Linear Regression Algorithm Research Articles

Integration of single-cell RNA-seq and bulk RNA-seq to construct liver hepatocellular carcinoma stem cell signatures to explore their impact on patient prognosis and treatment.

Liver hepatocellular carcinoma (LIHC) is a prevalent form of primary liver cancer. Research has demonstrated the contribution of tumor stem cells in facilitating tumor recurrence, metastasis, and treatment resistance. Despite this, there remains a lack of established cancer stem cells (CSCs)-associated genes signatures for effectively predicting the prognosis and guiding the treatment strategies for patients diagnosed with LIHC. The single-cell RNA sequencing (scRNA-seq) and bulk RNA transcriptome data were obtained based on public datasets and computerized firstly using CytoTRACE package and One Class Linear Regression (OCLR) algorithm to evaluate stemness level, respectively. Then, we explored the association of stemness indicators (CytoTRACE score and stemness index, mRNAsi) with survival outcomes and clinical characteristics by combining clinical information and survival analyses. Subsequently, weighted co-expression network analysis (WGCNA) and Cox were applied to assess mRNAsi-related genes in bulk LIHC data and construct a prognostic model for LIHC patients. Single-sample gene-set enrichment analysis (ssGSEA), Cell-type Identification By Estimating Relative Subsets Of RNA Transcripts (CIBERSORT) and Tumor Immune Estimation Resource (TIMER) analysis were employed for immune infiltration assessment. Finally, the potential immunotherapeutic response was predicted by the Tumor Immune Dysfunction and Exclusion (TIDE), and the tumor mutation burden (TMB). Additionally, pRRophetic package was applied to evaluate the sensitivity of high and low-risk groups to common chemotherapeutic drugs. A total of four genes (including STIP1, H2AFZ, BRIX1, and TUBB) associated with stemness score (CytoTRACE score and mRNAsi) were identified and constructed a risk model that could predict prognosis in LIHC patients. It was observed that high stemness cells occurred predominantly in the late stages of LIHC and that poor overall survival in LIHC patients was also associated with high mRNAsi scores. In addition, pathway analysis confirmed the biological uniqueness of the two risk groups. Personalized treatment predictions suggest that patients with a low risk benefited more from immunotherapy, while those with a high risk group may be conducive to chemotherapeutic drugs. The current study developed a novel prognostic risk signature with genes related to CSCs, which provides novel ideas for the diagnosis, prognosis and treatment of LIHC.

Exploration and Practice of the Integration and Development of Educational Technology and Teaching in Colleges and Universities in the Context of Educational Informatization

Abstract In the context of education informatization, this paper discusses how to deeply integrate advanced educational technology with traditional teaching. By constructing a blended teaching model with the goal of deep learning and using linear regression, decision tree and other algorithms to build a data analysis framework, this paper aims to assess the practical application effect of educational technology in universities. The empirical study explores the development of deep blending between educational technology and teaching by taking the Information Technology Course of University J as an example. The results showed that after the teaching, the posttest mean of profound learning ability of students in the mixed, online, and offline groups were 1.948, 0.182 and 0.065 higher than the pretest mean, respectively. z-values ranked in the top three were the perseverance of students in the mixed group (-12.642) and the ability to think creatively (-11.682) and critically (-9.875), which were higher than those of students in the online group and the offline group, the overall profound learning ability of students in the mixed group was effectively improved, which verified the effectiveness of the blended teaching model proposed in this paper.

Machine learning algorithms to study the relative roles of jet convection and natural convection in the presence of surface roughness elements on enhancement of jet impingement heat transfer

