The Exploration of Predictors for Peruvian Teachers’ Life Satisfaction through an Ensemble of Feature Selection Methods and Machine Learning

Sustainability, Год журнала: 2024, Номер 16(17), С. 7532 - 7532

Опубликована: Авг. 30, 2024

Teacher life satisfaction is crucial for their well-being and the educational success of students, both essential elements sustainable development. This study identifies most relevant predictors among Peruvian teachers using machine learning. We analyzed data from National Survey Teachers Public Basic Education Institutions (ENDO-2020) conducted by Ministry Peru, filtering methods (mutual information, analysis variance, chi-square, Spearman’s correlation coefficient) along with embedded (Classification Regression Trees—CART; Random Forest; Gradient Boosting; XGBoost; LightGBM; CatBoost). Subsequently, we generated learning models Decision CatBoost; Support Vector Machine; Multilayer Perceptron. The results reveal that main are health, employment in an institution, living conditions can be provided family, performing teaching duties, as well age, degree confidence Local Management Unit (UGEL), participation continuous training programs, reflection on outcomes practice, work–life balance, number hours dedicated to lesson preparation administrative tasks. Among algorithms used, LightGBM Forest achieved best terms accuracy (0.68), precision (0.55), F1-Score Cohen’s kappa (0.42), Jaccard Score (0.41) LightGBM, (0.67), (0.54), (0.41), (0.41). These have important implications management public policy implementation. By identifying dissatisfied teachers, strategies developed improve and, consequently, quality education, contributing sustainability system. Algorithms such valuable tools management, enabling identification areas improvement optimizing decision-making.

Язык: Английский

---

Stacked ensemble machine learning approach for electroencephalography based major depressive disorder classification using temporal statistics

Systems Science & Control Engineering, Год журнала: 2024, Номер 12(1)

Опубликована: Ноя. 13, 2024

Major depressive disorder (MDD) is a serious and widespread mental health condition that remains challenging to diagnose accurately. Traditional psychological assessments, which can be subjective sometimes unreliable, emphasize the need for more objective diagnostic tools. In this study, we present machine learning (ML) model designed depression by analysing statistical time-domain features extracted from Electroencephalography (EEG) data. The built using stacked ensemble ML approach, incorporating nine-base estimators with various meta-classifiers. Through multiple trials, achieved an accuracy of 98.01%, precision recall rates 97.78% 96.61%, respectively Adaptive Boosting (AdaBoost) as meta-classifer. We also investigated effects data sampling number base classifiers on model's performance. findings demonstrate approach significantly enhances diagnosing MDD proposed outperforms methods used in previous studies. This offers promising tool psychologists medical professionals reliably, potentially leading better treatment outcomes those affected disorder.

Язык: Английский

---

Machine Learning and Deep Learning Techniques to Predict Software Defects: A Bibliometric Analysis, Systematic Review, Challenges and Future Works

Опубликована: Янв. 1, 2024

In Australia, approximately 66.00% of projects exceeded the programmed budget and 33% were out time, all them due to software failures.The purpose this study is gain a deeper understanding quartiles, countries, keywords, techniques, metrics, tools, platforms or languages, variables, data source dataset that have been used in predicting defects. A comprehensive search 55 articles was conducted, using keywords from 5 databases: Scopus, ProQuest, ScienceDirect, Ebscohost, Web Science 2019 2023. This article based on PRISMA (Preferred Reporting Items for Systematic Reviews Meta-Analysis) methodology, taking into account inclusion exclusion criteria. To then make synthesis findings studies following aspects such as dataset.The most techniques Support Vector Machine (SVM) Random Forest (RF), along with Accuracy F1-Score programming language Python, prominent variables Kilo (thousands) lines code (KLOC) Cyclomatic complexity, finally NASA's Metrics Data Program Repository dasource range minimum 759 instances 37 attributes maximum 3579 38 projects: CM1, MW1, PC1, PC3 PC4. systematic review provides scientific evidence, results describing how machine learning help predict

Язык: Английский

---

SISTEM KLASIFIKASI UNTUK MENENTUKAN TINGKAT STRESS MAHASISWA SECARA UMUM MENGGUNAKAN METODE K-NEAREST NEIGHBORS

Jurnal Informatika Teknologi dan Sains (Jinteks), Год журнала: 2024, Номер 6(3), С. 568 - 578

Опубликована: Авг. 1, 2024

Stres seringkali menjadi tantangan utama yang dihadapi oleh mahasiswa akibat tuntutan akademis dan sosial di lingkungan pendidikan. Faktor-faktor seperti gugup, ketidakmampuan untuk mengontrol diri, kekhawatiran, dsb. adalah beberapa pemicu stres semuanya dapat berdampak negatif terhadap kesehatan fisik mental mahasiswa. Penelitian ini bertujuan mengidentifikasi tingkat dialami dengan menggunakan metode K-Nearest Neighbors (KNN) mengevaluasi keakuratan hasil penelitian ini. Metode KNN digunakan mengklasifikasikan berdasarkan kemiripan atau kedekatan data lain dalam dataset. Dengan diambil dari situs data.world, menunjukkan bahwa mampu mencapai akurasi sebesar 91,58%. Selain itu, nilai presisi, recall, f1-score masing-masing 76,10%, 73,11%, 74,17%. memberikan kontribusi penting memahami efektivitas stres. Hasil diharapkan membantu pengembangan strategi lebih baik mengelola mengurangi kalangan

---

Clinical applications of artificial intelligence in diabetes management: A bibliometric analysis and comprehensive review

Informatics in Medicine Unlocked, Год журнала: 2024, Номер 50, С. 101567 - 101567

Опубликована: Янв. 1, 2024

Язык: Английский

---

Interpretasi model Stacking Ensemble untuk analisis sentimen ulasan aplikasi pinjaman online menggunakan LIME

