Mean Average Error Research Articles

Computer vision digitization of smartphone images of anesthesia paper health records from low-middle income countries

BackgroundIn low-middle income countries, healthcare providers primarily use paper health records for capturing data. Paper health records are utilized predominately due to the prohibitive cost of acquisition and maintenance of automated data capture devices and electronic medical records. Data recorded on paper health records is not easily accessible in a digital format to healthcare providers. The lack of real time accessible digital data limits healthcare providers, researchers, and quality improvement champions to leverage data to improve patient outcomes. In this project, we demonstrate the novel use of computer vision software to digitize handwritten intraoperative data elements from smartphone photographs of paper anesthesia charts from the University Teaching Hospital of Kigali. We specifically report our approach to digitize checkbox data, symbol-denoted systolic and diastolic blood pressure, and physiological data.MethodsWe implemented approaches for removing perspective distortions from smartphone photographs, removing shadows, and improving image readability through morphological operations. YOLOv8 models were used to deconstruct the anesthesia paper chart into specific data sections. Handwritten blood pressure symbols and physiological data were identified, and values were assigned using deep neural networks. Our work builds upon the contributions of previous research by improving upon their methods, updating the deep learning models to newer architectures, as well as consolidating them into a single piece of software.ResultsThe model for extracting the sections of the anesthesia paper chart achieved an average box precision of 0.99, an average box recall of 0.99, and an mAP0.5-95 of 0.97. Our software digitizes checkbox data with greater than 99% accuracy and digitizes blood pressure data with a mean average error of 1.0 and 1.36 mmHg for systolic and diastolic blood pressure respectively. Overall accuracy for physiological data which includes oxygen saturation, inspired oxygen concentration and end tidal carbon dioxide concentration was 85.2%.ConclusionsWe demonstrate that under normal photography conditions we can digitize checkbox, blood pressure and physiological data to within human accuracy when provided legible handwriting. Our contributions provide improved access to digital data to healthcare practitioners in low-middle income countries.

Comparing the performance of pediatric weight estimation methods

BackgroundWeight estimation is essential in the care of ill children when a weight cannot be obtained. This is particularly important for children with medical complexity, who are at higher risk for adverse drug events. Our objective was to compare the accuracy of different methods of weight estimation in children and stratify by the presence of medical complexity. MethodsWe performed a retrospective cross-sectional study of children (<18 years) seen in the emergency department (ED) or ambulatory clinic from January 1, 2013 to December 31, 2022 at a tertiary academic pediatric center. We compared the performance of nine age-based formulae and two length-based methods using metrics of mean average error (MAE), root mean square error (RMSE), and agreement within 10% and 20% of measured weight. We additionally evaluated the approaches stratified by body mass index (BMI) and the presence of medical complexity. ResultsOf 361,755 children (median age 8.2 years, IQR 2.5–14.2 years; 51.5% male), 59,283 (16.4%) were seen in the ED. Length was measured or available in 21,330 (36.0%) patients in the ED and 293,410 (97%) patients in clinics. The Broselow tape outperformed all methods, with 50.7% estimates within 10% of measured weight, 80.0% estimates within 20% of measured weight, the lowest MAE (2.5 kg), and lowest RMSE (4.5 kg). The Antevy formula was the most accurate age-based formula, with 49.2% estimates within 10% of measured weight, 80.1% estimates within 20% of measured weight, MAE of 2.8 kg, and RMSE of 4.7 kg. Estimates became less accurate as BMI and estimated weight increased for all methods. Among children with medical complexity (14.1%), the Broselow tape consistently outperformed age-based formulae, with 47.7% estimates within 10% of measured weight, 77.1% estimates within 20% of measured weight, MAE of 2.6 kg, and RMSE of 5.4 kg. The Antevy formula remained the most accurate age-based method among children with medical complexity. ConclusionThe Broselow tape predicted weight most accurately in this large sample of children, including among those with medical complexity. The Antevy formula is the most accurate age-based method for pediatric weight estimation.

Machine learning assisted 5-part tooth segmentation method for CBCT-based dental age estimation in adults.

