Absolute Percentage Error Research Articles

An optimal weight heterogeneous integrated carbon price prediction model based on temporal information extraction and specific comprehensive feature selection

Accurate prediction of carbon price provides a strong guarantee for the prosperity of carbon market and the sustainable development of society. This paper proposes an optimal weight heterogeneous integrated carbon price prediction model based on temporal information extraction and specific comprehensive feature selection. Specifically, improved variational mode decomposition is first employed to segment the original carbon price data into distinct sequences, each capturing unique time scale characteristics. Secondly, by comprehensively considering 12 feature screening methods, specifically obtain the optimal impact factors of each subsequence, achieving the purpose of reducing noise interference and improving input quality. Finally, heterogeneous modeling and optimal weight integration, coupled with the northern goshawk optimization, fully leverage the distinct strengths of each model and achieve advantageous complementarity, thereby bolstering the prediction's robustness and precision. The research results demonstrate that, in comparison to the baseline model, the proposed model has achieved remarkable accuracy enhancements in two markets. Taking the Shanghai market as a case, it achieved mean squared error, mean absolute error and mean absolute percentage error values of 1.5199, 0.846, and 0.0145, respectively, with the highest accuracy improvements reaching 43.5555%, 48.7471%, and 49.6552%, respectively. This underscores the outstanding carbon price prediction capability of the model.

A comparative analysis of variants of machine learning and time series models in predicting women’s participation in the labor force

Labor force participation of Egyptian women has been a chronic economic problem in Egypt. Despite the improvement in the human capital front, whether on the education or health indicators, female labor force participation remains persistently low. This study proposes a hybrid machine-learning model that integrates principal component analysis (PCA) for feature extraction with various machine learning and time-series models to predict women’s employment in times of crisis. Various machine learning (ML) algorithms, such as support vector machine (SVM), neural network, K-nearest neighbor (KNN), linear regression, random forest, and AdaBoost, in addition to popular time series algorithms, including autoregressive integrated moving average (ARIMA) and vector autoregressive (VAR) models, have been applied to an actual dataset from the public sector. The manpower dataset considered gender from different regions, ages, and educational levels. The dataset was then trained, tested, and evaluated. For performance validation, forecasting accuracy metrics were constructed using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), R-squared (R2), and cross-validated root mean squared error (CVRMSE). Another Dickey-Fuller test was performed to evaluate and compare the accuracy of the applied models, and the results showed that AdaBoost outperforms the other methods by an accuracy of 100%. Compared to alternative works, our findings demonstrate a comprehensive comparative analysis for predicting women’s participation in different regions during an economic crisis.

A Fuzzy Logic Approach to Enhance GPS Accuracy for Blood Cooler Box Tracking

An innovative technological development, the position tracking system uses latitude and longitude coordinates to determine the GPS's location. The covid-19 pandemic has caused the demand for cool box delivery for convalescent blood plasma to increase significantly. The obstacle in the field is the hospital's position and patient rooms far from the reach convalescent donors, so they require a cool box for delivery. The problem is tracking the cool box accurately and precisely so that it can be monitored by the hospital properly. For this reason, it is necessary to increase the accuracy of the GPS position in the cool box by using fuzzy logic algorithms The Ublox NEO-6M is one GPS module that can be utilized for navigation. This module uses UART connection using the NMEA 0183 protocol and has an accuracy level of around 2.5 meters to 10 meters. In this research, validation of the accuracy of the GPS coordinate position was carried out on a Blood Cool Box device which was designed using the fuzzy logic method. The Sugeno method fuzzy logic algorithm is used to validate the accuracy of GPS coordinate positions based on latitude and longitude obtained from the GPS sensor module. The test results show a Mean Absolute Percent Error (MAPE) value of 21.66% which can be concluded that the Sugeno fuzzy logic method algorithm has forecasting model capabilities that are suitable for use as a validation method for testing GPS position coordinates.

