Lowest Mean Absolute Error Research Articles

Valuation of the EQ-5D-3L in Jordan.

In Jordan, no national value set is available for any preference-accompanied health utility measure. This study aims to develop a value set for EQ-5D-3L based on the preferences of the Jordanian general population. A representative sample of the Jordanian general population was obtained through quota sampling involving age, gender, and region. Participants aged above 18 years were interviewed via videoconferencing using the EuroQol Valuation Technology 2.1 protocol. Participants completed ten composite time trade-offs (cTTO) and ten discrete choice experiments (DCE) tasks. cTTO and DCE data were analyzed using linear and logistic regression models, respectively, and hybrid models were applied to the combined DCE and cTTO data. A total of 301 participants with complete data were included in the analysis. The sample was representative of the general population regarding region, age, and gender. All model types applied, that is, random intercept model, random intercept Tobit, linear model with correction for heteroskedasticity, Tobit with correction for heteroskedasticity, and all hybrid models, were statistically significant. They showed logical consistency in terms of higher utility decrements with more severe levels. The hybrid model corrected for heteroskedasticity was selected to construct the Jordanian EQ-5D-3L value set as it showed the best fit and lowest mean absolute error. The predicted value for the most severe health state (33333) was -0.563. Utility decrements due to mobility had the largest weight, followed by anxiety/depression, while usual activities had the smallest weight. This study provides the first EQ-5D-3L value set in the Middle East. The Jordanian EQ-5D-3L value set can now be used in health technology assessments for health policy planning by the Jordanian health sector's decision-makers.

Artificial intelligence-implemented prediction and cost-effective optimization of micropollutant photodegradation using g-C3N4/Bi2O3 heterojunction

Micropollutants pose a formidable hazard to human health, however, conventional water treatment fails to efficiently and economically eliminate them. The imperative need for real-time concentration monitoring of these micropollutants, vital for effective elimination and cost optimization, has proven elusive without the intervention of artificial intelligence. To bridge these critical gaps, g-C3N4/Bi2O3 heterojunction was proposed as an efficient catalyst to eliminate recalcitrate micropollutants under visible light in this study, demonstrating a 1.8-fold increase in catalytic efficiency compared to g-C3N4, and furthermore, artificial intelligence models, i.e., the proposed Long short-term memory combined with Gated residual network (ALG) and Deep Deterministic Policy Gradient (DDPG), were employed for real-time concentration prediction of micropollutants (R2 = 0.9541) and their treatment processing optimization, respectively. The predominant active species for degrading micropollutants were identified as O2•− and 1O2. We proved that HOO• serves as an intermediate to transform HO• and H2O2 generated in-situ to O2•− and 1O2, further enhancing micropollutant elimination. Compared to other models, the ALG demonstrated significantly lower root mean square error (RMSE = 0.0432) and mean absolute percentage error (MAPE = 4.8273). Weight analysis revealed that Catalyst Type (31.80 %) is the most critical factor. Finally, the proposed DDPG model dynamically adjusted its treatment strategy, aiming to discover an optimal balance among cost, reaction time, and removal efficiency. This study provides mechanistic insights into the pivotal roles of artificial intelligence in prediction and cost-effective optimization of micropollutant elimination.

A hybrid BOA-SVR approach for predicting aerobic organic and nitrogen removal in a gas-liquid-solid circulating fluidized bed bioreactor

This study introduces the hybrid of the Bayesian optimization algorithm and support vector regression (BOA-SVR) models to predict the removal of aerobic organic (total chemical oxygen demand, COD) and nitrogen compounds such as total Kjeldahl Nitrogen (TKN), ammonium nitrogen (NH4-N), and nitrate nitrogen (NO3-N) from municipal wastewater in a gas-liquid-solid circulating fluidized bed (GLSCFB) bioreactor. GLSCFB bioreactors treat wastewater by removing nutrients biologically. The downer of a GLSCFB bioreactor provided experimental data on TKN, NH4-N, NO3-N, and TCOD removal. The hybrid optimal intelligence algorithm (BOA-SVR) has improved model accuracy across multiple domains by combining BOA and SVR. The coefficient of determination (R2), residual, mean absolute error (MAE), root mean square error (RMSE), and fractional bias (FB) were used to analyze BOA-SVR model performance. The models match experimental data from four operational stages well, with R2 or adj R2 values above 0.99 for all responses. The model's accuracy was confirmed by relative deviations and residual plots showing dispersion around the zero-reference line. The BOA-SVR model consistently predicted dependent variables with low RMSE and MAE values (≤ 2.24 and 2.21, respectively) and near-zero FB. Computing efficiency was shown by optimizing TCOD, TKN, NH4-N, and NO3-N models in 70.61, 72.89, 74.37, and 54.07 s. A rigorous test on unseen data with different noise levels confirmed the model's stability. Furthermore, BOA-SVR performs better than traditional multiple linear regression (MLR). Overall, the BOA-SVR model predicts biological nutrient removal in municipal wastewater utilizing a GLSCFB bioreactor quickly, correctly, and efficiently, reducing experimental stress and resource use.

