Application Of Machine Learning Methods Research Articles

Machine Learning Algorithms for Predicting Energy Consumption in Educational Buildings

In the past few years, there has been a notable interest in the application of machine learning methods to enhance energy efficiency in the smart building industry. The paper discusses the use of machine learning in smart buildings to improve energy efficiency by analyzing data on energy usage, occupancy patterns, and environmental conditions. The study focuses on implementing and evaluating energy consumption prediction models using algorithms like long short-term memory (LSTM), random forest, and gradient boosting regressor. Real-life case studies on educational buildings are conducted to assess the practical applicability of these models. The data is rigorously analyzed and preprocessed, and performance metrics such as root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) are used to compare the effectiveness of the algorithms. The results highlight the importance of tailoring predictive models to the specific characteristics of each building’s energy consumption.

Drug discovery and development in the era of artificial intelligence: From machine learning to large language models

Drug Research and Development (R&D) is a complex and difficult process, and current drug R&D faces the challenges of long time span, high investment, and high failure rate. Machine learning, with its powerful learning ability to characterize big data and complex networks, is increasingly effective to improve the efficiency and success rate of drug R&D. Here we review some recent examples of the application of machine learning methods in six areas: disease gene prediction, virtual screening, drug molecule generation, molecular attribute prediction, and prediction of drug combination synergism. We also discuss the advantages of integrative learning in multi-attribute prediction. Integrative models based on base learners constructed from data of different dimensions on the one hand fully utilize the information contained in these data, and on the other hand improve the average prediction performance. Finally, we envision a new paradigm for drug discovery and development: a large language model acts as a central hub to organize public resources into a knowledge base, validating the knowledge with computational software and smaller predictive models, as well as high-throughput automated screening platforms based on organoidal technologies, to speed up development and reduce the differences in efficacy between disease models and humans to improve the success rate of a drug.

A comprehensive assessment of machine learning algorithms for enhanced characterization and prediction in orodispersible film development

Orodispersible films (ODFs) have emerged as innovative pharmaceutical dosage forms, offering patient-specific treatment through adjustable dosing and the combination of diverse active ingredients. This expanding field generates vast datasets, requiring advanced analytical techniques for deeper understanding of data itself. Machine learning is becoming an important tool in the rapidly changing field of pharmaceutical research, particularly in drug preformulation studies. This work aims to explore into the application of machine learning methods for the analysis of experimental data obtained by ODF characterization in order to obtain an insight into the factors governing ODF performance and use it as guidance in pharmaceutical development. Using a dataset derived from extensive experimental studies, various machine learning algorithms were employed to cluster and predict critical properties of ODFs. Our results demonstrate that machine learning models, including Support vector machine, Random forest and Deep learning, exhibit high accuracy in predicting the mechanical properties of ODFs, such as flexibility and rigidity. The predictive models offered insights into the complex interaction of formulation variables. This research is a pilot study that highlights the potential of machine learning as a transformative approach in the pharmaceutical field, paving the way for more efficient and informed drug development processes.

Application of machine learning methods for spent fuel characterization based on gamma spectrometry measurements

Machine learning models have been developed to predict properties of spent nuclear fuel assemblies from Paks NPP, such as burnup, cooling time, initial enrichment, and Pu-239 content. Measured gamma spectra are processed, and activity ratios of fission products are calculated to serve as input features for Support Vector Regression, Random Forest, and Multi-Layer Perceptron models. Data uncertainty is considered during inference to produce prediction intervals, and input features are ranked using the Gini importance of Random Forest models. A deep learning approach using Convolutional Neural Networks has also been developed to predict the spent fuel parameters from the measured spectra directly. The new models can predict spent fuel parameters with great precision, outperforming earlier approaches that rely on nonlinear regression using a single feature to predict burnup and cooling time and can estimate initial enrichment and Pu-239 content.