The utilization of segmentation method using volumetric data in adults dental age estimation (DAE) from cone-beam computed tomography (CBCT) was further expanded by using current 5-Part Tooth Segmentation (SG) method. Additionally, supervised machine learning modelling -namely support vector regression (SVR) with linear and polynomial kernel, and regression tree - was tested and compared with the multiple linear regression model. CBCT scans from 99 patients aged between 20 to 59.99 was collected. Eighty eligible teeth including maxillary canine, lateral incisor, and central incisor were used in this study. Enamel to dentine volume ratio, pulp to dentine volume ratio, lower tooth volume ratio, and sex was utilized as independent variable to predict chronological age. No multicollinearity was detected in the models. The best performing model comes from maxillary lateral incisor using SVR with polynomial kernel ( = 0.73). The lowest error rate achieved by the model was given also by maxillary lateral incisor, with 4.86 years of mean average error and 6.05 years of root means squared error. However, demands a complex approach to segment the enamel volume in the crown section and a lengthier labour time of 45 minutes per tooth.

Performance analysis of a blockchain enabled domestic power consumption monitoring and forecasting system

Purpose The purpose of this paper is to develop a blockchain-based data capture and transmission system that will collect real-time power consumption data from a household electrical appliance and transfer it securely to a local server for energy analytics such as forecasting. Design/methodology/approach The data capture system is composed of two current transformer (CT) sensors connected to two different electrical appliances. The CT sensors send the power readings to two Arduino microcontrollers which in turn connect to a Raspberry-Pi for aggregating the data. Blockchain is then enabled onto the Raspberry-Pi through a Java API so that the data are transmitted securely to a server. The server provides real-time visualization of the data as well as prediction using the multi-layer perceptron (MLP) and long short term memory (LSTM) algorithms. Findings The results for the blockchain analysis demonstrate that when the data readings are transmitted in smaller blocks, the security is much greater as compared with blocks of larger size. To assess the accuracy of the prediction algorithms data were collected for a 20 min interval to train the model and the algorithms were evaluated using the sliding window approach. The mean average percentage error (MAPE) was used to assess the accuracy of the algorithms and a MAPE of 1.62% and 1.99% was obtained for the LSTM and MLP algorithms, respectively. Originality/value A detailed performance analysis of the blockchain-based transmission model using time complexity, throughput and latency as well as energy forecasting has been performed.

Automatic simulation of electrochemical sensors by machine learning for drugs quantification

Multiple drug concentrations concurrent detection and quantification based on electrochemical sensors are of great importance for therapeutic drug monitoring (TDM) and the development of personalized therapy. Cyclic voltammogram (CV) results obtained by electrochemical sensors can be used to offer quantitative information about drug concentrations. Several approaches have been proposed for single-concentration quantification based on CV results and machine learning (ML) models with lower training difficulty. However, insufficient measured dataset hinders the application of diverse large-scale ML algorithms in this field. A new method for automatic parameter estimation by ML of measured CV samples is here illustrated with the aim to generate a large simulated dataset for generalized drug concentration quantification model training in this paper. We present an ML-based approach that combines k-means clustering, polynomial regression, and Gaussian Mixture Model (GMM), which automates parameter estimation and simulation using peak detection, baseline subtraction, and peak Gaussian fitting with a small number of measurements. Large simulation datasets constructed on the basis of the estimation results open the possibility of training ML models for more generalized drug concentration quantification. The simulated dataset is processed to assess the efficiency of the proposed method. The Mean Average Percentage Error (MAPE) was 0.32% for etoposide (ETO) and 4.78% for methotrexate (MTX).

