WiFind: A Smart Long-Range WiFi-Based Tagging System for Enhanced Object Tracking and Motion Detection

WiFind: A Smart Long-Range WiFi-Based Tagging System for Enhanced Object Tracking and Motion Detection

1st S.Ramachandran

Department of Computer science and Engineering IFET College of Engineering

ramachandran85966@gmail.com

2nd K.Vetriselvam

Department of Computer science and Engineering IFET College of Engineering kvetriselvamvpm@gmail.com

3rd M.Vijayakumar

Department of Computer science and Engineering IFET College of Engineering vijayakumarmuthukumaran@gmail.com

Abstract This paper presents WiFind, a long-range WiFi-based tagging system designed to improve object tracking and motion detection. Unlike traditional tracking systems, such as those using Bluetooth Low Energy (BLE), which are limited by range and require proximity for accurate location tracking, WiFind lev- erages WiFi technology to extend the working distance and improve accuracy through Signal strength (RSSI) and triangle analysis The method works in two differ- ent modes: normal mode for short-range monitoring and mesh mode for long-distance monitoring over a mesh WiFi network. This dynamic mode switching al- lows for smooth tracking at different distances. The hardware implementation uses an ESP32 microcon- troller with a WiFi module, while the mobile applica- tion provides real-time location data and distance cal- culations. Experimental results show that WiFind ef- fectively improves its ability to detect objects at longer distances compared to BLE-based solutions. This doc- ument details its design, implementation, and perfor- mance evaluation. WiFind marks a significant ad- vancement in remote object detection for IoT applica- tions.

KeywordsWiFind, WiFi-based tracking, object tracking, RSSI, ESP32, triangulation, IoT, motion detection, mesh networks, long-range tracking.

4th Dr S.Sivasankaran

Assistant professor

Department of Computer science and Engineering IFET College of Engineering sankarsvision@gmail.com

1. INTRODUCTION

   The evolution of wireless communication and Internet of Things (IoT) technologies has brought about significant ad- vancements in tracking and monitoring systems, enabling diverse applications across industries such as logistics, healthcare, smart cities, and consumer electronics. Existing tracking systems, such as those relying on Bluetooth or GPS, often face limitations in range, scalability, and power effi- ciency, particularly when deployed in challenging environ- ments or over long distances. These constraints underline the need for innovative approaches that combine advanced communication protocols, machine learning techniques, and adaptive networking to enhance the effectiveness of object- tracking systems [1]. Recent studies have highlighted the role of deep learning techniques in improving the accurac

   and reliability of location-based services. For example, convolu- tional neural networks (CNNs) and autoencoders have been used to extract significant features from sensor data and images, allowing for real-time decision-making and precise localization [2]. Apple AirTags have been a widely discussed BLE tracking solution. The authors explored the safety features of Apple AirTags and how BLE signals are used to provide location updates. The study em- phasized safety alerts for potential unauthorized tracking. The pro- posed system uses BLE to communicate with nearby devices and relies on Apple's network of devices to locate objects. Results showed that BLE is effective for short-range tracking within 30 meters but required reliance on external Apple devices for broader coverage. The authors concluded that BLE-based tracking works efficiently in dense urban environments, although privacy concerns need to be addressed.By integrating such methodologies with wire- less networking technologies like Wi- Fi, researchers have devel- oped solutions that address

