Опубликована: Янв. 1, 2024
Язык: Английский
Sustainability, Год журнала: 2024, Номер 16(11), С. 4642 - 4642
Опубликована: Май 30, 2024
Driver behavior plays a pivotal role in ensuring road safety as it is significant factor preventing traffic crashes. Although extensive research has been conducted on this topic developed countries, there notable gap understanding driver developing such Pakistan. It essential to recognize that the cultural nuances, law enforcement practices, and government investments Pakistan are significantly different from those other regions. Recognizing disparity, study aims comprehensively understand risky driving behaviors Peshawar, To achieve goal, Behavior Questionnaire was designed, responses were collected using Google Forms, resulting 306 valid responses. The employs Fuzzy Analytical Hierarchy Process framework evaluate behavior’s ranking criteria weight factors. This assigns relative weights captures uncertainty of thought patterns. Additionally, machine learning techniques, including support vector machine, decision tree, Naïve Bayes, Random Forest, ensemble model, used predict behavior, enhancing reliability accuracy predictions. results showed approach outperformed others with prediction 0.84. In addition, findings revealed three most attributes violations, errors, lapses. Certain factors, clear signage attention, identified important factors improving drivers’ risk perception. serves benchmark for policymakers, offering valuable insights formulate effective policies safety.
Язык: Английский
Процитировано
3
FinTech, Год журнала: 2024, Номер 3(1), С. 184 - 215
Опубликована: Март 5, 2024
Peer-to-peer lending, a novel element of Internet finance that links lenders and borrowers via online platforms, has generated large profits for investors. However, borrowers’ missed payments have negatively impacted the industry’s sustainable growth. It is imperative to create system can correctly predict loan defaults lessen damage brought on by defaulters. The goal this study fill gap in literature exploring feasibility developing prediction models P2P without relying heavily personal data while also focusing identifying key variables influencing repayment capacity through systematic feature selection exploratory analysis. Given this, aims computational model aids determining approval or rejection application, financial provided applicants. selected dataset, sourced from an open database, contains 8578 transaction records includes 14 attributes related information, with no included. A dataset first subjected in-depth analysis find behaviors connected defaults. Subsequently, diverse noteworthy machine learning classification algorithms, including Random Forest, Support Vector Machine, Decision Tree, Logistic Regression, Naïve Bayes, XGBoost, were employed build capable discerning who repay their loans those do not. Our findings indicate fail comply lenders’ credit policies, pay elevated interest rates, possess low FICO ratings are at higher likelihood defaulting. Furthermore, risk observed among clients obtain small businesses. All models, XGBoost successfully developed performed satisfactorily achieved accuracy over 80%. When decision threshold set 0.4, best performance predicting defaulters using logistic regression, which accurately identifies 83% defaulted loans, recall 83%, precision 21% f1 score 33%.
Язык: Английский
Процитировано
2
Chemical Engineering Journal, Год журнала: 2024, Номер unknown, С. 155948 - 155948
Опубликована: Сен. 1, 2024
Язык: Английский
Процитировано
2
Procedia Computer Science, Год журнала: 2024, Номер 241, С. 476 - 481
Опубликована: Янв. 1, 2024
The paper is dedicated to the security measures within concept of MetaHospital. idea MetaHospital an answer modern challenges time where interaction through digital media no longer a fantasy. In this authors describe and its modules as well ways personal data protection. protection model given with detailed description each stage. Through incorporation rigorous protocols, guarantees safeguarding patient information, cultivating trustworthy environment for medical care research endeavours. Committed progress well-being, persistently refines practices, leveraging technology data-driven perspectives enhance healthcare delivery optimize outcomes.
Язык: Английский
Процитировано
1
Life, Год журнала: 2024, Номер 14(11), С. 1488 - 1488
Опубликована: Ноя. 15, 2024
The purpose of this research is to contribute the development approaches for classification and segmentation various gastrointestinal (GI) cancer diseases, such as dyed lifted polyps, resection margins, esophagitis, normal cecum, pylorus, Z line, ulcerative colitis. This relevant essential because current challenges related absence efficient diagnostic tools early diagnostics GI cancers, which are fundamental improving diagnosis these common diseases. To address above challenges, we propose a new hybrid model, U-MaskNet, combination U-Net Mask R-CNN models. Here, utilized pixel-wise instance segmentation, together forming solution classifying segmenting cancer. Kvasir dataset, includes 8000 endoscopic images validate proposed methodology. experimental results clearly demonstrated that novel model provided superior compared other well-known models, DeepLabv3+, FCN, DeepMask, well improved performance state-of-the-art (SOTA) including LeNet-5, AlexNet, VGG-16, ResNet-50, Inception Network. quantitative analysis revealed our outperformed achieving precision 98.85%, recall 98.49%, F1 score 98.68%. Additionally, achieved Dice coefficient 94.35% IoU 89.31%. Consequently, developed increased accuracy reliability in detecting cancer, it was proven can potentially be used process and, consequently, patient care clinical environment. work highlights benefits integrating opening way further medical image segmentation.
Язык: Английский
Процитировано
1
Опубликована: Янв. 1, 2024
Язык: Английский
Процитировано
0