Lowest Mean Absolute Percentage Error Research Articles

Using partial discharge data to identify highly sensitive electrochemical parameters of aged lithium-ion batteries

Highly sensitive (HS) electrochemical parameters can serve as battery aging indicators, deserving thorough examination. To identify these parameters and determine their cycle evolution across a wide range of battery state of health, this study conducts a three-stage analysis. First, after a detailed evaluation, a global sensitivity analysis is performed to evaluate the sensitivity values of ten selected parameters across five intervals of discharge voltage curves simulated through the Doyle-Fuller-Newman theory. Such analysis facilitates the classification of these parameters into HS and low sensitive (LS) groups. Next, a deep learning (DL) model is developed for parameter identification, employing as minimal data as possible, specifically only partial discharge curves and their corresponding first-order derivatives, as inputs, while the electrochemical parameters are generated as outputs. It is found that utilizing the model built with the HS parameters achieves a remarkably low mean absolute percentage error (MAPE) of 0.25 % for output prediction. On the contrary, adopting the LS parameters yields a MAPE of 13.30 %, highlighting the significant impact of parameter sensitivity on the model outputs. Lastly, the well-trained DL model is directly applied to identify the five HS parameters pertaining to real-world commercial batteries, whose state of health spans approximately from 97 % down to 55 %. With the experimentally recorded partial discharge voltage data, the model generates the cycle evolutions of the HS parameters, revealing a noticeable decrease in their values ranging from 12 % to 40 % with aging.

Predicting the fetal weight by ultrasonography for isolated polyhydramnios: Comparison of 14 formulas.

To recalculate the estimated fetal weight (EFW) based on ultrasound measurements in patients complicated with isolated polyhydramnios, using 14 current formulas to observe which formula better predicts the EFW. This study examined pregnant women who gave birth in the hospital between January 2015 and January 2020. Maximum vertical pocket (MVP) was classified as, mild, moderate, and severe polyhydramnios, and the patients' measurements were reanalyzed using 14 formulas. The estimation of birth weight (EBW) alongside observed birth weight (OBW) facilitated the computation of statistical indices, namely the mean absolute percentage error (MAPE) expressed as [(EBW - OBW)/OBW × 100], the mean percentage error (MPE) denoted as (EBW - OBW)/(OBW × 100), and their corresponding 95% confidence intervals. A total of 564 polyhydramnios patients were included in the study. When looking at the MAPE, the lowest rate (7.65) was found in the Hadlock 2 formula. Hadlock 1, Hadlock 3, and Shinozuka formulas demonstrated MAPE values most closely aligned with Hadlock 2. Weiner I and Thurnau were the formulas with the highest MAPE values. When the cut-off values for MAPE were taken as 10%, 4/14 of the formulas (Weiner I-II, Vintzleos and Thurnau) gave results above 10%. Among 14 formulas, 3 (21.4%) had positive (sonographic overestimation) (Hadlock 3, Shinozuka, and Vintzleos) and the other 11 (78.6%) had negative MPE (sonographic underestimation). The Hadlock 2 formula had the lowest MAPE in predicting birth weight in patients with polyhydramnios, closely followed by the Hadlock 1, Hadlock 3, and Shinozuka formulas.

Short-Term Energy Forecasting to Improve the Estimation of Demand Response Baselines in Residential Neighborhoods: Deep Learning vs. Machine Learning