   challenges associated with range, ener- gy consumption, and environmental interference [4]. In addition to leveraging advancements in machine learning, emerging systems are increasingly incorporating mesh networking protocols. Mesh networks extend connectivity by enabling devices to communicate directly with one another, rather than relying solely on centralized infrastructure. This approach not only enhances range and reliabil- ity but also ensures that systems can adapt to network failures or dynamically changing environments [5]. When combined with Wi- Fi technologies, mesh networking further expands the potential of object- tracking systems by enabling long-range tracking and re- ducing latency, making them suitable for applications in densely populated urban areas or rural regions with sparse connectivity in- frastructure [6]. The integration of smart devices and voice- controlled systems such as Alexa and Siri has also gained promi- nence, reflecting the growing emphasis on user-friendly interfaces in IoT applications. Systems capable of interacting seamlessly with smart assistants and cloud-based storage enable users to access lo- cation data and manage tracking devices intuitively. Such features are particularly beneficial for applications in smart homes, weara- ble technologies, and industrial automation, where simplicity and accessibility are paramount [7]. Another significant challenge in tracking systems is ensuring the timely and reliable update of loca- tion data. Real-time monitoring, especially in critical applications like healthcare or disaster management, requires efficient data transmission mechanisms that minimize delays and enhance the accuracy of distance measurements. Technologies leveraging Re-

   ceived Signal Strength Indicator (RSSI) for triangulation and distance estimation have demonstrated promising re- sults, providing precise location data even in complex envi- ronments[8]. Object tracking systems are increasingly im- portant in modern applications. From asset management to tracking personal devices. to industrial tracking and security With the advent of Bluetooth Low Energy (BLE) technolo- gy such as Apple's Airtags, short-range tracking solutions have gained popularity due to their simplicityThis paper provides a comprehensive overview of the design, imple- mentation, and evaluation of WiFind, demonstrating WiFind's performance as a remote object tracking solution. We compare WiFind with existing BLE-based systems to highlight its advantages in range, accuracy, and adaptability. Experimental results show that WiFind significantly extends the functionality of traditional tracking systems. while main- taining accurate tracking and motion detection capabilities

2. LITERATURE SURVEY

   In recent years, wireless object tracking and motion detec- tion systems have gained significant attention due to their diverse applications in various industries such as logistics, healthcare, and consumer electronics. Several existing tech- nologies, such as Bluetooth tags, GPS tags, and RFID sys- tems, have been developed to address the growing demand for long-range tracking and motion detection. The WiFind project aims to enhance these systems by leveraging Wi-Fi networks to offer extended range and improved functionali- ty. This section reviews recent literature (20222024) that focuses on object tracking and motion detection using tech- nologies similar to WiFind, including Bluetooth-based sys- tems, GPS-based systems, and other Wi-Fi-based systems. Indoor environment datasets based on BLE have been ex- plored to enhance proximity detection. In Girolami et al. col- lected proximity detection data using smartphones and BLE devices. The proposed system used BLE signals to deect ob- jects in indoor spaces with a 90% accuracy rate. The authors concluded that BLE technology offers reliable proximity de- tection for indoor applications, making it ideal for smart homes and offices[9]. In Assayag et al. built an indoor envi- ronment dataset based on RSSI values collected from BLE devices. The proposed system used RSSI-based measure- ments to estimate proximity and location indoors. The sys- tem achieved 85% accuracy in location estimation within a 40-meter range. The authors concluded that while RSSI- based BLE systems are effective for indoor environments, signal interference and multipath effects can reduce accura- cy[10].Contact tracing during the COVID-19 pandemic was another use case for BLE technology. In the authors pro- posed an AI-empowered contact tracing system for residen- tial care homes using BLE devices. The BLE-based system tracked proximity between residents and used AI to predict potential outbreaks. Results showed a 93% accuracy in de- tecting close contacts within 30 meters. The authors con- cluded that BLE is an effective tool for contact tracing, par- ticularly in controlled environments like care homes[11]. Condition monitoring sensors using BLE and LoRa were discussed in the proposed system combined a MEMS accel- erometer and microphone with BLE radios for condition monitoring. Results showed that BLE achieved 85% accura-

