AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning Datum-Wise Sampling Frequency for Energy-Efficient Human Activity Recognition

Weihao Cheng, Sarah Erfani, Rui Zhang, Ramamohanarao Kotagiri

AAAI 2018 · Architectures and efficiency › RNNs and normalization · approach: LSTM design and memory · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
alternating learning of theta and psi instead of separate learning (ablation)DWFS · HARSD, lambda=0.5Error-Cost Index: 26.44 -> 25.37Improved
alternating learning instead of separate learning (ablation)DWFS · HASCError-Cost Index: 22.51 -> 22.27No clear effect
alternating learning instead of separate learning (ablation)DWFS · DSA, lambda=0.5Error-Cost Index: 34.89 -> 34.87Improved
alternating learning instead of cross-validation learning of psi (ablation)DWFS · DSA, lambda=0.5Error-Cost Index: 37.35 -> 34.87Improved
datum-wise MDP policy instead of discrete-state MDP-DSDWFS · HASC, lambda=0.5Error-Cost Index: 26.40 -> 22.27Improved
datum-wise MDP policy instead of RNN policyDWFS · HARSD, lambda=0.5Error-Cost Index: 25.99 -> 25.37Improved
adaptive frequency selection instead of random frequencyDWFS · HASC, lambda=0.5Error-Cost Index: 39.54 -> 22.27Improved
adaptive DWFS instead of best constant frequencyDWFS · HASC, lambda=0.5Error-Cost Index: 23.08 -> 22.27Improved
lambda = 0 (energy ignored)DWFS · all datasetsError-Cost IndexHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy