Effective Machine Learning Algorithm Research Articles

Efficient machine learning models for the detection of coconut milk adulteration

Coconut milk adulteration detection involves the use of analytical methods, including machine learning, to detect the presence of impurities or additives in coconut milk. Adulteration can occur when substances such as water or other cheaper ingredients are added to coconut milk, compromising its quality, nutritional value, and authenticity. Identifying adulteration is crucial for ensuring consumer safety, maintaining product quality, and upholding industry standards. The aim of this study was to propose a machine learning model to detect adulteration in coconut milk. To implement the proposed work, a coconut milk adulteration dataset is collected from a standard source. The amount of available data is limited; hence, synthetic data is generated by applying the CTGAN algorithm. The proposed framework employs three different Feature Extraction (FE) strategies, i.e., Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Autoencoder (AE). Then, the feature-extracted dataset is classified through four effective machine learning algorithms, such as Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The machine learning algorithms outcomes are evaluated using four performance metrics, i.e., Accuracy, Precision, Recall, and F1-score. RF provides the highest accuracy of 99.17%, precision value of 97.29%, recall value of 96.71%, and F1 Score of 97% for the LDA techniques.

Prediction of Coronary Artery Disease using Machine Learning – A Comparative study of Algorithms

Purpose: Heart illness is one of the major killers of humans worldwide. Heart illness and the possibility of experiencing a heart attack have both increased in recent years. Medical professionals face significant difficulties when attempting to forecast heart disease. One of the medical field's virtuosi is early prediction, and this is particularly true in cardiology. The early prediction model-building studies illuminated the most up-to-date methods for locating variations in medical imaging. The study of computer-assisted diagnosis is a dynamic and quickly developing field. Since wrong medical diagnoses can lead to dangerous treatments, a lot of work has been done recently to enhance computer programs that help doctors make diagnoses. Computer-assisted diagnosis relies heavily on machine learning. The basic aspect of pattern recognition is the capability to learn from precedents. Pattern identification and artificial intelligence have a lot of promise to improve the accuracy with which biomedical professionals perceive and diagnose illness. They also help make decisions more objectively. Machine learning is a promising method for developing elegant and automatic algorithms for the study of high-dimensional and multimodal bio-medical data. Two heart disease-related datasets were considered for the purpose of this research. The study implements several machine learning algorithms and compares their prediction accuracy and a handful of other performance metrics to determine which one is the most effective. Objective: The primary goal of the research is to evaluate the performance of several machine learning algorithms using different evaluation criteria such as f1 score, roc, and auc values. The aim is to discover the most effective machine learning algorithm for the datasets obtained for the study. Design/Methodology/Approach: The research utilizes datasets from Kaggle heart information. Python, Skilearn, Pandas, and Jupyter Notebook have been used to build various machine learning prediction models and the outcomes have been compared. Findings/Results: Both datasets comprise of different parameters, therefore pre-processing had to be customized. Applying machine learning algorithms to the training dataset and comparing the trained models to the testing dataset yielded varied results for each dataset. Model performance was measured by accuracy and AUC. Both datasets gave good results with boosting algorithms, however the Cleveland dataset did better with decision trees. Originality/Value: The research included an examination of two Kaggle heart databases. It has been seen how data is distributed, how various features depend on each other, and how all the features influence the target feature of heart disease prediction. Models have been constructed and trained using different machine learning methods, each with its own set of hyper-tuning parameters. To learn which machine learning model is most effective for a given collection of data, the study has looked into both the prediction results using the trained models and the performance parameters of the individual models. Through this study, we now know more about how different machine learning methods work. To determine the most effective algorithm, it is necessary to conduct additional research of the datasets using Deep Learning techniques. Paper Type: Comparative Study

APPLICATION OF NAÏVE BAYES CLASSIFIER ALGORITHM IN DETERMINING THE LEVEL OF CUSTOMER SATISFACTION WITH RUMBAI POST OFFICE SERVICES