   cy in proximity detection within a 40-meter range. The authors concluded that BLE is an affordable solution for condition monitor- ing in industrial settings, with potential for wider adoption[12]. In the authors integrated BLE and LoRa technologies for campus safe- ty systems. BLE devices were used to track students' movements on campus, while LoRa extended communication range. The pro- posed system achieved 90% accuracy in tracking within 70 meters, proving the efficacy of combining BLE with long-range communi- cation technologies. The authors concluded that BLE is suitable for short-range tracking, while LoRa complements it by extending the system's range[13]. Device discovery and tracing using BLE were the focus of where Locatelli et al. proposed a BLE-based system for real-time device tracing. The system used BLE trackers to dis- cover and trace devices within 50 meters, achieving 92% accuracy. The authors concluded that BLE is an effective solution for device discovery, although security challenges remain a concern[14]. In the construction industry, PPE misuse prevention using BLE was explored in the proposed system used BLE devices to track PPE usage and ensure compliance in construction zones. The system achieved 88% accuracy in tracking PPE usage within a 60-meter range. The authors concluded that BLE-based tracking systems can significantly improve safety compliance in hazardous work envi- ronments[15]. Motion capturing with BLE was tested in where Veijalainen et al. developed a system using BLE radios and inertial measurement units (IMUs) to capture human movements. Results showed that the BLE system achieved 87% accuracy in motion tracking within a 30-meter range. The authors concluded that BLE is feasible for motion capture, although it may not match the preci- sion of more advanced systems[16]. In the authors proposed a self- learning filter to improve Bluetooth 5.1 AoA positioning accuracy in ship environments. The proposed system used BLE 5.1 technol- ogy for indoor positioning, achieving improved accuracy over pre- vious systems. Results showed a 92% improvement in positioning accuracy within 40 meters. The authors concluded that BLE 5.1 of- fers enhanced accuracy for indoor environments but may still face challenges in complex ship environments[17]. In BLE indoor local- ization for large industrial areas was explored. The proposed sys- tem used BLE devices to track objects in industrial settings with limited infrastructure. Results showed 85% accuracy in tracking objects within 100 meters. The authors concluded that BLE is a cost-effective solution for industrial localization, although interfer- ence from other devices can affect accuracy[18]. Tracking academ- ic performance on campuses using BLE was discussed in [19]. The proposed system used BLE devices to monitor student activity and improve academic performance. Results showed that BLE-based tracking achieved 90% accuracy in detecting student presence with- in 50 meters. The authors concluded that BLE technology can be used to enhance academic performance by tracking student en- gagement on campus. Finally, BLE networks for ultra-accurate ge- olocation applications were explored in The proposed system used BLE devices to provide geo-location updates with high accuracy. Results showed that BLE-based tracking achieved 92% accuracy in urban environments within a 100-meter range. The authors con- cluded that BLE networks are suitable for geolocation applications, though urban infrastructure can sometimes interfere with sig- nal strength[20].

3. PROPOSED RESEARCH METHODOLOGY

   WiFind extends coverage through two operating modes: Normal Mode and Mesh Mode. Normal Mode functions within a single

   WiFi network, while Mesh Mode connects multiple WiFi nodes to create an expansive tracking network, ensuring reli- able performance in diverse environments.

   The system leverages ESP32 modules and uses Received Signal Strength Indicator (RSSI) values for accurate distance calculations. By integrating triangulation methods, WiFind provides precise location tracking. Its compact design and energy efficiency make it suitable for personal item tracking, vehicle navigation, and emergency response, catering to both urban and remote scenarios.

   This paper builds using a novel approach that combines mo- tion detection and emergency alerts to enhance functionality. WiFind detects unusual movements or impacts and triggers instant notifications to contacts or emergency services. Ac- cessible through a mobile app and web interface, the sys- tems scalable design and minimal infrastructure require- ments make it a practical solution for modern tracking needs.

   1. Hardware Design

      The hardware design of WiFind revolves around three criti- cal components: the ESP32 module, WiFi routers, and bat- tery-powered trackers. These components are selected to en- sure efficient communication, portability, and energy effi- ciency, making the system reliable for long-range object tracking and motion detection.

