Home > News > AIT’s Deep-Learning-Based Wireless Indoor Localization Paper Ranks in Top 10% of Downloads & is the Most Cited Paper

AIT’s Deep-Learning-Based Wireless Indoor Localization Paper Ranks in Top 10% of Downloads & is the Most Cited Paper

31 Mar 2024
School of Engineering and Technology

By School of Engineering and Technology

31 March 2024: AIT proudly shares that in a notable achievement, AIT’s Alumni from Telecommunications Program, School of Engineering and Technology and currently a researcher in Location and Automatic Identification System Research Team, National Electronics and Computer Technology Center (NECTEC), Thailand, Dr. Juthatip Wisanmongkol and Associate Professor Dr. Attaphongse Taparugssanagorn’s paper achieved a significant milestone. This paper exploring deep learning-based wireless indoor localization became the top 10% most downloaded and is the most cited paper in IET Wireless Sensor Systems Journal. This achievement speaks volume about the impact and significance of their research.

This work presents a comprehensive approach to indoor localization, featuring theoretical groundwork, simulations, real experiments, and machine learning modeling. With around 100 equations, the authors establish a robust theoretical framework. Simulations validate the approach, while real experiments confirm its practical applicability. Machine learning enhances accuracy by leveraging Wi-Fi data. This methodology ensures both theoretical rigor and practical effectiveness in advancing indoor localization technology.

An application of the work utilizing Wi-Fi and deep learning for indoor localization could be in the context of enhancing navigation and location-based services in large indoor spaces such as shopping malls, airports, or hospitals. By leveraging the data collected from Wi-Fi signals and applying deep learning techniques as described in the referenced research, the system can accurately determine the user’s location within the indoor environment in real-time. This technology could be integrated into mobile applications to provide users with precise indoor navigation instructions, personalized recommendations, and location-based notifications, improving overall user experience and efficiency in indoor navigation.

Use of ensemble methods as proposed in the paper has shown a significant improvement in the pre –existing approaches and by using this method, it is possible to estimate the location of the target with precision. This approach can not just be used for indoor navigation but also it is useful in creating a more inclusive society for the disabled, kids and the old-age people.

Overall, Wi-Fi-based indoor localization offers a versatile and practical solution for navigating indoor spaces, with advantages in accessibility, scalability, and compatibility over other techniques. School of Engineering and Technology, Asian Institute of Technology would like to congratulate Dr. Juthatip Wisanmongkol and Dr. Attaphongse Taparugssanagorn for the significant achievement in the field of wireless to create the technologies of the future.

To read more about the article kindly visit the following link.

An ensemble approach to deep-learning-based wireless indoor localization