Promoting flexible energy demand through response programs in residential neighborhoods would play a vital role in addressing the issues associated with increasing the share of distributed solar systems and balancing supply and demand in energy networks. However, accurately identifying baseline-related energy measurements when activating energy demand response events remains challenging. In response, this study presents a deep learning-based, data-driven framework to improve short-term estimates of demand response baselines during the activation of response events. This framework includes bidirectional long-term memory (BiLSTM), long-term memory (LSTM), gated recurrent unit (GRU), convolutional neural networks (CNN), deep neural networks (DNN), and recurrent neural networks (RNN). Their performance is evaluated by considering different aggregation levels of the demand response baseline profile for 337 dwellings in the city of La Rochelle, France, over different time horizons, not exceeding 24 h. It is also compared with fifteen traditional statistical and machine learning methods in terms of forecasting accuracy. The results demonstrated that deep learning-based models, compared to others, significantly succeeded in minimizing the gap between the actual and forecasted values of demand response baselines at all different aggregation levels of dwelling units over the considered time-horizons. BiLSTM models, followed by GRU and LSTM, consistently demonstrated the lowest mean absolute percentage error (MAPE) in most comparison experiments, with values up to 9.08%, 8.71%, and 9.42%, respectively. Compared to traditional statistical and machine learning models, extreme gradient boosting (XGBoost) was among the best, with a value up to 11.56% of MAPE, but could not achieve the same level of forecasting accuracy in all comparison experiments. Such high performance reveals the potential of the proposed deep learning approach and highlights its importance for improving short-term estimates of future baselines when implementing demand response programs in residential neighborhood contexts.

Compressive behavior of sustainable rubberized concrete‐filled steel tube columns having various recycled tire rubber aggregate contents and developing a predictive design model

AbstractAs a sustainable solution, employing recycled tire rubber aggregates in the production of concrete is of considerable interest. However, the applicability of rubberized concretes in construction is restricted due to their relatively low mechanical performance. Using rubberized concrete as a filling material in a steel tube provides a suitable solution for overcoming this issue and for using it effectively as a load‐bearing element. The objective of this study is to examine the impact of the material characteristics of the sustainable rubberized concrete‐filled steel tube (Ru‐CFST) and develop a design model based on ultimate strength prediction for the axially loaded Ru‐CFST stub columns with varying contents of tire rubber aggregate. The model was developed through the gene expression programming (GEP) technique by employing the experimental test results to determine the ultimate compressive strength of Ru‐CFST columns. Based on the principal component analysis, the sectional properties of the load‐bearing element (such as outer diameter, thickness, and length), material strengths (such as rubberized concrete and steel tube strengths), and rubber content were determined as statistically significant parameters affecting the ultimate axial strength of Ru‐CFST stub columns and thus, they were considered in the stage of the model generation. Furthermore, the proposed model's performance was compared to that of available models suggested for traditional CFST columns by commonly employed design codes, namely, ACI, AIJ, AISC, CSA, EC4, and GB. Based on the statistical analysis of the results, it can be concluded that the existing formulations have a relatively acceptable randomness and scatter of observations within the distribution, while the proposed design model gives a more accurate prediction for the ultimate bearing capacity of axially loaded Ru‐CFST columns with the highest R‐squared value of about 0.99 and the comparatively lowest mean absolute percent error of 7.54. It can be stated that the proposed GEP‐based design model will encourage engineers to use such sustainable structural members in their designs and constructions.

A sensorless centrifugal pump operation states estimation method based on HSSA-BPNN

As a liquid transportation equipment, centrifugal pumps find extensive use in industrial process control. Certain environments involving high temperature, high pressure, and highly corrosive media may not permit the installation of flow and pressure sensors. Consequently, accurately estimating the operating status of centrifugal pumps in the absence of sensors has become a prominent research focus. However, the precision of existing sensorless estimation methods remains a concern. This study introduces a HSSA-BPNN model utilizing valve opening degree, motor rotational speed and shaft power as input variables. A hybrid strategy improved sparrow search algorithm (HSSA) is developed to optimize the back propagation neural network (BPNN). Experimental results demonstrate a low mean absolute percentage error (MAPE) of the test data, which are 2.2741% and 1.6502%, respectively. The absolute errors of flow rate and head are below 0.3 m3/h and 0.5 m, respectively, with relative errors less than 4% and 3%, meeting practical applications.