      Indusboard Coin : In WiFind, the IndusBoard Coin serves as the primary hardware for tracking, leveraging its ESP32 microcontroller for WiFi-based communication and RSSI calculations. It enables Normal and Mesh Mode operations, facilitating real-time location tracking and distance estima- tion. The board includes sensors such as accelerometers and motion detectors for identifying object movements and trig- gering alerts during unusual activity. Its core functionality lies in accurate signal processing, seamless network switch- ing, and energy-efficient operation for long-range tracking.

      Fig.1 IndusBoard coin

      WiFi Routers: WiFi routers are used to facilitate communica- tion in Normal Mode and establish the mesh network in Mesh Mode. These routers act as hubs, enabling long-range tracking by linking multiple ESP32 nodes. Standard dual-band WiFi routers ensure compatibility with most ESP32 modules and enhance the range and stability of the connection.

      Fig.2 Wifi Router

      Battery-Powered Trackers

      The trackers are lightweight, portable devices powered by lithium- ion batteries, ensuring long-lasting performance. These trackers in- tegrate an ESP32 module, a power management system, and mo- tion sensors. Their small form factor makes them convenient for users to attach to personal belongings, vehicles, or other objects.

   2. Software Architecture

      Mobile Application

      The mobile app acts as the user interface for interacting with the WiFind system, enabling configuration, monitoring, and control of the hardware trackers. The app fatures intuitive functionalities and integrates seamlessly with the WiFind hardware.

      Features of the Mobile App:

      1. Network Switching:

         The app identifies the optimal WiFi network for connectivity. When operating in Mesh Mode, the app connects to other de- vices in the network for extended range, automatically switch- ing between networks to maintain a stable connection.

      2. Real-Time Tracking:

         Using RSSI (Received Signal Strength Indicator) values, the app calculates the location of the tagged objects and displays their positions on an interactive map.

      3. Notifications and Alerts:

         The app provides notifications for significant events like low battery, device movement, or disconnection. In case of emer- gencies (e.g., accidents), it alerts pre-defined contacts or emer- gency services with location details.

      4. Device Configuration:

         Users can manage device settings, such as tag names, opera- tional modes (Normal or Mesh), and alert preferences.

         1. Web Server

            The web server in WiFind acts as the central hub for pro- cessing and managing tracking data, ensuring seamless communication between the ESP32 modules and the mobile app. It stores the data received from the trackers, such as RSSI values, and processes it to calculate precise locations using triangulation techniques. The server also coordinates devices in the mesh network to optimize connectivity and performance during network switching. Through real-time processing, the web server continuously updates the mobile app with live location data and handles notifications, ensur- ing users stay informed about device movement, low bat- tery, or emergencies. In addition, the server enables alert management by communicating critical updates, such as emergency messages, via push notifications, SMS, or email to pre-defined contacts.

         2. Software Workflow

            The software workflow begins with the ESP32 modules collecting RSSI data and transmitting it to the web server. The server processes this data to determine object locations, which are displayed on the mobile app in real-time. The app facilitates seamless network switching by ensuring the trackers connect to the optimal WiFi network or form a mesh network for extended range. Alerts and notifications are triggered based on user preferences, such as proximity alerts or critical events like disconnection or emergencies,

            ensuring timely updates for the user. This integration of data collection, processing, and user interaction ensures a reliable and efficient tracking system. WiFind's mobile app UI is designed for simplicity and functionality, featuring a real-time map interface for object tracking and distance estimation using RSSI data. It provides seamless network switching, mesh mode visualization, and instant notifications for enhanced user experience. The intuitive layout en- sures quick access to tagging, tracking, and emergen- cy alert features.

