XAI-3DP: Diagnosis and Understanding Faults of 3-D Printer With Explainable Ensemble AI

Article Chemistry, Analytical

Classification and Explanation for Intrusion Detection System Based on Ensemble Trees and SHAP Method

Thi-Thu-Huong Le et al.

Summary: This paper proposes an ML-based IDS method that improves attack detection performance and provides explanations of classification decisions using an ensemble tree approach combined with explainable AI. The method is evaluated using large IoT-based IDS datasets, achieving effective attack detection and supporting cybersecurity experts in optimizing and evaluating their judgments based on explanations.

SENSORS (2022)

Add to Collection

Article Energy & Fuels

An optimized XGBoost method for predicting reservoir porosity using petrophysical logs

Shaowei Pan et al.

Summary: The XGBoost algorithm is used to construct a porosity prediction model that is optimized through grid search and genetic algorithm, significantly improving prediction accuracy and generalization performance. The model outperforms other methods in terms of RMSE, MAE, and MAPE on the test set, providing useful technical references for porosity prediction models in oil fields.

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING (2022)

Add to Collection

Article Geology

Ensemble learning models with a Bayesian optimization algorithm for mineral prospectivity mapping

Jiangning Yin et al.

Summary: This study applied machine learning algorithms (XGBoost and RF models) to create mineral prospectivity mapping (MPM) for a specific area in southern Hunan Province, China. The models were optimized using a Bayesian optimization algorithm (BOA) to improve their performance. The results showed that the XGBoost model outperformed the RF model in terms of accuracy and stability, indicating its great potential for MPM.

ORE GEOLOGY REVIEWS (2022)

Add to Collection

Article Telecommunications

CovidXAI: explainable AI assisted web application for COVID-19 vaccine prioritization

Deepraj Chowdhury et al.

Summary: COVID-19 vaccines are in limited supply and face a significant gap between supply and demand, resulting in uneven distribution. To address this issue, a novel architecture called CovidXAI is proposed, which utilizes a self-collected dataset to train models and employs explainable AI to optimize vaccine distribution.

INTERNET TECHNOLOGY LETTERS (2022)

Add to Collection

Article Automation & Control Systems

A novel doublet extreme learning machines for Delta 3D printer fault diagnosis using attitude sensor

Jianwen Guo et al.

Summary: The study introduces a new activation function, doublet ELM (DELM), evaluates its performance using experimental data collected from a 3D printer platform, and compares it with other activation functions. Results show that DELM achieves the highest accuracy in different hidden nodes and performs well even with small samples.

ISA TRANSACTIONS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI

Erico Tjoa et al.

Summary: Artificial intelligence and machine learning have shown remarkable performances in various fields, but the challenge of interpretability remains. The medical sector requires higher levels of interpretability to ensure the reliability of machine decisions, and a deeper understanding of the mechanisms behind machine algorithms is needed to advance medical practices.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic

Deep Learning-Based 3D Printer Fault Detection

Mark Verana et al.

Summary: An fault diagnosis method for 3D printers based on convolutional neural network (CNN) was proposed in this work, achieving high accuracy by utilizing a large set of data streams. The proposed CNN outperformed traditional methods in accuracy.

12TH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN 2021) (2021)

Add to Collection

Article Green & Sustainable Science & Technology