Description:FIELD OF THE INVENTION

The present disclosure relates to vehicle tracking and monitoring systems, and more specifically to systems and methods employing Radio-Frequency Identification (RFID) technology for real-time identification and tracking of vehicle components, such as tyres, to enhance vehicle management, prevent theft, and monitor component usage.

BACKGROUND OF THE INVENTION

The escalating challenges of vehicle theft, efficient fleet management, and accurate maintenance scheduling have driven significant advancements in vehicle tracking and monitoring technologies. Traditional vehicle tracking systems primarily rely on Global Positioning System (GPS) technology to ascertain vehicle location and movement. While effective for overall vehicle tracking, these systems often fall short in providing granular insights into the individual components of a vehicle, particularly critical assets like tyres. This limitation often leads to inefficiencies in asset management, increased operational costs, and vulnerabilities to theft for individual vehicle components.

Existing tyre management practices in various industries, especially in commercial fleets, frequently involve manual inspections and ledger-based tracking. This approach is inherently labor-intensive, prone to human error, and lacks real-time data on tyre usage, wear, and crucially, potential unauthorized removal or swapping. Such manual processes contribute significantly to financial losses stemming from tyre theft, premature tyre replacement due to inadequate tracking, inefficient maintenance scheduling, and a general lack of accountability for individual tyre assets throughout their lifecycle. The absence of automated, precise tracking for each tyre necessitates a more sophisticated and integrated solution to address these long-standing industry problems.

Several prior art solutions have attempted to address aspects of vehicle tracking and tyre monitoring, but each presents distinct limitations that the present invention aims to overcome. For instance, GPS-based vehicle tracking systems are widely prevalent and provide comprehensive vehicle-level tracking. However, they inherently lack the capability to provide component-level detail, meaning they cannot detect if a specific tyre has been swapped, stolen, or moved to another vehicle. Furthermore, GPS signals are vulnerable to obstruction or intentional jamming, leading to data inaccuracies or loss, and the power dependency of GPS devices can be a practical concern for continuous, long-term monitoring.

Similarly, Tyre Pressure Monitoring Systems (TPMS), as exemplified by patents like US 11,641,053 B2 (The Goodyear Tire & Rubber Company) and EP 2 202 099 A1, utilize sensors to monitor tyre pressure and temperature, providing crucial safety information. However, their scope is limited to these parameters and they do not inherently provide unique, tamper-proof identification for each tyre that can be tracked independently for asset management or theft detection purposes. This means a stolen tyre, once removed from its registered vehicle, becomes untraceable by such systems. Additionally, direct TPMS sensors can have issues with malfunction or limited battery life, requiring periodic replacement.

Furthermore, advancements have been made in RFID-enabled tyre manufacturing and supply chain tracking, as seen in patents like US 8,025,238 B2 (Asiana Idt Inc.) and EP 3 637 322 A1 (Bridgestone Americas Tire Operations, LLC). These patents describe the embedding of RFID tags into tyres during production for inventory and quality control within the supply chain. While addressing the technical feasibility of embedding durable RFID tags, these solutions primarily focus on pre-sale logistics. They generally do not extend to comprehensive, real-time post-sale vehicle-level tracking, theft detection, or detailed mileage and maintenance history for individual tyres in operational use by an end-user or fleet manager. Crucially, they typically lack the dynamic functionality of continuously linking a specific tyre's RFID ID to a specific vehicle's registration number and automatically verifying this association across diverse operational environments. Consequently, these prior art systems do not include a robust mechanism for automatically detecting mismatches between a tyre's identity and the vehicle it is attached to, nor for issuing real-time alerts to prevent or detect theft and unauthorized swapping. The current state of the art therefore lacks a holistic, integrated system that combines tamper-proof individual tyre identification with robust, real-time vehicle-to-tyre association verification, comprehensive mileage tracking, and automated theft detection capabilities across multiple scanning points, which the present invention aims to significantly improve upon.

In view of the foregoing discussion, it is portrayed that there is a need to have a smart vehicle tracking system and method for smart vehicle tracking and tyre monitoring.

SUMMARY OF THE INVENTION

The present disclosure seeks to provide an RFID-enabled tyre system wherein each tyre contains a uniquely coded RFID tag embedded inside it as well as exernally installed RFID tag. This tag is linked to a digital record stored in an application developed by the inventor. When a vehicle passes a scanning point (e.g., RFID gate, roadside scanner, toll, depot, or any scanner etc.), the scanner reads the tyre RFID tags and sends data to the central app.

In an embodiment, a smart vehicle tracking system is disclosed. The system includes a plurality of tyres, each tyre comprising a unique, non-removable, and tamper-proof Radio-Frequency Identification (RFID) tag embedded therein, the RFID tag configured to store a unique serial number associated with the respective tyre.
The system further includes a registration module configured to receive the unique serial number from each of the plurality of RFID tags and associate each received unique serial number with a specific vehicle registration number in a data storage system.
The system further includes a plurality of RFID scanners strategically located at a plurality of scanning locations, each RFID scanner configured to read the unique serial number from the RFID tags embedded in tyres of a vehicle passing within a reading range of the RFID scanner.
The system further includes a processing module communicatively coupled to the plurality of RFID scanners and the data storage system, the processing module configured to receive read data from the plurality of RFID scanners and compare the unique serial number read from the RFID tag of a tyre with the unique serial number associated with the vehicle registration number of the vehicle carrying the tyre, as stored in the data storage system thereby determine a match or a mismatch between the read unique serial number and the associated unique serial number.
The system further includes an alert module communicatively coupled to the processing module, the alert module configured to generate an alert when a mismatch is detected between the read unique serial number and the associated unique serial number, or when suspicious movement history of a tyre is detected thereby transmit the alert to a designated recipient. The suspicious movement history of a tyre is detected based on at least one criterion selected from the tyre appearing on multiple different vehicles within a short period; the tyre traveling an abnormally high distance without recorded maintenance; or the tyre being registered in one geographical region and subsequently scanned in a distant, unrelated geographical region, wherein the criteria for detecting suspicious movement are configured and updated using a combination of a rule-based system with fixed rules set by experts and a machine learning model that learns from historical data to identify complex or hidden patterns, wherein the machine learning model is retrained regularly with new data to adapt to evolving patterns of suspicious activity.

