO), and an orthopedic traumatologist with less than 1 year of experience and no experience in vertebrology (OB) and computer program (KP). The number and proportion of exact matches and mean absolute percentage error (MAPE) of results of measuring the Cobb angle of reference data were compared with indicators obtained by OO, OB, and KP in, for various types of scoliosis according to the classification of Rigо, as well as in determining the main arc. Bland–Altman graphs were used. The mean absolute deviation (MAD) and MAPE for the main arc with magnitude ranging from 20° to 50° were calculated. RESULTS: The exact matches of KP with standard were 21%. Hence, every fifth measurement of the Cobb angle on X-ray, calculated automatically, was identical to standard. The highest proportion of matches with standard was noted in OO (33%), and the lowest in OB (16%). The highest accuracy of KP was found at types E1 and E2, and the arc of 3 was 30% and 24%, respectively. The proportion of KP matches with standard increased to 61%, with an error of 3°, and to 75%, with an error of 5°; with an error of 7°, the proportion of matches reached 84%. Moreover, the proportion of coincidences of a non-experienced researcher increased from 34% to 58%. When determining magnitude of the main arc of scoliosis, OO increased his/her accuracy by almost 2,6 times, KP by 2,1 times, and OB by 1,5 times. The MAD of KP for all major arcs was 3.8°. Good reliability of the obtained KP indicators compared to the reference (ICC = 0.9) was noted. CONCLUSIONS: The use of a computer program may be recommended for automated determination of Cobb angle, because current algorithm of computer program has been found to be accurate compared to reference measurement. Its accuracy was significantly higher than that of novice orthopedic traumatologists with no experience in vertebrology.

Comparison of the Accuracy Between the Z CALC2 Calculator and Barrett Toric Calculator in Toric IOL Calculation.

To compare the accuracy of the Z CALC2 calculator and Barrett toric calculator in toric intraocular lens (IOL) calculation. Eighty-five eyes of 85 patients who underwent uneventful cataract surgery with toric IOL implantation were included. The accuracy was compared between the Z CALC2 calculator and Barrett toric calculator under two calculation modes: using simulated keratometry (SimK) from the IOLMaster 700 (Carl Zeiss Meditec AG) for posterior corneal astigmatism (PCA) prediction and employing total corneal astigmatism (total corneal refractive power [TCRP] or measured PCA) obtained from the Pentacam (Oculus Optikgeräte GmbH). The centroid of prediction errors, percentage of eyes with prediction errors within ±0.50 diopter (D), mean prediction error, and mean absolute prediction error were calculated. Subgroup analysis was conducted based on the orientation and magnitude of anterior corneal astigmatism and axial length. When using SimK, the two calculators with predicted PCA showed comparable accuracy. When employing total corneal astigmatism, the Barrett toric calculator with measured PCA showed a lower centroid error (0.15 vs 0.38 D), a higher percentage of eyes with prediction errors within ±0.50 D (47.1% vs 32.9%, P = .018), and a lower mean prediction error (0.57 vs 0.71 D, P = .033) compared to the Z CALC2 calculator with TCRP in the 4-mm zone. In subgroup analysis, when employing total corneal astigmatism, the Barrett toric calculator with measured PCA exhibited superior accuracy, especially in the with-the-rule and anterior corneal astigmatism of 2.00 D or less subgroups. When using SimK, the Z CALC2 calculator and Barrett toric calculator yield comparable accuracy. The Barrett toric calculator with measured PCA may be more recommended when employing total corneal astigmatism. [J Refract Surg. 2024;40(10):e681-e691.].

Evaluation of Trend Models Performance and Forecasting Onion Production: A Comparative Study

Onions, a significant spice crop in Bangladesh, frequently experience price surges due to an imbalance between demand and supply, compelling the government to import onions. The volatility of the onion market in Bangladesh and the measures needed to stabilize the situation require intensive policy attention. Therefore, this study was carried out to forecast the onion production over time and to evaluate the efficacy of various trend models. The secondary data was collected from the Food and Agriculture Organization's Statistical Database (FAOSTAT) from 1972 to 2022. The autoregressive integrated moving average (ARIMA) model was used to predict the onion production over time. Additionally, metrics such as modified and the coefficient of determination were used to evaluate the effectiveness of eight trend models comprehensively. The findings indicate that the cubic model is superior to others since it has larger and adjusted values. The models' accuracy is also determined utilizing mean absolute percentage error (MAPE) and mean absolute deviation (MAD) metrics. The cubic trend model exhibits lower MAPE and MAD values of 29.43% and 80638.67, respectively. Therefore, it is concluded that the ARIMA (2, 2, 2) model is the best model for forecasting the annual production of onion in Bangladesh. A five-year trend analysis spanning from 2023-2027 indicates an upward trend. Such a result offers a critical insight for stakeholders and policymakers in formulating sustainable onion production strategies. J Bangladesh Agril Univ 22(3): 386-395, 2024

