BLIPS: Bluetooth locator for an Indoor Positioning System in Realtime (2024)

Traditional localization systems often rely on a network of external sensors, making the setups cumbersome, expensive, and requiring significant calibration effort. The advent of Bluetooth 5.1 and later versions brought enhancements that enable precise localization using constant tone extension (CTE) in the signal through Angle of Arrival (AoA) and Angle of Departure (AoD) techniques. This work examines the capacity of a single Bluetooth Low-Energy (BLE) locator with an antenna array based on AoA in terms of performance, efficiency, and latency in real-time indoor positioning. While traditional neural networks train measured entities to match calculated distances, we utilize the azimuth and elevation angle components in the AoA measured and train neural networks to match their theoretical counterparts. We conducted extensive experiments in a real-world lab environment, providing ablation studies in the design. The results demonstrate the system's capability in real-time with many potential interference variables. Under lab conditions, our results show the capacity of a single locator wanes past 4m with the best average accuracy of 0.09m error in positioning within a 5m radius to as much as ∼ 1m of error beyond 6m up to the maximum possible measuring distance in the lab.

CCS Concepts: • Human-centered computing → Ubiquitous and mobile devices; • Human-centered computing → Ubiquitous and mobile computing systems and tools; Empirical studies in ubiquitous and mobile computing; • Human-centered computing → Accessibility technologies; • General and reference → Empirical studies; • Human-centered computing → Interaction devices; • Human-centered computing → Collaborative and social computing systems and tools;

Indoor localization is a deeply researched topic, yet it remains a major unsolved problem. The ability to obtain accurate location information indoors has been important for a plethora of applications. There are use cases in industrial/production applications (like warehousing [38, 43, 44], assembly [19, 21], production [22, 59], supply chain and logistics [18, 30, 65] etc.). There are also commercial applications (like advertisem*nts [15, 57], social networks [17], etc.) and emergency services (such as critical care [62], emergency guidance [35, 49], and disaster recovery applications [11]).

The technology used for performing indoor localization has evolved over the years. Many sensing technologies like ultrasound [19, 29, 60], magnetic-field fingerprinting [3, 20, 41], LIDAR [23, 37, 53, 58], WiFi RSSI [31, 51], WiFi CSI (Channel State Information) [66], WiFi multi-channel methods [64, 70], filtering [64, 69], machine learning/neural network [4, 51], sensor/information fusion [16, 22, 24, 28, 56], and Industry 4.0 [25] technologies such as Zigbee [40, 48], RFID [5, 27, 42], UWB (Ultra-wideband) [7, 14, 18, 36, 52, 68], Lora [46], iBeacons [10], Bluetooth low energy [8, 26, 45, 55, 71] have been explored. Yet, the primary drawback of most of these technologies involves requiring deployed sensor arrays, which involves increased effort, time, and costs. Bluetooth is one such technology that is constantly evolving. With the advanced capabilities from Bluetooth 5.1 or above [63], the Ble (Bluetooth low-energy) channels are enriched with multi-channel Constant Tone Extension (CTE) information. This information can be used in localization techniques such as AoA and AoD, which can help improve the accuracy of the signal captured without the requirement of multiple additional sensors and hardware. This article examines using a single Ble locator antenna array as the central device for coordinating the real-time indoor position system.

There have been prior works that have explored Ble-AoA. However, the initial works [28, 50, 61] lacked the hardware to perform extensive experiments, and the later works [39, 67] were experimented on use-case-specific environments. Lin et al.[39] propose the Self-Learning Mean Optimization Filter (SLMOF) to minimize the multipath effect in the indoor positioning accuracy in a narrow space suited for ship environments and do not consider external noise. While the theory and experiments list significant improvements to existing State-of-the-Art, the proposed method is not easily transferable to a more generic environment, such as commercial buildings and office spaces, as they are more prone to environmental interference. While commercial products such as Quuppa, BlueIoT, and CoreHW use Ble-AoA, it often requires a bunch of these Locators to be deployed around the area to localize effectively or do not mention the actual coverage but provide a range of the hardware instead, or often have to work with other technologies to be effective. To identify this technology's effectiveness, we experiment with a single locator-based Ble-AoA application for real-time indoor positioning. The primary contributions of this evaluation work are: 1. Testing the capacity of a single Ble-AoA locator for real-time indoor localization in terms of performance, efficiency, and latency; 2. Identifying the best orientation and positioning of the Ble-AoA locator for maximum hardware utilization. In this article, we provide a brief history of prior work using Ble-AoA and the motivation for our evaluation work, the preliminaries covering essential Ble-AoA concepts, and an overview of the proposed method and implementation. Then, we briefly evaluate the performance of our experiments with various ablations, followed by a discussion and implication of this research for future work and conclusion.

Bluetooth technology has evolved significantly since its inception in 1994, and indoor localization has been one of the areas that have benefited from these advancements. Initially, Bluetooth was designed primarily for wireless audio streaming and file transfers between devices. However, with the advent of BLE technology, its potential has been explored in other areas. BLE technology consumes significantly less power than traditional Bluetooth, making it ideal for battery-powered devices. This feature is critical for asset tracking applications, where the devices must operate for an extended period without frequent battery replacements. Also, it has a range of up to 100 meters, making it suitable for indoor environments. Additionally, it has a higher level of accuracy than traditional Bluetooth, making it optimal for indoor positioning. Since then, many works [8, 26, 45, 55, 71], UHF-RFID [27, 42] have utilized the utility of low power and low energy required ble technology alone or along with other sensors for indoor localization approaches.