In another embodiment, a method for smart vehicle tracking and tyre monitoring is disclosed. The method includes embedding a unique, non-removable, and tamper-proof Radio-Frequency Identification (RFID) tag within each of a plurality of tyres, the RFID tag storing a unique serial number associated with the respective tyre.
The method further includes registering each unique serial number of the RFID tags by associating it with a specific vehicle registration number in a data storage system.
The method further includes scanning, by a plurality of RFID scanners, the RFID tags embedded in tyres of a vehicle passing within a reading range of the RFID scanners to obtain read unique serial numbers, wherein scanning is performed at least one of vehicle depots, toll booths, parking lots, or garages.
The method further includes comparing, by a processing module, the read unique serial number from an RFID tag of a tyre with the unique serial number associated with the vehicle registration number of the vehicle carrying the tyre, as stored in the data storage system upon utilizing a graphical user interface installed on a user computing device to input and store the associations.
The method further includes determining, by the processing module, a match or a mismatch between the read unique serial number and the associated unique serial number.
The method further includes generating an alert when a mismatch is detected between the read unique serial number and the associated unique serial number, or when suspicious movement history of a tyre is detected, and transmitting the alert to a designated recipient.
The method further includes storing historical data associated with each tyre, the historical data including at least one of distance traveled, dates of scans, locations of scans, or mileage.
The method further includes calculating tyre mileage and running cost per kilometer or mile based on the stored historical data.
The method further includes integrating live vehicle movement data from a Global Positioning System (GPS) with the tyre tracking data and maintaining maintenance logs for each tyre based on scanned data and user input.

An object of the present disclosure is to provide a robust and tamper-proof method for uniquely identifying individual tyres throughout their lifecycle, regardless of the vehicle they are mounted on.
Another object of the present disclosure is to establish an automated system for continuously associating and verifying the identity of each tyre with the specific vehicle registration number to which it is legitimately assigned.
Another object of the present disclosure is to enable real-time detection and prevention of tyre theft, unauthorized tyre swapping, and fraudulent tyre activities by automatically identifying discrepancies between a tyre's registered identity and its current vehicle assignment.
Another object of the present disclosure is to facilitate efficient and accurate tracking of individual tyre usage, including mileage, scan locations, and dates, thereby providing valuable data for fleet management, maintenance scheduling, and cost analysis.
Another object of the present disclosure is to eliminate the need for manual physical verification of tyres, thereby reducing human resource requirements, minimizing errors, and streamlining auditing processes for fleet owners and compliance.
Another object of the present disclosure is to provide historical tracking capabilities for each tyre, including its movement history, to enhance traceability and accountability for tyre assets.
Another object of the present disclosure is to integrate seamlessly with existing vehicle tracking technologies, such as GPS, to provide a holistic view of both vehicle and component movement and status.
Another object of the present disclosure is to ultimately reduce financial losses for vehicle owners and fleet managers by deterring theft, optimizing tyre utilization, and simplifying tyre auditing and compliance.
Yet another object of the present invention is to deliver an expeditious and cost-effective scalable and flexible system that can be readily adopted by multiple tyre manufacturers and integrated into various vehicle types and fleet sizes.

To further clarify the advantages and features of the present disclosure, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail in the accompanying drawings.

BRIEF DESCRIPTION OF FIGURES

These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read concerning the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

Figure 1 illustrates a block diagram of a smart vehicle tracking system in accordance with an embodiment of the present disclosure;
Figure 2 illustrates a flow chart of a method for smart vehicle tracking and tyre monitoring in accordance with an embodiment of the present disclosure.

Further, skilled artisans will appreciate those elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

DETAILED DESCRIPTION:

To promote an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.

It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be restrictive thereof.

Reference throughout this specification to “an aspect”, “another aspect” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrase “in an embodiment”, “in another embodiment” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises...a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.

Embodiments of the present disclosure will be described below in detail concerning the accompanying drawings.

Referring to Figure 1, a block diagram of a system for analyzing Tamil tweets into positive and negative sentiments is illustrated in accordance with an embodiment of the present disclosure. The system (100) includes a plurality of tyres (102), each tyre (102) comprising a unique, non-removable, and tamper-proof Radio-Frequency Identification (RFID) tag (104) embedded therein, the RFID tag (104) configured to store a unique serial number associated with the respective tyre (102).

In an embodiment, a registration module (106) is configured to receive the unique serial number from each of the plurality of RFID tags (104) and associate each received unique serial number with a specific vehicle registration number in a data storage system.

In an embodiment, a plurality of RFID scanners (108) are strategically located at a plurality of scanning locations, each RFID scanner configured to read the unique serial number from the RFID tags (104) embedded in tyres (102) of a vehicle passing within a reading range of the RFID scanner.

In an embodiment, a processing module (110) is communicatively coupled to the plurality of RFID scanners (108) and the data storage system, the processing module (110) configured to receive read data from the plurality of RFID scanners (108) and compare the unique serial number read from the RFID tag (104) of a tyre (102) with the unique serial number associated with the vehicle registration number of the vehicle carrying the tyre (102), as stored in the data storage system thereby determine a match or a mismatch between the read unique serial number and the associated unique serial number.

In an embodiment, an alert module (112) is communicatively coupled to the processing module (110), the alert module (112) configured to generate an alert when a mismatch is detected between the read unique serial number and the associated unique serial number, or when suspicious movement history of a tyre (102) is detected thereby transmit the alert to a designated recipient. The suspicious movement history of a tyre is detected based on at least one criterion selected from the tyre appearing on multiple different vehicles within a short period; the tyre traveling an abnormally high distance without recorded maintenance; or the tyre being registered in one geographical region and subsequently scanned in a distant, unrelated geographical region, wherein the criteria for detecting suspicious movement are configured and updated using a combination of a rule-based system with fixed rules set by experts and a machine learning model that learns from historical data to identify complex or hidden patterns, wherein the machine learning model is retrained regularly with new data to adapt to evolving patterns of suspicious activity.