Analisis Peramalan Penjualan untuk Perencanaan Produksi pada Lavanda Brownies Karawang

This research was conducted at Lavanda Brownies Karawang which compared the moving average and exponential smoothing forecasting methods. This research aims to find out, calculate, analyze and explain how to use the moving average and exponential smoothing methods in sales forecasting for production planning at Lavanda Brownies Karawang as well as to find out, calculate, analyze and explain what forecasting method is most appropriate to use for Lavanda Brownies Karawang based on calculations of Mean Absolute Devitiation (MAD), Mean Square Error (MSE), and Mean Absolute Percent Error (MAPE). This research uses a quantitative descriptive method, to get a general picture of the company's condition, a literature review related to the research topic is carried out as well as field research through interviews and direct observation. Based on the research results, the exponential smoothing forecasting method based on alpha 0.9 is the best forecasting method for production planning. This method was chosen because it has the smallest MAD, MSE and MAPE accuracy values ​​when compared to other methods, namely with MAD of 489,909, MSE of 506.950 and a MAPE percentage of 14,14%, which percentage has the smallest value and is included in the category Good. A smaller MAPE accuracy value indicates more precise forecasting. Because in forecasting the smaller the accuracy value, the better the forecasting results so that the Lavanda Brownies business can plan optimal steamed brownie production activities in the next period.

Criterion validity and accuracy of actigraph and Xiaomi Smart Band to count steps after stroke

Purpose Finding valid and accurate methods to count steps is important after a stroke. To determine the criterion validity and accuracy of the Actigraph and Xiaomi Smart Band to count steps in individuals after stroke. To explore the influence of walking speed on the accuracy of these activity monitors. Method Individuals after stroke performed the 2-min Walk Test while wearing the ActiGraph and Xiaomi Smart Band. The 2-min Walk Test was recorded, and the observed step count was compared with the estimated step count of both activity monitors. Results Fifty individuals after stroke were included. The ActiGraph had a low correlation (rho 0.41) between observed and estimated step count and a high percentage absolute error (39%). The Xiaomi Smart Band had a high correlation (rho 0.83) and a moderate percentage absolute error (12%). At high walking speeds, the Xiaomi Smart Band had a low percentage absolute error (3%) and at slow walking speeds had 18% a moderate percentage absolute error. Conclusion The Xiaomi Smart Band has good criterion validity and moderate-to-high accuracy counting steps after stroke. It is a low-cost activity monitor that is a viable alternative to the more expensive activity monitors used in research. IMPLICATIONS FOR REHABILITATION The ActiGraph has low criterion validity and accuracy at counting steps after stroke. The Xiaomi Smart Band has good criterion validity and accuracy at counting steps after a stroke. The Xiaomi Smart Band is a low-cost activity monitor that is a viable alternative to the more expensive activity monitors used in research.

A 2D echocardiographic method for accurate right ventricular quantification using deep learning

Abstract Background/Introduction Transthoracic two-dimensional echocardiography (2DE) remains the backbone for non-invasive assessment of the right ventricle (RV) size and function. However, calculation of RV end-diastolic (RVEDV), end-systolic volume (RVESV) and ejection fraction (RVEF) cannot be performed using 2DE due to the complex RV shape (1), whereas currently used, respective 2DE indices lack diagnostic accuracy. Deep learning (DL) may be able to assist in developing new 2DE methods for RV quantification. Purpose To develop a novel DL-based 2DE method for quantitative evaluation of RV size and function without geometric assumptions. Methods 50 adult patients underwent 2DE and CMR within 30 days as part of routine cardiac care between 6/2020 – 9/2021 at a medical center. We excluded patients with prior cardiac surgery of the RV, tricuspid or pulmonic valve repair or replacement, complex congenital heart disease, more than small pericardial effusion, cardiac tamponade, atrial fibrillation at the time of either study, severe RV dysfunction or inadequate imaging quality. End-diastolic and end-systolic areas derived from planimetry of 8 2DE RV views, along with patient age and gender, were to used to train and test a DL algorithm, namely the Feature-Tokenizer and Transformer (Figure 1) in order to predict the corresponding, CMR-derived, RVEDV or RVESV, and subsequently calculate RVEF. We used 5-fold cross-validation for training and evaluation. We assessed the relative importance of each 2DE view using gain metric-powered explainability analysis and subsequently performed a sensitivity analysis to identify optimal combinations of views. Variability analysis was performed for a random subcohort of 10 patients. Results Median age was 51 (interquartile range 32-62) and 42% were women. Mean RVEDV, RVESV and RVEF) by CMR were 163±70ml, 82±42ml and 51±8% respectively. Six patients (12%) had RV dilatation and 9 (18%) had RV dysfunction when using published CMR criteria. Explainability analysis showed that the 3 most important views were parasternal long axis (PLAX) (relative feature importance [RFI] = 0.197), 4-chamber (RFI=0.145) and parasternal short axis at the base (PSAX-base) (RFI=0.112). The 3-view combination of PLAX, 4-chamber and PSAX-base achieved high accuracy when compared to CMR (R2=0.964, absolute percentage error [APE]=8.09±12.07% for RV volumes and APE=9.86±10.68% for RVEF). Good (intraclass correlation coefficient [ICC]>0.75) to excellent (ICC>0.90) intra- and interobserver variability was found for these 3 views. Conclusions We propose an innovative, clinically applicable DL-based 2DE method for quantification of RV size and function that requires manual RV planimetry of 3 views, namely 4-chamber, PLAX and PSAX-base (Figure 2). This method may revolutionize 2DE RV assessment. Further studies with largest number of patients and wider range of RV size and function are needed to validate this method.Deep learning architectureGraphical abstract