Technological advances make service and delivery of goods grow rapidly. Coupled with people's changing shopping habits by shopping online, shipping companies are increasingly needed. PT. POS Indonesia is the first expedition company in Indonesia. Currently PT. POS Indonesia has opened many POS Office branches in every region in Indonesia, one of which is the Rumbai POS Office located in Pekanbaru City. To continue to maintain the company while competing with other expeditions, the Rumbai POS Office must continue to maintain its customers by improving the quality of service. Survey analysis can be done to determine the extent of customer satisfaction with the services provided. To find out the level of customer satisfaction, you can use the classification method. Naive Bayes is a popular and effective machine learning algorithm for classification problems. The study used datasets sourced from the results of questionnaire distribution to customers of the Rumbai POS Office. The questionnaire used 14 indicators derived from the Community Satisfaction Index set by the Ministry of Agriculturein 2004. The classification resulted in a Satisfied class of 16 data with a percentage of 84.2% and a Dissatisfied class of 3 data with a percentage of 15.8%, it can be concluded that the service at the Rumbai POS Office is good. From the classification results, it is proven that the Naïve Bayes algorithm is able to predict well the level of customer satisfaction with an accuracy value of 94.74%, precision of 100%, and recall of 94.12%. The results of this research can later be used as information for the Rumbai POS Office to be able to improve service quality.

A multi-factor quantitative model based on weighted SIR-SAVE and model averaging

In financial quantitative research, there are many kinds of predictors that are closely related to stock prices, so how to design effective machine learning algorithms for such high-dimensional prediction problems is a hot issue. Based on this, this paper proposes a stock factor quantization and prediction model based on the idea of sufficient dimensionality reduction and model averaging. The proposed method is based on the principle of conditional independence, which can greatly retain the validity of the predictors on the stock price while solving the dimensionality catastrophe problem. In addition, the method adaptively learns the link function between the quantized factors and stock prices by using the model averaging method to effectively weigh the variance and bias of the prediction model. In the actual data analysis, this paper chooses the weighted SIR-SAVE as the adequate dimensionality reduction method, the mutual information criterion as the assignment rule of model averaging, and some classical high-dimensional regression techniques as the comparison method, and the empirical results show that the proposed method has a higher accuracy under the evaluation indexes of mean squared error and absolute error, and possesses a certain degree of robustness. Finally, since the sub-models in the model averaging are free, the proposed method is also applicable to the problem of classifying the prediction of stock ups and downs.

MACHINE LEARNING APPROACH FOR SCIENTIFIC AND TECHNICAL EXPERTISE

When conducting scientific and technical expertise, it is necessary to analyze the texts of reports on scientific research work. The analysis is carried out in order to determine whether the research being conducted belongs to the class of scientific research and development work in the field of IT. The main purpose of this study is to improve algorithms for analyzing text documents during scientific and technical expertise. To achieve this goal, the tasks of binary classification of documents provided by companies using machine learning technologies are considered. As a result of the study, a comparative analysis was carried out and the most effective machine learning algorithms were identified. The proposed algorithms will be used in a system that automates the process of checking documents submitted to taxpayers by the tax office.

Effective Machine Learning Algorithm to Predict House Price

Effective Machine Learning Algorithm to Predict House Price

Constructing a Deep Learning Radiomics Model Based on X-ray Images and Clinical Data for Predicting and Distinguishing Acute and Chronic Osteoporotic Vertebral Fractures: A Multicenter Study