BLE technology has enabled the development of several indoor localization systems that utilize Bluetooth beacons [9, 10, 12, 13, 47, 52, 71]. These beacons transmit signals to mobile devices that can be used to determine their location. The beacons can be placed at strategic locations within the indoor environment, and mobile devices can use the signal strength of the beacons to triangulate their position. This approach has several advantages over traditional systems, such as Wi-Fi or RFID, which require significant infrastructure cost, setup, and maintenance.

During the COVID-19 pandemic, BLE technology has become a significant player in various applications. In a notable study by Lin et al. [39], the authors explore the utilization of Bluetooth 5.1 Angle of Arrival (AoA) to emulate localization in narrow ship environments. Their work centers on developing a self-learning mean optimization filter to track close contacts within controlled ship settings effectively. The primary objective is to mitigate the risk of virus transmission—a critical concern during the pandemic. The results obtained by Lin et al. demonstrate the efficacy of their approach. However, it is essential to recognize the study's specific focus on performing experiments in an interference-free and narrow environment. This specificity may limit the generalizability of their findings to other indoor contexts or outdoor scenarios. As we delve deeper into the implications of BLE technology, further research is warranted to explore its applicability beyond controlled environments.

In their seminal work, Qiu et al. [54] present a novel BLE localization algorithm characterized by high accuracy. This algorithm explicitly tackles the formidable challenge of carrier frequency offset (CFO). The authors substantially enhance localization precision by integrating a Maximum Likelihood-based weighted algorithm and an Extended Kalman Filter. Despite these promising results, practical implementation encounters certain limitations. Notably, the efficacy of this approach is contingent upon the context of indoor localization, where BLE technology exhibits inherent deficiencies. Uncertain environmental conditions, including dynamic obstacles and human movement, significantly impact real-time performance, constraining its practical utility. As we delve deeper into the intricacies of BLE-based localization, it becomes imperative to address these practical considerations. Future research endeavors should explore strategies to mitigate the impact of environmental variability, ensuring robust and reliable localization solutions.

Furthermore, BLE technology has seen significant adoption in the smart building industry, where it is used for various applications such as asset tracking, occupancy sensing, and indoor navigation. The technology has enabled the development of smart buildings [33] that can optimize energy consumption, improve safety, and enhance the overall user experience. However, previous research has encountered several obstacles in using Bluetooth for indoor localization due to their techniques. Techniques such as Received Signal Strength Indicator (RSSI) and Time of Flight (ToF) are vulnerable to signal interference, multipath fading, and non-line-of-sight (NLOS) conditions, resulting in inaccurate localization.

Recently, Bluetooth Angle of Arrival (AoA) has emerged as a promising technique for indoor localization. AoA uses an array of antennas to determine the angle of incoming signals from Bluetooth beacons, which reduces the impact of signal interference and multipath fading. Despite this, using Bluetooth AoA in a noisy environment remains challenging. A dense and synchronized array of antennas is required, which can be costly and difficult to set up. Furthermore, NLOS conditions can affect the accuracy of AoA, leading to incorrect angle estimates and reduced localization accuracy. For example, the work by Hajiakhondi-Meybodi et al. [28] explored using AoA via a switch antenna array, however, due to the limited number of antennas, the AoA was still prone to heavy multipath effects, noise, and fading. Wang et al. [61] worked on a similar approach but on a polarization-sensitive array; however, the experiments lack depth and are not replicable for any other environment. Another work by Pau et al. [50] briefly analyses the practical use of Bluetooth 5.1 based on naive experiments and shows that the enhancements provided to Bluetooth 5.1 show immense promise for critical applications. The work by Ye et al. [67] shows promise by introducing the PDDA algorithm on the angle data obtained; however, the localization errors seem erratic in noisy environments. Finally, the work by Lin et al. [39] explores filtering techniques to remove outlier readings in the measured angles followed by a genetic algorithm for precise indoor positioning. While the results show promise, the experiments are done in a clean environment that is not relatable to real-world settings, and the repeatability of the experiments needs validation.

This article addresses the difficulties of using Bluetooth AoA in a real-world environment with possible interference by examining single Ble locator-based real-time localization capabilities. By doing so, we hope to contribute to the progression of research on indoor localization using BLE technology.

The basis of this work depends on understanding the specifications of BLe-AoA as introduced by Bluetooth 5.1. While AoA has been used in prior radio signals-based localization, the features BLe-AoA brings are elucidated below.

With the release of Bluetooth 5.1, direction-finding features were introduced in the specification document. These features enable Bluetooth devices to determine the direction of a Bluetooth signal, which can be helpful in indoor positioning and location-based services. The direction-finding feature uses Bluetooth Low Energy (BLE), a low-power wireless communication technology, making direction-finding efficient and suitable for edge devices. One of the advantages of this feature is that it can work well in noisy environments where other positioning technologies may struggle.