Convergent Validity of Garmin Vivofit Jr. 3 and Fitbit Ace 3 for Monitoring Daily Physical Activity of Children

ABSTRACT This study aimed to assess the agreement in physical activity (PA) estimates from Garmin Vivofit Jr. 3 (VFJ 3) and Fitbit Ace 3 (Ace 3) with a research-grade accelerometer (wGT3X-BT) in children under free-living conditions. Twenty-five children (Girls: 56%, Age: 10.1 ± 2.5 years, BMI: 17.1 ± 2.4 kg/m2) performed daily activities for 7 consecutive days while wearing VFJ 3, Ace 3, and wGT3X-BT. Pearson correlations, Bland–Altman plots, mean percent error (MPE), mean absolute percent error (MAPE), and equivalence tests were conducted to evaluate the agreement of VFJ 3 and Ace 3 with wGT3X-BT. VFJ 3 and Ace 3 had strong positive correlations (range: r = 0.71 to 0.95) with wGT3X-BT in estimating steps and moderate-to-vigorous PA (MVPA) and provided relatively valid estimates for daily steps. Although Ace 3 had no systematic bias and a low group measurement error (MPE: −10.1%) in estimating MVPA, VFJ 3 consistently overestimated daily MVPA. Collectively, VFJ 3 and Ace 3 can be valid devices to monitor children’s PA levels with daily step counts.

Carbon Stock Estimation of Poplar Plantations Based on Additive Biomass Models

Accurate estimation of biomass and carbon stocks in forest ecosystems is critical for understanding their roles in carbon sequestration and climate change mitigation. Currently, the development of stand biomass models and carbon stock estimation at the regional scale has emerged as a prominent research priority. In this study, 225 Populus spp. (poplar) trees in Shandong Province, China, were destructively sampled to obtain the biomass of their components. Two models (MS1 and MS2) were developed using allometric equations and the seemingly unrelated regression (SUR) method to ensure additive properties across tree components. The model evaluation employed the leave-one-out jackknife (LOO) method, considering statistics such as adjusted R-squared (Ra2), root mean square error (RMSE), mean absolute percent error (MAPE), and mean absolute error (MAE). The results from our models demonstrated high accuracy, with MS2 slightly outperforming MS1 after incorporating tree height as an independent variable. The models reliably estimated component-specific biomass and carbon stocks, with distinct variations observed in the carbon content among foliage (47.14 ± 2.07%), branches (47.26 ± 2.48%), stems (47.67 ± 2.21%), and roots (46.37 ± 2.78%). Carbon stocks in poplar plantations increased with the diameter class, ranging from 5 to 35 cm and correspondingly from 3.670 to 172.491 Mg C ha−1. As the diameter class increases, the carbon allocation strategy of poplars aligns with the CSR strategy, transitioning from prioritizing growth competition to emphasizing self-stabilization. Our research proposes a robust framework for assessing biomass and carbon stocks in poplar plantations, which is essential for evidence-based forest management strategies.

