Feb 1, 2021 · Extensive experimental results show that our proposed method outperforms the fixed threshold method, tra- ditional machine learning-based ...

Extensive experimental results show that our proposed method outperforms the fixed threshold method, traditional machine learning based methods, and other ...

This work proposes a multisensor deep learning model to predict the IO state, which outperforms the fixed threshold method, traditional machine ...

Our proposed model first leverages the deep learning neural network to extract higher-level features for different sensors, then utilizes LSTM to capture ...

Nov 24, 2023 · Indoor/Outdoor (IO) status serves as a critical foundation for various upstream tasks, including seamless pedestrian navigation, power ...

Indoor/outdoor switching detection using multisensor DenseNet and LSTM. Y Zhu, H Luo, F Zhao, R Chen. IEEE Internet of Things Journal 8 (3), 1544-1556, 2020.

The overall objective of the framework is to accurately classify users' indoor–outdoor contexts by integrating sensory data, location information, adaptive ...

Feb 29, 2024 · This article proposes a hybrid model that combines a dense convolutional network (DenseNet) and long short-term memory (LSTM) with a channel attention ...

The proposed DL multivariate TSC framework exploits only low power consumption sensors to infer a user's environment, and it outperforms state-of-the-art models ...

A lightweight sensing service that runs on the mobile phone and detects the indoor/outdoor environment in a fast, accurate, and efficient manner.