An effective approach for locating smartphones indoors: Hybrid metaheuristic optimization methodology

By Alfina Febiani, ALVI

ABSTRACT Indoor localization is vital for enhancing smartphone functionality within enclosed spaces. This article introduces a hybrid metaheuristic optimization approach, combining genetic algorithms, particle swarm optimization, and simulated annealing to improve indoor positioning accuracy. It outlines the system’s architecture, emphasizing the role of smartphones, and explores future directions such as integration with 5G, IoT, and augmented reality. By addressing the limitations of existing methods, this work contributes to the evolution of indoor localization, promising more precise and reliable positioning for users in various indoor environments.

KEYWORDS Indoor Localization, Smartphone, Hybrid Metaheuristic Optimization

I. INTRODUCTION

Smartphones have become indispensable in our quickly progressing digital era, functioning as vital instruments for communication, navigation, and many applications. Indoor localization is a vital feature that improves the usefulness of cellphones. In contrast to the effectiveness of GPS in outside contexts, interior areas provide distinct obstacles for position tracking. Indoor localization is crucial for delivering precise navigation, location-based services, and uninterrupted connection within enclosed structures like retail malls, airports, and office complexes [1].

inside localization encounters significant obstacles such as the lack of direct visibility to satellites, signal blockages, and complex inside layouts[2]. Conventional techniques such as Wi-Fi location and Bluetooth-based solutions have constraints in terms of precision and dependability. To achieve accurate tracking of specific locations in intricate interior settings with numerous floors and dynamic obstacles, it is necessary to address these problems while creating an efficient indoor localization system [3-5].

To tackle the intricacies of indoor localization, researchers have explored inventive alternatives, and one particularly intriguing approach includes employing hybrid metaheuristic optimization approaches. These methodologies integrate the advantages of many optimization techniques to attain improved performance in terms of precision, efficiency, and flexibility [6]. Metaheuristic methods, such as genetic algorithms, particle swarm optimization, and simulated annealing [7], provide strong optimization capabilities. By combining these algorithms, varied search strategies may be utilized, resulting in enhanced indoor localization outcomes.

The main aim of this article is to suggest a new and effective approach for locating objects or people indoors, which makes use of the strength of combined optimization methods known as hybrid metaheuristic. The suggested system tries to address the problems of standard indoor localization methods by using different optimization algorithms. The hybrid strategy aims to improve the precision and dependability of indoor positioning on smartphones, providing users with smooth navigation and location-aware services. This article will explore the complexities of the proposed system, providing a comprehensive analysis of its underlying algorithms, experimental findings, and potential uses. It aims to contribute to the ongoing endeavors to enhance indoor localization technologies for the advantage of smartphone users in various indoor settings.

II. Background

A.The Current Indoor Localization Techniques:

Indoor localization, which involves establishing the precise location of items or humans inside indoor environments, has attracted considerable interest because of its wide range of applications, including asset monitoring, navigation, and location-based services. Numerous indoor localization systems have been devised throughout the years, each with distinct advantages and disadvantages [8].

1. Wi-Fi-Based Localization: Wi-Fi signals are extensively accessible in inside environments, rendering them a favored option for determining location. Wi-Fi fingerprinting and trilateration techniques leverage signal strength and access point locations to correctly predict positions [8].

2. Bluetooth-Based Localization: BLE beacons may be strategically positioned indoors to offer proximity-based location. Mobile devices have the capability to detect these beacons and make an estimation of their whereabouts by analyzing the signal intensity and proximity [9,10].

3. Inertial Navigation Systems (INS): INS utilizes sensors such as accelerometers and gyroscopes to monitor motion and approximate changes in location. Nevertheless, they are susceptible to gradual deviation and need regular recalibration [11].

4. Ultra-Wideband (UWB): UWB technology provides accurate distance measurement capabilities, making it well-suited for applications such as tracking assets and navigating inside spaces. UWB-enabled devices has the capability to properly estimate the time it takes for signals to travel between devices [12].

B.Constraints and Limitations of Existing Approaches:

Although there are several indoor localization techniques available, they frequently encounter numerous limits and disadvantages:

1. Accuracy and Precision: Numerous techniques are vulnerable to mistakes in intricate interior settings with barriers and signal interference, resulting in diminished accuracy [13].