A sensorless centrifugal pump operation states estimation method based on HSSA-BPNN

As a liquid transportation equipment, centrifugal pumps find extensive use in industrial process control. Certain environments involving high temperature, high pressure, and highly corrosive media may not permit the installation of flow and pressure sensors. Consequently, accurately estimating the operating status of centrifugal pumps in the absence of sensors has become a prominent research focus. However, the precision of existing sensorless estimation methods remains a concern. This study introduces a HSSA-BPNN model utilizing valve opening degree, motor rotational speed and shaft power as input variables. A hybrid strategy improved sparrow search algorithm (HSSA) is developed to optimize the back propagation neural network (BPNN). Experimental results demonstrate a low mean absolute percentage error (MAPE) of the test data, which are 2.2741% and 1.6502%, respectively. The absolute errors of flow rate and head are below 0.3 m3/h and 0.5 m, respectively, with relative errors less than 4% and 3%, meeting practical applications.

A fused convolutional transformer for voltammetric electronic tongue analysis tasks

Electronic tongue and artificial intelligence have been evaluated as new rapid analysis technologies in complex solution research. The use of nanomaterials to modify the screen-printed carbon electrode (SPCE) increased the specific surface area and electrocatalytic active sites of the electrode. The voltammetric electronic tongue utilizes multiple cross sensitive sensors to describe the overall characteristics of complex samples, and the complementary information between sensors provides rich and comprehensive descriptions for analyzing various components. The use of electronic tongue for rapid analysis of water quality has gradually become a trend, but the overlapping phenomenon of peaks formed by the similar redox potential of each component in water and the interference of the substrate makes it difficult to obtain effective information of each component in water quality. Here, we propose a Fused Convolutional Transformer model (FCvT) that removes the limitation of overlapping peaks by fusing local features and global complementary features to quantify components in complex solutions. The performance of FCvT was evaluated by testing synthetic water samples consisting of four standardized substance solutions and compared with partial least squares (PLS), support vector regression (SVR), artificial neural networks (ANN), and convolutional neural networks (CNN). The results show that the FCvT obtains the lowest mean absolute percentage error in the set of independent tests.The average quantization error of FCvT is reduced by 34.4 % relative to other methods.

Peramalan Tingkat Penghunian Kamar Hotel Bintang Lima Provinsi Bali Menggunakan Metode ARIMA dan Fuzzy Time Series Lee

This research focuses on forecasting the Occupancy Rate of five-star hotels in the Province of Bali. The increase in Occupancy Rate directly impacts the increase in the number of hotel rooms, which is a key factor for Bali Province as a leading tourist destination in Indonesia and globally. The data used spans from November 2021 to November 2023, with the methods employed being ARIMA with a model of (1,1,1) and Fuzzy Time Series Lee. After conducting the research, the accuracy of the forecast is evaluated through Mean Absolute Percentage Error (MAPE). The MAPE for ARIMA (1,1,1) is found to be 71.4413, while the Fuzzy Time Series Lee method yields a MAPE of 1.1778. With a significantly lower MAPE, the Fuzzy Time Series Lee method is considered more accurate in forecasting the Occupancy Rate of five-star hotels in the Province of Bali for the December 2023 period, with a forecast result of 70.4033%.

Optimizing the deep learning parameters using metaheuristic algorithms for PV-battery-based DC nanogrids

