@article{ART003399408},
author={Kwon Jung-Hyok and EUIJIK KIM},
title={Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition},
journal={Journal of Internet of Things and Convergence},
issn={2466-0078},
year={2026},
volume={12},
number={5},
pages={12}
TY - JOUR
AU - Kwon Jung-Hyok
AU - EUIJIK KIM
TI - Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition
JO - Journal of Internet of Things and Convergence
PY - 2026
VL - 12
IS - 5
PB - The Korea Internet of Things Society
SP - 12
EP -
SN - 2466-0078
AB - This paper presents a channel state information (CSI)-based hierarchical temporal inference scheme for recognizing human activity contexts in Internet of Things (IoT) environments. Accurate context inference requires comprehensive consideration of not only the types of individual activities but also their durations and the transitions between preceding and subsequent activities. However, conventional CSI-based human activity recognition (HAR) approaches that rely on short-term activity classification results have difficulty adequately reflecting these temporal characteristics. The proposed scheme estimates a short-term activity probability vector from CSI observed over a fixed period and accumulates consecutive probability vectors to derive a long-term activity state. It then infers the human activity context by considering the duration and transitions of long-term activity states. The proposed scheme uses the entire probability vector instead of assigning a single label to each short-term activity, thereby mitigating the propagation of momentary misclassifications to context decisions. Experimental results showed that the proposed scheme achieved higher context recognition performance than the existing scheme using only the classification labels of short-term activities.
KW - Hierarchical temporal inference;Context recognition;Context-aware IoT;HAR;CSI
DO -
UR -
ER -
Kwon Jung-Hyok and EUIJIK KIM. (2026). Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition. Journal of Internet of Things and Convergence, 12(5), 12.
Kwon Jung-Hyok and EUIJIK KIM. 2026, "Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition", Journal of Internet of Things and Convergence, vol.12, no.5 12.
Kwon Jung-Hyok, EUIJIK KIM "Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition" Journal of Internet of Things and Convergence 12.5 12 (2026) : 12.
Kwon Jung-Hyok, EUIJIK KIM. Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition. 2026; 12(5), 12.
Kwon Jung-Hyok and EUIJIK KIM. "Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition" Journal of Internet of Things and Convergence 12, no.5 (2026) : 12.
Kwon Jung-Hyok; EUIJIK KIM. Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition. Journal of Internet of Things and Convergence, 12(5), 12.
Kwon Jung-Hyok; EUIJIK KIM. Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition. Journal of Internet of Things and Convergence. 2026; 12(5) 12.
Kwon Jung-Hyok, EUIJIK KIM. Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition. 2026; 12(5), 12.
Kwon Jung-Hyok and EUIJIK KIM. "Channel State Information-based Hierarchical Temporal Inference for Human Activity Context Recognition" Journal of Internet of Things and Convergence 12, no.5 (2026) : 12.