Performance Improvement of an Integrated Collector Storage Solar Water Heater by Using an Additional Glass Cover: A Numerical Study

This paper describes the analysis of a solar storage water heating system, emphasizing its cost-effectiveness and integrated design. The study employs numerical analysis to assess and optimize the performance of a rectangular solar collector with an added glass cover and an internal horizontal barrier. Using COMSOL software, a three-dimensional modeling study was conducted in the Kufa-Najaf climate on May 9th. The analysis focused on fundamental convection equations governing mass, momentum, and energy conservation. Temperature and velocity distributions were obtained at 13:30 PM, revealing a peak storage water temperature of 56.3 °C. The additional glass cover-barrier storage collector, set at a 60° angle, exhibited the highest stored energy at 2065.6 W, surpassing the conventional storage collector at 1007.06 W. Furthermore, the model demonstrated an increased instantaneous efficiency of 58.3%, compared to 28.4% for the conventional collector. The simulation results align well with previous findings, showing a maximum mean absolute percent error (MAE) of 4.5%.

Reliable measures of rest-activity rhythm fragmentation: how many days are needed?

BackgroundA more fragmented, less stable rest-activity rhythm (RAR) is emerging as a risk factor for health. Accelerometer devices are increasingly used to measure RAR fragmentation using metrics such as inter-daily stability (IS), intradaily variability (IV), transition probabilities (TP), self-similarity parameter (α), and activity balance index (ABI). These metrics were proposed in the context of long period of wear but, in real life, non-wear might introduce measurement bias. This study aims to determine the minimum number of valid days to obtain reliable fragmentation metrics.MethodsWrist-worn accelerometer data were drawn from the Whitehall accelerometer sub-study (age: 60 to 83 years) to simulate different non-wear patterns. Pseudo-simulated data with different numbers of valid days (one to seven), defined as < 1/3 of non-wear during both day and night periods, and with omission or imputation of non-wear periods were compared against complete data using intraclass correlation coefficient (ICC) and mean absolute percent error (MAPE).ResultsFive days with valid data (97.8% of participants) and omission of non-wear periods allowed an ICC ≥ 0.75 and MAPE ≤ 15%, acceptable cut points for reliability, for IS and ABI; this number was lower for TPs (two-three days), α and IV (four days). Overall, imputation of data did not provide better estimates. Findings were consistent across age and sex groups.ConclusionsThe number of days of wrist accelerometer data with at least 2/3 of wear time for both day and night periods varies from two (TPs) to five (IS, ABI) days for reliable RAR measures among older adults.

Ground settlement prediction for highway subgrades with sparse data using regression Kriging

Ground settlement prediction for highway subgrades is crucial in related engineering projects. When predicting the ground settlement, sparse sample data are often encountered in practice, which greatly affects the prediction accuracy. However, this has been seldom explored in previous studies. To resolve it, this paper proposes a regression Kriging (RK)—based method for ground settlement prediction with sparse data. Under the framework of RK, the stationarity of sample residual and trend structure are key factors for prediction accuracy. It is found that the use of Box–Cox transformation, which can help to achieve stationarity of sample residual, leads to significant increase of the prediction accuracy with sparse data. Specifically, the various evaluation metrics (i.e., root mean square error (RMSE), mean absolute error (MAE), mean arctangent absolute percent error (MAAPE) and scatter index (SCI)) are significantly decreased when the Box–Cox transformation is incorporated. In addition, the first-order polynomial trend structure is found to be more appropriate than those with higher orders for predicting settlements resulting from primary consolidation. Moreover, comparative study is conducted among the proposed RK method, classical prediction methods and back propagation neural network (BPNN). It is found that the evaluation metrics obtained by the RK method are significantly smaller than those obtained by the other methods, indicating its highest accuracy. By contrast, BPNN has the worst performance among the various methods, because the sparse data are inadequate to establish a satisfactory BPNN model.