            Fig.3 Network Switching

         3. Technology Used for Mobile App Development The WiFind mobile application is developed using Flutter, a powerful cross-platform framework that enables a consistent user experience across Android and iOS devices. Flutter's widget-based architecture ensures a highly responsive and customizable inter- face, ideal for real-time tracking and intuitive user in- teraction. The app communicates with the backend web server through RESTful APIs, enabling efficient data exchange and live updates. Firebase or SQLite is used for local data caching, ensuring the app remains functional even with intermittent connectivity. Flut- ters capabilities allow for a feature-rich app that combines performance, scalability, and modern de- sign, making it a robust tool for managing and inter- acting with WiFinds tracking system.

         Fig.4 Location Processing

   3. Modes of Operation

      The WiFind system operates in two distinct modes to provide versatile tracking and object detection capabili- ties: Normal Mode and Mesh Mode.

      1. Normal Mode: WiFind operates as a single network, where a single WiFi access point (AP) is used to track the tagged objects. This mode is ideal for small-scale applications where the range of tracking is limited but still highly accurate. When an object is equipped with a WiFi-enabled tag (such as an ESP32 module), the system utilizes the Received Signal Strength Indicator (RSSI) data from the WiFi sig-

         nals to calculate the distance between the device and the ac- cess point. Basic triangulation is performed using the strength of the signals received by the access point from the tagged object. This allows the WiFind system to estimate the object's location within a certain radius, making it suita- ble for localized tracking within a room or a small outdoor area. The accuracy of this mode is dependent on factors such as signal interference and the environments layout.

      2. Mesh Mode : WiFind transforms into a multi-node system that uses multiple WiFi routers or access points to form a mesh network, extending the tracking range significantly. This mode is particularly useful in larger areas or complex environments where a single access point would be insuffi- cient. Each node in the mesh network communicates with others, allowing for greater coverage by passing infor- mation between nodes. This approach enables WiFind to provide real-time tracking across wider areas, such as in in- dustrial settings, large buildings, or outdoor environments. Mesh Mode enhances the accuracy of the system by using the collaborative data from several access points, effective- ly eliminating dead zones and ensuring consistent tracking of tagged objects, even as they move through different re- gions of the network.

   4. Mathematical modelling

      Variables and Their Meanings:

      1. D: The calculated distance in meters between the transmit- ter and receiver.

      2. PMThe measured transmission power of the device in dBm at a reference distance (usually 1 meter).

      3. RSSI: The signal strength received by the receiver, meas- ured in dBm.

      4. N: The environmental attenuation factor, accounting for obstacles and signal interference. Typical values for Nrange from 2 (open space) to 4 (dense urban areas).

      Accuracy Considerations:

      1. Environmental Interference: Obstacles like walls, furni- ture, or people can cause signal scattering, absorption, or re- flection, introducing inaccuracies.

      2. Signal Noise: Variations in RSSI measurements due to background noise or electronic interference may reduce precision.

      3. Calibration of PM and N: Accurate calibration of these parameters for the specific environment is critical to mini- mize errors.

   5. Triangulation and Multilateration

      1. WiFind employs a robust methodology for location tracking us- ing Triangulation and Multilateration, tailored to its Normal and Mesh Modes. In Normal Mode, WiFind uses Triangulation to determine a device's position by leveraging the Angle of Ar- rival (AoA) from at least three access points. This method cal- culates the intersection of angular measurements to identify the precise location. In contrast, Mesh Mode incorporates Multilat-

         eration, where the Received Signal Strength Indicator (RSSI) or Time of Flight (ToF) is used to estimate dis- tances from multiple access points. These distances are represented as circles, with the device's location calculat- ed at their intersection point.

      2. T improve accuracy, WiFind optimizes its performance with advanced techniques like Weighted Centroid Lo- calization (WCL), which assigns importance to signal sources based on reliability, and Kalman Filters to miti- gate environmental noise and signal fluctuations. Addi- tionally, environmental calibration and adaptive signal adjustments ensure precision even in complex environ- ments. By leveraging multiple access points in Mesh Mode, WiFind enhances accuracy over greater ranges, enabling more reliable tracking compared to traditional Bluetooth systems. This dual-mode approach ensures consistent and accurate performance across diverse use cases.