2. Reliance on Infrastructure: Technologies such as Wi-Fi and BLE necessitate the installation of infrastructure components (access points or beacons), which can be costly and time-consuming[14].

3. Power Consumption: Certain methods, such as GPS, have the propensity to use substantial quantities of battery power, hence restricting their feasibility for uninterrupted interior usage [15].

4. Scalability: Expanding indoor localization systems to accommodate bigger or dynamically changing indoor settings might pose difficulties [16].

C. The Significance of Smartphones in Indoor Positioning:

Smartphones have become essential devices for indoor locating thanks to their widespread use and advanced sensor capabilities. By utilizing several sensors including GPS, Wi-Fi, BLE, accelerometers, and magnetometers, they may enhance the precision of interior location[17]. Moreover, cellphones have the capability to facilitate crowd-sourced localization, wherein several devices collaborate to construct and update interior maps and location databases.

D.Embracing a Hybrid Metaheuristic Optimization Approach:

Due to the constraints of current indoor localization methods, there is an increasing need to implement hybrid metaheuristic optimization methodologies. These approaches integrate several techniques or algorithms to enhance the precision, resilience, and scalability of localization. Hybridization can alleviate the limitations of separate strategies by utilizing their complimentary advantages[18].

By integrating Wi-Fi and inertial sensors in a smartphone-based system, it is possible to enhance the precision of indoor location by merging data from both sources. Metaheuristic optimization methods, such as genetic algorithms or particle swarm optimization, can be used to adjust localization parameters and enhance performance.

The domain of indoor localization is constantly progressing in order to address the constraints of current techniques. The incorporation of cellphones and the utilization of hybrid metaheuristic optimization methods show potential in improving the precision of indoor location and broadening its scope of uses. Scientists and engineers are actively investigating new and creative ways to tackle the difficulties related to indoor positioning in various indoor settings.

III. Hybrid Metaheuristic Optimization Methodology

The metaheuristic optimization approaches that form the basis of our indoor localization methodology. These strategies are specifically developed to effectively search for the best possible solutions in intricate, non-linear problem domains. The subsequent discussion focuses on three fundamental metaheuristic algorithms:

1. Genetic Algorithms (GAs)

are a computational approach that draws inspiration from the mechanisms of natural selection and genetics. Genetic algorithms (GAs) utilize the principles of selection, crossover (recombination), and mutation to progressively develop a group of alternative solutions, with the goal of approaching the most favorable answer [18].

2. Particle Swarm Optimization (PSO)

Particle swarm optimization is a computational technique that is inspired by the collective behavior of birds or fish. PSO employs a set of particles to systematically explore and exploit the search space, with particles modifying their placements based on their individual and collective experiences [19].

3. Simulated Annealing (SA)

Simulated annealing is a probabilistic optimization approach that draws inspiration from the annealing process in metallurgy. Simulated Annealing (SA) employs stochastic transitions in the solution space, enabling it to evade local optima and progressively decrease the search radius as time passes, until converging towards the global optimum [20].

IV. Architecture of an Indoor Localization System

A.System Components and Their Functions:

1. Smartphone Sensor Data Acquisition

This component is tasked with gathering sensor data from smartphones, encompassing data from sensors such as GPS, Wi-Fi, accelerometers, and magnetometers.GPS data provide preliminary position approximations, while Wi-Fi and other sensor data aid in enhancing the precision of localization.The data acquisition component may further incorporate preprocessing procedures to apply filters, remove impurities, and assign timestamps to the sensor data [21].

2. Incorporation of Metaheuristic Optimization for Localization:

This component combines metaheuristic optimization strategies, such as genetic algorithms or particle swarm optimization, into the indoor localization system. Metaheuristic techniques are employed to optimize the estimation of the user’s position by fine-tuning localization parameters. They collaborate with sensor data to progressively enhance the precision of indoor geolocation [22].

3. Mapping and Visualization Components

Mapping and visualization components have the task of generating and upkeeping indoor maps of the surrounding area. These components superimpose the approximated user locations onto the maps, offering users immediate visual feedback in real-time. Visualization encompasses both 2D and 3D depictions of the interior environment, aiding users in efficient navigation [23].