Based on data-driven approaches, eight machine-learning algorithms have been proposed to characterize the heat transfer performance of turbulent jet impingement cooling. These algorithms are designed to cool high-heat-flux surfaces modified with single protrusions, multi-protrusions, or V-grooves. To train these algorithms, an experimental dataset was used, which included 184 experiments with Reynolds numbers ranging from 10,000 to 33,000, nozzle exit-to-plate distances ranging from 2 to 10 jet diameters, and two different heat inputs of 60 W and 90 W. Multiple linear regression algorithms in Python programming were used to model jet impingement cooling, showing that the proposed machine learning models provided more accurate predictions with a 20.4 % to 66.5 % relative residual improvement over the existing conventional regression model based on performance metrics like R2 and relative residual. This improvement was leveraged to quantify natural convection's impact on the effectiveness of heat transfer enhancement due to different types and sizes of roughness elements in high-temperature applications. The research found that as the protrusion surface area increased from 0.02 % to 0.188 % compared to the flat plate, the effectiveness of heat transfer enhancement decreased from 2.69 % to 8.37 % at similar operating conditions. These results revealed that natural convection, which opposes forced jet impingement, was strengthened with increased heat input values, roughness element surface area, and the local turbulence generated. The higher natural convection weakened the enhancement afforded by jet impingement on the modified plates relative to the flat plate. Additionally, the capabilities of machine learning algorithms were explored to unlock the full potential of the jet impingement technique and to overcome the associated complexity in jet impingement applications for next-generation electronics cooling. Finally, the Decision Tree Classifier algorithm was applied to classify the performance of the surface roughness element as either effective or ineffective.

Inventory Optimization Using Data Science Technologies for Supply Chain 4.0

In the context of supply chain 4.0, Data Science (DS) can improve operations and inventory management by using statistical and machine learning techniques. Additionally, big data can reveal valuable insights for predictive and prescriptive analytics, which can aid in enhancing competitiveness in today’s business environment. Accurate demand forecasting in supply chain inventory is a fundamental step to improve inventory management, address ordering uncertainties, and minimize costs while meeting customer demands. This requires the efficient use of demand forecasting tools, assessing predictive data analysis techniques. Challenges can arise from inefficient ordering models, selecting accurate forecasting models, and considering issues like over-and underestimation leading to food waste and profit margin impacts, particularly for products with short shelf life. Other challenges include enhancing inventory optimization efficiency, adapting to dynamic demands, and formulating optimal inventory decisions. In this work, we introduce a supply chain 4.0 inventory management approach, where we combined DS techniques, predictive analytics, and big data approach to enhance inventory control. A prediction model is also introduced in order to forecast incoming and outgoing inventory. This model is based on a detailed dataset that takes into account the districts and seasons data. The model’s performance was evaluated based on performance measurements, such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). Significantly, the results show that the random forest algorithm was the best in predicting OUT inventory quantities with an average error equal to 0.011, while the linear regression algorithm produced the best performance in predicting IN inventory quantities with an average error of 0.03

Research on the Influence of Modern Informatization Technology on English Education and Teaching in Colleges and Universities

Abstract With the development of modern informatization technology, how to combine modern informatization technology with English education and teaching in colleges and universities has become a key research direction in the current education sector. This paper proposes English information literacy education and teaching based on linear regression. The research problem and object are identified based on the current situation of English education and teaching in colleges and universities, and then a research design program is developed. Using a combination of linear regression algorithms and statistical analysis software, the mechanism of the influence of modern information technology on English education and teaching is analyzed by example. The results show that the average pre-test score of students at the intermediate level is 83.854 points. In comparison, the post-test score is 89.789 points, and the post-test score is about 5.935 points higher than the pre-test score, which indicates that there is a significant improvement in the English scores of students at the intermediate level after English informatization teaching. Taking English informatization teaching as the dependent variable and “teaching equipment” and “class size” as the independent variables, the regression equation of English informatization teaching = 0.215×teaching equipment+0.144×class size. This study has a far-reaching and positive impact on improving the quality and level of university English teaching, making teaching methods richer and the teaching effect more significant.

