Deep Learning Approach for Optimal Localization Using an mm-Wave Sensor

• Published in: IEEE transactions on instrumentation and measurement Vol. 72; pp. 1 - 15
• Main Authors: Amjad, Bisma, Ahmed, Qasim Z., Lazaridis, Pavlos I., Khan, Faheem A., Hafeez, Maryam, Zaharis, Zaharias D.
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Angle of arrival; Angle of arrival (AoA); Artificial neural networks; Costs; Data models; Deep learning; deep learning (DL); Hardware; indoor localization; Localization; Location awareness; Low cost; Machine learning; machine learning (ML); Maximum likelihood estimation; millimeter wave (mm-wave); Millimeter waves; Neural networks; Optimization; Perturbation; point clouds; Regression models; Robot sensing systems; Sensors; Support vector machines; System effectiveness
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2023.3311055

Short-range indoor localization is one of the key necessities in automation industries and healthcare setups. With its increasing demand, the need for more precise positioning systems is rapidly increasing. Millimeter-wave (mm-wave) technology is emerging to enable highly precise localization performance. However, due to the limited availability of low-cost mm-wave sensors, it is challenging to accelerate research on real data. Furthermore, noise due to the hardware components of a sensor incurs perturbation in the received signal, which corrupts the estimation of range and the angle of arrival (AoA). Due to the huge success of data-driven algorithms in solving regression problems, we propose a data-driven approach, which employs two deep learning (DL)-based regression models, i.e., dense neural network and convolutional neural network, and compare their performance with two machine learning-based regression models, linear regression and support vector regression, to reduce errors in the estimate of AoA and range obtained via an mm-wave sensor. Our main goal is to optimize the localization measurements acquired from a low-cost mm-wave sensor for short-range applications. This will accelerate the development of proof of concept and foster research on cost-effective mm-wave-based indoor positioning systems. All experiments were conducted using over-the-air data collected with an mm-wave sensor, and the validity of the experiments was verified in unseen environments. The results obtained from our experimental evaluations, both for in-sample and out-of-sample testing, indicate improvements in the estimation of AoA and range with our proposed DL models. The improvements achieved were greater than 15% for AoA estimation and over 85% for range estimation compared to the baseline methods.