In another embodiment, the RFID tag (104) is a passive RFID tag, wherein the RFID tag is an active RFID tag, wherein said RFID tag is embedded within a trye of said vehicle upon sticking on an inner surface, an outer surface, and by embedding within a rubber layer between said tyre, wherein each RFID scanner is configured to mitigate interference from other radio frequency sources or metal objects in the scanning environment by employing special RF filters and anti-collision techniques, wherein the anti-collision techniques are configured to detect and filter out disturbances caused by signals from other devices or reflections from nearby metal objects, wherein each RFID scanner is further configured to identify only the correct and nearest RFID tag to minimize incorrect readings.

In another embodiment, the processing module is configured to compare the read unique serial number with the associated stored unique serial number using an exact matching technique, ensuring a one-to-one string match for validation, wherein the processing module is configured to perform a single comparison, selected from reading, matching, and response, in under 300 milliseconds, wherein the processing module is configured to handle a high volume of concurrent vehicle scans by employing parallel processing, load balancing, and message queues, wherein the message queues utilize a Kafka-based system for efficient message handling, wherein the processing module further utilizes cloud auto-scaling and edge computing to optimize performance during peak loads, wherein the processing module is configured to retrieve the associated unique serial number from the data storage system by performing a SELECT query using a unique identifier selected from the RFID tag ID, vehicle number, or chassis number.

In a further embodiment, the plurality of scanning locations includes at least one of: vehicle depots, toll booths, parking lots, or garages, wherein the alert module is configured to trigger an alert when the detected suspicious activity crosses a preset limit for the defined criteria, wherein the generated alert includes information comprising the scan date and time, vehicle details, including the vehicle registration number, tyre details, including the scanned tyre serial number and the system-recorded serial number, an alert message indicating whether an allotted tyre is missing or does not match with records, and the type of issue, selected from a missing tyre, a serial number mismatch, or an unauthorized change, wherein the alert module is configured to transmit said alert to a designated recipient via at least one method selected from: SMS notifications, email alerts, mobile application notifications, dashboard pop-ups, direct integration with a fleet management system (FMS), or messaging services, wherein the alert module is configured to transmit alerts through multiple redundant channels and employ retry mechanisms to ensure successful delivery even during brief network interruptions, wherein the alert module is configured to customize alert severity and type, allowing different alerts to be sent to different recipients based on their roles or the nature of the alert.

The system (100) further comprising a historical tracking module (114) configured to store and retrieve historical data associated with each tyre (102), the historical data including at least one of: distance traveled, dates of scans, locations of scans, or mileage, wherein the historical data for each tyre further includes: precise GPS coordinates at each scan, duration of stop at a location, average speed between scans, alert logs associated with the tyre, and information about the user or device that performed the scan, wherein the historical tracking module is configured to consolidate data from various scanning locations by: collecting data in real-time or at scheduled intervals; transmitting the collected data to a central database; tagging each scan with a unique tyre ID, timestamp, and location metadata; and aggregating the tagged data chronologically to build a comprehensive historical record for each tyre.

The system (100) further comprising a maintenance log module (116) configured to store and retrieve maintenance records associated with each tyre (102), wherein the historical tracking module (114) is further configured to calculate tyre mileage and running cost per kilometer or mile based on the stored historical data, wherein the tyre mileage is calculated using a methodology selected from GPS-based odometer readings from an integrated GPS system, or inferring distance from scan locations and map data, wherein the running cost per kilometer or mile is calculated using parameters comprising tyre purchase price, expected lifespan, maintenance costs, fuel efficiency impact, and retread/disposal costs, wherein said parameters are input manually or automatically fetched from integrated GPS/telematics systems and service logs, wherein the system is configured to project future running costs based on historical tyre data, usage patterns, maintenance records, and predicted mileage, utilizing trend analysis and predictive techniques.

The system (100) further comprising a Global Positioning System (GPS) integration module (118) configured to integrate live vehicle movement data with the tyre tracking data, wherein maintenance records are entered into the system via manual input through a graphical user interface or automatically through integration with third-party maintenance systems using Application Programming Interfaces (APIs).

In some embodiments, the data storage system is a cloud-based server system (120) and a local server system, wherein the data storage system is configured to capture and store, for each tyre, details comprising: tyre brand, product details, tyre number, buyer details, warranty information, guarantee information, vehicle information, and an initial odometer reading of the vehicle at the time of tyre assignment, wherein the data storage system is further configured to automatically record an updated odometer reading through a tracking application.

In one of the above embodiments, the registration module (106) is accessible via a graphical user interface (122) installed on a user computing device, wherein the registration module is further configured to map the RFID unique serial number with a tyre's unique serial number, and enable a user to assign the tyre to a specific vehicle based on the vehicle registration number and optionally a chassis number, wherein the registration module is further configured to allow retrieval of an assigned tyre and reassignment of the tyre to another vehicle thereby automatically receives the unique serial number from the RFID tag via automated scanning through a smart application, wherein the registration module is configured to receive the unique serial number from the RFID tag via at least one of a fixed RFID reader installed at a manufacturing facility, a fixed RFID reader installed at a registration facility, or a handheld RFID reader.