Intelligent Analysis Method of E-Commerce Data Based on Multiple Machine Learning Algorithms

Machine learning algorithm is one of the most popular research fields in the 21st century, and it is widely used in various industries. This paper first discusses the development status, characteristics and intelligent classification technology of e-commerce based on various methods. Then, through statistical analysis of multiple samples, this paper establishes a model to predict the quantity of goods and other time-related changes in the future period of time, and proposes an improved variance estimate to achieve the best effect under different data scenarios. Finally, the experiment proves that the response time of the linear regression algorithm fluctuates between 20ms and 25ms, and the overall fluctuation is small. For different samples, the response time of the linear regression algorithm is maintained in a relatively stable range, showing the stability of different input data. The response time of the decision tree algorithm fluctuates between 28ms and 33ms, showing a certain fluctuation. For different samples, the response time of decision tree algorithm fluctuates greatly, which may be affected by the characteristics of input data and show different processing efficiency. The response time of support vector machine algorithm fluctuates between 14ms and 18ms, and the change is relatively stable. For different samples, the response time of SVM algorithm is kept at a relatively stable level, showing the consistency of input data processing ability.

Comparative Study of Iconnet Jabodetabek and Banten Using Linear Regression and Support Vector Regression

PT PLN Indonesia Comnets Plus has little information regarding future customer growth, making it difficult to take steps to meet customer needs. This research aims to predict customer growth in the future based on quantitative data from the previous year, where the output provided produces data in the form of numbers that are analyzed using statistical methods. The hope is to provide information to maximize customer growth with the minimum area or bandwidth used by the company. This research uses linear regression and support vector regression (SVR) algorithms using a company secondary dataset of 252 data points with 5 attributes. Data was collected during the last one-year period, from January to December 2021. The results of the research show that predictions using both algorithms have increased, customer growth when viewed from the number of customers, bandwidth, and regional data has increased significantly. This can be seen from the value of the number of customers, which continues to increase, while the highest number of customers falls in December, the most requested bandwidth is 20 mbps, and the largest customer area is in the Depok area. The results of the research show that the SVR algorithm is superior in terms of mean absolute percentage error (MAPE): 0.02% MAPE, 0.10 MAE, and 0.99 RMSE, while for linear regression, the MAPE values were 36.28%, MAE 201, and RMSE 0.80.

Man-Hour Estimation Model Development in BIM-Based Projects with Machine Learning-Regression Algorithms

Construction management is a service that uses project management techniques to planning, design and construction of a project. Another branch of construction management is the planning made during the bidding stages before the construction starts. At this stage, the scheduling of the work, mobilization and most importantly the project design and drawing time should be analyzed and accurate estimates should be made. For this estimation, the experience of the bidding organization is the biggest reference. Construction management techniques in a BIM-based project are challengeable. The biggest reason is that knowledge about BIM is much less than the others and still a developing system. Therefore, the margin of error in the estimated project duration to be predicted in the bids to be made for such projects increases. Considering that man-hour estimations are financially very important for the company. This study is aimed to make observations with advanced technologies which is applied ML algorithms and analysis methods for man-hour estimations in BIM projects at the bidding stage. The project information to perform a man-hour analysis of completed construction projects was requested from offices that have gained experience in BIM projects. The project information of 16 projects were tabulated. The collected information was converted into a data set and transferred into regression analysis algorithms using Python format. Data set, which was turned into a matrix, was analysed and the consistency of the parameters in data set was tested. Spent man-hour estimation was made, graphed over parameters with simple and multiple linear regression algorithms. 
 Keywords: Building Information Modelling (BIM), construction management, bidding, project management, Artificial Intelligence (AI), machine learning, regression analysis

Optimization of correction factors for WBS in SARS-COV-2 uncertainty factors

Effluent-based epidemiological methods based on effluent analysis are a new method to study drug consumption. In this study, CF was reestimated and improved by establishing a reasonable model to improve the accuracy of the WBE method. Before analyzing the obtained data, we need to eliminate errors and their blank data. Then, after downloading the exported data, knowing that there were 1099 sewers in the data downloaded on CDC, the data table was filtered, the blank data was excluded, and the data from April 24, 2022 to May 8, 2022 was selected as the percentage change in SARS-CoV-2RNA levels at 15-day intervals; Publication of SARS-CoV-2 concentration data sheets in wastewater in nuclear-weapon States. The data on CoV-2 concentration in wastewater were screened and eliminated, deleted from the blank data of SARS-CoV-2 virus concentration, and classified according to the measured serial number of sewers, and the SARS-CoV-2 virus concentration data of a total of 451 sewers were summarized. Then select based on the heatmap of the number of new cases in each state in the last 30 days, and based on the heatmap of the number of new cases in each state in the last 30 days, select the abbreviated state name of CA, CT, ID, IL, IL, KS, KY, MA, MI, MO, NE, NV, New York, Ohio, Oregon, TX, UT, VA, WA, WV, WI. Analyze the data. Finally, based on K-means clustering, linear regression and bootstrap algorithms, combined with relevant parameters, normal distribution and bias distribution, a new CF is re-established to improve the accuracy of WBE.