Selective discrimination and accurate quantification of five target vapors among multiple vapors using 2D CuO and Co3O4 sensors

Selective and sensitive detection of volatile organic compounds (VOCs) are critically needed for various applications like environmental sustainability, industrial safety, healthcare, etc Metal oxides are one of the most explored chemiresistive sensing materials because of their high sensitivity, but they lack selectivity. This work reports synthesis of two metal oxides - CuO and Co3O4 using surfactant assisted hydrothermal method. The 2D morphologies of both the metal oxides were ensured through fielded emission scanning electron microscope. The polycrystalline nature of the materials was studied using X-ray diffractometer and bandgaps were found to be 1.72 eV (CuO) and 1.9 and 2.89 eV (Co3O4) through the Kubelka Munk plot. The two metal oxides were employed to detect four different concentrations (6–50 ppm) of five targeted VOCs (lung cancer biomarkers) - acetone, acetonitrile, isopropanol, methanol, and toluene. In addition, response of the sensors for 6–50 ppm of ethyl acetate, hexanal, ammonia, and NO2 were also recorded as these VOCs are naturally produced in the body as a result of metabolic processes. The responses were recorded for 10 min for all the gases with CuO and Co3O4. Despite the intrinsic metal oxides lacking selectivity towards a specific VOC, careful feature selection achieved a classification accuracy of 95% using random forest (RF) algorithm. Subsequent application of RF model on validation dataset yielded a 91% accuracy in identifying target VOCs. Multilinear regression (MLR) algorithm was then employed to quantify the concentrations of the VOCs and low mean absolute error (MAE) values were obtained.

Anomalous Network Behaviour Detection in Interoperable Health Systems using Machine Learning in Resource Limited Areas

The connection of devices in distributed environments produces and shares a vast amount of data useful for different organisational decision-making. In healthcare service organisations, for example, multiple e-health systems from different departments or facilities connect and share health data and information. During sharing, proper management is important to ensure the information is secure against intruders. Machine learning as a non-conventional security technique can be used along conventional techniques like firewalls, antivirus and intrusion detection systems to predict future network threats and other anomalies using historical backgrounds and other features. However, some machine learning algorithms have complex computation thus requiring resourceful systems in terms of network bandwidth, CPU power, memory, and storage capacity. In resource-constrained environments, therefore, special consideration is needed to ensure that the analysis of the big data is successful and that the benefits associated with them are effectively obtained. In this paper, a Machine Learning algorithm was selected among four algorithms whose performance was compared through various performance metrics. Classification accuracy, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Relative Absolute Error (RAE) among other performance metrics were used to compare the ANN, Random forest, Decision trees, and Naïve byes classification algorithms using an extract from CICDDOS2019 dataset. Using the Weka version 3.8.6, the algorithms were compared to choose the best one to classify the data. By using three computers with different resources, the experiments were carried out to determine the performance of those machine learning algorithms. The result revealed that the random forest produced a good average classification performance in resource-limited systems since it surpassed other algorithms in classifying the data at an average of 99 per cent with a low average mean absolute error of 0.0001. Furthermore, as an ensemble that classifies with multiple decision trees algorithm, it likewise uses reasonable time to build and test the model therefore recommended for resource-limited systems.