Spike-based computation using classical recurrent neural networks

Abstract Spiking neural networks are a type of artificial neural networks in which communication between neurons is only made of events, also called spikes. This property allows neural networks to make asynchronous and sparse computations and therefore drastically decrease energy consumption when run on specialised hardware. However, training such networks is known to be difficult, mainly due to the non-differentiability of the spike activation, which prevents the use of classical backpropagation. This is because state-of-the-art spiking neural networks are usually derived from biologically-inspired neuron models, to which are applied machine learning methods for training.
Nowadays, research about spiking neural networks focuses on the design of training algorithms whose goal is to obtain networks that compete with their non-spiking version on specific tasks. In this paper, we attempt the symmetrical approach: we modify the dynamics of a well-known, easily trainable type of recurrent neural network to make it event-based. This new RNN cell, called the Spiking Recurrent Cell, therefore communicates using events, i.e. spikes, while being completely differentiable. Vanilla backpropagation can thus be used to train any network made of such RNN cell. We show that this new network can achieve performance comparable to other types of spiking networks in the MNIST benchmark and its variants, the Fashion-MNIST and the Neuromorphic-MNIST. Moreover, we show that this new cell makes the training of deep spiking networks achievable.

Forecasting of the Dental Workforce with Machine Learning Models

The aim of this study is to determine the factors affecting the dental workforce in Turkey to estimate the dentists employed with machine learning models. The predicted results were obtained by applying machine learning methods; namely, generalized linear model (GLM), deep learning (DL), decision tree (DT), random forest (RF), gradient boosted trees (GBT), and support vector machine (SVM) were compared. The RF model, which has a high correlation value (R2=0.998) with the lowest error rate (RMSE=656.6, AE=393.1, RE=0.025, SE=496115.7), provided the best estimation result. The SVM model provided the worst estimate data based on the values of the performance measurement criteria. This study is the most comprehensive in terms of the dental workforce, which is among the healthcare resources. Finally, we present an example of future applications for machine learning models that will significantly impact dental healthcare management.

Revisiting the potential value of vital signs in the real-time prediction of mortality risk in intensive care unit patients

BackgroundPredicting patient mortality risk facilitates early intervention in intensive care unit (ICU) patients at greater risk of disease progression. This study applies machine learning methods to multidimensional clinical data to dynamically predict mortality risk in ICU patients.MethodsA total of 33,798 patients in the MIMIC-III database were collected. An integrated model NIMRF (Network Integrating Memory Module and Random Forest) based on multidimensional variables such as vital sign variables and laboratory variables was developed to predict the risk of death for ICU patients in four non overlapping time windows of 0–1 h, 1–3 h, 3–6 h, and 6–12 h. Mortality risk in four nonoverlapping time windows of 12 h was externally validated on data from 889 patients in the respiratory critical care unit of the Chinese PLA General Hospital and compared with LSTM, random forest and time-dependent cox regression model (survival analysis) methods. We also interpret the developed model to obtain important factors for predicting mortality risk across time windows. The code can be found in https://github.com/wyuexiao/NIMRF.ResultsThe NIMRF model developed in this study could predict the risk of death in four nonoverlapping time windows (0–1 h, 1–3 h, 3–6 h, 6–12 h) after any time point in ICU patients, and in internal data validation, it is suggested that the model is more accurate than LSTM, random forest prediction and time-dependent cox regression model (area under receiver operating characteristic curve, or AUC, 0–1 h: 0.8015 [95% CI 0.7725–0.8304] vs. 0.7144 [95%] CI 0.6824–0.7464] vs. 0.7606 [95% CI 0.7300–0.7913] vs 0.3867 [95% CI 0.3573–0.4161]; 1–3 h: 0.7100 [95% CI 0.6777–0.7423] vs. 0.6389 [95% CI 0.6055–0.6723] vs. 0.6992 [95% CI 0.6667–0.7318] vs 0.3854 [95% CI 0.3559–0.4150]; 3–6 h: 0.6760 [95% CI 0.6425–0.7097] vs. 0.5964 [95% CI 0.5622–0.6306] vs. 0.6760 [95% CI 0.6427–0.7099] vs 0.3967 [95% CI 0.3662–0.4271]; 6–12 h: 0.6380 [0.6031–0.6729] vs. 0.6032 [0.5705–0.6406] vs. 0.6055 [0.5682–0.6383] vs 0.4023 [95% CI 0.3709–0.4337]). External validation was performed on the data of patients in the respiratory critical care unit of the Chinese PLA General Hospital. Compared with LSTM, random forest and time-dependent cox regression model, the NIMRF model was still the best, with an AUC of 0.9366 [95% CI 0.9157–0.9575 for predicting death risk in 0–1 h]. The corresponding AUCs of LSTM, random forest and time-dependent cox regression model were 0.9263 [95% CI 0.9039–0.9486], 0.7437 [95% CI 0.7083–0.7791] and 0.2447 [95% CI 0.2202–0.2692], respectively. Interpretation of the model revealed that vital signs (systolic blood pressure, heart rate, diastolic blood pressure, respiratory rate, and body temperature) were highly correlated with events of death.ConclusionUsing the NIMRF model can integrate ICU multidimensional variable data, especially vital sign variable data, to accurately predict the death events of ICU patients. These predictions can assist clinicians in choosing more timely and precise treatment methods and interventions and, more importantly, can reduce invasive procedures and save medical costs.