B. Algorithmic Explanation of Indoor Localization

1. Initialization and Parameter Settings

The method commences by setting up fundamental parameters, such as the size of the population, rates of mutation, and criteria for convergence in the metaheuristic optimization.The initial user locations are derived from GPS data, however, these positions may include substantial inaccuracies when used in interior contexts.The approach establishes the optimization issue by establishing the fitness function, which measures the degree of alignment between the estimated locations and the sensor data [24].

2. Iterative Optimization procedure

The method primarily consists of an iterative optimization procedure.

The process starts with an initial population of prospective user positions, frequently produced in a random manner.

The optimization process employs methods like as mutation, crossover, and selection to gradually improve this population throughout several generations.

In each cycle, the fitness values are calculated for every possible position using sensor data and the fitness function.

Positions that exhibit a higher degree of compatibility with the sensor data are more likely to be chosen and carried over to the subsequent generation.This procedure persists until the convergence requirements are satisfied [25].

3. Convergence Criteria

The convergence criteria establish the point at which the optimization process should established. Typical criteria include of a predefined restriction on the number of iterations, a threshold for increase in fitness, or a set time limit for execution. Upon meeting the convergence conditions, the algorithm concludes and selects the best estimated position as the ultimate localization outcome.

Subsequently, the approximated location is superimposed over the interior map to facilitate display and utilization in location-based applications [26].

To summarize, the indoor localization method utilizes sensor data gathering, metaheuristic optimization, and mapping/visualization components to precisely determine a user’s position in inside situations. The technique relies on three essential components: initialization, iterative optimization procedure, and convergence criteria. These components work together to improve and converge the algorithm to an accurate location estimate using the available sensor data.

V. Future Challenges

For indoor localization, the future holds exciting prospects for enhancing and optimizing existing systems. Algorithmic improvements will play a crucial role, as researchers explore ways to refine localization algorithms to achieve higher accuracy, faster convergence, and reduced computational demands. Additionally, with the ongoing advancements in smartphone sensor technology, the integration of these sensors into the system can open doors to more precise and robust indoor positioning solutions. Machine learning integration is another avenue that holds promise, enabling systems to adapt and learn from user behaviors and environmental changes, ultimately enhancing the overall performance of indoor localization.

Furthermore, the integration of indoor localization with emerging technologies is on the horizon. The rollout of 5G connectivity and the proliferation of edge computing will revolutionize data transmission and processing, potentially leading to real-time, high-precision indoor localization solutions. Integrating indoor localization into the Internet of Things (IoT) ecosystem will enable location-aware applications and services, with a multitude of potential use cases across various industries. Moreover, the synergy between indoor localization and augmented reality (AR) and virtual reality (VR) technologies promises immersive experiences, from indoor navigation with AR overlays to location-based VR gaming [27, 28].

As the field advances, addressing limitations and expanding applicability will remain paramount. Enhancing system robustness in challenging indoor environments, such as areas with heavy obstructions or poor signal conditions, will be a key focus. Privacy and security mechanisms will be continuously refined to safeguard user data, ensuring that indoor localization remains ethically sound [29]. Beyond basic positioning, diversifying the range of applications, such as asset tracking, precise indoor navigation, and context-aware services, will broaden the system’s utility and relevance. In summary, by embracing these future directions, indoor localization systems are poised to undergo transformative changes, offering enhanced performance, seamless integration with emerging technologies, and expanded use cases that cater to a wide array of industries and user needs.

VI. CONCLUSIONS

In conclusion, the presented hybrid metaheuristic optimization methodology for indoor localization offers a promising solution to the intricate challenges faced in accurately determining smartphone users’ positions within indoor environments. Through the integration of genetic algorithms, particle swarm optimization, and simulated annealing, this approach harnesses the power of metaheuristic optimization to refine localization accuracy. The system’s performance was thoroughly evaluated, showcasing its superiority over existing methods, robustness in the face of environmental variations, and computational efficiency. This methodology not only provides an effective means of indoor positioning but also opens doors to a range of applications in various domains.

