Home > Research > Publications & Outputs > DeepILS

Associated organisational unit

Electronic data

Links

Text available via DOI:

View graph of relations

DeepILS: Towards Accurate Domain Invariant AIoT-enabled Inertial Localization System

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

DeepILS: Towards Accurate Domain Invariant AIoT-enabled Inertial Localization System. / Tariq, Omer; Dastagir, Bilal; Bilal, Muhammad et al.
In: IEEE Internet of Things Journal, 05.02.2025.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Tariq, O., Dastagir, B., Bilal, M., & Han, D. (2025). DeepILS: Towards Accurate Domain Invariant AIoT-enabled Inertial Localization System. IEEE Internet of Things Journal. Advance online publication. https://doi.org/10.1109/jiot.2025.3538938

Vancouver

Tariq O, Dastagir B, Bilal M, Han D. DeepILS: Towards Accurate Domain Invariant AIoT-enabled Inertial Localization System. IEEE Internet of Things Journal. 2025 Feb 5. Epub 2025 Feb 5. doi: 10.1109/jiot.2025.3538938

Author

Tariq, Omer ; Dastagir, Bilal ; Bilal, Muhammad et al. / DeepILS : Towards Accurate Domain Invariant AIoT-enabled Inertial Localization System. In: IEEE Internet of Things Journal. 2025.

Bibtex

@article{b8ce7ff0644d470d8c9429599e4e6d19,
title = "DeepILS: Towards Accurate Domain Invariant AIoT-enabled Inertial Localization System",
abstract = "Accurate indoor localization and navigation enable real-time, ubiquitous, location-based services. Over the past decade, data-driven approaches for inertial odometry have shown the potential to enhance indoor positioning accuracy. However, low-cost inertial measurement units (IMUs), commonly used in smartphones and IoT devices, are prone to significant noise, leading to drift and degraded performance in navigation algorithms. This paper presents a novel, lightweight, and real-time end-to-end framework, DeepILS1,designed to process raw inertial data for precise pedestrian localization in indoor environments. DeepILS utilizes a residual network enhanced with channel-wise and spatial attention mechanisms, enabling accurate velocity and position estimation across diverse motion dynamics. The framework{\textquoteright}s effectiveness is validated using four benchmarks and two newly introduced datasets in real-time edge scenarios. These datasets were collected across diverse indoor environments at the KAIST campus and Incheon National Airport, using multiple hardware platforms, including the KAIST IoT positioning module and Android smartphones. Experimental results, including tests on unseen data and comprehensive ablation studies, demonstrate that DeepILS improves localization accuracy by 70% compared to state-of-the-art methods while effectively mitigating sensor noise and enhancing robustness in real-world environments. Specifically, DeepILS exhibits excellent edge performance on IoT devices, making it highly suitable for real-time applications.",
author = "Omer Tariq and Bilal Dastagir and Muhammad Bilal and Dongsoo Han",
year = "2025",
month = feb,
day = "5",
doi = "10.1109/jiot.2025.3538938",
language = "English",
journal = "IEEE Internet of Things Journal",
issn = "2327-4662",
publisher = "IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC",

}

RIS

TY - JOUR

T1 - DeepILS

T2 - Towards Accurate Domain Invariant AIoT-enabled Inertial Localization System

AU - Tariq, Omer

AU - Dastagir, Bilal

AU - Bilal, Muhammad

AU - Han, Dongsoo

PY - 2025/2/5

Y1 - 2025/2/5

N2 - Accurate indoor localization and navigation enable real-time, ubiquitous, location-based services. Over the past decade, data-driven approaches for inertial odometry have shown the potential to enhance indoor positioning accuracy. However, low-cost inertial measurement units (IMUs), commonly used in smartphones and IoT devices, are prone to significant noise, leading to drift and degraded performance in navigation algorithms. This paper presents a novel, lightweight, and real-time end-to-end framework, DeepILS1,designed to process raw inertial data for precise pedestrian localization in indoor environments. DeepILS utilizes a residual network enhanced with channel-wise and spatial attention mechanisms, enabling accurate velocity and position estimation across diverse motion dynamics. The framework’s effectiveness is validated using four benchmarks and two newly introduced datasets in real-time edge scenarios. These datasets were collected across diverse indoor environments at the KAIST campus and Incheon National Airport, using multiple hardware platforms, including the KAIST IoT positioning module and Android smartphones. Experimental results, including tests on unseen data and comprehensive ablation studies, demonstrate that DeepILS improves localization accuracy by 70% compared to state-of-the-art methods while effectively mitigating sensor noise and enhancing robustness in real-world environments. Specifically, DeepILS exhibits excellent edge performance on IoT devices, making it highly suitable for real-time applications.

AB - Accurate indoor localization and navigation enable real-time, ubiquitous, location-based services. Over the past decade, data-driven approaches for inertial odometry have shown the potential to enhance indoor positioning accuracy. However, low-cost inertial measurement units (IMUs), commonly used in smartphones and IoT devices, are prone to significant noise, leading to drift and degraded performance in navigation algorithms. This paper presents a novel, lightweight, and real-time end-to-end framework, DeepILS1,designed to process raw inertial data for precise pedestrian localization in indoor environments. DeepILS utilizes a residual network enhanced with channel-wise and spatial attention mechanisms, enabling accurate velocity and position estimation across diverse motion dynamics. The framework’s effectiveness is validated using four benchmarks and two newly introduced datasets in real-time edge scenarios. These datasets were collected across diverse indoor environments at the KAIST campus and Incheon National Airport, using multiple hardware platforms, including the KAIST IoT positioning module and Android smartphones. Experimental results, including tests on unseen data and comprehensive ablation studies, demonstrate that DeepILS improves localization accuracy by 70% compared to state-of-the-art methods while effectively mitigating sensor noise and enhancing robustness in real-world environments. Specifically, DeepILS exhibits excellent edge performance on IoT devices, making it highly suitable for real-time applications.

U2 - 10.1109/jiot.2025.3538938

DO - 10.1109/jiot.2025.3538938

M3 - Journal article

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

ER -