Investigating the impact of fatty acid profiles on biodiesel lubricity using artificial intelligence techniques

Cleaner Engineering and Technology, Год журнала: 2025, Номер unknown, С. 100913 - 100913

Опубликована: Фев. 1, 2025

Язык: Английский

---

Automated detection of construction work at heights and deployment of safety hooks using IMU with a barometer

Automation in Construction, Год журнала: 2022, Номер 147, С. 104714 - 104714

Опубликована: Дек. 28, 2022

Язык: Английский

---

Cancer Metastasis Prediction and Genomic Biomarker Identification through Machine Learning and eXplainable Artificial Intelligence in Breast Cancer Research

Diagnostics, Год журнала: 2023, Номер 13(21), С. 3314 - 3314

Опубликована: Окт. 26, 2023

Method: This research presents a model combining machine learning (ML) techniques and eXplainable artificial intelligence (XAI) to predict breast cancer (BC) metastasis reveal important genomic biomarkers in patients.A total of 98 primary BC samples was analyzed, comprising 34 from patients who developed distant metastases within 5-year follow-up period 44 remained disease-free for at least 5 years after diagnosis. Genomic data were then subjected biostatistical analysis, followed by the application elastic net feature selection method. technique identified restricted number associated with metastasis. A light gradient boosting (LightGBM), categorical (CatBoost), Extreme Gradient Boosting (XGBoost), Trees (GBT), Ada (AdaBoost) algorithms utilized prediction. To assess models' predictive abilities, accuracy, F1 score, precision, recall, area under ROC curve (AUC), Brier score calculated as performance evaluation metrics. promote interpretability overcome "black box" problem ML models, SHapley Additive exPlanations (SHAP) method employed.The LightGBM outperformed other yielding remarkable accuracy 96% an AUC 99.3%. In addition evaluation, XAI-based SHAP results, increased expression levels TSPYL5, ATP5E, CA9, NUP210, SLC37A1, ARIH1, PSMD7, UBQLN1, PRAME, UBE2T (p ≤ 0.05) found be incidence Finally, decreased CACTIN, TGFB3, SCUBE2, ARL4D, OR1F1, ALDH4A1, PHF1, CROCC genes also determined increase risk BC.The findings this study may prevent disease progression potentially improve clinical outcomes recommending customized treatment approaches patients.

Язык: Английский

---

Chronic kidney disease prediction using boosting techniques based on clinical parameters

PLoS ONE, Год журнала: 2023, Номер 18(12), С. e0295234 - e0295234

Опубликована: Дек. 1, 2023

Chronic kidney disease (CKD) has become a major global health crisis, causing millions of yearly deaths. Predicting the possibility person being affected by will allow timely diagnosis and precautionary measures leading to preventive strategies for health. Machine learning techniques have been popularly applied in various diagnoses predictions. Ensemble approaches useful predicting many complex diseases. In this paper, we utilise boosting method, one popular ensemble learnings, achieve higher prediction accuracy CKD. Five algorithms are employed: XGBoost, CatBoost, LightGBM, AdaBoost, gradient boosting. We experimented with CKD data set from UCI machine repository. Various preprocessing steps employed better performance, along suitable hyperparameter tuning feature selection. assessed degree importance each dataset The performance model was evaluated accuracy, precision, recall, F1-score, Area under curve-receiving operator characteristic (AUC-ROC), runtime. AdaBoost found overall best among five algorithms, scoring highest almost all measures. It attained 100% 98.47% training testing sets. This also exhibited AUC-ROC curve performance.

Язык: Английский

---

Novel Biomarker Prediction for Lung Cancer Using Random Forest Classifiers

Cancer Informatics, Год журнала: 2023, Номер 22

Опубликована: Янв. 1, 2023

Lung cancer is considered the most common and deadliest type. could be mainly of 2 types: small cell lung non-small cancer. Non-small affected by about 85% while only 14%. Over last decade, functional genomics has arisen as a revolutionary tool for studying genetics uncovering changes in gene expression. RNA-Seq been applied to investigate rare novel transcripts that aid discovering genetic occur tumours due different cancers. Although helps understand characterise expression involved diagnostics, biomarkers remains challenge. Usage classification models uncover classify based on levels over The current research concentrates computing transcript statistics from files with normalised fold change genes identifying quantifiable differences between reference genome samples. collected data analysed, machine learning were developed causing NSCLC, SCLC, both or neither. An exploratory analysis was performed identify probability distribution principal features. Due limited number features available, all them used predicting class. To address imbalance dataset, an under-sampling algorithm Near Miss carried out dataset. For classification, primarily focused 4 supervised algorithms: Logistic Regression, KNN classifier, SVM classifier Random Forest additionally, ensemble algorithms considered: XGboost AdaBoost. Out these, weighted metrics considered, showing 87% accuracy best performing thus predict NSCLC SCLC. dataset restrict any further improvement model's precision. In our present study using values (LogFC, P Value) feature sets Classifier BRAF, KRAS, NRAS, EGFR predicted possible ATF6, ATF3, PGDFA, PGDFD, PGDFC PIP5K1C SCLC transcriptome analysis. It gave precision 91.3% 91% recall after fine tuning. Some CDK4, CDK6, BAK1, CDKN1A, DDB2.

Язык: Английский

---

Digital twin and blockchain-enabled trusted optimal-state synchronized control approach for distributed smart manufacturing system in social manufacturing

Journal of Manufacturing Systems, Год журнала: 2024, Номер 76, С. 385 - 410

Опубликована: Авг. 17, 2024

Язык: Английский

---

Re-tear after arthroscopic rotator cuff tear surgery: risk analysis using machine learning

Journal of Shoulder and Elbow Surgery, Год журнала: 2023, Номер 33(4), С. 815 - 822

Опубликована: Авг. 23, 2023

Язык: Английский

---

Entropy and improved k‐nearest neighbor search based under‐sampling (ENU) method to handle class overlap in imbalanced datasets

Concurrency and Computation Practice and Experience, Год журнала: 2023, Номер 36(2)

Опубликована: Авг. 30, 2023

Summary Many real‐world application datasets such as medical diagnostics, fraud detection, biological classification, risk analysis and so forth are facing class imbalance overlapping problems. It seriously affects the learning of classification model on these because minority instances not visible to learner in overlapped region performance learners is biased towards majority. Undersampling‐based methods most commonly used techniques handle above‐mentioned The major problem with excessive elimination information loss, that is, unable retain potential informative majority instances. We propose a novel entropy neighborhood‐based undersampling (ENU) removed only those from which having less informativeness (entropy) score than threshold entropy. Most existing improved sensitivity scores significantly but many other contexts. ENU first computes for and, local density‐based KNN search identify To tackle effectively defined four KNN‐based procedures (ENUB, ENUT, ENUC, ENUR) effective undersampling. outperformed sensitivity, G‐mean, F1‐score average ranking reduced loss compared state‐of‐the‐art methods.

Язык: Английский

---

Computer-aided methods for combating Covid-19 in prevention, detection, and service provision approaches

Neural Computing and Applications, Год журнала: 2023, Номер 35(20), С. 14739 - 14778

Опубликована: Май 5, 2023

Язык: Английский

---

Stacking Ensemble Algorithm to Predict Re-keying in Group Key Management

Arabian Journal for Science and Engineering, Год журнала: 2025, Номер unknown

Опубликована: Фев. 3, 2025

Язык: Английский

---