This direction-finding feature utilizes In-Phase and Quadrature (IQ) sampling to measure the phase of radio waves incident upon an antenna array. It supports two methods, namely Angle of Arrival (AoA) and Angle of Departure (AoD) (as shown in Figure 1), which necessitate the antenna array to be in the receiving or transmitting device, respectively. The feature introduces a new field called Constant Tone Extension (CTE), which provides constant frequency and wavelength signal material for IQ sampling. The CTE contains a sequence of 1s, is not subject to the usual whitening process (making the spectral density uniform), and is not included in the Cyclic Redundancy Check (CRC) calculation. The Bluetooth 5.1 specification also defines a new link layer and Host Controller Interface Packet Data units (HCI PDUs) to support IQ sampling and using IQ samples by higher layers in the stack. After receiving the data vector containing the IQ samples from the antenna, an estimation algorithm is required to calculate the arrival angle using the phase difference (ϕ).

Some of such estimation algorithms [6] include phase-shifting beamforming, Minimum Variance Distortionless Response (MVDR) beamforming, Multiple Signal Identification and Classification (MUSIC), and Maximum Likelihood Estimation (MLE). These algorithms utilize the IQ sample data vector to compute intermediary results before calculating the azimuth and elevation angles. Once the angle of elevation (e) and angle of azimuth (a) are calculated, they are used in the coordinates equations listed below. Once the x and y coordinates are determined, the distance from the locator is calculated using $d = \sqrt {x^2 + y^2}$.

The initial experiments were conducted to assess the effectiveness of the 4x4 BLE (Bluetooth Low Energy) antenna locator array. We systematically explored various physical configurations of the antenna array. Subsequently, after identifying the optimal orientation that maximized the system's utilization, further experiments were conducted to enhance the localization accuracy within the finalized setup. This iterative process aimed to refine the system's performance, ensuring its suitability for practical applications.

4.1 BleIPS Experiment Design

The experiments to improve localization accuracy were performed in a 6mx10m laboratory space with many electronic and wireless hardware for potential interference. The primary element used in the experiments included a Ble-AoA Antenna Array of the Silicon Labs make, called the BG22 Bluetooth Dual Polarized Antenna Array Radio Board (figure 3) a. This antenna array board was operated through a EFR32xG22 Wireless Gecko Starter Kit (figure 3 b used as the mainboard flashed with the AoA Locator application provided by Silicon Labs proprietary RTL library. To remotely run the locator application as required, this setup was connected to a Raspberry Pi 3B+ hardware, accessed through SSH to operate the setup. The entirety of this hardware was placed in a box (shown in figure 4 affixed to the ceiling (3.6m from the ground) in the middle of the experimental setup area to utilize all quadrants around the array board with the 4x4 antenna array faced towards the ground. The height at which the antenna array is deployed is always assumed to be a known entity for fixed experiment setups

In our investigation, we explored various configurations to enhance the performance of our localization system. Initially, we used an inverted configuration, positioning the locator 1.2 meters above the ground while maintaining the asset tag at specific heights above it (C1). Consequently, we conducted an additional experiment, placing the locator at the top and keeping the transmitter at the bottom (C2). Furthermore, we investigated the impact of varying the locator's height in C2.

The four quadrants around the board are divided based on the azimuth angle measured (− 180° to 180°), and the horizontal distance from the locator can be directly mapped to a specific elevation angle measured. The azimuth and elevation angles compute the Bluetooth signal's arrival angle. We utilized this intuition to further test other setups on the neural network training, such as training separately for various quadrants around the Ble-AoA locator and at different distances from the locator as the reference. The neural network choice is based on the quadrant where the person stands, approximated from the azimuth angle, and the approximate distance between the person and the locator, approximated from the elevation angle. We choose a model trained for those points between that distance range in that particular quadrant.

The points for signal measurements were established at 0.5m equidistant points (as shown encircled in figure 5) in a 6mx10m rectangular area with the locator box at its center having coordinates (0, 0) with the transmitter held at 1.2m from the ground. The useable width limited the experimental area's size due to the presence of the lab's systems and equipment. The height of 1.2m for the tags was chosen to accommodate the points on top of the cubicle divider in the lab making the effective height of locator from tag to be 3.6m − 1.2m = 2.4m. The longest distance from the locator in the center to the corner points (± 5, ± 3) was $\sqrt {(\sqrt {5^2 + 3^2})^2 + (2.4)^2}m \approx 6.30m$, which defines the distance range. The entire experiment was conducted in two phases—the offline phase and then the online phase. The offline phase involved the collection of signal values at each point to create a dataset for training the neural networks. This data is used to obtain pre-trained models. Then, all the pre-trained models are sent to the mobile application, which contains a visual interface to show the tag's position within the room. The online phase involves signal data being passed through the pre-trained model to obtain processed angle data. The x and y coordinates obtained from the processed angle data for real-time measurements are displayed on the application interface as the tag's position in the room relative to the locator. The complete overview of the experimental design can be seen in figure 6.