Prediction of Total Petroleum Hydrocarbons and Heavy Metals in Acid Tars Using Machine Learning

Hazardous petroleum wastes are an inevitable source of environmental pollution. Leachates from these wastes could contaminate soil and potable water sources and affect human health. The management of acid tars, as a byproduct of refining and petrochemical processes, represented one of the major hazardous waste problems in Romania. Acid tars are hazardous and toxic waste and have the potential to cause pollution and environmental damage. The need for the identification, study, characterization, and subsequently either the treatment, valorization, or elimination of acid tars is determined by the fact that they also have high concentrations of hydrocarbons and heavy metals, toxic for the storage site and its neighboring residential area. When soil contamination with acid tars occurs, sustainable remediation techniques are needed to restore soil quality to a healthy production state. Therefore, it is necessary to ensure a rapid but robust characterization of the degree of contamination with hydrocarbons and heavy metals in acid tars so that appropriate techniques can then be used for treatment/remediation. The first stage in treating these acid tars is to determine its properties. This article presents a software program that uses machine learning to estimate selected properties of acid tars (pH, Total Petroleum Hydrocarbons—TPH, and heavy metals). The program uses the Automatic Machine Learning technique to determine the Machine Learning algorithm that has the lowest estimation error for the given dataset, with respect to the Mean Average Error and Root Mean Squared Error. The chosen algorithm is used further for properties estimation, using the R2 correlation coefficient as a performance criterion. The dataset used for training has 82 experimental points with continuous, unique values containing the coordinates and depth of acid tar samples and their properties. Based on an exhaustive search performed by the authors, a similar study that considers machine learning applications was not found in the literature. Further research is required because the method presented therein can be improved because it is dataset dependent, as is the case with every ML problem.

Neural networks as effective surrogate models of radio-frequency quadrupole particle accelerator simulations

Radio-frequency quadrupoles (RFQs) are multi-purpose linear particle accelerators that simultaneously bunch and accelerate charged particle beams. They are ubiquitous in accelerator physics, especially as injectors to higher-energy machines, owing to their impressive efficiency. The design and optimization of these devices can be lengthy due to the need to repeatedly perform high-fidelity simulations. Several recent papers have demonstrated that machine learning can be used to build surrogate models (fast-executing replacements of computationally costly beam simulations) for order-of-magnitude computing time speedups. However, while these pilot studies are encouraging, there is room to improve their predictive accuracy. Particularly, beam summary statistics such as emittances (an important figure of merit in particle accelerator physics) have historically been challenging to predict. For the first time, we present a surrogate model trained on 200 000 samples that yields < 6% mean average percent error for the predictions of all relevant beam output parameters from defining RFQ design parameters, solving the problem of poor emittance predictions by identifying and including hidden variables which were not accounted for previously. These surrogate models were made possible by using the Julia language and GPU computing; we briefly discuss both. We demonstrate the utility of surrogate modeling by performing a multi-objective optimization using our best model as a callback in the objective function to select an optimal RFQ design. We consider trade-offs in RFQ performance for various choices of Pareto-optimal design variables—common issues for any multi-objective optimization scheme. Lastly, we make recommendations for input data preparation, selection, and neural network architectures that pave the way for future development of production-capable surrogate models for RFQs and other particle accelerators.

Machine Learning Algorithms for Power System Sign Classification and a Multivariate Stacked LSTM Model for Predicting the Electricity Imbalance Volume

The energy transition to a cleaner environment has been a concern for many researchers and policy makers, as well as communities and non-governmental organizations. The effects of climate change are evident, temperatures everywhere in the world are getting higher and violent weather phenomena are more frequent, requiring clear and firm pro-environmental measures. Thus, we will discuss the energy transition and the support provided by artificial intelligence (AI) applications to achieve a cleaner and healthier environment. The focus will be on applications driving the energy transition, the significant role of AI, and collective efforts to improve societal interactions and living standards. The price of electricity is included in almost all goods and services and should be affordable for the sustainable development of economies. Therefore, it is important to model, anticipate and understand the trend of electricity markets. The electricity price includes an imbalance component which is the difference between notifications and real-time operation. Ideally it is zero, but in real operation such differences are normal due to load variation, lack of renewable energy sources (RES) accurate prediction, unplanted outages, etc. Therefore, additional energy has to be produced or some generating units are required to reduce generation to balance the power system. Usually, this activity is performed on the balancing market (BM) by the transmission system operator (TSO) that gathers offers from generators to gradually reduce or increase the output. Therefore, the prediction of the imbalance volume along with the prices for deficit and surplus is of paramount importance for producers’ decision makers to create offers on the BM. The main goal is to predict the imbalance volume and minimize the costs that such imbalance may cause. In this chapter, we propose a method to predict the imbalance volume based on the classification of the imbalance sign that is inserted into the dataset for predicting the imbalance volume. The imbalance sign is predicted using several classifiers and the output of the classification is added to the input dataset. The rest of the exogenous variables are shifted to the values from previous day d − 1. Therefore, the input variables are either predicted (like the imbalance sign) or are known from d − 1. Several metrics, such as mean average percentage error (MAPE), determination coefficient R2 and mean average error (MAE) are calculated to assess the proposed method of combining classification machine learning (ML) algorithms and recurrent neural networks (RNN) that memorize variations, namely long short-term memory (LSTM) model.