AITI, Год журнала: 2024, Номер 21(2), С. 183 - 196

Опубликована: Сен. 30, 2024

Local Interpretable Model-agnostic Explanations(LIME) dapat digunakan untuk mengatasi masalah blackbox pada hasil model klasifikasi analisis sentimen. Penelitian ini menggunakan ulasan aplikasi pinjaman online di play store sebagai dataset. Masing-masing memiliki kelemahan dan ditingkatkan kinerjanya dengan stacking ensemble terutama permasalahan kelas data yang tidak seimbang. Dataset sudah diperoleh, dilakukan pembersihan data, pre-processing serta dirubah menjadi vektor numerik TF-IDF. Klasifikasi tiga dasar yaitu random forest, naïve bayes support vector machine(SVM). Luaran dari dijadikan masukan bagi logistic regression. Berdasarkan komparasi keempat model, kinerja terbaik akurasi 87,05%. Penerapan LIME intrepretasi sampel berhasil menjelaskan faktor-faktor berpengaruh terhadap keputusan probabilitas prediksi 95% sesuai pengamatan manual. Hasil penelitian bisa wawasan edukasi kepada masyarakat tentang kemudahan pinjol bahayanya tercermin sentimen positif negatif sebuah ulasan.

---

The usability of stacking-based ensemble learning model in crime prediction: a systematic review

Crime Prevention and Community Safety, Год журнала: 2024, Номер 26(4), С. 440 - 489

Опубликована: Ноя. 20, 2024

This research addresses the potential for tackling crime volumes and improving analytics through new enhancement strategies. The use of machine learning deep solutions is increasing in prediction, as many other fields. study aims to strengthen proactive approaches criminology by evaluating effectiveness stacking-based ensemble (S-BEL) model, which enhance overall performance combining strengths various algorithms improve facilitate prevention analyzes six studies leveraging S-BEL model along with 28 articles on seven utilizing models, 56 general prediction studies. findings highlight that stands out a prominent technique providing valuable insights law enforcement.

Язык: Английский

---

How do machine learning models perform in the detection of depression, anxiety, and stress among undergraduate students? A systematic review

Cadernos de Saúde Pública, Год журнала: 2024, Номер 40(11)

Опубликована: Янв. 1, 2024

Abstract: Undergraduate students are often impacted by depression, anxiety, and stress. In this context, machine learning may support mental health assessment. Based on the following research question: “How do models perform in detection of stress among undergraduate students?”, we aimed to evaluate performance these models. PubMed, Embase, PsycINFO, Web Science databases were searched, aiming at studies meeting criteria: publication English; targeting university students; empirical studies; having been published a scientific journal; predicting or outcomes via learning. The certainty evidence was analyzed using GRADE. As January 2024, 2,304 articles found, 48 met inclusion criteria. Different types data identified, including behavioral, physiological, internet usage, neurocerebral, blood markers, mixed data, as well demographic mobility data. Among 33 that provided accuracy assessment, 30 reported values exceeded 70%. Accuracy detecting ranged from 63% 100%, anxiety 53.69% 97.9%, depression 73.5% 99.1%. Although most present adequate performance, it should be noted 47 them only performed internal validation, which overstate Moreover, GRADE checklist suggested quality very low. These findings indicate algorithms hold promise Public Health; however, is crucial scrutinize their practical applicability. Further invest mainly external validation

Язык: Английский

---

Prediction of Diabetes Disease Based on Stacking Ensemble Using Oversampling Method and Hyperparameters

Опубликована: Янв. 1, 2023

Background: Diabetes is a very common disease today and has acquired worrying focus in the field of public health globally, fact, it estimated that number people with diabetes worldwide reached 415 million.Objective: Propose method 4 combined models based on Stacking order to predict diabetes. In addition, web interface was developed best model proposed this study.Methods: The dataset collected from Dataset composed 768 patient records used. data then pre-processed using Python programming language. To balance data, divided into values an oversampling applied distribute proportionally. Then, divisions were made balanced cross-validation for training, calibrated. Regarding development base algorithms, 7 independent algorithms used, proposed, finally obtain evaluation their respective metrics.Results: 1A (Logistic regression) Oversampling value Accuracy=91.50%, Sensitivity=91.60%, F1-Score=91.49% Precision= 91.50%, while respect metric ROC Curve, Oversampling, 2A (Random Forest) oversampling, Random Forest (Independent) percentage, being 97.00%.Conclusions: Implementing stacking method, helps make adequate diagnosis Therefore, by improvement prediction observed, surpassing performance

Язык: Английский

---

AI-based Depression Detection using Profile Information

Опубликована: Дек. 11, 2023

Depression is a severe mental health problem for people around the world, regardless of age, gender, or race. It cause psychological disability, and these disorders can have an impact on person's interpersonal connections, such as work environment family life, well their overall routines, irregular eating sleeping patterns. However, unfortunately, majority cases depression go undiagnosed and, therefore, untreated. Depression, when not detected at earlier stage, become illness may lead to suicide later stages. Consequently, it becomes crucial identify prevent stage. The data this study are collected through survey from undergraduates in consultation with psychiatrists professors.Further, Natural Language Processing(NLP) techniques Machine learning methodologies were used train evaluate efficiency proposed model. This looked various feature selection (FS) filter method Maximum Relevance Minimum Redundancy-mRMR, wrapper Recursive Feature Elimination-RFE, Boruta, Embedded method: Least Absolute Shrinkage Selection Operator-LASSO extract most significant features profile information user responsible forming depression. Adaboost model produced accuracy 94% considering all elements dataset. different techniques, applied, we found mRMR FS using Optuna Hypertuning 96%.

Язык: Английский

---