   6. Motion Detection and Emergency Response

      1. WiFind incorporates Motion Detection and Emer- gency Response functionalities to enhance safety and utility. Motion detection is achieved through the integration of accelerometers and gyroscopes within the WiFind tags, which monitor changes in velocity, orientation, and movement patterns. These sensors detect significant movements, such as abrupt acceler- ations or impacts, which could indicate accidents or unusual activity. In Normal Mode, motion data is transmitted directly to the mobile app or server, while in Mesh Mode, the data is relayed through in- terconnected nodes, ensuring coverage over a wider area.

      2. The Emergency Response system in WiFind is designed to promptly alert users and responders in critical situations. Up- on detecting an accident or significant movement, the system triggers an automatic alert mechanism. This includes sending real-time notifications to pre-configured emergency contacts and providing precise location details using the triangulated or multilaterated position data. For enhanced functionality, the system can also communicate with nearby devices within a specified radius (e.g., 50-100 meters) to alert other users or authorities, ensuring timely intervention. By combining mo- tion detection with accurate location tracking, WiFind offers a comprehensive solution for accident prevention and emergen- cy response, setting it apart as a reliable and versatile tracking system.

4. IMPLEMENTATION AND ANALYSIS

   System Architecture Overview : WiFind is a long- range WiFi-based tracking system using an ESP32 mi- crocontroller and a rechargeable battery. It operates through the WiFind mobile app, offering two modes: Normal Mode for basic tracking and Mesh Mode for ex- tended range using multiple devices and a router. This system provides efficient and reliable object tracking

   with enhanced connectivity.

   Fig.5 System Architechture

   1. Hardware Setup:

      The deployment begins with configuring ESP32 modules as tags, access points, and nodes. The tags are attached to ob- jects to be tracked, while access points or routers are posi- tioned strategically for optimal coverage. A portable power source is integrated to ensure uninterrupted operation of the hardware.

   2. Network Configuration

      In Normal Mode, the ESP32 modules connect to a single WiFi network, while in Mesh Mode, multiple nodes are linked to form a mesh network for extended range. The de- vices are programmed to switch between these modes dy- namically, depending on the network environment.

   3. Software Installation:

      The mobile application and web server are set up to handle data collection, processing, and user interaction. The app is installed on user devices to provide real-time tracking, net- work switching, and emergency notifications. The web server, hosted on a cloud platform, manages data storage, triangulation, and multilateration processes.

   4. Calibration and Testing:

      Calibration involves adjusting parameters like the path-loss exponent (nnn) for accurate RSSI-to-distance conversion based on the specific deployment environment. Extensive testing is conducted in different scenarios, such as indoor spaces, open areas, and obstructed environments, to ensure accuracy and reliability.

   5. Deployment and Monitoring:

   Once deployed, WiFind continuously tracks tagged objects and updates their locations on the mobile app and server. Regular monitoring of network performance and hardware functionality ensures the system operates seamlessly.

   1. Performance and Evaluation

      Tests Conducted

      1. Range Testing: WiFind was tested in both Normal Mode and Mesh Mode to determine its effective tracking range. In Normal Mode, the system maintained consistent perfor- mance up to 50 meters, while in Mesh Mode, the range ex-

         tended to over 100 meters by utilizing interconnected nodes.

      2. Accuracy Assessment: The accuracy of WiFind's distance estimation was measured by comparing cal- culated RSSI-based distances with actual distances. For Normal Mode, an average accuracy of 85% was achieved, while Mesh Mode demonstrated an im- proved accuracy of 93%, thanks to data aggregation and multilateration techniques.

      3. Reliability Testing: The system's reliability was evaluated by simulating various real-world scenarios, including environments with interference (e.g., walls, electronic devices) and dynamic movement. WiFind maintained stable connectivity and accurate tracking in most cases, with slight degradation in heavily ob- structed environments.