To construct and validate a deep learning radiomics (DLR) model based on X-ray images for predicting and distinguishing acute and chronic osteoporotic vertebral fractures (OVFs). A total of 942 cases (1076 vertebral bodies) with both vertebral X-ray examination and MRI scans were included in this study from three hospitals. They were divided into a training cohort (n=712), an internal validation cohort (n=178), an external validation cohort (n=111), and a prospective validation cohort (n=75). The ResNet-50 model architecture was used for deep transfer learning (DTL), with pre-training performed on RadImageNet and ImageNet datasets. DTL features and radiomics features were extracted from lateral X-ray images of OVFs patients and fused together. A logistic regression model with the least absolute shrinkage and selection operator was established, with MRI showing bone marrow edema as the gold standard for acute OVFs. The performance of the model was evaluated using receiver operating characteristic curves. Eight machine learning classification models were evaluated for their ability to distinguish between acute and chronic OVFs. The Nomogram was constructed by combining clinical baseline data to achieve visualized classification assessment. The predictive performance of the best RadImageNet model and ImageNet model was compared using the Delong test. The clinical value of the Nomogram was evaluated using decision curve analysis (DCA). Pre-training resulted in 34 and 39 fused features after feature selection and fusion. The most effective machine learning algorithm in both DLR models was Light Gradient Boosting Machine. Using the Delong test, the area under the curve (AUC) for distinguishing between acute and chronic OVFs in the training cohort was 0.979 and 0.972 for the RadImageNet and ImageNet models, respectively, with no statistically significant difference between them (P=0.235). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.629, 0.886 vs 0.817, and 0.933 vs 0.661, respectively, with statistically significant differences in all comparisons (P<0.05). The deep learning radiomics nomogram (DLRN) was constructed by combining the predictive model of RadImageNet with clinical baseline features, resulting in AUCs of 0.981, 0.974, 0.895, and 0.902 in the training cohort, internal validation cohort, external validation cohort, and prospective validation cohort, respectively. Using the Delong test, the AUCs for the fused feature model and the DLRN in the training cohort were 0.979 and 0.981, respectively, with no statistically significant difference between them (P=0.169). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.974, 0.886 vs 0.895, and 0.933 vs 0.902, respectively, with statistically significant differences in all comparisons (P<0.05). The Nomogram showed a slight improvement in predictive performance in the internal and external validation cohort, but a slight decrease in the prospective validation cohort (0.933 vs 0.902). DCA showed that the Nomogram provided more benefits to patients compared to the DLR models. Compared to the ImageNet model, the RadImageNet model has higher diagnostic value in distinguishing between acute and chronic OVFs. Furthermore, the diagnostic performance of the model is further improved when combined with clinical baseline features to construct the Nomogram.

Artificial Intelligence for Surface Water Quality Evaluation, Monitoring and Assessment

The study utilizes a dataset with seven critical constraints and creates models that are estimated based on various metrics. The goal is to categorize and properly predict the water quality index (WQI) using the suggested models. The outcomes show that the implied models can accurately assess water quality and forecast WQI with high rates of success. Temperature, pH, dissolved oxygen (DO), conductivity, total dissolved solids (TDS), turbidity, and chlorides (Cl-) are some of the six crucial factors used in the study’s dataset. The mean absolute error (MAE), mean squared error (MSE), and coefficient of determination (R2) are some of the metrics used to develop and assess the Artificial Neural Networks (ANN) and Long Short-Term Memory (LSTM) models. The study also makes use of heat maps and correlation graphs to shed further light on the connections between various water quality measures. The color-coded values of the seven parameters, which represent the water quality level of the sample, are displayed on the heat map. The link between the two parameters is shown by the correlation graph between TDS and turbidity, which depicts their correlation coefficient. The study’s results show how effective machine learning algorithms may be as a tool for observing surface water quality. Himachal Pradesh is the tourist hub, so with the rapid increase in the volume of surface water contamination, the application of artificial intelligence will give a better view of data analytics and help with prediction and modeling. It was obtained from the study that the mean square error and root mean square error of ANN and LSTM lie between 0.52–6.0 and 0.04–0.21, respectively. However, the LSTM model’s accuracy is 95%, which is higher than the ANN model. The study highlights the importance of leveraging machine learning techniques in water quality monitoring to ensure the protection and management of water resources. With advancements in machine learning, artificial intelligence (AI) techniques have emerged as a promising tool for surface water quality monitoring. The major goal of the study is to explore the potential of two types of machine learning algorithms, namely artificial neural networks (ANNs) and long short-term memory (LSTM) models, for surface water quality monitoring.

