Multilayer probability extreme learning machine for device-free localization

Abstract

Device-free localization (DFL) is becoming one of the new techniques in wireless localization field, due to its advantage that the target to be localized does not need to attach any electronic device. One of the key issues of DFL is how to characterize the influence of the target on the wireless links, such that the target's location can be accurately estimated by analyzing the changes of the signals of the links. Most of the existing related research works usually extract the useful information from the links through manual approaches, which are labor-intensive and time-consuming. Deep learning approaches have attempted to automatically extract the useful information from the links, but the training of the conventional deep learning approaches are time-consuming, because a large number of parameters need to be fine-tuned multiple times. Motivated by the fast learning speed and excellent generalization performance of extreme learning machine (ELM), which is an emerging training approach for generalized single hidden layer feedforward neural networks (SLFNs), this paper proposes a novel hierarchical ELM based on deep learning theory, named multilayer probability ELM (MP-ELM), for automatically extracting the useful information from the links, and implementing fast and accurate DFL. The proposed MP-ELM is stacked by ELM autoencoders, so it also keeps the very fast learning speed of ELM. In addition, considering the uncertainty and redundant links existing in DFL, MP-ELM outputs the probabilistic estimation of the target's location instead of the deterministic output. The validity of the proposed MP-ELM-based DFL is evaluated both in the indoor and the outdoor environments, respectively. Experimental results demonstrate that the proposed MP-ELM can obtain better performance compared with classic ELM, multilayer ELM (ML-ELM), hierarchical ELM (H-ELM), deep belief network (DBN), and deep Boltzmann machine (DBM).

Non-iterative and Fast Deep Learning: Multilayer Extreme Learning Machines

“…In [57], we stacked ELM-AEs for designing a multilayer probability ELM (MP-ELM). Different from the aforementioned ML-ELMs, MP-ELM outputs the probability of the predicted results belonging to all the classes instead of fitting to data, which can significantly alleviate the effects of accumulated errors on the final predicted results.…”

Online Sequential Extreme Learning Machine With Dynamic Forgetting Factor

“…Extreme learning machine (ELM) is a special type of feedforward neural network, in which the input weights and hidden bias are assigned randomly and then remain the same throughout the training process while the output weights are obtained analytically. This non-iterative learning mechanism enables it to achieve much faster training speed than the traditional neural networks in many scenarios [50], [51]. This section briefly reviews the training mechanism of ELM and online sequential ELM (OS-ELM).…”

Kullback–Leibler Divergence Based Probabilistic Approach for Device-Free Localization Using Channel State Information

“…Zhang et al [32] proposed an ELM algorithm incorporated with a residual compensation strategy and demonstrated its efficiency in an RSSI-based DFL application. Additionally, probability-based machine learning algorithms, such as multilayer probability ELM (MP-ELM) [33], are also proposed to implement a DFL application. Gao et al [34] utilized an ELM Ensemble together with Principal Component Analysis (PCA) to implement a DFL application.…”