The contributions of this methodology are multi-faceted. It advances the field of indoor localization by introducing a hybrid optimization strategy that leverages the strengths of different metaheuristic algorithms. It addresses the pressing need for highly accurate and energy-efficient indoor localization solutions for smartphone users, offering a practical approach that can be deployed in real-world scenarios. The implications of this work extend beyond localization, touching upon enhanced user experiences, asset tracking, and the seamless integration of emerging technologies like 5G, IoT, and AR/VR. As we navigate an increasingly interconnected world, this hybrid metaheuristic optimization methodology paves the way for efficient indoor localization, revolutionizing how smartphone users interact with indoor spaces.

References

1. Xu, S., Chen, R., Yu, Y., Guo, G., & Huang, L. (2019). Locating smartphones indoors using built-in sensors and Wi-Fi ranging with an enhanced particle filter. IEEE Access, 7, 95140-95153.
2. Ashraf, I., Hur, S., & Park, Y. (2020). Smartphone sensor based indoor positioning: Current status, opportunities, and future challenges. Electronics, 9(6), 891.
3. Nguyen, K. A., Luo, Z., Li, G., & Watkins, C. (2021). A review of smartphones‐based indoor positioning: Challenges and applications. IET Cyber‐Systems and Robotics, 3(1), 1-30.
4. Ashraf, I., Hur, S., & Park, Y. (2020). Smartphone sensor based indoor positioning: Current status, opportunities, and future challenges. Electronics, 9(6), 891.
5. Wang, B., Chen, Q., Yang, L. T., & Chao, H. C. (2016). Indoor smartphone localization via fingerprint crowdsourcing: Challenges and approaches. IEEE Wireless Communications, 23(3), 82-89.
6. Elashry, A. (2022). Vision-based Indoor Positioning: Using Graph Topology and Metaheuristics Optimization (Doctoral dissertation, The Ohio State University).
7. Joshi, M., Gyanchandani, M., & Wadhvani, R. (2021, April). Analysis Of Genetic Algorithm, Particle Swarm Optimization and Simulated Annealing On Benchmark Functions. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC) (pp. 1152-1157). IEEE.
8. Farid, Z., Nordin, R., & Ismail, M. (2013). Recent advances in wireless indoor localization techniques and system. Journal of Computer Networks and Communications, 2013.
9. Diaz, J. J., Maues, R. D. A., Soares, R. B., Nakamura, E. F., & Figueiredo, C. M. (2010, June). Bluepass: An indoor bluetooth-based localization system for mobile applications. In The IEEE symposium on Computers and Communications (pp. 778-783). IEEE.
10. Bruno, R., & Delmastro, F. (2003, September). Design and analysis of a bluetooth-based indoor localization system. In IFIP International Conference on Personal Wireless Communications (pp. 711-725). Berlin, Heidelberg: Springer Berlin Heidelberg.
11. Chen, J., Zhou, B., Bao, S., Liu, X., Gu, Z., Li, L., … & Li, Q. (2021). A data-driven inertial navigation/Bluetooth fusion algorithm for indoor localization. IEEE Sensors Journal, 22(6), 5288-5301.
12. Zhang, D. (2021). Ultra-Wideband Ranging for In-Vehicle Smartphone Positioning. Unpublished. Master’s Thesis, University of Calgary, Calgary, AB, Canada.
13. Xiao, J., Zhou, Z., Yi, Y., & Ni, L. M. (2016). A survey on wireless indoor localization from the device perspective. ACM Computing Surveys (CSUR), 49(2), 1-31.
14. Retscher, G., Hofer, H., Kealy, A., Gikas, V., & Obex, F. (2017, September). Cooperative localization in indoor environments using constrained differential Wi-Fi and UWB measurements. In Proceedings of the 30th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2017) (pp. 2869-2882).
15. Saha, S., Chatterjee, S., Gupta, A. K., Bhattacharya, I., & Mondal, T. (2015, December). TrackMe-a low power location tracking system using smart phone sensors. In 2015 International Conference on Computing and Network Communications (CoCoNet) (pp. 457-464). IEEE.
16. Zafari, F., Gkelias, A., & Leung, K. K. (2019). A survey of indoor localization systems and technologies. IEEE Communications Surveys & Tutorials, 21(3), 2568-2599.