In an embodiment, the machine learning model dynamically reconfigures its decision parameters in response to newly identified anomalies by incorporating each transmitted anomaly score as a labeled data point into a continuously updated training dataset, performing incremental parameter updates without requiring full retraining of the model by applying online learning techniques, and recalibrating feature importance weights in real-time by receiving confirmation of a detected anomaly as a verified misuse event from the alert module, the anomaly types including at least one of: a multi-vehicle association anomaly, wherein a single tyre’s RFID tag is detected on multiple non-associated vehicles within a short predefined interval; a geographical inconsistency anomaly, wherein a tyre is scanned in two or more geographically incompatible locations within an unfeasible time window; an authentication failure anomaly, wherein a tyre’s RFID tag fails a predefined number of cryptographic handshake verifications; or an excessive usage anomaly, wherein accumulated mileage or usage duration of the tyre exceeds an expected operational threshold without a corresponding maintenance record; mapping the verified anomaly type to the contributing features in the tyre’s historical data; calculating the statistical contribution of each contributing feature to the occurrence of the verified anomaly using a gradient-based sensitivity analysis on the machine learning model’s decision function; and dynamically adjusting the feature weights by amplifying the weight of features strongly correlated with the verified anomaly type and reducing those with negligible correlation, thereby enhancing the model’s capability to detect similar anomalies in future operations.
In an embodiment, the processing module is further configured to authenticate each tyre’s RFID tag during a scanning event by executing a multi-phase handshake procedure, the multi-phase handshake procedure comprising: (a) generating, by the processing module, a random nonce value upon receiving an initial tag read request from an RFID scanner; (b) transmitting said nonce value to the corresponding RFID tag via the scanner, wherein the RFID tag is pre-configured with a secret key stored within a secure memory section inaccessible from external interfaces; (c) receiving, by the processing module, a response comprising the nonce value encrypted using said secret key, wherein the processing module validates the response by decrypting it with a corresponding server-side key stored in a hardware security module; (d) marking the RFID tag as verified only when the decrypted response matches the originally transmitted nonce, and rejecting the tag otherwise; and (e) recording the result of each handshake in a secure audit trail indexed to the unique serial number of the tyre.
In this embodiment, the processing module is designed to provide a robust and tamper-resistant mechanism for verifying the authenticity of each tyre’s RFID tag during every scanning event, thereby significantly enhancing security and traceability. Upon receiving a tag read request from an RFID scanner, the processing module initiates a multi-phase handshake by generating a unique random nonce value, which serves as a one-time challenge that prevents replay attacks or unauthorized duplication attempts. This nonce is transmitted to the target RFID tag, which is pre-programmed with a secret cryptographic key stored in a secure memory area that cannot be accessed from any external interface, ensuring that even physical access to the tag cannot compromise its security. The RFID tag uses this secret key to encrypt the nonce and sends the encrypted response back to the processing module. The module then validates the response by decrypting it with a corresponding server-side key stored within a hardware security module, which provides a hardware-enforced layer of security against key theft or software-based attacks. Only if the decrypted nonce exactly matches the originally transmitted value is the tag considered verified; any mismatch results in immediate rejection, preventing unauthorized or cloned tags from being recognized. Additionally, the outcome of each handshake is recorded in a secure audit trail linked to the unique serial number of the tyre, ensuring full traceability of every authentication event. This embodiment provides a clear technical effect by ensuring end-to-end integrity of tyre identification and authentication, and represents a technical advancement over conventional RFID verification methods that rely solely on static identifiers, which are susceptible to cloning, tampering, or replay attacks. For example, in a scenario where a fleet operator wants to ensure that tyres are genuine and correctly installed, this system prevents any tampering attempts, as an attacker cannot generate a valid encrypted nonce without access to the tag’s secure secret key, and every authentication event is securely logged for future verification or audit.
In an embodiment, the secure audit trail is maintained in the data storage system by implementing a chained-hash structure, the chained-hash structure configured to: (a) generate a cryptographic hash for each new authentication event by combining the current authentication record with the hash of the immediately preceding record; (b) prevent undetected alteration of historical authentication data by invalidating any subsequent hash in the chain if a prior entry is modified; and (c) enable the processing module to perform rapid verification of data integrity by recalculating and comparing hash sequences during each tyre scan.
In this embodiment, the secure audit trail is designed to provide tamper-evident, verifiable records of every tyre authentication event by implementing a chained-hash structure within the data storage system. Each new authentication event generates a cryptographic hash that combines the current event’s record with the hash of the immediately preceding record, effectively creating a continuous chain of linked hashes. This design ensures that any alteration of a prior record, whether accidental or malicious, immediately disrupts the integrity of all subsequent hashes in the chain, making any tampering instantly detectable. The processing module leverages this structure to perform rapid integrity verification during each tyre scan by recalculating the hash sequence and comparing it with stored values. This approach provides a technical effect of real-time, automated detection of unauthorized modifications and guarantees that historical authentication data remains verifiably accurate. Technically, it advances beyond conventional logging mechanisms by introducing a cryptographically linked structure that allows secure, efficient validation without the need to manually audit or cross-check all records. For example, if a fleet operator attempts to backdate or modify an authentication event to mask a tyre swap, the system immediately identifies the inconsistency because the recalculated hashes no longer match the stored sequence, ensuring data integrity and enhancing operational trustworthiness.
In this embodiment, the secure audit trail is implemented by constructing a cryptographic chained-hash structure within the data storage system, and is achieved through systematic record linking and hash computation. When a tyre authentication event occurs, the processing module first serializes the event data—including the tyre’s unique ID, timestamp, scanner ID, and authentication result—into a standardized data format. The module then generates a cryptographic hash (e.g., using SHA-256) of this serialized record. To link the event into the chain, this hash is concatenated with the hash of the immediately preceding record, and a new hash is computed for the combination. This new hash is stored alongside the current event in the database, forming a sequential chain where each record cryptographically depends on all prior records. During verification, the processing module retrieves the relevant portion of the chain and recalculates hashes sequentially, comparing each recalculated hash to the stored value. If any prior record was altered, the recomputed hashes will differ from the stored hashes, and the system immediately flags the anomaly. To optimize performance, the system may maintain the latest hash in memory or a secure index, allowing incremental hash updates without recalculating the entire chain. This implementation ensures that the integrity of the audit trail is continuously verifiable in real time during each tyre scan, making it computationally efficient while maintaining strong cryptographic security. Technically, this provides both immutable event storage and rapid detection of tampering, an advancement over conventional logging mechanisms that lack cryptographic linkage or real-time verification. For example, if an attacker attempts to modify an authentication result for a tyre swapped weeks ago, the hash chain would break at that point, and the system would immediately detect the inconsistency during the next verification cycle.
In an embodiment, each RFID scanner further incorporates a phased-array antenna controlled by a digital signal processor (DSP), and wherein the DSP is configured to: (a) estimate the direction of arrival of each backscattered RFID signal using phase difference measurements across the antenna elements; (b) electronically steer the antenna beam toward the detected direction while suppressing side lobes using adaptive beamforming; (c) re-validate the read signal by correlating it with previously known positional data of the vehicle's tyres from the historical tracking module; and (d) discard any signal whose angle-of-arrival deviates beyond a predetermined positional tolerance, thereby reducing erroneous tag captures.
In this embodiment, each RFID scanner incorporates a phased-array antenna controlled by a digital signal processor (DSP) to achieve precise tyre tag detection. The DSP measures phase differences across the antenna elements for every received backscattered RFID signal and uses these measurements to determine the direction from which the signal originates. Based on the estimated direction, the DSP electronically adjusts the antenna elements’ phase and amplitude to steer the beam toward the target signal while suppressing signals from other directions. After capturing the signal, the DSP cross-checks it against historical positional data of the vehicle’s tyres stored in the tracking module to verify that the detected tag corresponds to the expected tyre location. Any signal whose angle-of-arrival falls outside a predefined positional tolerance is discarded. This step-by-step implementation ensures that only genuine tyre tags are detected, reduces false positives caused by environmental reflections or nearby tags, and enables real-time validation during vehicle monitoring. The embodiment fully enables replication because it specifies how the DSP interacts with the antenna array, how signals are directionally filtered, and how cross-validation with historical positional data is performed to ensure accurate and reliable tyre identification.