Prediction and Optimisation of Copper Recovery in the Rougher Flotation Circuit

In this work, the prediction and optimisation of copper flotation has been conducted in the rougher flotation circuit. The copper-recovery prediction involved the application of support vector machine (SVM), Gaussian process regression (GPR), multi-layer perceptron artificial neural network (ANN), linear regression (LR), and random forest (RF) algorithms on 15 rougher flotation variables at the BHP Olympic Dam. The predictive models’ performance was assessed using linear correlation (r), root mean square error (RMSE), mean absolute percentage error (MAPE), and variance accounted for (VAF). A simulated annealing (SA) optimisation algorithm, particle swarm optimisation (PSO) algorithm, surrogate optimisation (SO) algorithm, and genetic algorithm (GA) were investigated, using the GPR predictive function, to determine the optimal operating condition for maximising copper recovery. The predictive function of the best-performing model was extracted and used in optimising the flotation circuit. The results showed that the GPR model developed with the matern 3/2 kernel function makes the most precise copper-recovery prediction as compared to the other investigated predictive models, obtaining r values > 0.96, RMSE values < 0.42, MAPE values < 0.25%, and VAF values > 94%. A hypothetical optimisation solution assessment showed that SA provides the best set of solutions for the maximisation of rougher copper recovery, obtaining a throughput of 638.02 t/h and a total net gain percentage of 14%–15.5% over the other optimisation algorithms with a maximum copper recovery of 94.76%. The operational benefits of implementing these algorithms have been highlighted.

A Statistical Study of English Teaching Methods Incorporating Children’s Memory Characteristics

Abstract In this paper, a multivariate linear regression model of the English teaching method incorporating children’s memory characteristics is designed. The linear regression algorithm is utilized to reduce the error between the real and predicted data, and the multiple covariance problem is corrected through the principal component-ridge regression model to study in depth the effect of the implementation of the English teaching method that combines children’s memory characteristics. Taking students and teachers majoring in English as the research subjects, we designed a questionnaire survey to collect research data and reflect on the practice through classroom observation and interviews. The results showed that the regression coefficients of the variables of children’s memory characteristics, attention concentration, preference, memory repetition and association factor were ranked in the order of 0.290, 0.240, 0.182, 0.018, and the other three variables were significant at 0.5 significance level except for the variable memory repetition, which was significant at 0.1 significance level. This study shows that there is a causal relationship between children’s memory characteristics and English language teaching and that children’s memory characteristics can induce students to form positive preferences and improve their memory repetition in English language teaching.

Penerapan Metode Regresi Least Absolute Shrinkage and Selection Operator (LASSO) dan Regresi Linier untuk Memprediksi Tingkat Kemiskinan di Indonesia

Poverty is defined as a situation where a person or family is unable to meet the basic needs for survival, such as clothing, food, shelter, and education. This study aims to compare the accuracy of the Least Absolute Shrinkage and Selection Operator (Lasso) regression method and linear regression in predicting poverty levels in Indonesia and to choose the best model from the two methods used. The results of this study indicate that of the two algorithms used, namely the linear regression algorithm and Lasso regression, the algorithm that has a higher level of accuracy for predicting poverty rates in each province in Indonesia is the linear regression algorithm because it has a lower MSE value and has the value of R^2 is closer to 1 than the Lasso regression algorithm. In addition, the results of the analysis show that the variables that have the highest influence on poverty rates in provinces in Indonesia are education, as well as the Human Development Index (IPM).Keywords: Poverty Rate Prediction, Lasso Regression, Linear Regression