Modeling the bond–slip behavior of the interface between a stiffened core and cemented soil based on machine learning approaches

The bond–slip behavior of stiffened deep cement mixing (SDCM) piles—which is crucial for their bearing capacity—evolves continuously with curing age. In the study reported here, 20 element tests were conducted on the interface between cemented soil and a stiffened core, analyzing the bond–slip behavior affected by curing temperature and age, and then ensemble learning methods (XGBoost, random forest) were used to establish models for the evolution of the bond–slip behavior considering thermal effects. The constructed models can predict the peak shear strength (τmax), the residual shear strength (τres), and the interfacial shear modulus (G). The test results show that the shear strength of the stiffened-core–cemented-soil interface grows with the increasing curing temperature and age, with faster growth at 0–14 days compared to 60–90 days. To lessen the reliance on ineffective brute-force searching, Bayesian optimization with a tree-structured Parzen estimator is used to select the hyperparameters of the established models. The results demonstrate the superior performance of the chosen approach, with R2 > 0.93 for the training set and R2 > 0.81 for the test set. The results of the XGBoost model are best for τmax, with a mean absolute percentage error of less than 5 %, thereby enabling accurate predictions of the mechanical parameters of the stiffened-core–cemented-soil. This research enhances the understanding of the mechanical properties of SDCM piles and provides valuable guidance for projects involving such piles.

Modeling of Energy Usage Intensity Based on West Java Region Conditions Using Dynamic Systems Approach

Abstract West Java is a region in Indonesia experiencing significant population growth and economic activity, leading to a substantial increase in energy demand and presenting challenges for sustainable energy resource management. Energy is fundamental to economic and social activities, and efficient, sustainable management is essential for balancing economic growth with environmental preservation. Modeling energy usage intensity is crucial for understanding the dynamics of energy consumption and its influencing factors. This study aims to develop a model that accurately represents energy consumption patterns in West Java using a dynamic systems approach. The study utilizes Causal Loop Diagrams (CLD) and Stock Flow Diagrams (SFD) to systematically map and model the intricate dynamics of the energy system, providing a comprehensive understanding of the interactions and influences among various factors. The model was validated by comparing its outputs with historical data and calculating a Mean Absolute Percentage Error (MAPE). This enhances confidence in the analyses and recommendations derived from the model, making it a valuable tool for understanding and influencing energy usage patterns in West Java. In conclusion, this study not only provides deep insights into energy consumption in West Java but also offers practical approaches for improved energy management, supporting sustainable development and environmental protection in the region.

Analysis of carbon emission characteristics and establishment of prediction models for residential and office buildings in China

Intensifying environmental issues make carbon reduction crucial, especially in the construction industry. Embodied carbon emissions (ECE) in buildings characteristically involve concentrated, intensive emissions over a short period. Implementing energy-saving and carbon-reducing technologies has raised ECE rates. Therefore, analyzing carbon emission (CE) characteristics during the production and construction phases is necessary. Currently, essential data on ECE is lacking, the calculation methods are complex, and ECE's characteristics and influential factors in residential and office buildings remain unclear. Moreover, there is a lack of prediction models for ECE in the construction phase that apply to current construction methods and CE factors. The research on prediction models for ECE has primarily focused on the production phase but has paid little attention to the contribution of non-structural materials to embodied carbon (EC). In this study, reinforced concrete residential and office buildings in hot summer and cold winter regions (located in the southeast part of mainland China, with a subtropical monsoon climate) were considered typical types, and the CE characteristics of two main phases, the production and construction phases, were analyzed. Based on critical features, such as the number of floors and the basement, prediction models for ECE in residential and office buildings were established at the design stage. The models were validated with mean absolute percentage error (MAPE) values below 4%, and coefficient of variation (root mean square error) (CV [RMSE]) values less than 0.02. The prediction models enabled a rapid estimation of ECE, encouraging designers to consider EC in the early design stages.