Evaluation model design of project construction safety level based on bidirectional recurrent neural network (BiRNN) and bidirectional long short-term memory (BiLSTM)

Integrating deep learning methods for multi-element regression analysis poses a challenge in constructing safety evaluations for building construction. To address this challenge, this paper evaluates the integration of construction safety by quantitatively analyzing practitioners’ information and on-site construction conditions. The analytic hierarchy process (AHP) method quantifies construction safety capabilities, considering four key aspects: operators’ primary conditions, organizational personnel’s working conditions, on-site management conditions, and analysis of unsafe behaviors. A comprehensive set of 19 secondary causal factors is constructed. Furthermore, a hybrid model based on bidirectional recurrent neural network (BiRNN) and bidirectional long short-term memory (BiLSTM) is developed for construction safety evaluation, enhancing the model’s generalization ability by introducing the Dropout mechanism. Experimental results demonstrate that the fusion of BiRNN and BiLSTM methods outperforms traditional methods in construction safety evaluation, yielding mean squared error (MSE) and root mean squared error (RMSE) values of 0.48 and 0.69 and mean absolute error (MAE) and mean absolute percentage error (MAPE) values of 0.54 and 3.36%, respectively. The case study affirms that BiRNN-BiLSTM can accurately identify potential safety risks, providing reliable decision support for project management.

Application of Markov Chains and Artificial Neural Networks in the prediction of Hepatitis Cases in the southern states of Brazil

Viral hepatitis is a disease caused by five known types of virus and can be chronic or acute. This study collected historical data on hepatitis in the southern states of Brazil and applied Markov Chains as an input parameter for predicting cases, using Artificial Neural Networks (ANN). A comparison was then made between the method that includes the two methodologies and the prediction made by ANN using only the data from the historical series. The mean absolute error (MAE) and mean absolute percentage error (MAPE) were calculated to determine the best forecasting model for each state. It was not possible to determine a configuration that simultaneously presented the best MAE and MAPE values for each state, but it was found that the lowest errors were obtained by using Markov Chains as an information generator for the ANN models, with a MAPE of 4.45% using the Levenberg-Marquardt training algorithm, with a delay equal to 3 and a number of neurons equal to 60.

Forecasting Non-stationary Time Series Using Deep Learning in a Fuzzy Time Series Framework and its Application to Stock Markets

Non-stationary time series prediction is challenging due to its dynamic and complex nature. Fuzzy time series models offer a promising solution for forecasting such data, but a key challenge lies in partitioning the universe of discourse, which significantly impacts forecasting accuracy. Traditional fuzzy time series models often use equal-length interval partitioning, which is more suited for stationary data and limits their adaptability to non-stationary time series. This paper introduces a novel variable-length interval partitioning method designed specifically for non-stationary time series. The developed method combines a Long Short-Term Memory (LSTM) Autoencoder with K-means clustering, enabling dynamic, data-driven partitioning that adapts to the changing characteristics of the data. The LSTM Autoencoder encodes the time series, which is clustered using K-means, and intervals are defined based on cluster centers. Furthermore, the Variable Length Interval Partitioning-based Fuzzy Time Series model (VLIFTS) is developed by incorporating this partitioning method and the concepts of Markov chain and transition probability matrix. In this model, fuzzy sets are viewed as states of a Markov chain, and transition probabilities are used in the forecasting phase. The model is validated on stock market indices Nifty 50, NASDAQ, S&amp;P 500, and Dow Jones. Stationarity and heteroscedasticity are tested using Augmented Dickey-Fuller (ADF) and Levene's tests respectively. Statistical forecast accuracy metrics Root Mean Squared Error (RMSE) and Mean Absolute Percent Error (MAPE) show that VLIFTS significantly improves forecasting accuracy over traditional models. This hybrid approach enhances fuzzy time series modelling and can be applied to various non-stationary time series forecasting problems.

Machine learning-based analytical approach for mechanical analysis of composite hydrogen storage tanks under internal pressure