This study introduces BLIPS, an approach to evaluate indoor localization. Our focus lies in evaluating the accuracy, efficiency, and latency in real-time using a single Ble locator with Ble-AoA as the primary technology. The motivation behind our work stems from prior work failing to examine the capabilities of a single locator-based Ble-AoA localization in real-world settings with many potential interference. Our contributions extend to extensive experimentation, particularly in design configuration and angle computation. Within an area of 6m×10m, we successfully achieve sub-foot indoor localization, with our best models delivering centimeter-level precision. Furthermore, we examined the maximum coverage per locator. The crux of our approach lies in a neural network-based methodology, which exhibits remarkable performance even in real-time lab environments with signal interference and extreme occlusion. Notably, our observations suggest that the neural network training accounts for slight deviations in angle based on the transmitter's position, however plays a major role in improving accuracy. Our findings suggest that while many consumer-level products claim a good range on their Ble-AoA locator-based solutions, there is no demonstration of it in potentially noisy environments like offices or clarity on how they achieve such accuracy without any neural network training or genetic algorithm. While many restrict the knowledge about their approach on the grounds of propriety intellectual property, our experiments show a peek into the reality of the technology's capabilities.

This research was funded by the iHub Anubhuti IIITD Foundation for procuring the hardware to conduct the experiments. The authors would like to thank the advisors Prof. Pushpendra Singh & Prof. Mohan Kumar for the continuous feedback and direction in furthering the rigor of the experiments. The authors would also like to thank the Facility Management Services of the Institute for helping with the equipment set up in the lab, student Anshul Goswami for designing the case for the locator, and the Design & Innovation Lab at the Institute for supporting the 3D printing facilities to make the box for the locator.