This paper presents an implementation of metaheuristic algorithms to optimise deep learning neural networks (DNNs) for sensor-less control of photovoltaic (PV) Converters in DC nanogrids. Using a Fixed Forward Neural Network (FFNN), it estimates PV output current (IPV ) based on three days of real data. Given the vulnerability of current sensors in DC system measurements, accurately replicating current sensor data is vital. The data exhibits dynamic nonlinear relationships with inputs like solar irradiance, temperature, and voltage. The study assesses the effectiveness of Evolutionary Mating Algorithm (EMA) and Sand Cat Swarm Optimisation (SCSO), comparing them with Adaptive Moment Estimation (ADAM), Genetic Algorithm (GA), and Particle Swarm Optimisation (PSO). The research leverages these metaheuristic algorithms to optimise machine learning integration, addressing regression estimation problems, and enhancing system reliability by eliminating sensors. Key findings indicate that the EMA-DNN combination achieved remarkable performance, with the lowest Mean Squared Error (MSE) of 0.5906, the lowest Mean Absolute Error (MAE) of 0.4680, and the lowest Mean Absolute Percentage Error (MAPE) of 12.1780%. These results offer valuable insights into how the metaheuristic-DNN approach can solve regression estimation problems and reduce the number of sensors in PV battery-based nanogrids’ control layers.

Resting Energy Expenditure, comparison of predictive formulas with bioimpedance: Peruvian population

ntroduction: In areas with limited access to healthcare systems, Resting Energy Expenditure (REE) estimation is performed using predictive equations to calculate an individual’s caloric requirement. One problem is that these equations were validated in populations with different characteristics from those in Latin America, such as race, height, or body mass, leading to potential errors in the prediction of this parameter. Objective: To determine the REE using predictive formulas compared with bioimpedance in Peruvians. Materials and methods: A comparative analytical cross-sectional study with secondary database analysis of the CRONICAS cohort. Results: we worked with a total of 666 subjects. The Mjeor equation was the one with the highest rating of 0.95, a lower mean absolute percentage error (MAPE) of 4.69%, and equivalence was found with the REE values. In the multiple regression, it was observed that the Mjeor equation was the one that least overestimated the REE, increasing 0.77 Kcal/day (95% CI: 0.769-0.814; p<0.001) for each point that increased the REE determined by bioimpedance. The strength of association between Mjeor and bioimpedance was 0.9037. Furthermore, in the regression of the data (weight, height, age) in the Mjeor equation it was observed that the coefficients obtained were the same as those used in the original equation. Conclusions: The Mjeor equation seems to be the most adequate to estimate the REE in the Peruvian population. Future prospective studies should confirm the usefulness of this formula with potential utility in primary health care.

Machine learning based data governance methods for demand response databases

With the increasing level of grid intelligence and the related demand response database expanding, it is important to study a compound problem data governance method for demand response, while the traditional data governance methods have problems such as not considering data temporality and ignoring the impact of noise and duplicate data on data repair. As a result, this project will develop an anomaly data extraction and repair model based on two-way long and short memory networks, and repair the anomaly data by respective noise smoothing, missing data filling, and duplicate data cleaning. The paper also provides an adaptive moment estimation approach for optimisation to raise the model’s accuracy. The outcomes demonstrated that the study model’s precision for anomalous data extraction was 100% and its recall rate was 80%, which was a significant improvement over the previous state. In terms of anomalous data repair, the research model had the root mean square error value and lowest mean absolute percentage error value when compared with related models, at 0.0049 MPa and 1.375% respectively. Both the abnormal data extraction and repair performance of the research model are greatly improved over the related models, and have important value in the abnormal data governance of demand response databases.

Accurate Prediction Equations for Ventilatory Thresholds in Cardiometabolic Disease When Gas Exchange Analysis is Unavailable: Development and Validation.

