Visible to the public Improving Black Box Classification Model Veracity for Electronics Anomaly Detection

TitleImproving Black Box Classification Model Veracity for Electronics Anomaly Detection
Publication TypeConference Paper
Year of Publication2020
AuthorsHerrera, A. E. Hinojosa, Walshaw, C., Bailey, C.
Conference Name2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA)
Date Publishednov
KeywordsBB-stepwise algorithm, black box, black box classification model veracity, black box encryption, black box model, classification, Classification algorithms, classification model transparency, composability, Conferences, data driven classification models, Data models, decision tree models, Decision trees, electronics anomaly detection, electronics devices, electronics industry, fault detection, fault diagnosis, feature extraction, feature selection, higher transparency, Industrial electronics, KNN, KNN models, KNN-stepwise, learning (artificial intelligence), manufactured electronics, manufacturing systems, Metrics, nearest neighbour methods, pattern classification, performance evaluation, production engineering computing, pubcrawl, Resiliency, Stepwise, Veracity
AbstractData driven classification models are useful to assess quality of manufactured electronics. Because decisions are taken based on the models, their veracity is relevant, covering aspects such as accuracy, transparency and clarity. The proposed BB-Stepwise algorithm aims to improve the classification model transparency and accuracy of black box models. K-Nearest Neighbours (KNN) is a black box model which is easy to implement and has achieved good classification performance in different applications. In this paper KNN-Stepwise is illustrated for fault detection of electronics devices. The results achieved shows that the proposed algorithm was able to improve the accuracy, veracity and transparency of KNN models and achieve higher transparency and clarity, and at least similar accuracy than when using Decision Tree models.
Citation Keyherrera_improving_2020