• Web Admin. 2023. Bluetooth Location Services Solutions - Silicon Labs. https://www.silabs.com/wireless/bluetooth/location-services
• AbienFred Agarap. 2018. Deep Learning using Rectified Linear Units (ReLU). CoRR abs/1803.08375 (2018). arXiv:1803.08375 http://arxiv.org/abs/1803.08375
• Leonid Antsfeld, Boris Chidlovskii, and Dmitrii Borisov. 2020. Magnetic Sensor Based Indoor Positioning by Multi-Channel Deep Regression: Poster Abstract. In Proceedings of the 18th Conference on Embedded Networked Sensor Systems (Virtual Event, Japan) (SenSys ’20). Association for Computing Machinery, New York, NY, USA, 707–708. https://doi.org/10.1145/3384419.3430419
• Roshan Ayyalasomayajula, Aditya Arun, Chenfeng Wu, Sanatan Sharma, AbhishekRajkumar Sethi, Deepak Vasisht, and Dinesh Bharadia. 2020. Deep Learning Based Wireless Localization for Indoor Navigation. In Proceedings of the 26th Annual International Conference on Mobile Computing and Networking (London, United Kingdom) (MobiCom ’20). Association for Computing Machinery, New York, NY, USA, Article 17, 14pages. https://doi.org/10.1145/3372224.3380894
• Noor BahaAldin, Ergun Erçelebi, and Mahmut Aykaç. 2017. An Accurate Indoor RSSI Localization Algorithm Based on Active RFID System with Reference Tags. Wireless Personal Communications 97, 3 (Dec. 2017), 3811–3829. https://doi.org/10.1007/s11277-017-4700-7
• TaylorS Barber. 2019. Performance Analysis of Angle of Arrival Algorithms Applied to Radiofrequency Interference Direction Finding. Master's thesis. AIR FORCE INSTITUTE OF TECHNOLOGY.
• Luca Barbieri, Mattia Brambilla, Andrea Trabattoni, Stefano Mervic, and Monica Nicoli. 2021. UWB Localization in a Smart Factory: Augmentation Methods and Experimental Assessment. IEEE Transactions on Instrumentation and Measurement 70 (2021), 1–18. https://doi.org/10.1109/TIM.2021.3074403
• MdFazlay RabbiMasum Billah, Nurani Saoda, Jiechao Gao, and Bradford Campbell. 2021. BLE Can See: A Reinforcement Learning Approach for RF-based Indoor Occupancy Detection. In Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021). ACM, Nashville TN USA, 132–147. https://doi.org/10.1145/3412382.3458262
• Miran Borić, RebecaP. DíazRedondo, and Ana FernándezVilas. 2018. Space Occupancy through BLE Dynamic Broadcasting. Wireless Communications and Mobile Computing 2018 (Oct. 2018), e2182614. https://doi.org/10.1155/2018/2182614 Publisher: Hindawi.
• Miran Borić, Rebeca P.Díaz Redondo, and AnaFernández Vilas. 2018. Dynamic Content Distribution over BLE iBeacon Technology: Implementation Challenges. In 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT). IEEE, Thessaloniki, Greece, 910–915. https://doi.org/10.1109/CoDIT.2018.8394958 ISSN: 2576-3555.
• Regin Cabacas and In-Ho Ra. 2021. First Responder Positioning and Localization Based on Optimal Anchor Access Point Selection Using Minimum Uncertainty Propagation for Disaster Scenarios. In The 9th International Conference on Smart Media and Applications (Jeju, Republic of Korea) (SMA 2020). Association for Computing Machinery, New York, NY, USA, 425–428. https://doi.org/10.1145/3426020.3426157
• Zhenghua Chen, Qingchang Zhu, and YengChai Soh. 2016. Smartphone Inertial Sensor-Based Indoor Localization and Tracking With iBeacon Corrections. IEEE Transactions on Industrial Informatics 12, 4 (2016), 1540–1549. https://doi.org/10.1109/TII.2016.2579265
• Maciej Ciężkowski, Sławomir Romaniuk, and Adam Wolniakowski. 2020. Apparent beacon position estimation for accuracy improvement in lateration positioning system. Measurement 153 (March 2020), 107400. https://doi.org/10.1016/j.measurement.2019.107400
• Paolo Dabove, Vincenzo DiPietra, Marco Piras, AnsarAbdul Jabbar, and SyedAli Kazim. 2018. Indoor positioning using Ultra-wide band (UWB) technologies: Positioning accuracies and sensors’ performances. In 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS). IEEE, Monterey, CA, USA, 175–184. https://doi.org/10.1109/PLANS.2018.8373379
• S.P. Dhanushka. 2021. Location-Based Indoor Mobile Advertising. Thesis. University of Colombo School of Computing. https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4236Accepted: 2021-07-27T05:41:12Z.
• Abdelrahman El-Naggar, Amr Wassal, and Khaled Sharaf. 2019. Indoor Positioning Using WiFi RSSI Trilateration and INS Sensor Fusion System Simulation. In Proceedings of the 2019 2nd International Conference on Sensors, Signal and Image Processing (Prague, Czech Republic) (SSIP ’19). Association for Computing Machinery, New York, NY, USA, 21–26. https://doi.org/10.1145/3365245.3365261
• Moustafa Elhamshary, Anas Basalmah, and Moustafa Youssef. 2017. A Fine-Grained Indoor Location-Based Social Network. IEEE Transactions on Mobile Computing 16, 5 (2017), 1203–1217. https://doi.org/10.1109/TMC.2016.2591532
• Mahmoud Elsanhoury, Petteri Mäkelä, Janne Koljonen, Petri Välisuo, Ahm Shamsuzzoha, Timo Mantere, Mohammed Elmusrati, and Heidi Kuusniemi. 2022. Precision Positioning for Smart Logistics Using Ultra-Wideband Technology-Based Indoor Navigation: A Review. IEEE Access 10 (2022), 44413–44445. https://doi.org/10.1109/ACCESS.2022.3169267
