Too Good To Be True: performance overestimation in (re)current practices for Human Activity Recognition
원문 초록
Today, there are standard and well established procedures within the Human Activity Recognition (HAR) pipeline. However, some of these conventional approaches lead to accuracy overestimation. In particular, sliding windows for data segmentation followed by standard random k-fold cross validation, produce biased results. An analysis of previous literature and present-day studies, surprisingly, shows that these are common approaches in state-of-the-art studies on HAR. It is important to raise awareness in the scientific community about this problem, whose negative effects are being overlooked. Otherwise, publications of biased results lead to papers that report lower accuracies, with correct unbiased methods, harder to publish. Several experiments with different types of datasets and different types of classification models allow us to exhibit the problem and show it persists independently of the method or dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Network
Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural Networks
Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic Dataset
DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition
Label Leakage in Federated Inertial-based Human Activity Recognition
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices
토론
이 논문과 연결된 포럼 글이 아직 없습니다.