Prediction of Urban House Rental Prices in Lagos - Nigeria: A Machine Learning Approach

Often, prospective tenants need to know the rental price of an apartment, and homeowners need to know how best to price their apartments. This work aims to predict house rental prices in Lagos, Nigeria, using machine learning by examining the relationship between the rental price and features such as the number of bedrooms, bathrooms, toilets, location and house status(newly built, furnished, and/or serviced). Five machine learning models were trained and evaluated using mean absolute error (MAE), root mean squared error (RMSE) and r-square (R2); the random forest regression model outperformed the other four models with the lowest MAE, RMSE and the highest R2. This study also revealed that the number of bedrooms and the apartment's location are the most significant predictors, confirmed using the feature importance analysis. The developed model can be used to estimate the rental price of a property in Lagos, Nigeria.

Rapidly tailor metal–organic frameworks for arsenate removal using graph convolutional neural networks

Metal-organic frameworks (MOFs) are effective materials for the removal of highly toxic arsenates (As(V)). However, the intricate structure–activity relationships of MOFs for As(V) removal remain unclear, thus impeding its targeted fabrication. In this work, we used the graph convolutional neural network to integrate MOFs’ chemical composition, physical structure, and adsorption environment, thereby developing an end-to-end predictive model for As(V) adsorption by MOFs. The model’s high coefficient of determination, low mean absolute error, and experimental verification of MOFs synthesized based on model predictions not previously used in the As (V) adsorption confirmed the precision and general applicability of the model. Our constructed model identified two key features for adsorption, i.e., metal nodes and pore features, and the modular blocks for constructing MOFs. The strategic design for MOFs to absorb As(V) informed by the model, emphasized integrating open single or binuclear metal nets with aromatic di- or tricarboxylic acid linkers within a robust three-dimensional topological net. This work highlights the integration of predictive modeling and structural refinement to enhance MOF design for As (V) adsorption, even in more other pollutants.

From data to harvest: Leveraging ensemble machine learning for enhanced crop yield predictions across Canada amidst climate change

Accurate crop yield predictions are crucial for farmers and policymakers. Despite the widespread use of ensemble machine learning (ML) models in computer science, their application in crop yield prediction remains relatively underexplored. This study, conducted in Canada, aims to assess the potential of five distinct ensemble ML models—Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), XGBoost, LightGBM, and Random Forest (RF)—in predicting crop yields chosen for their ability to manage complex datasets and their strong performance potential. The study integrated various factors, including climate variables, satellite-derived vegetation indices, soil characteristics, and honeybee census data. Data preparation comprised two main steps: first, climate variables were interpolated and averaged for croplands in ArcGIS Pro, along with averaging vegetation indices and soil characteristics. Honeybee census data was also incorporated. Second, the data was organized in Python to create a structured format for models' input. The models' accuracy was assessed using Root Mean Squared Error (RMSE), R-squared, and Mean Absolute Error (MAE). XGBoost emerged as the most accurate model, with the lowest MAE (68.70 for canola and 39.47 for soybeans), lowest RMSE (119.48 for canola and 102.39 for soybeans), and highest R-squared values (0.95 for canola and 0.96 for soybeans) on the test dataset. The study also assessed crop yields under various climate change scenarios, finding minimal variations across the scenarios, but significant negative impacts on canola and soybean yields across Canada. Honeybee colonies were identified as the most influential factor on crop yields, contributing 52.34 % to canola and 57.18 % to soybean yields. This research provides detailed crop yield maps of canola and soybeans at the Census Consolidated Subdivisions (CCS) level across Canada's agricultural landscape, offering valuable forecasts for localized decision-making. Additionally, it offers a proactive strategy for climate change preparedness, assisting farmers and stakeholders optimise resource allocation and manage risks effectively.

A hybrid SARIMA-Prophet model for predicting historical streamflow time-series of the Sobat River in South Sudan