Deep Learning Method for Improving Rate of Penetration Prediction in Drilling

Summary The urgent global need to reduce CO2 emissions necessitates the development of sustainable power generation sources. Geothermal power emerges as a renewable and dependable energy option, harnessing the Earth’s natural heat sources for electricity generation. Unlike other renewables, geothermal energy offers uninterrupted power, immune to weather conditions. However, its efficiency hinges on technological innovation, particularly in the challenging realm of geothermal drilling. Rate of penetration (ROP) is a crucial drilling performance metric, and this study explores how deep learning models, particularly transformers, can optimize ROP prediction. Leveraging data from Utah Frontier Observatory for Research in Geothermal Energy (FORGE), we analyze the relationship between drilling parameters and ROP. Traditional drilling optimization methods face limitations, as drilling dysfunctions can disrupt the linear relationship between ROP and weight on bit (WOB). We propose a dynamic approach that allows adapting drilling parameters in real time to optimize ROP. Our experiments investigate optimal sampling intervals and forecast horizons for ROP prediction. We find that a 60-second sampling interval maximizes the transformer model’s forecasting accuracy. Additionally, we explore retraining to fine-tune models for specific wells, improving forecasting performance. Our transformer-based ROP forecaster outperforms deep learning models, achieving a low overall 5.22% symmetrical mean average percentage error (SMAPE) over a forecast horizon of 10 minutes. This model offers opportunities for cost-effective drilling optimization, with real-time accuracy, speed, and scalability. Future work will focus on larger data sets and integration with drilling automation systems to further enhance the model’s practicality and effectiveness in the field.

Wildfire Prediction in the United States Using Time Series Forecasting Models

Wildfires are a widespread phenomenon that affects every corner of the world with the warming climate. Wildfires burn tens of thousands of square kilometres of forests and vegetation every year in the United States alone with the past decade witnessing a dramatic increase in the number of wildfire incidents. This research aims to understand the regions of forests and vegetation across the US that are susceptible to wildfires using spatiotemporal kernel heat maps and, forecast these wildfires across the United States at country-wide and state levels on a weekly and monthly basis in an attempt to reduce the reaction time of the suppression operations and effectively design resource maps to mitigate wildfires. We employed the state-of-the-art Neural Basis Expansion Analysis for Time Series (N-BEATS) model to predict the total area burned by wildfires by several weeks and months into the future. The model was evaluated based on forecasting metrics including mean-squared error (MSE)., and mean average error (MAE). The N-BEATS model demonstrates improved performance compared to other state-of-the-art (SOTA) models, obtaining MSE values of 116.3, 38.2, and 19.0 for yearly, monthly, and weekly forecasting, respectively.

Handling of problematic ion chromatograms with the Automated Target Screening (ATS) workflow for unsupervised analysis of high-resolution mass spectrometry data