Immune Regulation Patterns in Response to Environmental Pollutant Chromate Exposure-Related Genetic Damage: A Cross-Sectional Study Applying Machine Learning Methods.

Exposure to hexavalent chromium damages genetic materials like DNA and chromosomes, further elevating cancer risk, yet research rarely focuses on related immunological mechanisms, which play an important role in the occurrence and development of cancer. We investigated the association between blood chromium (Cr) levels and genetic damage biomarkers as well as the immune regulatory mechanism involved, such as costimulatory molecules, in 120 workers exposed to chromates. Higher blood Cr levels were linearly correlated with higher genetic damage, reflected by urinary 8-hydroxy-2'-deoxyguanosine (8-OHdG) and blood micronucleus frequency (MNF). Exploratory factor analysis revealed that both positive and negative immune regulation patterns were positively associated with blood Cr. Specifically, higher levels of programmed cell death protein 1 (PD-1; mediated proportion: 4.12%), programmed cell death ligand 1 (PD-L1; 5.22%), lymphocyte activation gene 3 (LAG-3; 2.11%), and their constitutive positive immune regulation pattern (5.86%) indirectly positively influenced the relationship between blood Cr and urinary 8-OHdG. NOD-like receptor family pyrin domain containing 3 (NLRP3) positively affected the association between blood Cr levels and inflammatory immunity. This study, using machine learning, investigated immune regulation and its potential role in chromate-induced genetic damage, providing insights into complex relationships and emphasizing the need for further research.

Prediction of Noise Levels According to Some Exploitation Parameters of an Agricultural Tractor: A Machine Learning Approach

The paper presents research on measuring and the possibility of prediction of noise levels on the left and right sides of the operator within the cabin of an agricultural tractor when moving across various agrotechnical surfaces, considering movement velocity and tire pressures while employing machine learning techniques. Noise level measurements were conducted on a LANDINI POWERFARM 100 type tractor, and aligned with standards (HRN ISO 5008, HRN ISO 6396 and HRN ISO 5131). The obtained noise values were divided into two data sets (left and right set) and processed using multiple linear regression (mlr) and three machine learning methods (gradient boosting machine (gbm); support vector machine using radial basis function kernel (svmRadial); monotone multi-layer perceptron neural network (monmlp)). The most accurate method, considering surfaces, from the left side data set—(R2 0.515–0.955); (RMSE 0.302–0.704); (MAE 0.225–0.488)—and the right side—(R2 0.555–0.955); (RMSE 0.180–0.969); (MAE 0.139–0.644)—was monmlp predominantly, and to a lesser extent svmRadial. On analyzing the total data sets from the left and right sides regarding surfaces, gbm emerged as the most accurate method. The application of machine learning methods demonstrated data accuracy, yet in future research, measurements on certain surfaces may need to be repeated multiple times potentially to improve accuracy further.