Accurate river streamflow forecasting is pivotal for effective water resource planning, infrastructure design, utilization, optimization, and flood planning and warning. Streamflow prediction remains a difficult task due to several factors such as climate change, topography, and lack of observed data in some cases. This paper investigates and evaluates the individual performances of the seasonal auto-regressive integrated moving average (SARIMA) and Prophet models in forecasting the streamflow of the Sobat River and proposes a hybrid SARIMA-Prophet model to leverage the strengths of both approaches. Using the augmented Dickey-Fuller (ADF) and the Kwiatkowski-Phillips-Schmidt-Shin (KPSS) tests, the flow of the Sobat River was found to be stationary. The performance of the models was then assessed based on their residual errors and predictive accuracy using the mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R2). Residual analysis and prediction capabilities revealed that Prophet slightly edged SARIMA in terms of prediction efficacy; however, both models struggled to effectively capture extreme values, resulting in significant overestimations and slight underestimations. The hybrid SARIMA-Prophet model significantly reduced residual variability, achieving a lower MAE of 4.047 m3/s, RMSE of 6.17 m3/s, and a higher R2 of 0.92 than did the SARIMA (MAE: 5.39 m3/s, RMSE: 8.70 m3/s, R2: 0.85) and Prophet (MAE: 5.35 m3/s, RMSE: 8.32 m3/s, and R2: 0.86) models. This indicates that the hybrid model handles both long-term patterns and short-term fluctuations more effectively than the individual models. The findings of the present study highlight the potential of hybrid SARIMA-Prophet models for streamflow forecasting in terms of accuracy and reliability, thus contributing to more effective water resource management and planning, particularly in the Sobat River.

Application of machine learning approaches to predict ammonium nitrogen transport in different soil types and evaluate the contribution of control factors

The loss of nitrogen in soil damages the environment. Clarifying the mechanism of ammonium nitrogen (NH4+-N) transport in soil and increasing the fixation of NH4+-N after N application are effective methods for improving N use efficiency. However, the main factors are not easily identified because of the complicated transport and retardation factors in different soils. This study employed machine learning (ML) to identify the main influencing factors that contribute to the retardation factor (Rf) of NH4+-N in soil. First, NH4+-N transport in the soil was investigated using column experiments and a transport model. The Rf (1.29 – 17.42) was calculated and used as a proxy for the efficacy of NH4+-N transport. Second, the physicochemical parameters of the soil were determined and screened using lasso and ridge regressions as inputs for the ML model. Third, six machine learning models were evaluated: Adaptive Boosting, Extreme Gradient Boosting (XGB), Random Forest, Gradient Boosting Regression, Multilayer Perceptron, and Support Vector Regression. The optimal ML model of the XGB model with a low mean absolute error (0.81), mean squared error (0.50), and high test r2 (0.97) was obtained by random sampling and five-fold cross-validation. Finally, SHapely Additive exPlanations, entropy-based feature importance, and permutation characteristic importance were used for global interpretation. The cation exchange capacity (CEC), total organic carbon (TOC), and Kaolin had the greatest effects on NH4+-N transport in the soil. The accumulated local effect offered a fundamental insight: When CEC > 6 cmol+ kg−1, and TOC > 40 g kg−1, the maximum resistance to NH4+-N transport within the soil was observed. This study provides a novel approach for predicting the impact of the soil environment on NH4+-N transport and guiding the establishment of an early-warning system of nutrient loss.

Estimation of macro and micronutrient concentrations in ‘valencia’ orange leaves at different phenological stages using multispectral image analysis and multiple regression

ABSTRACT This study aimed at estimating the macro- and micronutrient concentrations in leaves of Valencia oranges (Citrus sinensis [L.] Osbeck) through multiple regression analysis using multispectral images and vegetation indices (VIs) selected through the stepwise regression method. The data were collected in a commercial orchard of Valencia oranges in El Barretal, Tamaulipas, Mexico. The leaf samples were analysed in a laboratory to determine the concentrations of N, P, K, Ca, Mg, Cu, Fe, Mn, and Zn using traditional chemical methods; the relative chlorophyll values were obtained using a chlorophyll metre (SPAD502 Plus). Multi-spectral images of the tree canopy were acquired using a UAV equipped with a multispectral camera with five wavelengths (blue, green, red, red edge, and near-infrared); based on these data, 85 VIs were calculated. To select the predictor variables that were most relevant for the model, 90 candidate variables were divided into three groups with 30 VIs grouped by nutrients based on the highest and lowest absolute values found in the correlation matrix. Heteroscedasticity and autocorrelation were also assessed through the Breusch-Pagan and Durbin-Watson tests, respectively. The selected variables were used in multiple regression analysis. The resulting models were validated by mean absolute error (MAE), root-mean-square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination ( R 2 ). The prediction models showed satisfactory results, with values R 2 between 0.79 and 0.95 and relatively low (<10) MAE and RMSE for all nutrients, except Fe ( < 30 ) in all phenological stages; MAPE values were lower than 0.5% for all nutrients. This study showed that multispectral imaging combined with multiple regression analysis effectively predicts nutrient levels in the leaves of Valencia oranges in various phenological stages. This study presents a new perspective on agricultural systems, offering an effective alternative to assess the nutritional conditions of crops.