• Dominik Esslinger, Martin Oberdorfer, Michael Zeitz, and Cristina Tarín. 2020. Improving ultrasound-based indoor localization systems for quality assurance in manual assembly. In 2020 IEEE International Conference on Industrial Technology (ICIT). IEEE, Buenos Aires, Argentina, 563–570. https://doi.org/10.1109/ICIT45562.2020.9067248
• Xirui Fan, Jing Wu, Chengnian Long, and Yanmin Zhu. 2017. Accurate and Low-Cost Mobile Indoor Localization with 2-D Magnetic Fingerprints. In Proceedings of the First ACM Workshop on Mobile Crowdsensing Systems and Applications (Delft, Netherlands) (CrowdSenSys ’17). Association for Computing Machinery, New York, NY, USA, 13–18. https://doi.org/10.1145/3139243.3139244
• Wei Fang, Wei Fan, Wei Ji, Lei Han, Shuhong Xu, Lianyu Zheng, and Lihui Wang. 2022. Distributed cognition based localization for AR-aided collaborative assembly in industrial environments. Robotics and Computer-Integrated Manufacturing 75 (2022), 102292. https://doi.org/10.1016/j.rcim.2021.102292
• J.C. FuentesMichel, Mark Christmann, Michael Fiegert, Peter Gulden, and Martin Vossiek. 2006. Multisensor Based Indoor Vehicle Localization System for Production and Logistic. In 2006 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. IEEE, Heidelberg, Germany, 553–558. https://doi.org/10.1109/MFI.2006.265666
• Giovanni Fusco and JamesM. Coughlan. 2020. Indoor Localization for Visually Impaired Travelers Using Computer Vision on a Smartphone. In Proceedings of the 17th International Web for All Conference (Taipei, Taiwan) (W4A ’20). Association for Computing Machinery, New York, NY, USA, Article 8, 11pages. https://doi.org/10.1145/3371300.3383345
• Jijun Geng, Xuexiang Yu, Congcong Wu, and Guoqing Zhang. 2023. Research on Pedestrian Indoor Positioning Based on Two-Step Robust Adaptive Cubature Kalman Filter with Smartphone MEMS Sensors. Micromachines 14, 6 (2023). https://doi.org/10.3390/mi14061252
• Alasdair Gilchrist. 2016. Industry 4.0: The Industrial Internet of Things (1st ed.). Apress, USA.
• Davide Giovanelli and Elisabetta Farella. 2018. RSSI or Time-of-flight for Bluetooth Low Energy based localization? An experimental evaluation. In 2018 11th IFIP Wireless and Mobile Networking Conference (WMNC). IEEE, Prague, 1–8. https://doi.org/10.23919/WMNC.2018.8480847
• Linqing Gui, Shuwen Xu, Fu Xiao, Feng Shu, and Shui Yu. 2022. Non-Line-of-Sight Localization of Passive UHF RFID Tags in Smart Storage Systems. IEEE Transactions on Mobile Computing 21, 10 (2022), 3731–3743. https://doi.org/10.1109/TMC.2021.3058952
• Zohreh Hajiakhondi-Meybodi, Mohammad Salimibeni, KonstantinosN. Plataniotis, and Arash Mohammadi. 2020. Bluetooth Low Energy-based Angle of Arrival Estimation via Switch Antenna Array for Indoor Localization. In 2020 IEEE 23rd International Conference on Information Fusion (FUSION). IEEE, Rustenburg, South Africa, 1–6. https://doi.org/10.23919/FUSION45008.2020.9190573
• M. Hazas and A. Hopper. 2006. Broadband ultrasonic location systems for improved indoor positioning. IEEE Transactions on Mobile Computing 5, 5 (2006), 536–547. https://doi.org/10.1109/TMC.2006.57
• Niklas Hesslein, Mike Wesselhöft, Johannes Hinckeldeyn, and Jochen Kreutzfeldt. 2021. Industrial Indoor Localization: Improvement of Logistics Processes Using Location Based Services. In Advances in Automotive Production Technology – Theory and Application, Philipp Weißgraeber, Frieder Heieck, and Clemens Ackermann (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 460–467.
• MohdNizam Husen and Sukhan Lee. 2014. Indoor Human Localization with Orientation Using WiFi Fingerprinting. In Proceedings of the 8th International Conference on Ubiquitous Information Management and Communication (Siem Reap, Cambodia) (ICUIMC ’14). Association for Computing Machinery, New York, NY, USA, Article 109, 6pages. https://doi.org/10.1145/2557977.2557980
• SiliconLaboratories Inc.2022. QSG175: Silicon Labs Direction-Finding Solution Quick-Start Guide., 19pages. https://www.silabs.com/documents/public/quick-start-guides/qsg175-direction-finding-solution-quick-start-guide.pdf
• Feiyu Jin, Kai Liu, Hao Zhang, Joseph Kee-Yin Ng, Songtao Guo, Victor C.S. Lee, and SangH. Son. 2020. Toward Scalable and Robust Indoor Tracking: Design, Implementation, and Evaluation. IEEE Internet of Things Journal 7, 2 (Feb. 2020), 1192–1204. https://doi.org/10.1109/JIOT.2019.2953376
• DiederikP. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arxiv:1412.6980[cs.LG] https://arxiv.org/abs/1412.6980
• OluwatayoY. Kolawole and Mythri Hunukumbure. 2022. UAV Based 5G Indoor Localization for Emergency Services. In Proceedings of the 5th International ACM Mobicom Workshop on Drone Assisted Wireless Communications for 5G and Beyond (Sydney, NSW, Australia) (DroneCom ’22). Association for Computing Machinery, New York, NY, USA, 43–48. https://doi.org/10.1145/3555661.3560862
• Jayakanth Kunhoth, AbdelGhani Karkar, Somaya Al-Maadeed, and Abdulla Al-Ali. 2020. Indoor positioning and wayfinding systems: a survey. Human-centric Computing and Information Sciences 10, 1 (May 2020), 18. https://doi.org/10.1186/s13673-020-00222-0