Machine Learning Algorithms for Performance Enhancement in DCO-OFDM-Based LiFi Systems

This study describes how machine learning methods can be used to enhance the performance of LiFi (light fidelity) systems that are based on DCO-OFDM (direct current bias optical orthogonal frequency division multiplexing). LiFi, a rapidly developing technology that uses light for wireless communication, has to contend with issues like channel impairments and signal interference. This work investigates several machine learning strategies to address these problems and improve the DCO-OFDM LiFi systems' overall performance. It is determined how well various machine learning techniques perform in terms of improving system parameters, decreasing latency, and raising throughput by analyzing real-world data and simulation studies. Various sorts of symmetrical recurrence division multiplexing (OFDM, for example, DC one-sided optical OFDM (DCO-OFDM), are utilized in light devotion (LiFi). A critical DC predisposition in DCO-OFDM brings about optical power failure, while a minor inclination increment cutting commotion. In this manner, it's essential to decide the appropriate DC predisposition level for DCO-OFDM. This examination finds the ideal DC-predisposition an incentive for DCO-OFDM based LiFi frameworks utilizing machine learning (ML) algorithms. To do this, a MATLAB device is utilized to create a dataset for DCO-OFDM. Thusly, Python writing computer programs is utilized to apply machine learning methods. ML is used to recognize the basic DCO-OFDM qualities that influence the ideal DC predisposition. Here, it is exhibited that the base, greatest, and standard deviation of the bipolar OFDM signal, as well as the size of the heavenly body, decide the ideal DC inclination.

Application of machine learning methods for predicting childhood anaemia: Analysis of Ethiopian Demographic Health Survey of 2016.

Childhood anaemia is a public health problem in Ethiopia. Machine learning (ML) is a growing in medicine field to predict diseases. Diagnosis of childhood anaemia is resource intensive. The aim of this study is to apply machine learning (ML) algorithm to predict childhood anaemia using socio-demographic, economic, and maternal and child related variables. The study used data from 2016 Ethiopian demographic health survey (EDHS). We used Python software version 3.11 to apply and test ML algorithms through logistic regression, Random Forest (RF), Decision Tree, and K-Nearest Neighbours (KNN). We evaluated the performance of each of the ML algorithms using discrimination and calibration parameters. The predictive performance of the algorithms was between 60% and 66%. The logistic regression model was the best predictive model of ML with accuracy (66%), sensitivity (82%), specificity (42%), and AUC (69%), followed by RF with accuracy (64%), sensitivity (79%), specificity (42%), and AUC (63%). The logistic regression and the RF models of ML showed poorest family, child age category between 6 and 23 months, uneducated mother, unemployed mother, and stunting as high importance predictors of childhood anaemia. Applying logistic regression and RF models of ML can detect combinations of predictors of childhood anaemia that can be used in primary health care professionals.

Design of Modified Polymer Membranes Using Machine Learning.

Surface modification is an attractive strategy to adjust the properties of polymer membranes. Unfortunately, predictive structure-processing-property relationships between the modification strategies and membrane performance are often unknown. One possibility to tackle this challenge is the application of data-driven methods such as machine learning. In this study, we applied machine learning methods to data sets containing the performance parameters of modified membranes. The resulting machine learning models were used to predict performance parameters, such as the pure water permeability and the zeta potential of membranes modified with new substances. The predictions had low prediction errors, which allowed us to generalize them to similar membrane modifications and processing conditions. Additionally, machine learning methods were able to identify the impact of substance properties and process parameters on the resulting membrane properties. Our results demonstrate that small data sets, as they are common in materials science, can be used as training data for predictive machine learning models. Therefore, machine learning shows great potential as a tool to expedite the development of high-performance membranes while reducing the time and costs associated with the development process at the same time.

Implementation of Credit Card Fraud Detection

The issue of credit card fraud presents a notable concern within the financial sector, leading to considerable finacial losses for both financial institutions and consumers. To address this challenge, this study investigates the application of machine learning methods for detecting credit card fraud. We explore the performance of diverse machine learning algorithms on an actual dataset and suggest an ensemble-based approach that harnesses the strengths of multiple models. Our experimental outcomes demonstrate the effectiveness of machine learning in accurately identifying fraudulent transactions while minimizing false positives.

Photocatalytic Efficiency for CO2 Reduction of Co and Cluster Co2O2 Supported on g-C3N4: A Density Functional Theory and Machine Learning Study.