In this embodiment, each RFID scanner is enhanced with a phased-array antenna system controlled by a digital signal processor (DSP) to significantly improve the precision and reliability of tyre tag detection. The DSP first estimates the direction of arrival (DoA) of each backscattered RFID signal by analyzing phase differences across multiple antenna elements, enabling the system to distinguish genuine tag signals from reflections or interference. Once the DoA is determined, the DSP electronically steers the antenna beam toward the detected direction while suppressing side lobes through adaptive beamforming, which concentrates signal reception on the intended target and minimizes reception of stray signals. To further ensure accuracy, the DSP re-validates the captured signal by correlating it with historical positional data of the vehicle’s tyres maintained by the tracking module, ensuring that each read aligns with the expected tyre locations. Signals that exhibit an angle-of-arrival deviation beyond a predefined positional tolerance are discarded, effectively reducing false positives caused by spurious or off-target reads. This embodiment delivers a clear technical effect by enhancing the spatial selectivity of RFID detection, reducing erroneous captures, and increasing overall system reliability. The technical advancement lies in integrating phased-array beamforming with contextual historical data for validation, a capability not present in conventional fixed-antenna RFID systems, which are more prone to multipath interference and misreads. For instance, in a busy depot where multiple tagged vehicles are in proximity, this system ensures that only the correct tyres of the target vehicle are identified, preventing misattribution of tags and improving operational accuracy.
In an embodiment, the historical tracking module is configured to resolve discrepancies between multiple independent data sources by implementing a temporal-spatial reconciliation comprising: (a) aligning each RFID scan record with a nearest-in-time GPS position fix from the vehicle’s telematics unit within a ±5 second window; (b) calculating a route consistency score by comparing the inferred path from RFID scan locations with the actual GPS trajectory; (c) assigning a weighted anomaly score to the tyre when the route consistency score falls below a threshold, said score increasing proportionally with the magnitude and frequency of deviations; and (d) transmitting said anomaly score to the machine learning model for iterative refinement of detection thresholds specific to individual tyres and vehicle classes. In this embodiment, the historical tracking module is implemented to reconcile discrepancies between RFID scan records and GPS data to ensure accurate tyre monitoring. Each RFID scan record is first time-aligned with the closest GPS position fix from the vehicle’s telematics unit within a ±5 second window, ensuring temporal synchronization between tag reads and the vehicle’s actual location. The module then compares the sequence of RFID scan locations against the GPS trajectory to evaluate consistency of the vehicle’s path. Based on this comparison, a route consistency score is calculated for each tyre, quantifying how closely the RFID-derived path matches the actual trajectory. If the consistency score falls below a predefined threshold, the system assigns a weighted anomaly score to the tyre, where the weight increases proportionally with both the frequency and magnitude of deviations, reflecting the likelihood of irregular activity or potential misuse. The anomaly score is then transmitted to the machine learning model, where it is used to iteratively adjust detection thresholds for individual tyres and vehicle types, enabling adaptive, data-driven calibration of anomaly detection. This implementation provides full technical enablement by specifying how RFID and GPS data are temporally aligned, how path consistency is evaluated, and how anomaly scoring is computed and utilized to refine detection logic, ensuring that the system can be reliably replicated and deployed in real-world monitoring scenarios.
In this embodiment, the historical tracking module is designed to enhance the reliability of tyre monitoring by reconciling discrepancies between multiple independent data sources through temporal-spatial alignment. Each RFID scan record is precisely matched with the nearest GPS position fix from the vehicle’s telematics unit within a narrow ±5 second window, ensuring that time-based inconsistencies are minimized and that each tag read is accurately placed in the context of the vehicle’s location. The module then calculates a route consistency score by comparing the inferred path derived from sequential RFID scan locations against the actual GPS trajectory recorded by the telematics unit. When the inferred path diverges significantly from the expected trajectory, the system assigns a weighted anomaly score to the tyre, with the score increasing proportionally to both the magnitude and frequency of deviations. This approach allows the system to quantify the degree of unusual activity or potential misuse for each tyre rather than relying on a binary indication of presence or absence. The anomaly score is then transmitted to a machine learning model, which iteratively refines detection thresholds for individual tyres and vehicle classes, enabling adaptive and context-aware anomaly detection. This embodiment provides a technical effect of improved detection accuracy and operational insight, ensuring that unusual movements or potential tampering are identified promptly. It represents a technical advancement over conventional systems that treat each scan in isolation without considering temporal or spatial consistency, thereby significantly reducing false positives and improving the reliability of tyre integrity monitoring. For example, if a tyre is scanned in a location inconsistent with the vehicle’s GPS trajectory—such as being detected on a different route or location—the system generates a high anomaly score and triggers further analysis, allowing fleet operators to intervene before potential misuse escalates.
In an embodiment, the processing module dynamically reconfigures decision parameters in response to newly identified anomalies by: (a) incorporating each transmitted anomaly score as a labeled data point into a continuously updated training dataset; (b) performing incremental parameter updates without requiring full retraining of the model by applying online learning techniques; (c) recalibrating feature importance weights in real-time based on observed correlations between specific anomaly types and confirmed instances of tyre misuse; and (d) synchronizing updated model parameters across all processing modules in geographically distributed data centers using a consensus-based parameter server to ensure uniformity of detection capabilities.
In this embodiment, the processing module is implemented to adaptively update its decision-making parameters in response to newly detected anomalies, ensuring continuous, real-time improvement of tyre misuse detection. Each anomaly score received from the historical tracking module is first incorporated as a labeled data point into a continuously updated training dataset, allowing the system to maintain an evolving representation of observed behaviour. The module then updates model parameters incrementally without retraining the entire model by applying online update techniques, which adjust the relevant weights and thresholds based on the newly added data. In parallel, feature importance weights are recalibrated in real time, so that the attributes most strongly correlated with confirmed instances of tyre misuse—such as positional deviations or angle-of-arrival inconsistencies—are given higher significance in subsequent evaluations. Once parameters are updated locally, the module synchronizes the changes across all processing modules in geographically distributed data centers using a consensus-based parameter server, ensuring that each node operates with uniform detection logic. This implementation provides full enablement by specifying how anomaly data is ingested, how incremental updates and feature recalibration are performed, and how parameter consistency is maintained across distributed modules, allowing the system to be reliably reproduced and deployed in real-world, large-scale fleet monitoring scenarios.
In this embodiment, the processing module is configured to provide adaptive, real-time anomaly detection by dynamically reconfiguring decision parameters in response to newly identified irregularities. Each anomaly score transmitted from the historical tracking module is incorporated as a labeled data point into a continuously updated training dataset, enabling the system to learn from real-world observations as they occur. Rather than requiring full retraining of the detection model, the module applies online learning techniques to perform incremental updates to model parameters, ensuring rapid adaptation while minimizing computational overhead. In parallel, the system recalibrates feature importance weights in real-time, adjusting the relative significance of various indicators based on observed correlations between specific anomaly types and confirmed cases of tyre misuse. This allows the detection model to prioritize features that are most predictive of genuine anomalies, enhancing detection accuracy. To maintain consistent detection capabilities across a distributed deployment, the updated model parameters are synchronized across all geographically dispersed processing modules using a consensus-based parameter server, ensuring that every node operates with uniform decision logic. The technical effect of this embodiment is a resilient, self-improving anomaly detection system that adapts to evolving patterns of tyre behavior, reducing false positives and improving reliability. The technical advancement lies in combining continuous learning, real-time feature reweighting, and distributed parameter synchronization—a capability beyond static, manually tuned models that degrade over time. For instance, if repeated minor deviations in tyre positioning are observed across a specific vehicle type, the system incrementally increases sensitivity to these patterns, ensuring emerging misuse is detected promptly while maintaining consistent detection thresholds across all monitoring locations.
Figure 2 illustrates a flow chart of a method for smart vehicle tracking and tyre monitoring in accordance with an embodiment of the present disclosure. At step (202), method (200) includes embedding a unique, non-removable, and tamper-proof Radio-Frequency Identification (RFID) tag within each of a plurality of tyres, the RFID tag storing a unique serial number associated with the respective tyre.