Machine learning and DFT-based combined framework for predicting transmission spectra of quantum-confined bio-molecular nanotube.

The Adenine-based nanotube is theoretically designed, and its transmission spectra are investigated. The quantum-confined Adenine nanotube shows electronic transmission of the carrier at minimum stress. In this paper, the prediction of transmission spectra of the quantum-confined bio-molecular nanotube is investigated and deeply studied. Molecular level structure prediction and their electronic characterization can be possible with ab initio accuracy using a machine learning algorithmic approach. At the molecular level, it is difficult to predict quantum transmission spectra as these results are always hampered by the carrier backscattering effect. However, mostly these predictive models are available for intrinsic semi-conducting materials and other inorganic structures. Machine learning algorithms are designed to predict the electronic properties of the nano-scale structure. This task is even more difficult when quantum-confined molecular arrangements are considered, whose transmission spectra are sensitive to the confinements applied. This paper presents an effective machine learning algorithms framework for predicting transmission spectra of quantum-confined nanotubes from their geometries. In this paper, we consider regression machine learning algorithms to find maximum accuracy with varying configurations and geometries to excerpt their atoms' local environment information. The Hamiltonian components are then used to enable the utilization of the information to predict the electronic structure at any arbitrary sampling point or k-point. The theoretical basics introduced in this process help to capture and incorporate minor changes in quantum confinements into transmission spectra and provide the framework algorithm with more accuracy. This paper shows the ability to predict the accurate algorithmic models of the Adenine nanotube. In this framework, we have considered a tiny data set to achieve a rapid and reliable method for electronic structure determination and also propose the best algorithm for predictive model analysis.

Rapid Diagnosis of Urinary Tract Cancers on a LEGO-Inspired Detection Platform via Chemiresistive Profiling of Volatile Metabolites.

Rapid and in situ profiling of volatile metabolites from body fluids represents a new trend in cancer diagnosis and classification in the early stages. We report herein an on-chip strategy that combines an array of conductive nanosensors with a chaotic gas micromixer for real-time monitoring of volatiles from urine and for accurate diagnosis and classification of urinary tract cancers. By integrating a class of LEGO-inspired microchambers immobilized with MXene-based sensing nanofilms and zigzag microfluidic gas channels, it enables the intensive intermingling of volatile organic chemicals with sensor elements that tremendously facilitate their ion-dipole interactions for molecular recognition. Aided with an all-in-one, point-of-care platform and an effective machine-learning algorithm, healthy or diseased samples from subpopulations (i.e., tumor subtypes, staging, lymph node metastasis, and distant metastasis) of urinary tract cancers can be reliably fingerprinted in a few minutes with high sensitivity and specificity. The developed detection platform has proven to be a noninvasive supplement to the liquid biopsies available for facile screening of urinary tract cancers, which holds great potential for large-scale personalized healthcare in low-resource areas.

Advanced machine learning techniques for cardiovascular disease early detection and diagnosis

The identification and prognosis of the potential for developing Cardiovascular Diseases (CVD) in healthy individuals is a vital aspect of disease management. Accessing the comprehensive health data on CVD currently available within hospital databases holds significant potential for the early detection and diagnosis of CVD, thereby positively impacting disease outcomes. Therefore, the incorporation of machine learning methods holds significant promise in the advancement of clinical practice for the management of Cardiovascular Diseases (CVDs). By providing a means to develop evidence-based clinical guidelines and management algorithms, these techniques can eliminate the need for costly and extensive clinical and laboratory investigations, reducing the associated financial burden on patients and the healthcare system. In order to optimize early prediction and intervention for CVDs, this study proposes the development of novel, robust, effective, and efficient machine learning algorithms, specifically designed for the automatic selection of key features and the detection of early-stage heart disease. The proposed Catboost model yields an F1-score of about 92.3% and an average accuracy of 90.94%. Therefore, Compared to many other existing state-of-art approaches, it successfully achieved and maximized classification performance with higher percentages of accuracy and precision.