It is well known from experimental results that a single atom of cobalt supported on g-C3N4 is an efficient photocatalyst for the reduction of CO2 to CO, with a better photocatalytic activity than g-C3N4. In this work, we investigate the performance as catalysts for the CO2 reduction of single atoms of cobalt and Co2O2 clusters supported on graphitic carbon nitride (g-C3N4). Employing density functional theory plus Hubbard (DFT + U) calculations, we investigate in detail the reduction mechanisms to CO and HCOOH for the first time. We find that deposition of cobalt on g-C3N4 decreases the work function of g-C3N4 to 6.6 eV and provides a better candidate for the reduction reaction. In addition, we find that the preferred product of CO2 reduction on Co@g-C3N4 is CO, with a rate-determining barrier of 0.97 eV, while on Co2O2@g-C3N4, CO2 reduces to formate with a rate-determining barrier of 0.44 eV. We determine the creation of CO2 from COOH to only take place on Co2O2@g-C3N4, with a (relatively high) barrier of 2.27 eV. In order to obtain more easily the transition state energies of the reactions mentioned above, we applied machine learning methods to search for high-importance descriptors for these quantities, in the case of single transition metal atoms supported on C3N4. Interestingly, our results show that our quantities of interest are closely related to the adsorption energies of products and normalized valence electrons of the products of the elementary reactions as well as those of the metal atoms. The former of these two sets of features can be straightforwardly obtained via DFT, while the latter energies are extensively tabulated. Our results offer guidance for the design of catalysts and photocatalysts for CO2 reduction on single-metal atoms supported on C3N4.

Explainable Machine Learning Method for Aesthetic Prediction of Doors and Home Designs

The field of interior home design has witnessed a growing utilization of machine learning. However, the subjective nature of aesthetics poses a significant challenge due to its variability among individuals and cultures. This paper proposes an applied machine learning method to enhance manufactured custom doors in a proper and aesthetic home design environment. Since there are millions of possible custom door models based on door types, wood species, dyeing, paint, and glass types, it is impossible to foresee a home design model fitting every custom door. To generate the classification data, a home design expert has to label thousands of door/home design combinations with the different colors and shades utilized in home designs. These data train a random forest classifier in a supervised learning context. The classifier predicts a home design according to a particular custom door. This method is applied in the following context: A web page displays a choice of doors to a customer. The customer selects the desired door properties, which are sent to a server that returns an aesthetic home design model for this door. This door configuration generates a series of images through the Unity 3D engine module, which are returned to the web client. The customer finally visualizes their door in an aesthetic home design context. The results show the random forest classifier’s good performance, with an accuracy level of 86.8%, in predicting suitable home design, marking the way for future developments requiring subjective evaluations. The results are also explained using a feature importance graphic, a decision tree, a confusion matrix, and text.

Credit Card Fraud Detection

The issue of credit card fraud presents a notable concern within the financial sector, leading to considerable financial losses for both financial institutions and consumers. To address this challenge, this study investigates the application of machine learning methods for detecting credit card fraud. We explore the performance of diverse ma- chine learning algorithms on an actual dataset and suggest an ensemble-based approach that harnesses the strengths of multiple models. Our experimental outcomes demon- strate the effectiveness of machine learning in accurately identifying fraudulent transactions while minimizing false positives.

Automatic selection of sites for drilling candidate injection wells

Background: The increasing difficulty in finding sites for drilling injection wells at the later stages of field development by NC “KazMunayGas” JSC, due to infill drilling of the grid of existing wells and uneven reserve production, is a pressing problem today. Developments in geospatial analysis and artificial intelligence have stimulated the search for new approaches to solve this problem.
 Aim: The research is aimed at developing an innovative approach to automatically identifying the most promising sites for drilling injection wells, based on comprehensive analysis of large volumes of data using advanced algorithms.
 Materials and methods: The work uses methods for collecting and analyzing production and geological data, uses spatial algorithms for multivariate analysis and data normalization methods, including the adjusted interquartile range to determine outliers.
 Results: Results are described showing the ranking of cells by drilling potential based on comprehensive analysis, as well as the assignment of unique codes to each cell to improve decision-making accuracy.
 Conclusion: Directions for further research are noted, including analysis of data inaccuracies, consideration of additional parameters, identification of effective interlayers, application of machine learning methods, and expansion of testing of the approach in other fields.

