DNN-Based Indoor Localization Under Limited Dataset Using GANs and Semi-Supervised Learning

Abstract

Indoor localization techniques based on supervised learning deliver great performance accuracy while maintaining low online complexity. However, such systems require massive amounts of data for offline training, which necessitates costly measurements. The essence of this paper is twofold with the purpose of providing solutions to missing data of different nature: available unlabeled data and missing unlabeled data. In both cases, we rely on a few labeled available data, which is costly yet insufficient to achieve a high localization accuracy. To address the problem of available unlabeled data, a weighted semisupervised DNN-based indoor localization approach leveraging pseudo-labeling methods in combination with real labeled samples and inexpensive pseudo-labeled samples is proposed in order to boost localization accuracy, while overcoming the high cost of collecting additional labeled data. As for the extreme case of unavailable unlabeled data, we propose an alternative localization system generating fake fingerprints based on generative adversarial networks (GANs) named 'Weighted GAN based indoor localization'. Furthermore, a deep neural network is trained on a mixed dataset containing both real collected and fake produced data samples using a similar weighting technique in order to improve location prediction performance and avoids overfitting. In terms of localization accuracy, our proposed localization approaches outperform conventional supervised localization schemes utilizing the same collection of real labeled samples. For experimental evaluations, we have tested our proposed methods on both simulated data and experimental data from the publicly available UJIndoorLoc database, which is built to test indoor positioning systems relying on Wi-Fi fingerprints. Results based on experimental data provide the localization accuracy increase compared to the classical supervised learning method using the same set of labeled collected data when using the weighted semi-supervised and the weighted-GAN approaches by 10.11 % and 8.53 %, respectively.

IoT with Big Data and Security Challenges of Present Era

“…The requirements to protect data, to secure private information existence at the similar time to ensure data quality, whether data sets are small or big. [5,6] In this research paper, we have emphasized two key big data scenarios namely IoT and social networks. We would like to point out that talking the nowadays and tomorrow tasks in data safety and secrecy involve multidisciplinary research from various different areas, as well as political sciences, engineering, psychology, information systems, computer science, economics, social sciences, statistics.…”

“…Every social media exchange and digital ways is responsible to generate and mobile devices, systems and sensors are responsible to send it out. This data must be recorded with the advancement of technology and must have meaningful value to extract from it [1][2][3][4][5][6][7].…”

Topology Control and Energy Efficiency of the Internet of Things (IOT)

“…Topology control introduced new types of topology classification. One is for those devices that all are same and have same capacities [26][27][28][29][30][31]. The second one's for those devices that are different from each other.…”

A Survey on Machine Learning Approaches For IOT Device Security

“…Physical unclonable based key sharing via machine learning for iot security [22][23][24][25]. Key generation and device authentication become two of the most challenging design concerns for iot devices.…”