Comparison of feature learning methods for non-invasive interstitial glucose prediction using wearable sensors in healthy cohorts: a pilot study

BackgroundAlterations in glucose metabolism, especially the postprandial glucose response (PPGR), are crucial contributors to metabolic dysfunction, which underlies the pathogenesis of metabolic syndrome (MetSyn). Personalized low-glycemic diets (PLGD) have shown promise in reducing postprandial glucose spikes. However, current methods such as invasive continuous glucose monitoring (CGM) or multi-omics data integration to assess PPGR come with limitations, including cost and invasiveness, hindering widespread adoption in primary disease prevention. Our aim is to assess machine-learning algorithms for predicting individual PPGR using non-invasive wearable data, thereby circumventing the limitations associated with existing approaches. By identifying the most accurate model, we seek to provide a more accessible and efficient method for managing glucose metabolism. MethodsThis data-driven analysis utilized the experimental dataset from the SENSE (”Systemische Ernährungsmedizin”) study. Healthy participants used an Empatica E4 wristband and Abbott Freestyle Libre 3 CGM for ten days. Blood volume pulse (BVP), electrodermal activity (EDA), heart rate (HR), skin temperature (TEMP), and the corresponding CGM values were measured. Subsequently, four data-driven deep learning (DL) model-convolutional neural network (CNN), lightweight transformer (LTF), long short-term memory with attention (LSTM-A), and Bi-directional LSTM (BiLSTM)-were implemented and compared to determine the potential of DL in predicting interstitial glucose levels without involving food and activity logs. ResultsThe proposed BiLSTM achieved the best interstitial glucose prediction performance, with an average root mean squared error (RMSE) of 13.42 mg/dL, an average mean absolute percentage error (MAPE) of 0.12, and only 3.01% values falling within area D in Clarke error grid analysis (CEGA), incorporating the leave-one-out cross-validation (LOOCV) strategy for a five-minute prediction horizon. ConclusionThe findings of this study may demonstrate the feasibility of transferring knowledge gained from invasive glucose monitoring devices to non-invasive approaches. Furthermore, it emphasizes the promising prospects of combining deep learning with wearable technologies to predict glucose levels in healthy individuals.

Signals denoising of leakage pressure in water supply pipelines using an improved wavelet filter algorithm

Abstract Accurate identification of leakage pressure signal is crucial for leakage detection and location of water supply pipelines. However, there is a lot of noise signals in the negative pressure waves generated during leakage accidents, making it difficult to identify leakage signals, and thus seriously affecting the accuracy of leakage detection. Therefore, in this study, we carried out leakage test of water transmission pipeline on our self-built test platform for transient flow with long-distance water transmission pipeline (pipeline length is 160 m, and diameter is 100 mm), and obtained the transient leakage pressure signals under various flow rates (15–55 m3/h). An improved wavelet filtering algorithm was proposed to filter the leakage pressure signal by optimizing the calculation of decomposition layers and the threshold processing strategy, and then compared with the traditional wavelet filtering method. The results show that the improved algorithm can denoise the leakage signals effectively, and the signal-to-noise ratio (SNR), mean square error (MSE) and mean absolute percentage error (MAPE) are all superior to those of the traditional wavelet algorithm. The results can provide support for leakage detection and location of water supply pipeline systems.

A Novel Characterization Methodology for Vapor-Injected Compressors: A Comparative Analysis with Existing Black-Box Models

In regions characterized by high temperature gradients, vapor compression systems often necessitate operation at very high-pressure ratios resulting in a reduction in system capacity. Economized vapor injection compressors are used to avoid these issues, yet a precise predictive map for various compressor technologies with minimal data and relatively better performance remains unclear. This paper establishes a black-box compressor model to accurately predict compressor power, injection mass ratio, and evaporator mass flow rate in compressors with a single vapor injection port. This model is compared against three legacy models from literature and the ANN model, for reference. All five models are evaluated based on their ability to predict the aforementioned metrics. The proposed black-box model can predict the relevant metrics all within 5% Mean Absolute Percentage Error (MAPE). Additionally, a refrigerant sensitivity analysis is performed with the black-box models. The model is trained using data from R410A and then used the coefficients to predict the performance of the same compressor when using R454B, and vice versa. It can estimate the evaporator mass flow rate with an accuracy within 3%, the power within 2%, and the injection mass ratio with MAPE less than 3%.