   Fig.6 Performance Table

   The graph illustrates the performance evaluation of WiFind and Bluetooth systems in terms of accuracy over varying distances. WiFind demonstrates consistently higher accuracy, maintaining above 80% even at 100 meters, whereas Bluetooth accuracy declines significant- ly beyond 40 meters. This highlights WiFind's superior range and precision compared to Bluetooth.

5. EXPERIMENTAL RESULTS AND OUTPUT

   The experimental evaluation of WiFind focused on key per- formance metrics, including range, accuracy, and reliability, under various environmental conditions. Testing was con- ducted in both controlled indoor and outdoor environments to assess the system's robustness and effectiveness. The re- sults highlight WiFind's superior performance in long-range tracking and accuracy when compared to traditional Blue- tooth-based systems.

   1. Accuracy Over Distance: WiFind demonstrated consistent accuracy levels, maintaining above 80% for distances up to 100 meters, as indicated in the graph. In contrast, Bluetooth accuracy dropped sig- nificantly, falling below 20% beyond 60 meters. This result confirms WiFinds enhanced precision over longer ranges.

   2. Range Comparison: WiFind's integration of WiFi technol- ogy allowed for extended tracking capabilities beyond the typical range of Bluetooth systems. The system successfully tracked objects up to 100 meters in normal mode, with fur- ther expansion possible in mesh mode using multiple access points.

   3. Motion Detection and Emergency Alerts: The integration of motion sensors enabled accurate detection of object movement. The system generated real-time alerts in scenar- ios such as significant movement or potential accidents, ef- fectively demonstrating its emergency response capabilities.

      Fig..7 Output

6. DISCUSSION

   WiFind successfully addresses several limitations faced by tra- ditional object-tracking solutions, particularly those relying on Bluetooth technology. The systems use of Wi-Fi through ESP32 modules offers increased range and flexibility. One of the standout features of WiFind is its mesh networking capabil- ity, which allows for coverage across larger distances and more compex environments, such as industrial settings, where tradi- tional tracking solutions fail.

   FUTURE WORKS:

   Online and Offline Modes:

   Enable WiFind to function seamlessly in both online and offline modes. In online mode, tracking data will be uploaded to the cloud for real-time access.In offline mode, data will be stored locally, al- lowing users to access tracking details even without an internet

   NcConITneScEtiToMn. – 25

   International Journal of Engineering Research & Technology (IJERT)

   Krugh et al. / Manufacturing Letters 41 (2024) 15961606

   Cloud Integration:

   Integrate cloud storage to enable remote management of tracking devices.Provide users with access to tracking histo- ry, analytics, and device data for enhanced flexibility and convenience.

   Data Management and Accessibility:

   Ensure data redundancy and security through cloud-based solutions.Allow users to access and manage tracking data easily from any location.

7. CONCLUSION

   WiFind is a versatile and scalable object-tracking system that effectively extends the range and capabilities of traditional Bluetooth-based solutions by utilizing Wi-Fi and mesh net- working with ESP32 modules. Through its two modes Normal Mode for direct tracking and Mesh Mode for long- range trackingWiFind demonstrates enhanced coverage, real-time tracking, and high accuracy in open environments. While there are opportunities to improve accuracy in com- plex indoor settings and optimize power consumption in Mesh Mode, the system shows significant promise for appli- cations ranging from personal use to industrial-scale track- ing. WiFind's flexibility and range make it a robust solution in the growing landscape of IoT-based tracking systems.