Application of machine learning methods to analyze customer migration risk in terms of corporate financial security

Effective prediction of customer migration is only possible through knowledge of the customer life cycle, which is characterized by the length of the relationship between buyer and provider, i.e. customer retention. A concept of opposite importance is customer migration, defined as the partial or total abandonment of the products or services offered by a company. Its knowledge and ability to predict it is crucial in terms of ensuring the continued financial security of target companies. The primary objective of this article was to present a method for assessing the risk of telecom industry customer migration using machine learning methods. The objective was achieved through the use of research methods, theoretical deductions such as and induction, system analysis and synthesis, and mathematical modelling, which additionally allowed for a practical analysis of the migration of customers of the telecommunications industry. Predictors with the greatest impact on the phenomenon under study were selected. It should be noted that the gain chart indicates that, in the case of contacting the 20% of customers selected by the models, the target coverage would be at the following levels, respectively: 70% for the boosted tree model and the decision tree based on the CART algorithm, and 75% for the random forest model. The research niche addressed in the article is the development of methods for assessing migration risk using machine learning techniques. The tool developed in the article can support decision-making in the creation of marketing campaigns aimed at retaining the largest number of customers.

Application of machine learning methods in the analysis of interface bonding strength for overmolded hybrid thermoset‐thermoplastic composites

AbstractThe focus of this study is to apply finite element method (FEM) and machine learning methods to investigate the interfacial bonding strength of continuous fiber reinforced thermoset composite (TSC)‐thermoplastic structures manufactured through co‐curing and overmolding processes, with polyamide 6 (PA 6) as the thermoplastic material. A model for interfacial healing degree in TSC‐PA 6 structures was developed. Then, FEM was employed to study the influence of various injection overmolding process parameters on the interfacial bonding strength of TSC‐PA 6 structures. The results show that there is a strong correlation between the degree of interface healing and the bonding strength. Subsequently, six machine learning methods were employed to correlate interfacial healing degree with diverse injection molding process parameters. Simulation data were utilized for training, calibration, and validation of the six machine learning models. Based on the results of simulation and machine learning predictions, a quantitative analysis of the significance of injection molding process parameters on healing degree was conducted. These parameters are ranked in descending order of importance as follows: insert temperature, melt temperature, and injection rate.Highlights The interfacial healing degree model of PA 6 was established and validated through the integration FEM and experiment. Six machine learning models were built to predict the interfacial healing degree. Grad boosting performed best in predicting the interfacial healing degree. Insert temperature had the greatest impact on the interface healing degree.

Prediction of Occult Hemorrhage in the Lower Body Negative Pressure Model: Initial Validation of Machine Learning Approaches.

Detection of occult hemorrhage (OH) before progression to clinically apparent changes in vital signs remains an important clinical problem in managing trauma patients. The resource-intensiveness associated with continuous clinical patient monitoring and rescue from frank shock makes accurate early detection and prediction with noninvasive measurement technology a desirable innovation. Despite significant efforts directed toward the development of innovative noninvasive diagnostics, the implementation and performance of the newest bedside technologies remain inadequate. This poor performance may reflect the limitations of univariate systems based on one sensor in one anatomic location. It is possible that when signals are measured with multiple modalities in multiple locations, the resulting multivariate anatomic and temporal patterns of measured signals may provide additional discriminative power over single technology univariate measurements. We evaluated the potential superiority of multivariate methods over univariate methods. Additionally, we utilized machine learning-based models to compare the performance of noninvasive-only to noninvasive-plus-invasive measurements in predicting the onset of OH. We applied machine learning methods to preexisting datasets derived using the lower body negative pressure human model of simulated hemorrhage. Employing multivariate measured physiological signals, we investigated the extent to which machine learning methods can effectively predict the onset of OH. In particular, we applied 2 ensemble learning methods, namely, random forest and gradient boosting. Analysis of precision, recall, and area under the receiver operating characteristic curve showed a superior performance of multivariate approach to that of the univariate ones. In addition, when using both invasive and noninvasive features, random forest classifier had a recall 95% confidence interval (CI) of 0.81 to 0.86 with a precision 95% CI of 0.65 to 0.72. Interestingly, when only noninvasive features were employed, the results worsened only slightly to a recall 95% CI of 0.80 to 0.85 and a precision 95% CI of 0.61 to 0.73. Multivariate ensemble machine learning-based approaches for the prediction of hemodynamic instability appear to hold promise for the development of effective solutions. In the lower body negative pressure multivariate hemorrhage model, predictions based only on noninvasive measurements performed comparably to those using both invasive and noninvasive measurements.