To develop and validate equations predicting heart rate (HR) at the first and second ventilatory thresholds (VTs) and an optimized range-adjusted prescription for patients with cardiometabolic disease (CMD). To compare their performance against guideline-based exercise intensity domains. Cross-sectional study involving 2,868 CMD patients from nine countries. HR predictive equations for first and second VTs (VT1, VT2) were developed using multivariate linear regression with 975 cycle-ergometer cardiopulmonary exercise tests (CPET). 'Adjusted' percentages of peak HR (%HRpeak) and HR reserve (%HRR) were derived from this group. External validation with 1,893 CPET (cycle-ergometer or treadmill) assessed accuracy, agreement, and reliability against guideline-based %HRpeak and %HRR prescriptions using mean absolute percentage error (MAPE), Bland-Altman analyses, intraclass correlation coefficients (ICC). HR predictive equations (R²: 0.77 VT1, 0.88 VT2) and adjusted %HRR (VT1: 42%, VT2: 77%) were developed. External validation demonstrated superiority over widely used guideline-directed intensity domains for %HRpeak and %HRR. The new methods showed consistent performance across both VTs with lower MAPE (VT1: 7.1%, VT2: 5.0%), 'good' ICC for VT1 (0.81, 0.82) and 'excellent' for VT2 (0.93). Guideline-based exercise intensity domains had higher MAPE (VT1: 6.8%-21.3%, VT2: 5.1%-16.7%), 'poor' to 'good' ICC for VT1, and 'poor' to 'excellent' for VT2, indicating inconsistencies related to specific VTs across guidelines. Developed and validated HR predictive equations and the optimized %HRR for CMD patients for determining VT1 and VT2 outperformed the guideline-based exercise intensity domains and showed ergometer interchangeability. They offer a superior alternative for prescribing moderate intensity exercise when CPET is unavailable.

Long-term solar radiation forecasting based on LSTM and attention mechanism: a case study in Algeria

The growing adoption of photovoltaic (PV) energy in urban areas underscores its capability to meet energy demands effectively. The accurate forecasting of meteorological parameters, particularly global solar radiation, is paramount for the efficient management and utilization of solar energy resources. Solar radiation forecasting methods typically fall into two main categories: cloud imagery combined with physical approaches, and Artificial Intelligence (AI) based methods. Due to the non-stationary nature of solar radiation and the high nonlinearity of atmospheric conditions, conventional forecasting approaches often exhibit poor accuracy. Artificial intelligence based approaches, such as machine learning and deep learning algorithms, are extensively employed in global solar radiation forecasting research, demonstrating impressive accuracy. In this respect, this paper presents a novel approach for long term monthly forecasting of global solar radiation using a Bidirectional Long Short-Term Memory (LSTM) architecture augmented with an attention mechanism that includes a Squeeze and Excitation (SE) block (SE-BiLSTM). The effectiveness of this model is extensively evaluated for long-term monthly solar radiation forecasting using meteorological data collected over a 20-year period (from Jan 2001 to Dec 2020) from the National Aeronautics and Space Administration (NASA). The proposed SE-BiLSTM model is compared with well-established forecasting models including Naïve, Autoregressive Moving Average (ARMA), Multi-layer Perceptron (MLP), LSTM, and Bidirectional LSTM. Through rigorous simulation tests, our model demonstrates superior performance, achieving the lowest mean absolute percentage error (MAPE) of 4.52% and mean absolute error (MAE) of 7.89 kW/m2. This advancement holds significant promise for enhancing solar energy forecasting accuracy and its practical application in renewable energy systems.

An integrated machine learning and metaheuristic approach for advanced packed bed latent heat storage system design and optimization

To tackle the challenge of waste heat recovery in the industrial sector, this research presents a novel design and optimization framework for Packed Bed Latent Heat Storage Systems (PBLHS). This features a Deep Learning (DL) model, integrated with metaheuristic algorithms. The DL model was developed to predict PBLHS performance, trained using data generated from a validated Computational Fluid Dynamics (CFD) model. The model exhibited a high performance with an R2 value of 0.975 and a low Mean Absolute Percentage Error (<9.14%). To enhance the ML model's efficiency and optimized performance, various metaheuristic algorithms were explored. The Harmony Search algorithm emerged as the most effective through an early screening and underwent further refinement. The optimized algorithm demonstrated its capability by rapidly producing designs that showcased an improvement in total efficiency of up to 85% over available optimized experimental PBLHS designs. This research underscores the potential of ML-integrated approaches in laying the groundwork for generalized design frameworks for TES systems, offering efficient and effective solutions for waste heat recovery.