Machine Learning Classification–Regression Schemes for Desert Locust Presence Prediction in Western Africa

For decades, humans have been confronted with numerous pest species, with the desert locust being one of the most damaging and having the greatest socio-economic impact. Trying to predict the occurrence of such pests is often complicated by the small number of records and observations in databases. This paper proposes a methodology based on a combination of classification and regression techniques to address not only the problem of locust sightings prediction, but also the number of locust individuals that may be expected. For this purpose, we apply different machine learning (ML) and related techniques, such as linear regression, Support Vector Machines, decision trees, random forests and neural networks. The considered ML algorithms are evaluated in three different scenarios in Western Africa, mainly Mauritania, and for the elaboration of the forecasting process, a number of meteorological variables obtained from the ERA5 reanalysis data are used as input variables for the classification–regression machines. The results obtained show good performance in terms of classification (appearance or not of desert locust), and acceptable regression results in terms of predicting the number of locusts, a harder problem due to the small number of samples available. We observed that the RF algorithm exhibited exceptional performance in the classification task (presence/absence) and achieved noteworthy results in regression (number of sightings), being the most effective machine learning algorithm among those used. It achieved classification results, in terms of F-score, around the value of 0.9 for the proposed Scenario 1.

Affective state estimation based on Russell’s model and physiological measurements

Affective states are psycho-physiological constructs connecting mental and physiological processes. They can be represented in terms of arousal and valence according to the Russel’s model and can be extracted from physiological changes in human body. However, a well-established optimal feature set and a classification method effective in terms of accuracy and estimation time are not present in the literature. This paper aims at defining a reliable and efficient approach for real-time affective state estimation. To obtain this, the optimal physiological feature set and the most effective machine learning algorithm, to cope with binary as well as multi-class classification problems, were identified. ReliefF feature selection algorithm was implemented to define a reduced optimal feature set. Supervised learning algorithms, such as K-Nearest Neighbors (KNN), cubic and gaussian Support Vector Machine, and Linear Discriminant Analysis, were implemented to compare their effectiveness in affective state estimation. The developed approach was tested on physiological signals acquired on 20 healthy volunteers during the administration of images, belonging to the International Affective Picture System, conceived for inducing different affective states. ReliefF algorithm reduced the number of physiological features from 23 to 13. The performances of machine learning algorithms were compared and the experimental results showed that both accuracy and estimation time benefited from the optimal feature set use. Furthermore, the KNN algorithm resulted to be the most suitable for affective state estimation. The results of the assessment of arousal and valence states on 20 participants indicate that KNN classifier, adopted with the 13 identified optimal features, is the most effective approach for real-time affective state estimation.

Breast cancer diagnosis using the fast learning network algorithm.

The use of machine learning (ML) and data mining algorithms in the diagnosis of breast cancer (BC) has recently received a lot of attention. The majority of these efforts, however, still require improvement since either they were not statistically evaluated or they were evaluated using insufficient assessment metrics, or both. One of the most recent and effective ML algorithms, fast learning network (FLN), may be seen as a reputable and efficient approach for classifying data; however, it has not been applied to the problem of BC diagnosis. Therefore, this study proposes the FLN algorithm in order to improve the accuracy of the BC diagnosis. The FLN algorithm has the capability to a) eliminate overfitting, b) solve the issues of both binary and multiclass classification, and c) perform like a kernel-based support vector machine with a structure of the neural network. In this study, two BC databases (Wisconsin Breast Cancer Database (WBCD) and Wisconsin Diagnostic Breast Cancer (WDBC)) were used to assess the performance of the FLN algorithm. The results of the experiment demonstrated the great performance of the suggested FLN method, which achieved an average of accuracy 98.37%, precision 95.94%, recall 99.40%, F-measure 97.64%, G-mean 97.65%, MCC 96.44%, and specificity 97.85% using the WBCD, as well as achieved an average of accuracy 96.88%, precision 94.84%, recall 96.81%, F-measure 95.80%, G-mean 95.81%, MCC 93.35%, and specificity 96.96% using the WDBC database. This suggests that the FLN algorithm is a reliable classifier for diagnosing BC and may be useful for resolving other application-related problems in the healthcare sector.