Liquid chromatography (LC) or gas chromatography (GC) coupled to high-resolution mass spectrometry (HRMS) is a versatile analytical method for the analysis of thousands of chemical pollutants that can be found in environmental and biological samples. While the tools for handling such complex datasets have improved, there are still no fully automated workflows for targeted screening analysis. Here we present an R-based workflow that is able to cope with challenging data like noisy ion chromatograms, retention time shifts, and multiple peak patterns. The workflow can be applied to batches of HRMS data recorded after GC with electron ionization (GC-EI) and LC coupled to electrospray ionization in both negative and positive mode (LC-ESIneg/LC-ESIpos) to perform peak annotation and quantitation fully unsupervised. We used Orbitrap HRMS data of surface water extracts to compare the Automated Target Screening (ATS) workflow with data evaluations performed with the vendor software TraceFinder and the established semi-automated analysis workflow in the MZmine software. The ATS approach increased the overall evaluation performance of the peak annotation compared to the established MZmine module without the need for any post-hoc corrections. The overall accuracy increased from 0.80 to 0.86 (LC-ESIpos), from 0.77 to 0.83 (LC-ESIneg), and from 0.67 to 0.76 (GC-EI). The mean average percentage errors for quantification of ATS were around 30% compared to the manual quantification with TraceFinder. The ATS workflow enables time-efficient analysis of GC- and LC-HRMS data and accelerates and improves the applicability of target screening in studies with a large number of analytes and sample sizes without the need for manual intervention.Graphical

An empirical confinement model for ANFO explosive

AbstractAmmonium‐nitrate‐fuel‐oil (ANFO) explosive, one of the most used mining explosives, exhibits highly non‐ideal behaviour. The non‐ideality of the detonation is manifested in the strong dependence of the detonation velocity on the charge radius and existence and the characteristics of confinement. This can lead to the detonation velocities as low as one‐third of the ideal velocity. The literature reported experimental detonation velocities of cylindrical ANFO charges confined in different confiners (aluminium, copper, steel, polymethyl methacrylate, and polyvinyl chloride) are analysed in this paper. An empirical confinement model, which relates the detonation velocity to the charge radius and the mass of the confiner to the mass of explosive ratio per unit length, is proposed. The model predicts the detonation velocity of unconfined and confined ANFO charges with a mean average percentage error of 8.8 %.

Construction of mathematical model for integration of engineering cost prediction and multiple algorithms

As a key link in engineering construction, reasonable evaluation of engineering cost can effectively control the budget and save costs. Therefore, the reliability of the engineering cost estimation will directly affect the economic status of the whole project. However, traditional prediction models are based on a single machine learning method, which is not generalized enough and has low accuracy. In view of this, a mathematical model for engineering cost prediction is constructed by combining a random forest algorithm, ridge regression algorithm, and extreme gradient boosting (XG Boost) algorithm to obtain a prediction model with higher generalization and accuracy, and to evaluate the cost of engineering projects reasonably and scientifically. The average relative error between predicted and actual values was only 0.872%. The root mean square error and average percentage error of the fusion model were relatively small. The superiority of the proposed mathematical model of prediction cost is verified, and the model possesses a certain application value in construction engineering, providing practical reference and guidance for engineering cost prediction.

Approaches to simplify industrial energy models for operational optimisation

Minimising energy consumption in today's industrial sector is a crucial objective for achieving established climate goals. One effective strategy to enhance efficiency is optimising energy system operations within industries. The initial step in establishing operational optimisation involves developing a comprehensive model of the energy system. This model necessitates a specific structure to meet optimisation requirements. However, creating a model from scratch incurs substantial effort. While numerous companies possess energy models, they often lack the requisite structure for optimisation. Consequently, simplifying existing models can significantly reduce the effort needed to implement operational optimisation.This paper investigates the simplification of intricate industrial energy system models for optimisation purposes. The subsequent sections analyse two distinct approaches. One approach involves linearisation, while the other utilises neural networks. To facilitate a comparative analysis of these approaches, a reference model is developed. The assessment of these methodologies includes an investigation into optimisation robustness, computation time, accuracy concerning the reference model, and the effort required for developing and maintaining the simplified models. It proved that both approaches are suitable for operational optimisation. Linearisation exhibits superior computational efficiency compared to the neural network approach. The linearisation modelling approach together with the optimisation only required a few milliseconds for the calculation. The neural network approach needed 3 h for the calculation of the optimum with the genetic algorithm. The simulation of the neural network itself only required a few milliseconds. Hence, an improvement of the genetic algorithm is needed. However, the accuracy of linearisation falls short of that achieved by neural networks. The linearisation achieves a mean average percentage error from only 13%. In comparison the neural network's mean average error is 2.3%. Therefore, the linearisation must be improved. The impact using a piecewise linearisation on the results will be analysed in further research.

