A survey on multi-label feature selection from perspectives of label fusion

Information Fusion, Journal Year: 2023, Volume and Issue: 100, P. 101948 - 101948

Published: Aug. 2, 2023

Language: Английский

---

Advanced filter-based feature selection for improved load identification in solar-powered aircraft distribution systems using XGBoost

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116764 - 116764

Published: Jan. 1, 2025

Language: Английский

---

TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration Data

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 75337 - 75350

Published: Jan. 1, 2023

Antimicrobial Resistance (AMR) is a growing public and veterinary health concern, the ability to accurately predict AMR from antibiotics administration data crucial for effectively treating managing infections. While genomics-based approaches can provide better results, sequencing, assembling, applying Machine Learning (ML) methods take several hours. Therefore, alternative are required. This study focused on using ML antimicrobial stewardship by utilising extracted hospital electronic records, which be done in real-time, developing an interpretable 1D-transformer model predicting AMR. A multi-baseline integrated gradient pipeline was also incorporated interpret model, quantitative validation metrics were introduced validate model. The performance of proposed evaluated dataset urinary tract infection (UTI) patients with four antibiotics. achieved 10% higher area under curve (AUC) outperformed traditional models. Explainable Artificial Intelligence (XAI) provided identifying signatures contributing predictions. could used as decision support tool personalised treatment, introducing AMR-aware food management AMR, it identify targeted interventions.

Language: Английский

---

A novel bayesian network-based ensemble classifier chains for multi-label classification

Complex & Intelligent Systems, Journal Year: 2024, Volume and Issue: 10(5), P. 7373 - 7399

Published: July 15, 2024

Abstract In this paper, we address the challenges of random label ordering and limited interpretability associated with Ensemble Classifier Chains (ECC) by introducing a novel ECC method, ECC-MOO&BN, which integrates Bayesian Networks (BN) Multi-Objective Optimization (MOO). This approach is designed to concurrently overcome these limitations. The ECC-MOO&BN method focuses on extracting diverse interpretable orderings for classifier. We initiated process employing mutual information investigate relationships establish initial structures BN. Subsequently, an enhanced NSGA-II algorithm was applied develop series Directed Acyclic Graphs (DAGs) that effectively balance likelihood complexity BN structure. rationale behind using MOO lies in its ability optimize both simultaneously, not only diversifies DAG generation but also helps avoid overfitting during production orderings. DAGs, once sorted topologically, yielded orderings, were then seamlessly integrated into framework addressing multi-label classification (MLC) problems. Experimental results show when benchmarked against eleven leading-edge MLC algorithms, our proposed achieves highest average ranking across seven evaluation criteria nine out thirteen datasets. Friedman test Nemenyi indicate performance has significant advantage compared other algorithms.

Language: Английский

---

Optimized Ensemble Learning Framework for Prioritizing Biomolecular Markers in Yield Prediction Efficiency Enhancement

Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 89 - 103

Published: Jan. 1, 2024

Language: Английский

---

Explainable Deep Learning Approach for Multilabel Classification of Antimicrobial Resistance With Missing Labels

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 113073 - 113085

Published: Jan. 1, 2022

Predicting Antimicrobial Resistance (AMR) from genomic sequence data has become a significant component of overcoming the AMR challenge, especially given its potential for facilitating more rapid diagnostics and personalised antibiotic treatments. With recent advances in sequencing technologies computing power, deep learning models have been widely adopted to predict reliably error-free. There are many different types AMR; therefore, any practical prediction system must be able identify multiple AMRs present sequence. Unfortunately, most datasets do not all labels marked, thereby making modelling approach challenging owing reliance on reliability accuracy. This paper addresses this issue by presenting an effective solution, Mask-Loss 1D convolution neural network (ML-ConvNet), with missing labels. The core ML- ConvNet utilises masked loss function that overcomes effect predicting AMR. proposed ML-ConvNet is demonstrated outperform state-of-the-art methods literature 10.5%, according F1 score. model's performance evaluated using degrees label found conventional 76% score when 86.68% missing. Furthermore, was established explainable artificial intelligence (XAI) pipeline, it ideally suited hospital healthcare settings, where model interpretability essential requirement.

Language: Английский

---

Leveraging class hierarchy for detecting missing annotations on hierarchical multi-label classification

Computers in Biology and Medicine, Journal Year: 2022, Volume and Issue: 152, P. 106423 - 106423

Published: Dec. 14, 2022

Language: Английский

---