House Price Prediction Using Data Mining with Linear Regression and Neural Network Algorithms

The need for housing in big cities is very high because most offices and economic centers are in big cities. Limited land and high demand cause house prices to rise. Many developers build housing on the outskirts of big cities with access to trains and toll roads to make transportation easier. Property developers compete by providing the best prices, various choices of house specifications, ease of the mortgage process, and attractive promotions such as no down payment. A house is a long-term investment whose price increases yearly, so proper analysis is needed to buy a place to live in. Several factors influence the price of a house, including location, land area, building area, building type, and so on. This research aims to create a house price prediction model using the Linear Regression Algorithm and Neural Network so that the results can be useful for property agents in predicting house sales or from the buyer's side in predicting house prices. The results of this research use the Linear Regression Algorithm RMSE 0.775, while the Neural Network Algorithm uses RMSE 0.645. From this research, modeling using the Linear Regression Algorithm has better results. Still, the Linear Regression Algorithm and Neural Network Algorithm have RMSE results that are close to accurate and have small errors.

7-Methoxy-4-methylcoumarin: Standard Molar Enthalpy of Formation Prediction in the Gas Phase Using Machine Learning and Its Comparison to the Experimental Data.

Experimentally, the standard molar enthalpy of formation in the crystalline phase at 298.15 K, ΔfHm°(cr) for 7-methoxy-4-methylcoumarin (7M4MC) was calculated by traditional linear regression, which was obtained by combustion calorimetry. Similarly, the standard molar enthalpy of sublimation was determined through the standard molar enthalpy of fusion and by the standard molar enthalpy of vaporization, from differential scanning calorimetry and thermogravimetry, respectively; lately using these results, the standard molar enthalpy of formation in the gas phase was calculated at 298.15 K, ΔfHm°(g). In addition ML was used to predict the standard molar enthalpy of formation in the gas phase for the 7M4MC, constructing an experimental data set containing three kinds of functional groups: esters, coumarins, and aromatic compounds. The procedure was performed by using multiple linear regression algorithms and stochastic gradient descent with a R2 of 0.99. The obtained models were used to compare those predicted values versus experimental for coumarins, resulting in an average error rate of 9.0%. Likewise, four homodesmic reactions were proposed and predicted with the multiple linear regression algorithm of ML obtaining good results.

Maximum Likelihood Instead of Least Squares in Fracture Analysis by Means of a Simple Excel Sheet with VBA Macro

This technical note illustrates a linear regression algorithm based on the Maximum Likelihood Estimation (MLE), with a related Excel spreadsheet and VBA program, adapted to the case of fracture aperture data sets in which sampling of the smallest values is problematic. The method has been tested by means of Monte Carlo simulations and exhibits significantly better convergence against Least Squares criterion (LSM). As the method is conceptually simple and, following the indications illustrated here, the relative spreadsheet can be easily designed, it may be routinely used, instead of the Least Squares, in fracture analysis. Furthermore, the proposed method, with the appropriate modifications, might be potentially extended to other cases in geology and geophysics, in which significant biases at the lower limits of the sampling scale occur.

Prediction of Liver Disease Using a Linear Regression Algorithm

The liver is the most essential organ in the human body. Hepatitis is one such disorder affecting the liver and is a global health issue, including in Indonesia. Liver disease is an inflammatory condition of the liver that can be triggered by genetic factors, viral infections, alcohol consumption, and the use of certain drugs. In principle, prevention of hepatitis or liver disease can be done by adopting a healthy lifestyle. In addition, early detection is also very important in preventing death in those affected by this disease. One method for early detection is through the application of data mining, which can help predict and reduce mortality in patients affected by this disease. Linear regression is a data mining technique utilized to predict the dependent variable or outcome based on the independent variable or predictor. The study conducted tests on this algorithm and obtained a Root Mean Squared Error of 0.349 +/- 0.000. This indicates the presence of a correlation or functional relationship (cause and effect) between the dependent variable (criterion) and the independent variable (predictor). The purpose of this testing process is to detect liver disease using the linear regression algorithm.