• Masaki Kuribayashi, Tatsuya Ishihara, Daisuke Sato, Jayakorn Vongkulbhisal, Karnik Ram, Seita Kayukawa, Hironobu Takagi, Shigeo Morishima, and Chieko Asakawa. 2023. PathFinder: Designing a Map-Less Navigation System for Blind People in Unfamiliar Buildings. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg, Germany) (CHI ’23). Association for Computing Machinery, New York, NY, USA, Article 41, 16pages. https://doi.org/10.1145/3544548.3580687
• C.K.M. Lee, C.M. Ip, Taezoon Park, and S.Y. Chung. 2019. A Bluetooth Location-based Indoor Positioning System for Asset Tracking in Warehouse. In 2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM). IEEE, Macao, China, 1408–1412. https://doi.org/10.1109/IEEM44572.2019.8978639
• Qianfeng Lin, Jooyoung Son, and Hyeongseol Shin. 2023. A self-learning mean optimization filter to improve bluetooth 5.1 AoA indoor positioning accuracy for ship environments. Journal of King Saud University - Computer and Information Sciences 35, 3 (2023), 59–73. https://doi.org/10.1016/j.jksuci.2023.01.019
• Fang-Tsung Liu, Chiung-Hsing Chen, Yi-Chun Kao, Chih-Ming Hong, and Chia-Ying Yang. 2017. Improved ZigBee module based on fuzzy model for indoor positioning system. In 2017 International Conference on Applied System Innovation (ICASI). IEEE, Sapporo, Japan, 1331–1334. https://doi.org/10.1109/ICASI.2017.7988150
• ChrisXiaoxuan Lu, Yang Li, Peijun Zhao, Changhao Chen, Linhai Xie, Hongkai Wen, Rui Tan, and Niki Trigoni. 2018. Simultaneous Localization and Mapping with Power Network Electromagnetic Field. In Proceedings of the 24th Annual International Conference on Mobile Computing and Networking (New Delhi, India) (MobiCom ’18). Association for Computing Machinery, New York, NY, USA, 607–622. https://doi.org/10.1145/3241539.3241540
• Yongtao Ma, Chenglong Tian, and Yue Jiang. 2019. A Multitag Cooperative Localization Algorithm Based on Weighted Multidimensional Scaling for Passive UHF RFID. IEEE Internet of Things Journal 6, 4 (2019), 6548–6555. https://doi.org/10.1109/JIOT.2019.2907771
• Mojtaba Masoudinejad, AswinKarthik RamachandranVenkatapathy, David Tondorf, Danny Heinrich, Robert Falkenberg, and Markus Buschhoff. 2018. Machine Learning Based Indoor Localisation Using Environmental Data in PhyNetLab Warehouse. In Smart SysTech 2018; European Conference on Smart Objects, Systems and Technologies. VDE, Munich, Germany, 1–8.
• A. Moura, J. Antunes, A. Dias, A. Martins, and J. Almeida. 2021. Graph-SLAM Approach for Indoor UAV Localization in Warehouse Logistics Applications. In 2021 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC). IEEE, Santa Maria da Feira, Portugal, 4–11. https://doi.org/10.1109/ICARSC52212.2021.9429791
• Sharareh Naghdi and Kyle O'Keefe. 2022. Combining Multichannel RSSI and Vision with Artificial Neural Networks to Improve BLE Trilateration. Sensors (Basel, Switzerland) 22, 12 (June 2022), 4320. https://doi.org/10.3390/s22124320
• Rajalakshmi Nandakumar, Vikram Iyer, and Shyamnath Gollakota. 2018. 3D Localization for Sub-Centimeter Sized Devices. In Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems (Shenzhen, China) (SenSys ’18). Association for Computing Machinery, New York, NY, USA, 108–119. https://doi.org/10.1145/3274783.3274851
• Thu L.N. Nguyen, TuanD. Vy, Kwan-Soo Kim, Chenxiang Lin, and Yoan Shin. 2021. Smartphone-Based Indoor Tracking in Multiple-Floor Scenarios. IEEE Access 9 (2021), 141048–141063. https://doi.org/10.1109/ACCESS.2021.3119577 Conference Name: IEEE Access.
• Huthaifa Obeidat, Wafa Shuaieb, Omar Obeidat, and Raed Abd-Alhameed. 2021. A Review of Indoor Localization Techniques and Wireless Technologies. Wireless Personal Communications 119, 1 (July 2021), 289–327. https://doi.org/10.1007/s11277-021-08209-5
• AyanKumar Panja, Dhritesh Bhagat, Sarmistha Neogy, and Chandreyee Chowdhury. 2022. Framework for Remote Device Localization and Application Level Visualization for Emergency Service Providers. In Adjunct Publication of the 24th International Conference on Human-Computer Interaction with Mobile Devices and Services (Vancouver, BC, Canada) (MobileHCI ’22). Association for Computing Machinery, New York, NY, USA, Article 19, 4pages. https://doi.org/10.1145/3528575.3551445
• Giovanni Pau, Fabio Arena, YonasEngida Gebremariam, and Ilsun You. 2021. Bluetooth 5.1: An Analysis of Direction Finding Capability for High-Precision Location Services. Sensors 21, 11 (Jan. 2021), 3589. https://doi.org/10.3390/s21113589 Number: 11 Publisher: Multidisciplinary Digital Publishing Institute.
• Chao Peng, Hong Jiang, and Liangdong Qu. 2021. Deep Convolutional Neural Network for Passive RFID Tag Localization Via Joint RSSI and PDOA Fingerprint Features. IEEE Access 9 (2021), 15441–15451. https://doi.org/10.1109/ACCESS.2021.3052567
• Milica Petrović, Maciej Ciężkowski, Sławomir Romaniuk, Adam Wolniakowski, and Zoran Miljković. 2021. A Novel Hybrid NN-ABPE-Based Calibration Method for Improving Accuracy of Lateration Positioning System. Sensors 21, 24 (Jan. 2021), 8204. https://doi.org/10.3390/s21248204 Number: 24 Publisher: Multidisciplinary Digital Publishing Institute.
