WiFi-Based Indoor Robot Positioning Using Deep Fuzzy Forests

Zhang, Le; Chen, Zhenghua; Cui, Wei; Li, Bing; Chen, Cen; Cao, Zhiguang; Gao, Kaizhou

doi:10.1109/jiot.2020.2986685

Cited by 65 publications

(36 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, our future work will focus on better feature extraction algorithm to address this issue. Moreover, we will also consider deep forest (Ma et al, 2020 ; Zhang et al, 2020 ) as classifier and deep neural networks (Wang et al, 2018 ) for microexpression recognition in the future.…”

Section: Discussionmentioning

confidence: 99%

A New Feature Extraction and Recognition Method for Microexpression Based on Local Non-negative Matrix Factorization

et al. 2020

View full text Add to dashboard Cite

Microexpression is usually characterized by short duration and small action range, and the existing general expression recognition algorithms do not work well for microexpression. As a feature extraction method, non-negative matrix factorization can decompose the original data into different components, which has been successfully applied to facial recognition. In this paper, local non-negative matrix factorization is explored to decompose microexpression into some facial muscle actions, and extract features for recognition based on apex frame. However, the existing microexpression datasets fall short of samples to train a classifier with good generalization. The macro-to-micro algorithm based on singular value decomposition can augment the number of microexpressions, but it cannot meet non-negative properties of feature vectors. To address these problems, we propose an improved macro-to-micro algorithm to augment microexpression samples by manipulating the macroexpression data based on local non-negative matrix factorization. Finally, several experiments are conducted to verify the effectiveness of the proposed scheme, which results show that it has a higher recognition accuracy for microexpression compared with the related algorithms based on CK+/CASME2/SAMM datasets.

show abstract

Section: Discussionmentioning

confidence: 99%

A New Feature Extraction and Recognition Method for Microexpression Based on Local Non-negative Matrix Factorization

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In the online positioning stage, Mahalanobis distance was used to replace Euclidean distance for positioning to improve positioning accuracy. In the field of robot positioning, Le Zhang et al [13] designed a lightweight indoor robot localization system that operates based on low-cost WiFi received signal strength (RSS) and can be readily plugged into any existing WiFi network infrastructure. And an end-to-end deep fuzzy forest algorithm was proposed for robust position estimation.…”

Section: Introductionmentioning

confidence: 99%

CCpos: WiFi Fingerprint Indoor Positioning System Based on CDAE-CNN

Feng

Zuo

Wang

2021

Sensors

View full text Add to dashboard Cite

WiFi is widely used for indoor positioning because of its advantages such as long transmission distance and ease of use indoors. To improve the accuracy and robustness of indoor WiFi fingerprint localization technology, this paper proposes a positioning system CCPos (CADE-CNN Positioning), which is based on a convolutional denoising autoencoder (CDAE) and a convolutional neural network (CNN). In the offline stage, this system applies the K-means algorithm to extract the validation set from the all-training set. In the online stage, the RSSI is first denoised and key features are extracted by the CDAE. Then the location estimation is output by the CNN. In this paper, the Alcala Tutorial 2017 dataset and UJIIndoorLoc are adopted to verify the performance of the CCpos system. The experimental results show that our system has excellent noise immunity and generalization performance. The mean positioning errors on the Alcala Tutorial 2017 dataset and the UJIIndoorLoc are 1.05 m and 12.4 m, respectively.

show abstract

“…Recently, the increasing indoor-based services have attracted the attention of researchers to study indoor localization approaches. Because Global Positioning System (GPS) signals cannot be accessed well in indoor environments, various other signals such as radio frequency identification (RFID) [1], magnetic and light sensors [2], [3], Wi-Fi [4], [5] or Bluetooth low energy (BLE) beacons [6]- [10] have been employed for this purpose. Among all approaches, most studies [7]- [12] have focused on the received signal strength indicator (RSSI) obtained from BLE beacons because of the low cost and compatibility for simultaneous scans.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, in an exhibition, a recommender system cannot recommend the exhibit based on coordinate positions (e.g. exhibit A at (12,5)), which would be difficult for visitors to understand. Therefore, it will be better if the usual indoor location is enriched by semantic information to provide seamless understanding for visitors (exhibit A is located in the Classical Area).…”

Section: Introductionmentioning

confidence: 99%

A Stacked Denoising Autoencoder and Long Short-Term Memory Approach With Rule-Based Refinement to Extract Valid Semantic Trajectories

2021

View full text Add to dashboard Cite

Indoor location-based services have been widely investigated to take advantage of semantic trajectories for providing user oriented services in indoor environments. Although indoor semantic trajectories can provide seamless understanding to users regarding the provided location-based services, studies on the application of deep learning approaches for robust and valid semantic indoor localization are lacking. In this study, we combined a stacked denoising autoencoder and long short term memory technique with a rule-based refinement method applying a rule-based hidden Markov model (HMM) to perform robust and valid semantic trajectory extraction. In particular, our rule-based HMM approach incorporates a direct set of rules into HMM to resolve invalid movements of the extracted semantic trajectories and is extensible to various deep learning techniques. We compared the performance of our proposed approach with that of other cutting-edge deep learning approaches on two different real-world data sets. The experimental results demonstrate the feasibility of our proposed approach to produce more robust and valid semantic trajectories.

show abstract

WiFi-Based Indoor Robot Positioning Using Deep Fuzzy Forests

Cited by 65 publications

References 45 publications

A New Feature Extraction and Recognition Method for Microexpression Based on Local Non-negative Matrix Factorization

A New Feature Extraction and Recognition Method for Microexpression Based on Local Non-negative Matrix Factorization

CCpos: WiFi Fingerprint Indoor Positioning System Based on CDAE-CNN

A Stacked Denoising Autoencoder and Long Short-Term Memory Approach With Rule-Based Refinement to Extract Valid Semantic Trajectories

Contact Info

Product

Resources

About