This study is a practical exploration of the application of machine learning for the mechanical analysis of filament-wound thin-composite hydrogen storage tanks under internal pressure. Our innovative approach seamlessly integrates classical laminate theory, comprehensive parametric analysis, and machine learning to advance the state-of-the-art in composite tank design. This versatile framework holds promise for addressing challenges in other structurally complex systems. A comprehensive parametric study was then conducted to explore the influence of key design parameters, such as internal pressure, tank radius, order of layer, and layer orientation. Pearson's correlation analysis was used to determine the parameters that had the most significant impact on the mechanical behavior of the tank. In addition, five machine learning models, namely, Extreme Gradient Boosting, Adaptive Boosting, Artificial Neural Network, Support Vector Machine, and Random Forest, were examined to determine their predictive capability for the mechanical performance of these composite tanks. Key findings demonstrate XGBoost's superior predictive capabilities, achieving a remarkable 99% accuracy in predicting stress in the x-direction compared to Random Forest's 96%. XGBoost also outperformed Random Forest in terms of Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) with values of 26 and 0.02, respectively, versus 207 and 0.16. These results underscore XGBoost's potential to revolutionize hydrogen storage tank design. The development of a user-friendly GUI application further enhances the practicality of this research, allowing engineers and composite designers to efficiently simulate the mechanical behavior of these tanks in real time by adjusting the cursors for variables such as the pressure, radius, layer order, and layer orientation. This tool, with its intuitive interface and elimination of manual calculations, promises significant enhancements in the design process, providing a platform for the rapid assessment and optimization of tank architectures, thereby improving the efficiency and reliability of the design process.

Hybrid CNC–MXene Nanolubricant for Tribological Application: Characterization, Prediction, and Optimization of Thermophysical Properties Evaluation

In the present work, hybrid Cellulose Nanocrystal–MXene (CNC–MXene) nanolubricants were prepared via a two-step method and investigated as potential heat-transfer hybrid nanofluids for the first time. CNC–MXene nanolubricants were synthesized via a two-step method by varying the weight percentage of CNC–MXene nanoparticles (ranging from 0.01 to 0.05 wt%) and characterized using Fourier-Transform Infrared Spectroscopy and TGA (Thermogravimetric Analysis). Response surface methodology (RSM) was used in conjunction with the miscellaneous design model to identify prediction models for the thermophysical properties of the hybrid CNC–MXene nanolubricant. Minitab 18 statistical analysis software and Response Surface Methodology (RSM) based on Central Composite Design (CCD) were utilized to generate an empirical mathematical model investigating the effect of concentration and temperature. The analysis of variance (ANOVA) results indicated significant contributions from the type of nanolubricant (p &lt; 0.001) and the quadratic effect of temperature (p &lt; 0.001), highlighting non-linear interactions that affect viscosity and thermal conductivity. The findings showed that the predicted values closely matched the experimental results, with a percentage of absolute error below 9%, confirming the reliability of the optimization models. Additionally, the models could predict more than 85% of the nanolubricant output variations, indicating high model accuracy. The optimization analysis identified optimal conditions for maximizing both dynamic viscosity and thermal conductivity. The predicted optimal values (17.0685 for dynamic viscosity and 0.3317 for thermal conductivity) were achieved at 30 °C and a 0.01% concentration, with a composite desirability of 1. The findings of the percentage of absolute error (POAE) reveal that the model can precisely predict the optimum experimental parameters. This study contributes to the growing field of advanced nanolubricants by providing insights into the synergistic effects of CNC and MXene in enhancing thermophysical properties. The developed models and optimization techniques offer valuable tools for tailoring nanolubricant formulations to specific tribological applications, potentially leading to improved efficiency and durability in various industrial settings.

Humans vs. large language models: Judgmental forecasting in an era of advanced AI

This study investigates the forecasting accuracy of human experts versus large language models (LLMs) in the retail sector, particularly during standard and promotional sales periods. Utilizing a controlled experimental setup with 123 human forecasters and five LLMs—namely, ChatGPT-4, ChatGPT3.5, Bard, Bing, and Llama2—we evaluated forecasting precision through the absolute percentage error. Our analysis centered on the effect of the following factors on forecasters’ performance: the supporting statistical model (baseline and advanced), whether the product was on promotion, and the nature of external impact. The findings indicate that LLMs do not consistently outperform humans in forecasting accuracy and that advanced statistical forecasting models do not uniformly enhance the performance of either human forecasters or LLMs. Both human and LLM forecasters exhibited increased forecasting errors, particularly during promotional periods. Our findings call for careful consideration when integrating LLMs into practical forecasting processes.