• James Pieszala, Gabriel Diaz, Jeff Pelz, Jacqueline Speir, and Reynold Bailey. 2016. 3D Gaze Point Localization and Visualization Using LiDAR-Based 3D Reconstructions. In Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications (Charleston, South Carolina) (ETRA ’16). Association for Computing Machinery, New York, NY, USA, 201–204. https://doi.org/10.1145/2857491.2857545
• Xinyou Qiu, Bowen Wang, Jian Wang, and Yuan Shen. 2020. AOA-Based BLE Localization with Carrier Frequency Offset Mitigation. In 2020 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, Dublin, Ireland, 1–5. https://doi.org/10.1109/ICCWorkshops49005.2020.9145137
• Ramiro Ramirez, Chien-Yi Huang, Che-An Liao, Po-Ting Lin, Hsin-Wei Lin, and Shu-Hao Liang. 2021. A Practice of BLE RSSI Measurement for Indoor Positioning. Sensors 21, 15 (Jan. 2021), 5181. https://doi.org/10.3390/s21155181 Number: 15 Publisher: Multidisciplinary Digital Publishing Institute.
• D.I.B. Randeniya, M. Gunaratne, S. Sarkar, and A. Nazef. 2008. Calibration of inertial and vision systems as a prelude to multi-sensor fusion. Transportation Research Part C: Emerging Technologies 16, 2 (2008), 255–274. https://doi.org/10.1016/j.trc.2007.08.003
• O. Rashid, P. Coulton, and R. Edwards. 2005. Implementing location based information/advertising for existing mobile phone users in indoor/urban environments. In International Conference on Mobile Business (ICMB’05). IEEE, Sydney, NSW, Australia, 377–383. https://doi.org/10.1109/ICMB.2005.45
• Darshana Rathnayake, Meeralakshmi Radhakrishnan, Inseok Hwang, and Archan Misra. 2023. LILOC: Enabling Precise 3D Localization in Dynamic Indoor Environments Using LiDARs. In Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation (San Antonio, TX, USA) (IoTDI ’23). Association for Computing Machinery, New York, NY, USA, 158–171. https://doi.org/10.1145/3576842.3582364
• András Rácz-Szabó, Tamás Ruppert, László Bántay, Andreas Löcklin, László Jakab, and János Abonyi. 2020. Real-Time Locating System in Production Management. Sensors 20, 23 (2020). https://doi.org/10.3390/s20236766
• JuanManuel Vera-Diaz, Daniel Pizarro, and Javier Macias-Guarasa. 2018. Towards End-to-End Acoustic Localization Using Deep Learning: From Audio Signals to Source Position Coordinates. Sensors 18, 10 (2018). https://doi.org/10.3390/s18103418
• Bowen Wang, Yunlong Wang, Xinyou Qiu, and Yuan Shen. 2021. BLE Localization With Polarization Sensitive Array. IEEE Wireless Communications Letters 10, 5 (2021), 1014–1017. https://doi.org/10.1109/LWC.2021.3055558
• WilliamVan Woensel, PatriceC. Roy, Syed SibteRaza Abidi, and SaminaRaza Abidi. 2020. Indoor location identification of patients for directing virtual care: An AI approach using machine learning and knowledge-based methods. Artificial Intelligence in Medicine 108 (2020), 101931. https://doi.org/10.1016/j.artmed.2020.101931
• Martin Woolley. 2020. Bluetooth® Core Specification Version 5.1 Feature Overview. https://www.bluetooth.com/bluetooth-resources/bluetooth-core-specification-v5-1-feature-overview/
• Chenshu Wu, Feng Zhang, Beibei Wang, and K.J.Ray Liu. 2020. EasiTrack: Decimeter-Level Indoor Tracking With Graph-Based Particle Filtering. IEEE Internet of Things Journal 7, 3 (March 2020), 2397–2411. https://doi.org/10.1109/JIOT.2019.2958040
• Wei Wu, Leidi Shen, Zhiheng Zhao, Ming Li, and GeorgeQ. Huang. 2022. Industrial IoT and Long Short-Term Memory Network-Enabled Genetic Indoor-Tracking for Factory Logistics. IEEE Transactions on Industrial Informatics 18, 11 (2022), 7537–7548. https://doi.org/10.1109/TII.2022.3146598
• Runming Yang, Xiaolong Yang, Jiacheng Wang, Mu Zhou, Zengshan Tian, and Lingxia Li. 2022. Decimeter Level Indoor Localization Using WiFi Channel State Information. IEEE Sensors Journal 22, 6 (2022), 4940–4950. https://doi.org/10.1109/JSEN.2021.3067144
• Hongyun Ye, Biao Yang, Zhiqiang Long, and Chunhui Dai. 2022. A Method of Indoor Positioning by Signal Fitting and PDDA Algorithm Using BLE AOA Device. IEEE Sensors Journal 22, 8 (April 2022), 7877–7887. https://doi.org/10.1109/JSEN.2022.3141739 Conference Name: IEEE Sensors Journal.
• Zhendong Yin, Xu Jiang, Zhutian Yang, Nan Zhao, and Yunfei Chen. 2019. WUB-IP: A High-Precision UWB Positioning Scheme for Indoor Multiuser Applications. IEEE Systems Journal 13, 1 (2019), 279–288. https://doi.org/10.1109/JSYST.2017.2766690
• Feng Zhang, Chen Chen, Beibei Wang, Hung-Quoc Lai, Yi Han, and K.J.Ray Liu. 2018. WiBall: A Time-Reversal Focusing Ball Method for Decimeter-Accuracy Indoor Tracking. IEEE Internet of Things Journal 5, 5 (Oct. 2018), 4031–4041. https://doi.org/10.1109/JIOT.2018.2854825 Conference Name: IEEE Internet of Things Journal.
• Mingyang Zhang, Jie Jia, Jian Chen, Yansha Deng, Xingwei Wang, and AbdolHamid Aghvami. 2021. Indoor Localization Fusing WiFi With Smartphone Inertial Sensors Using LSTM Networks. IEEE Internet of Things Journal 8, 17 (2021), 13608–13623. https://doi.org/10.1109/JIOT.2021.3067515
• Yuan Zhuang, Jun Yang, You Li, Longning Qi, and Naser El-Sheimy. 2016. Smartphone-Based Indoor Localization with Bluetooth Low Energy Beacons. Sensors 16, 5 (2016). https://doi.org/10.3390/s16050596