8. REFERENCE

1. A Survey On low energy bluetooth based key loca- tor and Device Detector Components,ISSN 2347 – 3983 Shivam Dongre et al., International Journal of Emerging Trends in Engineering Research, 11(2), February 2023, 87 92

2. BLUETOOTH-BASED REAL-TIME LUGGAGE TRACKING AND STATUS UPDATES Int.

   J.Adv.Sig.Img.Sci, Vol. 9, No. 2, 2023

3. Track You: A Deep Dive into Safety Alerts for Ap- ple AirTags, Proceedings on Privacy Enhancing Technologies 2023(4), 132148

4. RSSI-based attacks for identification of BLE devic- es. Guillaume Gagnona,, Sébastien Gambsa, Mathieu Cunche,Computers & Security 147 (2024)

   104080

5. Logistics 4.0 digital transformation with smart connected tracking and tracing devices. Petri Helo , Vinh V. Thai International Journal of Production Economics Volume 275, September 2024, 109336

6. Development of a novel Bluetooth Low Energy de- vice for proximity and location monitoring in graz- ing sheep A.M. Walkera,b,, N.N. Jonssonb, A. Waterhousea, H. McDougallc, F. Kenyonc, A. McLarena, C. Morgan-Davies, Animal 18 (2024)

   101276

7. Paranoid Operating System: Wearable Trackers. Afonso Almeidaa,*, Nuno Mateus-Coelhoa,c, Nuno Lopesa,b et al. / Procedia Computer Science 239 (2024) 23952404

8. Testing Scenario for Comparison of Real-time Lo- cating System in Automotive Manufacturing, M.

9. Bluetooth dataset for proximity detection in indoor envi- ronments collected with smartphones ,Michele Girolami

   , Davide La Rosa ,Paolo Barsocchi / Data in Brief 53 (2024) 110215

10. Indoor environment dataset based on RSSI collected with bluetooth devices Yuri Assayag , Horacio Oliveira, Max Lima, João Junior, Mateus Preste, Leonardo Guimarães, Eduardo Souto , / Data in Brief 55 (2024) 110692

11. An AI-empowered indoor digital contact tracing system for COVID-19 outbreaks in residential care homes,J. Meng, J.Y.W. Liu, L. Yang et al. Infectious Disease Mod- elling 9 (2024) 474e482

12. Low cost MEMS accelerometer and microphone based condition monitoring sensor, with LoRa and Bluetooth Low Energy radio.M.O. Jakobsen, HardwareX 18 (2024) e00525

13. Integration of LoRa-enabled IoT infrastructure for ad- vanced campus safety systems in Taiwan,S.-H. Liao et al,Internet of Things 28 (2024) 101347

14. Device discovery and tracing in the Bluetooth Low Ener- gy domain, Pierluigi Locatelli a,, Massimo Perria, Daniel Mauricio Jimenez Gutierreza, Andrea Lacavaa,b, Frances- ca Cuomoa,Computer Communications 202 (2023) 4256

15. paper 15: A Safety-System based on Bluetooth Low Ener- gy(BLE) to prevent the misuse of Personal Protection Equipment(PPE) inconstruction,J.M. Gómez-de-Gabriel et al. Safety Science 158 (2023) 105995

16. Feasibility of Bluetooth Low Energy for motion capturing with Inertial Measurement Units,P. Veijalainen et al. Journal of Network and Computer Applications 213 (2023) 103566

17. A self-learning mean optimization filter to improve blue- tooth 5.1 AoA indoor positioning accuracy for ship envi- ronments.Qianfeng Lina, Jooyoung Sonb,, Hyeongseol Shin Journal of King Saud University Computer and In- formation Sciences 35 (2023) 5973

18. Bluetooth low energy indoor localization for large indus- trial areas and limited infrastructure Kamil Szyca, Maciej Nikodema,, Micha Zdunek.,Ad Hoc Networks 139 (2023) 103024

19. Activities Tracking on Campus for Improving Academic Performance . Iyori Honma* Ryozo Kiyohara , / Proce- dia Computer Science 225 (2023) 28832891

20. Bluetooth Low Energy Urban Networks for Ultra- Accurate Geo Location Applications .,Friederike L. Kühl et al. / Transportation Research Procedia 72 (2023) 2566

257.

NCITSETM – 25 International Journal of Engineering Research & Technology (IJERT)