At step (204), method (200) includes registering each unique serial number of the RFID tags by associating it with a specific vehicle registration number in a data storage system.

At step (206), method (200) includes scanning, by a plurality of RFID scanners, the RFID tags embedded in tyres of a vehicle passing within a reading range of the RFID scanners to obtain read unique serial numbers, wherein scanning is performed at least one of vehicle depots, toll booths, parking lots, or garages.

At step (208), method (200) includes comparing, by a processing module, the read unique serial number from an RFID tag of a tyre with the unique serial number associated with the vehicle registration number of the vehicle carrying the tyre, as stored in the data storage system upon utilizing a graphical user interface installed on a user computing device to input and store the associations.

At step (210), method (200) includes determining, by the processing module, a match or a mismatch between the read unique serial number and the associated unique serial number.

At step (212), method (200) includes generating an alert when a mismatch is detected between the read unique serial number and the associated unique serial number, or when suspicious movement history of a tyre is detected, and transmitting the alert to a designated recipient.

At step (214), method (200) includes storing historical data associated with each tyre, the historical data including at least one of distance traveled, dates of scans, locations of scans, or mileage.

At step (216), method (200) includes calculating tyre mileage and running cost per kilometer or mile based on the stored historical data.

At step (218), method (200) includes integrating live vehicle movement data from a Global Positioning System (GPS) with the tyre tracking data and maintaining maintenance logs for each tyre based on scanned data and user input.

The RFID tags are installed in tyres using three methods — by sticking them on the inner surface, on the outer surface, or by embedding them within the rubber layer between the tyre components. Same details uploaded in our smart application. The RFID unique number is mapped with the tyre's unique serial number, and the user assigns the tyre to a specific vehicle. In the future, there will be an option to retrieve the tyre and reassign it to another vehicle. The vehicle is identified through the registration number and optionally the chassis number. Automated scanning through our smart application.

All necessary details are recorded as applicable. When the RFID tag is attached to the tyre, the tyre details like brand, product details tyre number, buyer details, other tyre related warranty guarantee etc are uploaded. When the tyre is assigned to a vehicle, the vehicle information and the current odometer reading are uploaded option available and with automatic start odometer through tracking application running kilometres reading in future. If the tyre is assigned to a trailer/vehicle, the current reading is used. When the tyre is removed, the running kilometres are calculated based on both the odometer and GPS data.
Processing modules (e.g., Wi-Fi, Ethernet, cellular) can also be transmitted via RFID scanners, tracking systems (VTS) and Bluetooth. The system uses special RF filters and anti-collision techniques to reduce interference. These technologies help detect and filter out disturbances caused by signals from other devices or reflections from nearby metal objects. Additionally, the system is designed to identify only the correct and nearest tag, minimizing the chances of incorrect readings. The processing module uses an exact matching technique to compare the RFID tag's read serial number with the stored serial number in the database. This comparison is typically done using a one-to-one string match, ensuring that only perfectly matched serial numbers are validated.
A single vehicle scan takes under 300 ms, including reading, matching, and response. The system uses parallel processing, load balancing, and message queues (e.g., Kafka) to handle high volumes. Cloud auto-scaling and edge computing (if used) further optimize performance during peak loads. To find the tyre’s serial number linked with an RFID tag, the system performs a SELECT query using a unique identifier such as the RFID tag ID, vehicle number, or chassis number. This query retrieves related details like tyre serial number, brand, product name, manufacturing details, buyer info, warranty, guarantee, and performance parameters.
The details of each tyre is mapped with its unique serial number using RFID tag. Once updated at the company registration centre, the RFID scanner will check for match or mismatch. Additionally, through the RFID scanner installed in your vehicle - will detect any suspicious activity related to tyres. Mismatching parameter after scanning immediate alert or message to pre-decided sources, via both rule-based, machine learning-driven, or a combination.
Suspicious movement is detected using a combination of:
• Rule-based system – fixed rules set by experts
• Machine learning – learns from data to catch complex or hidden patterns.
• Alerts – If a mismatch is found, an instant alert or message is sent to assigned contacts.
• Updates – Rules are updated manually; ML models are retrained regularly with new data.