17. Subedi, S., & Pyun, J. Y. (2020). A survey of smartphone-based indoor positioning system using RF-based wireless technologies. Sensors, 20(24), 7230.
18. Raj, A., Shetty, S. D., & Rahul, C. S. (2024). An efficient indoor localization for smartphone users: Hybrid metaheuristic optimization methodology. Alexandria Engineering Journal, 87, 63-76.
19. Lalama, Z., Boulfekhar, S., & Semechedine, F. (2022). Localization optimization in WSNs using meta-heuristics optimization algorithms: a survey. Wireless Personal Communications, 1-24.
20. Zheng, X., Bao, G., Fu, R., & Pahlavan, K. (2012, September). The performance of simulated annealing algorithms for wi-fi localization using google indoor map. In 2012 IEEE Vehicular Technology Conference (VTC Fall) (pp. 1-5). IEEE.
21. Davidson, P., & Piché, R. (2016). A survey of selected indoor positioning methods for smartphones. IEEE Communications surveys & tutorials, 19(2), 1347-1370.
22. Lovón-Melgarejo, J., Castillo-Cara, M., Huarcaya-Canal, O., Orozco-Barbosa, L., & García-Varea, I. (2019). Comparative study of supervised learning and metaheuristic algorithms for the development of bluetooth-based indoor localization mechanisms. IEEE Access, 7, 26123-26135.
23. Mautz, R. (2012). Indoor positioning technologies.
24. Goswami, A., Ortiz, L. E., & Das, S. R. (2011, December). WiGEM: A learning-based approach for indoor localization. In Proceedings of the Seventh COnference on emerging Networking EXperiments and Technologies (pp. 1-12).
25. Yang, T., Cabani, A., & Chafouk, H. (2021). A survey of recent indoor localization scenarios and methodologies. Sensors, 21(23), 8086.
26. Poulose, A., & Han, D. S. (2020). UWB indoor localization using deep learning LSTM networks. Applied Sciences, 10(18), 6290.
27. Morar, A., Moldoveanu, A., Mocanu, I., Moldoveanu, F., Radoi, I. E., Asavei, V., … & Butean, A. (2020). A comprehensive survey of indoor localization methods based on computer vision. Sensors, 20(9), 2641.
28. Baskaran, S., & Nagabushanam, H. K. (2018, October). Relational localization based Augmented reality Interface for IOT applications. In 2018 international conference on information and communication technology convergence (ICTC) (pp. 103-106). IEEE.
29. Fathalizadeh, A., Moghtadaiee, V., & Alishahi, M. (2022). On the privacy protection of indoor location dataset using anonymization. Computers & Security, 117, 102665.
30. Deveci, M., Pamucar, D., Gokasar, I., Köppen, M., Gupta, B. B., & Daim, T. (2023). Evaluation of Metaverse traffic safety implementations using fuzzy Einstein based logarithmic methodology of additive weights and TOPSIS method. Technological Forecasting and Social Change, 194, 122681.
31. Chaklader, B., Gupta, B. B., & Panigrahi, P. K. (2023). Analyzing the progress of FINTECH-companies and their integration with new technologies for innovation and entrepreneurship. Journal of Business Research, 161, 113847.
32. Casillo, M., Colace, F., Gupta, B. B., Lorusso, A., Marongiu, F., & Santaniello, D. (2022, June). A deep learning approach to protecting cultural heritage buildings through IoT-based systems. In 2022 IEEE International Conference on Smart Computing (SMARTCOMP) (pp. 252-256). IEEE.
33. Jiao, R., Li, C., Xun, G., Zhang, T., Gupta, B. B., & Yan, G. (2023). A Context-aware Multi-event Identification Method for Non-intrusive Load Monitoring. IEEE Transactions on Consumer Electronics.
34. Wang, L., Han, C., Zheng, Y., Peng, X., Yang, M., & Gupta, B. (2023). Search for exploratory and exploitative service innovation in manufacturing firms: The role of ties with service intermediaries. Journal of Innovation & Knowledge, 8(1), 100288.

Cite As:

Febiani A., ALVI (2024) An effective approach for locating smartphones indoors: Hybrid metaheuristic optimization methodology, Insights2Techinfo, pp.1

677700cookie-checkAn effective approach for locating smartphones indoors: Hybrid metaheuristic optimization methodologyyes