An effective no-reference image quality index prediction with a hybrid Artificial Intelligence approach for denoised MRI images

As the quantity and significance of digital pictures in the medical industry continue to increase, Image Quality Assessment (IQA) has recently become a prevalent subject in the research community. Due to the wide range of distortions that Magnetic Resonance Images (MRI) can experience and the wide variety of information they contain, No-Reference Image Quality Assessment (NR-IQA) has always been a challenging study issue. In an attempt to address this issue, a novel hybrid Artificial Intelligence (AI) is proposed to analyze NR-IQ in massive MRI data. First, the features from the denoised MRI images are extracted using the gray level run length matrix (GLRLM) and EfficientNet B7 algorithm. Next, the Multi-Objective Reptile Search Algorithm (MRSA) was proposed for optimal feature vector selection. Then, the Self-evolving Deep Belief Fuzzy Neural network (SDBFN) algorithm was proposed for the effective NR-IQ analysis. The implementation of this research is executed using MATLAB software. The simulation results are compared with the various conventional methods in terms of correlation coefficient (PLCC), Root Mean Square Error (RMSE), Spearman Rank Order Correlation Coefficient (SROCC) and Kendall Rank Order Correlation Coefficient (KROCC), and Mean Absolute Error (MAE). In addition, our proposed approach yielded a quality number approximately we achieved significant 20% improvement than existing methods, with the PLCC parameter showing a notable increase compared to current techniques. Moreover, the RMSE number decreased by 12% when compared to existing methods. Graphical representations indicated mean MAE values of 0.02 for MRI knee dataset, 0.09 for MRI brain dataset, and 0.098 for MRI breast dataset, showcasing significantly lower MAE values compared to the baseline models.

Leveraging Deep Learning for Time-Series Extrinsic Regression in Predicting the Photometric Metallicity of Fundamental-Mode RR Lyrae Stars.

Astronomy is entering an unprecedented era of big-data science, driven by missions like the ESA's Gaia telescope, which aims to map the Milky Way in three dimensions. Gaia's vast dataset presents a monumental challenge for traditional analysis methods. The sheer scale of this data exceeds the capabilities of manual exploration, necessitating the utilization of advanced computational techniques. In response to this challenge, we developed a novel approach leveraging deep learning to estimate the metallicity of fundamental mode (ab-type) RR Lyrae stars from their light curves in the Gaia optical G-band. Our study explores applying deep-learning techniques, particularly advanced neural-network architectures, in predicting photometric metallicity from time-series data. Our deep-learning models demonstrated notable predictive performance, with a low mean absolute error (MAE) of 0.0565, the root mean square error (RMSE) of 0.0765, and a high R2 regression performance of 0.9401, measured by cross-validation. The weighted mean absolute error (wMAE) is 0.0563, while the weighted root mean square error (wRMSE) is 0.0763. These results showcase the effectiveness of our approach in accurately estimating metallicity values. Our work underscores the importance of deep learning in astronomical research, particularly with large datasets from missions like Gaia. By harnessing the power of deep-learning methods, we can provide precision in analyzing vast datasets, contributing to more precise and comprehensive insights into complex astronomical phenomena.

A predictive SD‐WAN traffic management method for IoT networks in multi‐datacenters using deep RNN

AbstractDeploying the Internet of Things (IoT) in integrated edge‐cloud environments exposes the IoT traffic data to performance issues such as delay, bandwidth limitation etc. Recently, Software‐Defined Wide Area Network (SD‐WAN) has emerged as an architecture that originates from the Software‐Defined Network (SDN) paradigm and provides solutions for networking multiple data centers by allowing network administrators to manage and control network layers. In this article, an SDWAN‐based policy for traffic management in IoT is introduced in which the Quality of Service (QoS) metrics such as end‐to‐end delay and bandwidth utilization are optimized. The proposed method implements the traffic management policy in the SDWAN controller. When the IoT traffic flows reach the SDWAN infrastructure network, graph search algorithms are performed to find the near‐optimal paths that affect the end‐to‐end delay of traffic flows. Because of the ability of deep learning to process complex data, a deep RNN model is used to predict the network state information, such as link latency and available bandwidth, before the traffic flows reach the infrastructure network. The proposed method consists of four key modules to predict the routes for future time intervals: (a) an SD‐WAN topology updater unit that checks the link changes and availability, (b) the network state information collector, which collects the network state information to create a dataset, (c) the learning unit, which trains a deep RNN model using the created dataset, and (d) the route predictor unit, which uses the trained model to predict the network state information using a heuristic algorithm to determine the routes. The simulation results showed that the deep RNN model can achieve high accuracy and low Mean Absolute Error (MAE), and the proposed method outperforms shortest‐path algorithms in terms of latency. At the same time, the available bandwidth is almost fairly distributed among all network links.