An integrated clustering and BERT framework for improved topic modeling.

Topic modelling is a machine learning technique that is extensively used in Natural Language Processing (NLP) applications to infer topics within unstructured textual data. Latent Dirichlet Allocation (LDA) is one of the most used topic modeling techniques that can automatically detect topics from a huge collection of text documents. However, the LDA-based topic models alone do not always provide promising results. Clustering is one of the effective unsupervised machine learning algorithms that are extensively used in applications including extracting information from unstructured textual data and topic modeling. A hybrid model of Bidirectional Encoder Representations from Transformers (BERT) and Latent Dirichlet Allocation (LDA) in topic modeling with clustering based on dimensionality reduction have been studied in detail. As the clustering algorithms are computationally complex, the complexity increases with the higher number of features, the PCA, t-SNE and UMAP based dimensionality reduction methods are also performed. Finally, a unified clustering-based framework using BERT and LDA is proposed as part of this study for mining a set of meaningful topics from the massive text corpora. The experiments are conducted to demonstrate the effectiveness of the cluster-informed topic modeling framework using BERT and LDA by simulating user input on benchmark datasets. The experimental results show that clustering with dimensionality reduction would help infer more coherent topics and hence this unified clustering and BERT-LDA based approach can be effectively utilized for building topic modeling applications.

E-mail Spam Classification using KNN and Naive Bayes

E-mail spam filtering is becoming a critical and concerned issue in network security recently, and multiple machine learning techniques have been applied to tackle such sort of classification problem. With the emerging of machine learning framework, most of the tasks has been changed via the effective machine learning algorithms with satisfying performance and high speed. However, the underlying performances of different algorithms under certain given circumstances still lack of an intuitive demonstration. Hence, this study mainly focuses on the performance of two widely-used algorithms (KNN and Naive Bayes) from metrics including accuracy and running time, comparing the unique advantage of each algorithm when classifying emails. The paper uses thousands of spam data to feed two algorithms and analyzes both results respectively, indicating that KNN classifier performs better when determining the spam messages while the opposite is true for the Naive Bayes classifier. Thus, designers can pick an appropriate algorithm easily when dealing with spam filter issues under a given dataset whose features and properties are known.

Forecasting and Optimizing Dual Media Filter Performance via Machine Learning

Four different machine learning algorithms, including Decision Tree (DT), Random Forest (RF), Multivariable Linear Regression (MLR), Support Vector Regressions (SVR), and Gaussian Process Regressions (GPR), were applied to predict the performance of a multi-media filter operating as a function of raw water quality and plant operating variables. The models were trained using data collected over a seven year period covering water quality and operating variables, including true colour, turbidity, plant flow, and chemical dose for chlorine, KMnO4, FeCl3, and Cationic Polymer (PolyDADMAC). The machine learning algorithms have shown that the best prediction is at a 1-day time lag between input variables and unit filter run volume (UFRV). Furthermore, the RF algorithm with grid search using the input metrics mentioned above with a 1-day time lag has provided the highest reliability in predicting UFRV with a RMSE and R2 of 31.58 and 0.98, respectively. Similarly, RF with grid search has shown the shortest training time, prediction accuracy, and forecasting events using a ROC-AUC curve analysis (AUC over 0.8) in extreme wet weather events. Therefore, Random Forest with grid search and a 1-day time lag is an effective and robust machine learning algorithm that can predict the filter performance to aid water treatment operators in their decision makings by providing real-time warning of the potential turbidity breakthrough from the filters.