Alerts trigger when suspicious activity crosses preset limits like multiple vehicle uses in short time, abnormal distance travelled. Mismatching parameter after scanning immediate alert or message to pre-decided sources, via both rule-based, machine learning-driven, or a combination.
Information scan time& date, location with vehicles details, alerts message that found allotted tyre missing or not matching with records.
The generated alert includes the following key information:
• Scan Date & Time – when the scan was performed
• Vehicle Details – including Vehicle Registration Number
• Tyre Details – scanned tyre serial number vs. system-recorded serial number
• Alert Message – indicating if an allotted tyre is missing or does not match with the records
• Type of Issue – e.g., missing tyre, serial number mismatch, or unauthorized change

Alerts can be transmitted to designated recipients using multiple channels to ensure timely delivery and prompt action. These methods include SMS Notifications, Email Alerts , Mobile Application Notifications, Dashboard Pop-ups, Integration with Fleet Management Systems (FMS), or Messaging Services. The alerts can be customized by severity and type, such as critical or warning. The system allows role-based routing, so different alerts reach specific recipients like maintenance teams, security, or managers. This ensures the right person receives relevant information promptly, enabling faster decision-making and more effective issue resolution.
The expected alert transmission latency is typically within 5 to 10 seconds under normal network conditions. Reliability is above 99%, as alerts are sent through multiple redundant channels (e.g., SMS, app, email) and use retry mechanisms to ensure successful delivery even during brief network interruptions. Designated recipients are configured through an admin panel, where roles, departments, and contact details are assigned. A hierarchy or escalation protocol can be set, ensuring critical alerts are automatically forwarded to higher authorities if not acknowledged within a defined timeframe.

Historical data for each tyre includes the date and time of each scan, GPS location, vehicle details, tyre serial number history, duration of stop at locations, average speed between scans, alert logs, and information about the user or device that performed the scan, ensuring complete tracking and traceability. Data from various scanning locations is collected in real time or at scheduled intervals and transmitted to a central database. Each scan is tagged with a unique tyre ID, timestamp, and location metadata. The system then aggregates this data chronologically to build a comprehensive historical record for each tyre. This consolidated record includes usage, wear patterns, maintenance events, and location history, enabling effective tracking and analysis throughout the tyre's lifecycle.

Tyre mileage is calculated using GPS-based odometer readings or by inferring distance from scan locations and map data; GPS integration offers 95–98% accuracy, while scan-based estimation provides 95–98% accuracy, depending on data frequency and quality, ensuring reliable tracking of tyre usage across different vehicles and operating conditions. Running cost per km/mile is calculated using parameters like tyre purchase price, expected lifespan, maintenance costs, fuel efficiency impact, and retread/disposal costs. These values are entered manually or auto-fetched from GPS/telematics and service logs. The system updates them through maintenance records and usage data for accurate cost tracking.

The system can project future running costs using historical tyre data, usage patterns, maintenance records, and predicted mileage. It uses trend analysis and predictive techniques to estimate future expenses, helping in budgeting and lifecycle planning. Maintenance records are entered either manually via the system's GUI or automatically through integration with third-party maintenance systems using APIs. Real-time latitude/longitude, speed, heading, and altitude are integrated for accurate tracking and analysis. GPS data is typically updated every 5 to 30 seconds, depending on system settings. This data is synchronized with tyre tracking using a common timestamp and vehicle ID, ensuring accurate correlation between vehicle movement and tyre usage. The system supports both options: it can integrate with existing vehicle GPS units or telematics systems via APIs, or use a dedicated GPS module if needed, based on deployment requirements.

The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

Benefits, other advantages, and solutions to problems have been described above about specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims. , Claims:1. A smart vehicle tracking system, comprising:
a plurality of tyres, each tyre comprising a unique, non-removable, and tamper-proof Radio-Frequency Identification (RFID) tag embedded therein, said RFID tag configured to store a unique serial number associated with the respective tyre;
a registration module configured to receive said unique serial number from each of said plurality of RFID tags and associate each received unique serial number with a specific vehicle registration number in a data storage system;
a plurality of RFID scanners located at a plurality of scanning locations, each RFID scanner configured to read said unique serial number from said RFID tags embedded in tyres of a vehicle passing within a reading range of the RFID scanner;
a processing module communicatively coupled to the plurality of RFID scanners and the data storage system, said processing module configured to receive read data from said plurality of RFID scanners and compare the unique serial number read from the RFID tag of a tyre with the unique serial number associated with the vehicle registration number of the vehicle carrying said tyre, as stored in the data storage system thereby determine a match or a mismatch between the read unique serial number and the associated unique serial number; and
an alert module communicatively coupled to the processing module, said alert module configured to generate an alert when a mismatch is detected between the read unique serial number and the associated unique serial number, or when suspicious movement history of a tyre is detected thereby transmit said alert to a designated recipient;
wherein the suspicious movement history of a tyre is detected based on at least one criterion selected from the tyre appearing on multiple different vehicles within a short period; the tyre traveling an abnormally high distance without recorded maintenance; or the tyre being registered in one geographical region and subsequently scanned in a distant, unrelated geographical region;
wherein the criteria for detecting suspicious movement are configured and updated from historical data to identify complex or hidden patterns, wherein the machine learning model is retrained regularly with new data to adapt to evolving patterns of suspicious activity.

2. The system as claimed in claim 1, wherein said RFID tag is a passive RFID tag, wherein said RFID tag is an active RFID tag, wherein said RFID tag is embedded within a trye of said vehicle upon sticking on an inner surface, an outer surface, and by embedding within a rubber layer between said tyre, wherein each RFID scanner is configured to mitigate interference from other radio frequency sources or metal objects in the scanning environment by employing special RF filters and anti-collision techniques, wherein the anti-collision techniques are configured to detect and filter out disturbances caused by signals from other devices or reflections from nearby metal objects, wherein each RFID scanner is further configured to identify only the correct and nearest RFID tag to minimize incorrect readings.