Prediction of flash flood peak discharge in hilly areas with ungauged basins based on machine learning

ABSTRACT Peak discharge is an essential element of hydrological forecasting. Due to rapid outbreaks of flash floods in hilly areas and the lack of measured data, the fast and accurate estimation of peak discharge is crucial for flash flood hazard management. Three machine learning algorithms were applied to estimate peak discharge; this estimation was compared with the results of hydrological–hydraulic models, and the results were verified with measured watershed data. In this paper, 10 hydrological and geomorphological parameters were selected to predict the flood peak discharge in 103 watersheds in Taiyi Mountain North District. The results show that the particle swarm optimization backpropagation (PSO-BP) neural network model outperforms the BP neural network and random forest regression in prediction performance. PSO-BP has a lower mean absolute error (2.51%), root mean square error (3.74%), and mean absolute percentage error (2.74%) than the other models, which indicates that PSO-BP has high prediction accuracy. Importance analysis revealed that rainfall, early impact rainfall, catchment area, and rain intensity are the key input parameters of PSO-BP. The proposed method was confirmed to be a fast and relatively accurate algorithm for estimating the peak discharge of flash floods in ungauged basins.

Modeling the thermal transport properties of hydrogen and its mixtures with greenhouse gas impurities: A data-driven machine learning approach

This study introduces machine learning (ML) algorithms to predict hydrogen (H2) thermodynamic properties for geological storage, focusing on its mixtures with natural gas, nitrogen (N2), and carbon dioxide (CO2). Employing 1167 data samples, this research utilizes multiple linear regression (MLR), random forest (RF), gradient boosting (GB), and decision tree (DT) models, enhanced by sensitivity analysis for feature engineering. GB model's superior accuracy and efficiency over conventional statistical linear regression methods. The finding reveals that the GB model achieves superior performance, with an R2 value of 0.9998 for thermal capacity and the lowest mean absolute error (MAE)/root mean square error (RMSE) across all H2 properties—density (1.51%, 2.06 kg/m3), viscosity (0.000078%, 0.000117 cp), thermal conductivity (0.000427%, 0.000849 W/m.K), and thermal capacity (8.79%, 26.06 J/g.K). Moreover, this ML-based approach not only demonstrates remarkable accuracy and efficiency but also suggests the potential of smart paradigms to further enhance the safety and transportability of underground hydrogen storage projects. Ultimately, this work will help the reservoir simulation at field scale to be more robust and reliable.

A hierarchical estimation of road grade based on tire force observation

Road grade is important for autonomous vehicles, but it is difficult to measure directly. To address this issue, a hierarchical estimation of road grade is suggested based on the observation of tire forces. First, a 7-degree-of-freedom (DOF) dynamics model, including vehicle longitudinal, lateral, and yaw motions together with wheel rotations, is developed while considering the road grade. Subsequently, a dual-layer road grade estimation strategy is proposed based on an unscented Kalman filter (UKF). The lower-layer UKF estimates the longitudinal and lateral tire forces for road grade observation, and the upper-layer UKF is employed to estimate the road grade by considering the vehicle’s lateral acceleration and yaw rate. Finally, CarSim and MATLAB joint simulations and road tests are performed under different conditions to validate the correctness and effectiveness of the proposed estimation method. The results show that the proposed tire force observation-based estimator exhibits a lower mean absolute error and root mean square error on sloping roads and combined curved and sloping roads, and presents a better overall estimation performance on road grade compared with the widely used kinematics and dynamics model-based estimators.