Multi-camera tracking of mechanically thrown objects for automated in-plant logistics by cognitive robots in Industry 4.0

AbstractEmploying cognitive robots, capable of throwing and catching, is a strategy aimed at expediting the logistics process within Industry 4.0’s smart manufacturing plants, specifically for the transportation of small-sized manufacturing parts. Since the flight of mechanically thrown objects is inherently unpredictable, it is crucial for the catching robot to observe the initial trajectory with utmost precision and intelligently forecast the final catching position to ensure accurate real-time grasping. This study utilizes multi-camera tracking to monitor mechanically thrown objects. It involves the creation of a 3D simulation that facilitates controlled mechanical throwing of objects within the internal logistics environment of Industry 4.0. The developed simulation empowers users to define the attributes of the thrown object and capture its trajectory using a simulated pinhole camera, which can be positioned at any desired location and orientation within the in-plant logistics environment of flexible manufacturing systems. The simulation facilitated ample experimentation to be conducted for determining the optimal camera positions for accurately observing the 3D interception positions of a flying object based on its apparent size on the camera’s sensor plane. Subsequently, a variety of calibrated multi-camera setups were experimented while placing cameras at identified optimal positions. Based on the obtained results, the most effective multi-camera configuration setup is derived. Finally, a training dataset is prepared for 3000 simulated throwing experiments where the initial part of the trajectory consists of observed interception positions, through derived best multi-camera setup, and the final part consists of actual positions. The encoder–decoder Bi-LSTM deep neural network is proposed and trained on this dataset. The trained model outperformed the current state-of-the-art by accurately predicting the final 3D catching point, achieving a mean average error of 5 mm and a root-mean-square error of 7 mm in 200 real-world test experiments.

Trend-attribute forecasting of hourly PM2.5 trends in fifteen cities of Central England applying optimized machine learning feature selection

Recorded particulate matter (PM2.5) hourly trends are compared for fifteen urban recording sites distributed across central England for the period 2018 to 2022. They include 10 urban-background and five urban-traffic (roadside) sites with some located within the same urban area. The sites all show consistent background and peak distributions with mean annual values and standard deviations higher for 2018 and 2019 than for 2020 to 2022. The objective of this study is to demonstrate that trend attributes extracted from hourly recorded univariate PM2.5 trends at these sites can be used to provide reliable short-term hourly predictions and provide valuable insight into the regional variations in the recorded trends. Fifteen trend attributes extracted from the prior 12 h (t-1 to t-12) of recorded PM2.5 data were compiled and used as input to four supervised machine learning models (SML) to forecast PM2.5 concentrations up to 13 h ahead (t0 to t+12). All recording sites delivered forecasts with similar ranges of error levels for specific hours ahead which are consistent with their PM2.5 recorded ranges. Forecasting results for four representative sites are presented in detail using models trained and cross-validated with 2020 and 2021 hourly data to forecast 2021 and 2022 hourly data, respectively. A novel optimized feature selection procedure using a suite of five optimizers is used to improve the efficiency of the forecasting models. The LASSO and support vector regression models generate the best and most generalizable hourly PM2.5 forecasts from trained and validated SML models with mean average error (MAE) of between ∼1 and ∼3 μg/m3 for t0 to t+3 h ahead. A novel overfitting indicator, exploiting the cross-validation mean values, demonstrates that these two models are not affected by overfitting. Forecasts for t+6 to t+12 h forward generate higher MAE values between ∼3 and ∼4 μg/m3 due to their tendency to underestimate some of the extreme PM2.5 peaks. These findings indicate that further model refinements are required to generate more reliable short-term predictions for the t+6 to t+24 h ahead.