Development of a Real-Time NOx Prediction Soft Sensor Algorithm for Power Plants Based on a Hybrid Boost Integration Model

Nitrogen oxides (NOxs) are some of the most important hazardous air pollutants from industry. In China, the annual NOx emission in the waste gas of industrial sources is about 8.957 million tons, while power plants remain the largest anthropogenic source of NOx emissions, and the precise control of NOx in power plants is crucial. However, due to inherent issues with measurement and pipelines in coal-fired power plants, there is typically a delay of about three minutes in NOx measurements, bringing mismatch between its control and measurement. Measuring delays in NOx from power plants can lead to excessive ammonia injection or failure to meet environmental standards for NOx emissions. To address the issue of NOx measurement delays, this study introduced a hybrid boosting model suitable for on-site implementation. The model could serve as a feedforward signal in SCR control, compensating for NOx measurement delays and enabling precise ammonia injection for accurate denitrification in power plants. The model combines generation mechanism and data-driven approaches, enhancing its prediction accuracy through the categorization of time-series data into linear, nonlinear, and exogenous regression components. In this study, a time-based method was proposed for analyzing the correlations between variables in denitration systems and NOx concentrations. This study also introduced a new evaluation indicator, part of R2 (PR2), which focused on the prediction effect at turning points. Finally, the proposed model was applied to actual data from a 330 MW power plant, showing excellent predictive accuracy, particularly for one-minute forecasts. For 3 min prediction, compared to predictions made by ARIMA, the R-squared (R2) and PR2 were increased by 3.6% and 30.6%, respectively, and the mean absolute error (MAE) and mean absolute percentage error (MAPE) were decreased by 9.4% and 9.1%, respectively. These results confirmed the accuracy and applicability of the integrated model for on-site implementation as a 3 min advanced prediction soft sensor in power plants.

The Methods for Estimating Lake Volume, Mean Depth, and Maximum Depth in European Standard EN 16039:2011 Are Flawed and Should Not Be Used

ABSTRACTThe European Standard EN 16039:2011 provides guidelines for assessing lake hydromorphology within the Water Framework Directive and includes methods for estimating volume, mean depth, and maximum depth based on statistical models applied to data from topographic maps. We tested the predictive accuracy of these models using independently collected bathymetric data from 35 Swedish lakes. The models had no predictive power, and the maximum depth predictions were inversely correlated with the observed values. The mean absolute percent error was 46% for volume and mean depth, and 85% for maximum depth. The models are flawed and should not be used.

Development and validation of a deep learning model for detecting signs of tuberculosis on chest radiographs among US-bound immigrants and refugees.

Immigrants and refugees seeking admission to the United States must first undergo an overseas medical exam, overseen by the US Centers for Disease Control and Prevention (CDC), during which all persons ≥15 years old receive a chest x-ray to look for signs of tuberculosis. Although individual screening sites often implement quality control (QC) programs to ensure radiographs are interpreted correctly, the CDC does not currently have a method for conducting similar QC reviews at scale. We obtained digitized chest radiographs collected as part of the overseas immigration medical exam. Using radiographs from applicants 15 years old and older, we trained deep learning models to perform three tasks: identifying abnormal radiographs; identifying abnormal radiographs suggestive of tuberculosis; and identifying the specific findings (e.g., cavities or infiltrates) in abnormal radiographs. We then evaluated the models on both internal and external testing datasets, focusing on two classes of performance metrics: individual-level metrics, like sensitivity and specificity, and sample-level metrics, like accuracy in predicting the prevalence of abnormal radiographs. A total of 152,012 images (one image per applicant; mean applicant age 39 years) were used for model training. On our internal test dataset, our models performed well both in identifying abnormalities suggestive of TB (area under the curve [AUC] of 0.97; 95% confidence interval [CI]: 0.95, 0.98) and in estimating sample-level counts of the same (-2% absolute percentage error; 95% CIC: -8%, 6%). On the external test datasets, our models performed similarly well in identifying both generic abnormalities (AUCs ranging from 0.89 to 0.92) and those suggestive of TB (AUCs from 0.94 to 0.99). This performance was consistent across metrics, including those based on thresholded class predictions, like sensitivity, specificity, and F1 score. Strong performance relative to high-quality radiological reference standards across a variety of datasets suggests our models may make reliable tools for supporting chest radiography QC activities at CDC.