Fusing multi-scale functional connectivity patterns via Multi-Branch Vision Transformer (MB-ViT) for macaque brain age prediction

Brain age (BA) is defined as a measure of brain maturity and could help characterize both the typical brain development and neuropsychiatric disorders in mammals. Various biological phenotypes have been successfully applied to predict BA of human using chronological age (CA) as label. However, whether the BA of macaque, one of the most important animal models, can also be reliably predicted is largely unknown. To address this question, we propose a novel deep learning model called Multi-Branch Vision Transformer (MB-ViT) to fuse multi-scale (i.e., from coarse-grained to fine-grained) brain functional connectivity (FC) patterns derived from resting state functional magnetic resonance imaging (rs-fMRI) data to predict BA of macaques. The discriminative functional connections and the related brain regions contributing to the prediction are further identified based on Gradient-weighted Class Activation Mapping (Grad-CAM) method. Our proposed model successfully predicts BA of 450 normal rhesus macaques from the publicly available PRIMatE Data Exchange (PRIME-DE) dataset with lower mean absolute error (MAE) and mean square error (MSE) as well as higher Pearson's correlation coefficient (PCC) and coefficient of determination (R2) compared to other baseline models. The correlation between the predicted BA and CA reaches as high as 0.82 of our proposed method. Furthermore, our analysis reveals that the functional connections predominantly contributing to the prediction results are situated in the primary motor cortex (M1), visual cortex, area v23 in the posterior cingulate cortex, and dysgranular temporal pole. In summary, our proposed deep learning model provides an effective tool to accurately predict BA of primates (macaque in this study), and lays a solid foundation for future studies of age-related brain diseases in those animal models.

Forecasting the market value of power battery industry chain: A novel RRMIDAS-SVR model

The emergence of electric vehicles has contributed to mitigating air pollution and greenhouse effects caused by traditional fuel vehicles. The power battery industry chain, which is a primary component of electric vehicles, requires more attention to monitor its development status. This study proposes a novel method for forecasting the development status of the power battery industry chain by monitoring the market value index of all listed companies in the power battery industry. It proposes a new forecasting model, RRMIDAS-SVR, which outlines reverse-restricted mixed data sampling (RRMIDAS) into support vector regression (SVR) to end the data-driven challenges of mixed-frequency data and nonlinear relationships. We estimate the RRMIDAS-SVR model using a quadratic programming problem and mixed-frequency West Texas Intermediate crude oil futures prices, electric vehicle sales, and the consumer price index as predictors of the market value of all listed companies in the power battery industry chain. The experimental findings reveal that the RRMIDAS-SVR model outperforms the other models, as evidenced by its lower mean absolute error and root-mean-square error. This study contributes to understanding the development status of the power battery industry value chain by proposing and developing a new approach, RRMIDAS-SVR, to monitor the industry's development status that considers a multi-source information set. Moreover, this study provides strategic insights for stakeholders in the power battery industry.

Machine Learning Models for Predicting Cycloplegic Refractive Error and Myopia Status Based on Non-Cycloplegic Data in Chinese Students.

To develop and validate machine learning (ML) models for predicting cycloplegic refractive error and myopia status using noncycloplegic refractive error and biometric data. Cross-sectional study of children aged five to 18years who underwent biometry and autorefraction before and after cycloplegia. Myopia was defined as cycloplegic spherical equivalent refraction (SER) ≤-0.5 Diopter (D). Models were evaluated for predicting SER using R2 and mean absolute error (MAE) and myopia status using area under the receiver operating characteristic (ROC) curve (AUC). Best-performing models were further evaluated using sensitivity/specificity and comparison of observed versus predicted myopia prevalence rate overall and in each age group. Independent data sets were used for training (n = 1938) and validation (n = 1476). In the validation dataset, ML models predicted cycloplegic SER with high R2 (0.913-0.935) and low MAE (0.393-0.480 D). The AUC for predicting myopia was high (0.984-0.987). The best-performing model for SER (XGBoost) had high sensitivity and specificity (91.1% and 97.2%). Random forest (RF), the best-performing model for myopia, had high sensitivity and specificity (92.2% and 96.9%). Within each age group, difference between predicted and actual myopia prevalence was within 4%. Using noncycloplegic refractive error and ocular biometric data, ML models performed well for predicting cycloplegic SER and myopia status. When measuring cycloplegic SER is not feasible, ML may provide a useful tool for estimating cycloplegic SER and myopia prevalence rate in epidemiological studies. Using ML to predict cycloplegic refraction based on noncycloplegic data is a powerful tool for large, population-based studies of refractive error.