Empowering Sustainability: A Consumer-Centric Analysis Based on Advanced Electricity Consumption Predictions

This study addresses the critical challenge of accurately forecasting electricity consumption by utilizing Exponential Smoothing and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. The research aims to enhance the precision of forecasting in the dynamic energy landscape and reveals promising outcomes by employing a robust methodology involving model application to a large amount of consumption data. Exponential Smoothing demonstrates accurate predictions, as evidenced by a low Sum of Squared Errors (SSE) of 0.469. SARIMA, with its seasonal ARIMA structure, outperforms Exponential Smoothing, achieving lower Mean Absolute Percentage Error (MAPE) values on both training (2.21%) and test (2.44%) datasets. This study recommends the adoption of SARIMA models, supported by lower MAPE values, to influence technology adoption and future-proof decision-making. This study highlights the societal implications of informed energy planning, including enhanced sustainability, cost savings, and improved resource allocation for communities and industries. The synthesis of model analysis, technological integration, and consumer-centric approaches marks a significant stride toward a resilient and efficient energy ecosystem. Decision-makers, stakeholders, and researchers may leverage findings for sustainable, adaptive, and consumer-centric energy planning, positioning the sector to address evolving challenges effectively and empowering consumers while maintaining energy efficiency.

A Comparison of Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) in River Water Quality Prediction

River water is a crucial natural resource utilized for various purposes, including agriculture and drinking. Human activities such as mining, industrial discharge, and improper waste management contribute to river water pollution, affecting its quality and posing risks to human health. Monitoring and predicting river water quality are essential for effective management and pollution control. The research focuses on Dissolved Oxygen (DO), and comparing of Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) to developed prediction models. Evaluation of the models’ performance shows that the ANN model outperforms LSTM in predicting Dissolved Oxygen (DO) concentrations, achieving lower Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Although LSTM exhibits lower Mean Squared Error (MSE), the ANN model demonstrates better accuracy in minimizing the average distance between predicted and actual values. The findings suggest that ANN-based models offer good performance in river water quality prediction, with potential for further enhancement through additional variables or model architecture adjustments.

Comparison of different strategies for operating a solar-assisted ground-source CO2 heat pump system for space and water heating

This study quantifies and compares operational strategies as applied on a solar-assisted ground-source trans-critical CO2 heat pump (CO2 SAGSHP) system for simultaneous space and water heating, optimized on an hourly basis over the course of a week. Four (4) boundary conditions, representing spring, summer, autumn, and winter, were considered. To enable the use of a dynamic model for optimization simulations, the use of a previously developed surrogate Artificial Neural Network (ANN) model of a Modelica CO2 heat pump model was evaluated for use in this study. The simulation results from the system model that applies the surrogate ANN model demonstrated strong alignment with those generated by the full Modelica model, yielding low root mean square errors and mean absolute percentage errors. Furthermore, it accelerated the speed of results generation for a single forward run by 6–15 times, depending on the boundary conditions. It can be inferred from the results of the optimization runs that when warm climate conditions dominate, implementation of the on/off operation with thermal energy storage (TES) should be prioritized, given that it could potentially yield greater operational cost benefits (12% to 58 % cost reduction) compared to hourly discharge pressure optimization (0.5 to 1.5 % cost reduction). Conversely, when colder seasons are longer, optimizing the CO2 heat pump's discharge pressure becomes more practical (6.5 % to 6.9 % cost reduction) than on/off operation, particularly when only a small TES is installed (1.2 % to 2.6 % cost reduction). The optimization of the mass flow rate of the supply side working fluid of a CO2 SAGSHP system exhibited minimal benefit, except notably in the summer where it generated an even better cost reduction than controlling the discharge pressure. This shows the practicality of this strategy for conditions where relatively high solar irradiation and relatively low heat demand are concurrently expected. In general, weekly reductions in operational costs were more substantial when both the discharge pressure and the on/off operation of the CO2 heat pump were concurrently optimized, especially when using a larger TES tank. Hence, both should be applied if there are no practical or cost limitations that restrict their implementation. While previous studies on CO2 heat pumps primarily emphasized efficiency optimization via discharge pressure control, this study shows that comparable or greater operational cost reductions can also be achieved from other strategies, depending on the boundary conditions.