Analysis of Potential Water Inflow Rates at an Underground Coal Mine Using a WOA-CNN-SVM Approach

The water yield of aquifers increases the risk of water inflow, threatens the safe production of coal mines, and even causes geological disasters and construction hazards. To predict water yield quickly and accurately, multiple composite factors are used to invert unit water inflow rates to judge water yield grade. Taking the typical representative of north China-type coal fields as an example, six factors are selected: aquifer thickness, the radius of influence, normalized drawdown, permeability coefficient, the core rate of drilling holes, and the proportion of clay thickness to the thickness of the lower group. The whale optimization algorithm (WOA)–convolutional neural network (CNN)–support vector machine (SVM) model is established with the unit water inflow rate as the forecast target, and different models are selected for comparison. The water yield zoning map is obtained by bringing the borehole data into the model for prediction. The findings indicate that the root mean square error and average absolute error of the composite predictive model models are 0.0318 and 0.0268, respectively, and the model outperforms alternative models. The predicted water yield zoning aligns well with the actual conditions, offering a novel paradigm for water yield assessment.

Disaggregation Model: A Novel Methodology to Estimate Customers’ Profiles in a Low-Voltage Distribution Grid Equipped with Smart Meters

In the context of increasingly necessary energy transition, the precise modeling of profiles for low-voltage (LV) network consumers is crucial to enhance hosting capacity. Typically, load curves for these consumers are estimated through measurement campaigns conducted by Distribution System Operators (DSOs) for a representative subset of customers or through the aggregation of load curves from household appliances within a residence. With the instrumentation of smart meters becoming more common, a new approach to modeling profiles for residential customers is proposed to make the most of the measurements from these meters. The disaggregation model estimates the load profile of customers on a low-voltage network by disaggregating the load curve measured at the secondary substation level. By utilizing only the maximum power measured by Linky smart meters, along with the load curve of the secondary substation, this model can estimate the daily profile of customers. For 48 secondary substations in our dataset, the model obtained an average symmetric mean average percentage error (SMAPE) error of 4.91% in reconstructing the load curve of the secondary substation from the curves disaggregated by the model. This methodology can allow for an estimation of the daily consumption behaviors of the low-voltage customers. In this way, we can safely envision solutions that enhance the grid hosting capacity.

An iterative approach for deriving and solving an accurate regression equation

ABSTRACT This paper introduces a method for deriving an accurate regression equation based on a set of any paired data, and a technique for solving the equation. For a practical example, we used five hundred seventy-one pairs of sediment concentration and river flow data to derive an accurate sediment rating equation. The graphs of the measured and predicted sediment concentrations matched each other, and data correlation showed Nash–Sutcliffe efficiency (NSE) of 0.9999860, coefficient of determination ( R 2 ) of 0.99998679, root mean square error (RMSE) of 0.0345, mean average error (MAE) of 0.0067, volume error (VE) of 1, and sum of square error (SSE) of 0.678631. To explain the technique of deriving and solving the accurate regression equation, separate files of video presentation and excel spreadsheet are provided as supplementary materials. In general, the method can be used to model any processes, and any calibration and validation processes can be addressed.

Automated anatomical landmark detection on 3D facial images using U-NET-based deep learning algorithm.

Facial anthropometry based on 3-dimensional (3D) imaging technology, or 3D photogrammetry, has gained increasing popularity among surgeons. It outperforms direct measurement and 2-dimensional (2D) photogrammetry because of many advantages. However, a main limitation of 3D photogrammetry is the time-consuming process of manual landmark localization. To address this problem, this study developed a U-NET-based deep learning algorithm to enable automated and accurate anatomical landmark detection on 3D facial models. The main structure of the algorithm stacked 2 U-NETs. In each U-NET block, we used 3×3 convolution kernel and rectified linear unit (ReLU) as activation function. A total of 200 3D images of healthy cases, acromegaly patients, and localized scleroderma patients were captured by Vectra H1 handheld 3D camera and input for algorithm training. The algorithm was tested to detect 20 landmarks on 3D images. Percentage of correct key points (PCK) and normalized mean error (NME) were used to evaluate facial landmark detection accuracy. Among healthy cases, the average NME was 1.4 mm. The PCK reached 90% when the threshold was set to the clinically acceptable limit of 2 mm. The average NME was 2.8 and 2.2 mm among acromegaly patients and localized scleroderma patients, respectively. This study developed a deep learning algorithm for automated facial landmark detection on 3D images. The algorithm was innovatively validated in 3 different groups of participants. It achieved accurate landmark detection and improved the efficiency of 3D image analysis.