scholarly journals Fingerprint Feature Extraction for Indoor Localization

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5434
Author(s):  
Jehn-Ruey Jiang ◽  
Hanas Subakti ◽  
Hui-Sung Liang
Keyword(s):  
Feature Extraction ◽  
Indoor Localization ◽  
Principal Component ◽  
Reference Points ◽  
Average Error ◽  
Minkowski Distance ◽  
Received Signal Strength Indication ◽  
Fingerprint Feature Extraction ◽  
Fingerprint Feature ◽  
Better Than

This paper proposes a fingerprint-based indoor localization method, named FPFE (fingerprint feature extraction), to locate a target device (TD) whose location is unknown. Bluetooth low energy (BLE) beacon nodes (BNs) are deployed in the localization area to emit beacon packets periodically. The received signal strength indication (RSSI) values of beacon packets sent by various BNs are measured at different reference points (RPs) and saved as RPs’ fingerprints in a database. For the purpose of localization, the TD also obtains its fingerprint by measuring the beacon packet RSSI values for various BNs. FPFE then applies either the autoencoder (AE) or principal component analysis (PCA) to extract fingerprint features. It then measures the similarity between the features of PRs and the TD with the Minkowski distance. Afterwards, k RPs associated with the k smallest Minkowski distances are selected to estimate the TD’s location. Experiments are conducted to evaluate the localization error of FPFE. The experimental results show that FPFE achieves an average error of 0.68 m, which is better than those of other related BLE fingerprint-based indoor localization methods.

Indoor localization algorithm based on behavior-driven predictive learning in crowdsourced Wi-Fi environments

2019 ◽  
Vol 33 (14n15) ◽  
pp. 1940036 ◽  
Author(s):  
Boney A. Labinghisa ◽  
Dong Myung Lee
Keyword(s):  
Shortest Path ◽  
Indoor Localization ◽  
Principal Component ◽  
Reference Points ◽  
Average Error ◽  
Localization Algorithm ◽  
Received Signal Strength Indicator ◽  
Predictive Learning ◽  
Starting Location ◽  
Error Distance

The indoor localization algorithm based on the behavior-driven predictive learning (BDPLA) executes machine-learning predictions by computing the shortest path from a starting location to a destination. The proposed algorithm selects a set of reference points (RPs) to predict the shortest path using all available RPs from the crowdsourced Wi-Fi environment. In addition, the proposed algorithm utilizes the collected received signal strength indicator (RSSI) values to determine the error distance. Using principal component analysis (PCA), the existing crowdsourced RSSI data can be calibrated to help decrease the inconsistent RSSI values among all received signals by reconstructing the values. The average error distance of 3.68 m achieved better results compared with the traditional fingerprint map with an average result of 6.96 m.

Feature Extraction of Surface Electromyography Based on Improved Small-World Leaky Echo State Network

2020 ◽  
Vol 32 (4) ◽  
pp. 741-758
Author(s):  
Xugang Xi ◽  
Wenjun Jiang ◽  
Seyed M. Miran ◽  
Xian Hua ◽  
Yun-Bo Zhao ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Surface Electromyography ◽  
Contractile Activity ◽  
Random Network ◽  
Principal Component ◽  
Small World ◽  
Support Vector ◽  
Echo State Network ◽  
Better Than ◽  
Semg Signals

Surface electromyography (sEMG) is an electrophysiological reflection of skeletal muscle contractile activity that can directly reflect neuromuscular activity. It has been a matter of research to investigate feature extraction methods of sEMG signals. In this letter, we propose a feature extraction method of sEMG signals based on the improved small-world leaky echo state network (ISWLESN). The reservoir of leaky echo state network (LESN) is connected by a random network. First, we improved the reservoir of the echo state network (ESN) by these networks and used edge-added probability to improve these networks. That idea enhances the adaptability of the reservoir, the generalization ability, and the stability of ESN. Then we obtained the output weight of the network through training and used it as features. We recorded the sEMG signals during different activities: falling, walking, sitting, squatting, going upstairs, and going downstairs. Afterward, we extracted corresponding features by ISWLESN and used principal component analysis for dimension reduction. At the end, scatter plot, the class separability index, and the Davies-Bouldin index were used to assess the performance of features. The results showed that the ISWLESN clustering performance was better than those of LESN and ESN. By support vector machine, it was also revealed that the performance of ISWLESN for classifying the activities was better than those of ESN and LESN.

Sign in / Sign up

Export Citation Format

Share Document