3. The system as claimed in claim 1, further comprising a historical tracking module configured to store and retrieve historical data associated with each tyre, said historical data including at least one of: distance traveled, dates of scans, locations of scans, or mileage, wherein the historical data for each tyre further includes: precise GPS coordinates at each scan, duration of stop at a location, average speed between scans, alert logs associated with the tyre, and information about the user or device that performed the scan, wherein the historical tracking module is configured to consolidate data from various scanning locations by:
collecting data in real-time or at scheduled intervals;
transmitting the collected data to a central database;
tagging each scan with a unique tyre ID, timestamp, and location metadata; and
aggregating the tagged data chronologically to build a comprehensive historical record for each tyre.

4. The system as claimed in claim 1, wherein the processing module is configured to compare the read unique serial number with the associated stored unique serial number using an exact matching technique, ensuring a one-to-one string match for validation, wherein the processing module is configured to perform a single comparison, selected from reading, matching, and response, in under 300 milliseconds, wherein the processing module is configured to handle a high volume of concurrent vehicle scans by employing parallel processing, load balancing, and message queues, wherein the message queues utilize a Kafka-based system for efficient message handling, wherein the processing module further utilizes cloud auto-scaling and edge computing to optimize performance during peak loads, wherein the processing module is configured to retrieve the associated unique serial number from the data storage system using a unique identifier selected from the RFID tag ID, vehicle number, or chassis number.

5. The system as claimed in claim 1, wherein the processing module is further configured to authenticate each tyre’s RFID tag during a scanning event by executing a multi-phase handshake procedure, the multi-phase handshake procedure comprising:
(a) generating, by the processing module, a random nonce value upon receiving an initial tag read request from an RFID scanner;
(b) transmitting said nonce value to the corresponding RFID tag via the scanner, wherein the RFID tag is pre-configured with a secret key stored within a secure memory section inaccessible from external interfaces;
(c) receiving, by the processing module, a response comprising the nonce value encrypted using said secret key, wherein the processing module validates the response by decrypting it with a corresponding server-side key stored in a hardware security module;
(d) marking the RFID tag as verified only when the decrypted response matches the originally transmitted nonce, and rejecting the tag otherwise; and
(e) recording the result of each handshake in a secure audit trail indexed to the unique serial number of the tyre.
6. The system as claimed in claim 5, wherein the secure audit trail is maintained in the data storage system by implementing a chained-hash structure, the chained-hash structure configured to:
(a) generate a cryptographic hash for each new authentication event by combining the current authentication record with the hash of the immediately preceding record;
(b) prevent undetected alteration of historical authentication data by invalidating any subsequent hash in the chain if a prior entry is modified; and
(c) enable the processing module to perform rapid verification of data integrity by recalculating and comparing hash sequences during each tyre scan.
7. The system as claimed in claim 1, wherein each RFID scanner further incorporates a phased-array antenna controlled by a digital signal processor (DSP), and wherein the DSP is configured to:
(a) estimate the direction of arrival of each backscattered RFID signal using phase difference measurements across the antenna elements;
(b) electronically steer the antenna beam toward the detected direction while suppressing side lobes using adaptive beamforming;
(c) re-validate the read signal by correlating it with previously known positional data of the vehicle's tyres from the historical tracking module; and
(d) discard any signal whose angle-of-arrival deviates beyond a predetermined positional tolerance, thereby reducing erroneous tag captures.

8. The system as claimed in claim 1, wherein the historical tracking module is configured to resolve discrepancies between multiple independent data sources by implementing a temporal-spatial reconciliation comprising:
(a) aligning each RFID scan record with a nearest-in-time GPS position fix from the vehicle’s telematics unit within a ±5 second window;
(b) calculating a route consistency score by comparing the inferred path from RFID scan locations with the actual GPS trajectory;
(c) assigning a weighted anomaly score to the tyre when the route consistency score falls below a threshold, said score increasing proportionally with the magnitude and frequency of deviations; and
(d) transmitting said anomaly score to the machine learning model for iterative refinement of detection thresholds specific to individual tyres and vehicle classes.
9. The system as claimed in claim 1, wherein the processing module dynamically reconfigures decision parameters in response to newly identified anomalies by:
(a) incorporating each transmitted anomaly score as a labeled data point into a continuously updated training dataset;
(b) performing incremental parameter updates without requiring full retraining of the model by applying online learning techniques;
(c) recalibrating feature importance weights in real-time based on observed correlations between specific anomaly types and confirmed instances of tyre misuse; and
(d) synchronizing updated model parameters across all processing modules in geographically distributed data centers using a consensus-based parameter server to ensure uniformity of detection capabilities.
10. A method for smart vehicle tracking and tyre monitoring, comprising:
embedding a unique, non-removable, and tamper-proof Radio-Frequency Identification (RFID) tag within each of a plurality of tyres, said RFID tag storing a unique serial number associated with the respective tyre;
registering each unique serial number of said RFID tags by associating it with a specific vehicle registration number in a data storage system;
scanning, by a plurality of RFID scanners, said RFID tags embedded in tyres of a vehicle passing within a reading range of the RFID scanners to obtain read unique serial numbers, wherein scanning is performed at least one of vehicle depots, toll booths, parking lots, or garages;
comparing, by a processing module, the read unique serial number from an RFID tag of a tyre with the unique serial number associated with the vehicle registration number of the vehicle carrying said tyre, as stored in the data storage system upon utilizing a graphical user interface installed on a user computing device to input and store the associations;
determining, by the processing module, a match or a mismatch between the read unique serial number and the associated unique serial number;
generating an alert when a mismatch is detected between the read unique serial number and the associated unique serial number, or when suspicious movement history of a tyre is detected, and transmitting said alert to a designated recipient;
storing historical data associated with each tyre, said historical data including at least one of distance traveled, dates of scans, locations of scans, or mileage;
calculating tyre mileage and running cost per kilometer or mile based on the stored historical data; and
integrating live vehicle movement data from a Global Positioning System (GPS) with the tyre tracking data and maintaining maintenance logs for each tyre based on scanned data and user input.