Rental Price Prediction of Boarding Houses in Batam City Using Linear Regression and Random Forest Algorithms

Boarding houses, commonly known as "kost," are residential places typically rented by individuals, serving a function similar to hotels, but with more affordable pricing. With the proliferation of boarding house businesses, residents and newcomers in Batam city face challenges in selecting suitable accommodation based on both price and amenities. Leveraging machine learning, a branch of artificial intelligence (AI), and incorporating various algorithms, a system can be developed to predict the rental prices of boarding houses. This helps individuals make informed decisions regarding the suitability of a boarding house based on their preferences and budget. The algorithms utilized in this study are Linear Regression and Random Forest. The modeling process resulted in R2 Scores, with Linear Regression achieving a score of 64%, while Random Forest outperformed with an impressive 99% R2 Score. Due to the higher R2 Score of Random Forest, this model was selected for the development of a website using the Scrum framework. The outcome of this research is a predictive pricing website for boarding houses, offering a valuable tool for residents and visitors in Batam when seeking to rent or lease a boarding house.

Correction to: Impact of Process Variation on Leakage and Drive Currents of FED Structures Using Linear Regression and Random Forest Algorithms

Correction to: Impact of Process Variation on Leakage and Drive Currents of FED Structures Using Linear Regression and Random Forest Algorithms

Examining the impact of neighborhood environment factors on residents’ emotions during COVID-19 lockdown and reopening: A Wuhan study on mediation and moderation

Due to COVID-19, the urban lockdown has caused a significant impact on the mental health of residents. However, limited research investigates the role of neighborhood factors on residents’ mental health during and after the lockdown. This study examines Wuhan, the first city to experience the COVID-19 outbreak, employing multiple linear regression and XGBoost algorithms to analyze the emotional status and distribution of Wuhan residents. The goal of this study is to identify the moderating effect of the neighborhood environment scale on emotional positivity and the marginal effect of the neighborhood environment on residents’ emotions. The results of the study indicate that specific neighborhood environmental characteristics have varying effects on residents’ positive emotions, both before and after the COVID-19 lockdown. The green space ratio, attraction density, waterfront space density, and service facility density all positively affected mood within different distance ranges. Shopping facilities, on the other hand, had mainly positive effects during the open period, with negative effects during the closed period. Furthermore, this study determined scale thresholds where neighborhood environments had a positive effect on mood. For instance, attractions and waterfront areas improved the mood of residents in residential areas, up to at least 3 km away. Medical facilities had a positive effect on residents’ mood beyond 2.2 km. This study highlights crucial implications for planning and managing neighborhoods to promote resilience during future public health crises.

An empirical study on the effect of academic engagement on academic achievement of engineering students in colleges and universities

Abstract Based on the linear regression algorithm, this paper uses the basic linear regression algorithm and the kernel linear regression algorithm to construct the relationship model between academic input and academic achievement based on linear regression and to determine the independent variables, dependent variables and control variables in the model. The engineering students of East China Normal University are selected as the research object, the research instrument is determined, the research index is determined according to the survey, and the research hypothesis is proposed, and then the research and analysis design of the impact of academic input on academic achievement is completed. Using reliability and validity to test the validity of the questionnaire, the initial data of the study can be obtained by distributing the questionnaire, and correlation analysis and regression analysis are used to carry out an empirical study of academic input and academic achievement based on linear regression. The results show that the correlation coefficient between academic input and academic achievement of master’s degree students is R=0.892 and R2=0.792, indicating that the predictive variance of academic input on academic achievement is 89.2%. The effects of the dimensions under the academic input on the social adjustment dimension under the academic achievement were, in descending order, as follows: active cooperation > teacher-student interaction > educational enrichment > academic challenge > campus support. This study comprehensively analyzes the impact of academic engagement on academic achievement, and colleges and universities should change the test of students’ ability to memorize knowledge and skills to the test of students’ ability to analyze and solve problems by applying what they have learned.