Ensemble learning prediction of soybean yields in China based on meteorological data

The accurate prediction of soybean yield is of great significance for agricultural production, monitoring and early warning. Although previous studies have used machine learning algorithms to predict soybean yield based on meteorological data, it is not clear how different models can be used to effectively separate soybean meteorological yield from soybean yield in various regions. In addition, comprehensively integrating the advantages of various machine learning algorithms to improve the prediction accuracy through ensemble learning algorithms has not been studied in depth. This study used and analyzed various daily meteorological data and soybean yield data from 173 county-level administrative regions and meteorological stations in two principal soybean planting areas in China (Northeast China and the Huang–Huai region), covering 34 years. Three effective machine learning algorithms (K-nearest neighbor, random forest, and support vector regression) were adopted as the base-models to establish a high-precision and highly-reliable soybean meteorological yield prediction model based on the stacking ensemble learning framework. The model’s generalizability was further improved through 5-fold cross-validation, and the model was optimized by principal component analysis and hyperparametric optimization. The accuracy of the model was evaluated by using the five-year sliding prediction and four regression indicators of the 173 counties, which showed that the stacking model has higher accuracy and stronger robustness. The 5-year sliding estimations of soybean yield based on the stacking model in 173 counties showed that the prediction effect can reflect the spatiotemporal distribution of soybean yield in detail, and the mean absolute percentage error (MAPE) was less than 5%. The stacking prediction model of soybean meteorological yield provides a new approach for accurately predicting soybean yield.

Forecasting Sales for Super Store Data

Abstract: In moment’s ultramodern world, large shopping promenades and commerce calculate on data about the deals of particulars and products and their colourful dependent or independent factors as a crucial step in Prognosticating unborn demand and force operation. Deals are so important to your business that soothsaying deals helps you plan your unborn opinions. Deals soothsaying isn’t accurate enough, it’s a time- consuming process and is mathematically created using being formulas that can only be answered through statistics. Linear retrogression is a machine learning algorithm Grounded on supervised literacy. Retrogression models are intended for predictors grounded on independent variables. It is primarily used to find relationships between variables and predictions. ARIMA stands for Bus Regression Integrated Moving Average. It is one of the simplest and most effective machine learning algorithms for time series forecasting. It’s a combination of autoregression and emotional normalcy.

Implementation of five machine learning methods to predict the 52-week blood glucose level in patients with type 2 diabetes.

For the patients who are suffering from type 2 diabetes, blood glucose level could be affected by multiple factors. An accurate estimation of the trajectory of blood glucose is crucial in clinical decision making. Frequent glucose measurement serves as a good source of data to train machine learning models for prediction purposes. This study aimed at using machine learning methods to predict blood glucose for type 2 diabetic patients. We investigated various parameters influencing blood glucose, as well as determined the most effective machine learning algorithm in predicting blood glucose. 273 patients were recruited in this research. Several parameters such as age, diet, family history, BMI, alcohol intake, smoking status etal were analyzed. Patients who had glycosylated hemoglobin less than 6.5% after 52 weeks were considered as having achieved glycemic control and the rest as not achieving it. Five machine learning methods (KNN algorithm, logistic regression algorithm, random forest algorithm, support vector machine, and XGBoost algorithm) were compared to evaluate their performances in prediction accuracy. R 3.6.3 and Python 3.12 were used in data analysis. The statistical variables for which p< 0.05 was obtained were BMI, pulse, Na, Cl, AKP. Compared with the other four algorithms, XGBoost algorithm has the highest accuracy (Accuracy=99.54% in training set and 78.18% in testing set) and AUC values (1.0 in training set and 0.68 in testing set), thus it is recommended to be used for prediction in clinical practice. When it comes to future blood glucose level prediction using machine learning methods, XGBoost algorithm scores the highest in effectiveness. This algorithm could be applied to assist clinical decision making, as well as guide the lifestyle of diabetic patients, in pursuit of minimizing risks of hyperglycemic or hypoglycemic events.