Enhancing Demand Forecasting Accuracy for Electronic Components: A Case Study of PT Omron Indonesia

In the dynamic realm of manufacturing, precise demand forecasting is crucial for optimizing supply chains and production processes. This study addresses PT Omron Indonesia's challenge of inaccurate demand forecasts leading to production disruptions. Utilizing the Plan-Do-Study-Act (PDSA) cycle, alongside Multiplicative Decomposition methods, the research aims to improve forecasting accuracy. Results indicate that the Multiplicative Decomposition - Centered Moving Average method yields a lower Mean Absolute Percentage Error (MAPE), though refinement is needed to meet set standards. The estimated demand for the next period is 1308 units, with a MAPE of 140%. The study concludes that iterative refinement of the selected method is essential for achieving higher forecasting accuracy. This research contributes to enhancing production efficiency and mitigating the impact of part shortages in the electronics industry.

Maximizing heat transfer potential with graphene nanofluids along with structured copper surfaces for pool boiling

Increasing the demand and depletion of energy sources confront every technological development with energy conversation and its utilization. Boiling heat transfer is the most applicable heat transfer method in many industries, from electronic chip manufacturing to heavy nuclear power plants. Hence, the augmentation of it is of prime importance for future requirements. The present investigation focused on the augmentation of boiling heat transfer by considering a novel V-pattern staggered copper surface for pool boiling in graphene nanofluid media. The study encompasses a detailed exploration of nanofluid concentrations ranging from 0.1% to 0.40 vol% prepared in equal volumes of dimethylformamide and distilled water. The nanofluid's stability is observed to be quite promising, and the results are presented. The wall superheat was drastically reduced to 48.73%, and the maximum heat transfer coefficient enhancement of 83.47% was achieved for 0.04% concentration of graphene nanofluid with a V-pattern surface compared to a smooth copper surface with water. This is due to the micro-level structured convection patterns promoted by the microstructures. The thermophysical properties of nanofluid and peculiar microstructures enhanced the relative heat transfer coefficient by 63.37%. On the other hand, two popular machine learning models, Random Forest Regression (RFR) and Multi-Layer Perceptron (MLP), are used to predict the boiling heat transfer coefficient. Moreover, it is observed that the RFR model fitted the data well and yielded the lowest mean absolute percentage error within the bounds of computational time.

Validity of iPhone health application step count in semi free-living conditions

The iPhone’s validity for measuring steps has been mainly investigated under laboratory conditions, while studies that include real-world conditions are still scarce. We examined the validity of iPhones in measuring steps in real-world walking conditions, while using direct observation with video as reference. A sample of 100 adults who owned an iPhone 5S or higher was included and participants were randomly allocated to one of two protocols. Limits of Agreement (LoA), Mean Absolute Percentage Error (MAPE), linear-regression and Bland-Altman analyses were carried out. In Protocol-1, which includes straight-line and zigzag conditions, we observed a low MAPE lower than 4%. Bland-Altman analyses assessed a high accordance of approximately 6 steps under both conditions. Differences between the iPhone and direct observation were only noticeable in straight-line condition (p = 0.002). Likewise, protocol-2 (three 50-step conditions: an upward 5 % slope, a flat surface, and a downward -5% slope) showed low MAPE values (3.78 %) for the upward slope, 2.41 % for the downward slope, and 2.37 % in absence of slope), and differences between the iPhone and direct observation were only observed for the downward slope (p = 0.017), with the iPhone overestimating. Our findings revealed that iPhone might be a reliable tool for monitoring walking in real-life conditions, however, downward slope seems to generate overestimation, which deserves future investigation.