DESC:METHOD AND SYSTEM FOR DETERMINING DRIVING PATTERN

CROSS REFERENCE TO RELATED APPLICATIONS
The present application claims priority from Indian Provisional Patent Application No. 202421076055 filed on 08/10/2024, the entirety of which is incorporated herein by a reference.
TECHNICAL FIELD
Generally, the present disclosure relates to driving analytics. Particularly, the present disclosure relates to a system and method of determining the driving pattern of a driver.
BACKGROUND
An electric vehicle operates through propulsion based on stored electrical energy supplied by a rechargeable battery pack. The propulsion system relies on electric motors that generate torque under the control of electronic power modules. Driving characteristics of the electric vehicle are influenced by driver inputs such as, but not limited to, throttle demand, brake force application, and steering angle, along with environmental and road surface conditions. Therefore, accurate determination of driving patterns becomes essential for analyzing driver behavior, enhancing safety features, and optimizing vehicle performance parameters.
Existing technologies include arrangements such as accelerometer-based driver behavior monitoring platforms that utilize vibration signals and motion patterns to classify road surface irregularities. Such platforms extract frequency domain features from accelerometer data to differentiate between smooth asphalt, uneven concrete, or pothole-affected roads. The same systems derive driver aggressiveness scores by correlating acceleration magnitude, braking intensity, and steering variations with the identified road surfaces. A fixed-weight scoring algorithm assigns predetermined values to each operational parameter, and the combined weighted sum is used to generate a driver aggressiveness score. Although such methods provide a structured approach to classify road surfaces and quantify driving aggressiveness, the reliance on static weighting reduces responsiveness to evolving driver behavior and dynamic road conditions.
However, there are certain problems associated with the existing or above-mentioned mechanism for determining the driving pattern of a driver of a vehicle. The existing technologies face multiple limitations, including insufficient integration of diverse sensor data, a lack of adaptive weighting mechanisms, and limited capability to distinguish between aggressive manoeuvres and necessary responses to poor road conditions. Specifically, the static scoring approaches in conventional models reduce accuracy by treating all operational parameters with fixed importance, irrespective of temporal variations or contextual changes in road surfaces. In the accelerometer-based driver behavior monitoring platforms, the reliance on frequency-domain vibration features and fixed-weight scoring constrains accuracy by failing to differentiate sustained driver aggressiveness from temporary adjustments due to rough terrain. Such limitations result in misclassification of normal defensive driving actions as aggressive, leading to unreliable driver assessment and reduced effectiveness in applications such as safety monitoring, telematics, and performance optimization.
Therefore, there exists a need for a secure, interoperable, and automated alternative for determining the driving pattern of a driver of a vehicle.
SUMMARY
An object of the present disclosure is to provide a system for determining a driving pattern of a driver of a vehicle.
Another object of the present disclosure is to provide a method for determining a driving pattern of a driver of a vehicle.
Yet another object of the present disclosure is to provide a context-sensitive aggressiveness score by integrating operational parameters with road surface classifications from the system and method.
In accordance with a first aspect of the present disclosure, there is provided a system for determining a driving pattern of a driver of a vehicle, the system comprising:
- at least one sensor module configured to sense at least one operational parameter of the vehicle;
- at least one road classifier module communicably coupled to the at least one sensor module and configured to classify road surface characteristics based on the sensed data; and
- a behavior analysis module communicably coupled to the sensor module and the road classifier module,
wherein, the behavior analysis module is configured to generate a driver aggressiveness score by correlating the sensed data received from the sensor module with the road classifications received from the road classifier module via a dynamic weighting algorithm.
The system for determining a driving pattern of a driver of a vehicle, as described in the present disclosure, is advantageous in terms of producing a context-sensitive aggressiveness score by integrating operational parameters with road surface classifications, ensuring accurate driver behavior assessment. Further, the system uses an adaptive statistical technique that provides dynamic weighting of sensor data, resulting in a more reliable evaluation under varying conditions. Furthermore, the system uses temporal weighting to enhance long-term accuracy by capturing repetitive aggressive maneuvers across multiple driving intervals. Moreover, the system architecture enables seamless deployment in connected vehicles and supports integration with telematics and fleet management platforms. Additionally, the enhanced precision in driver profiling supports safety optimization, insurance risk evaluation, and predictive maintenance strategies.
In accordance with another aspect of the present disclosure, there is provided a method for determining a driving pattern of a driver of a vehicle, the method comprising:
- sensing at least one operational parameter of the vehicle, via at least one sensor module;
- classifying road surface characteristics by extracting at least one frequency-based signal feature, via a road classifier module;
- employing an adaptive statistical technique to assign variable position to each operational parameter and road classification, via a behavior analysis module;
- integrating the adaptive statistical technique and temporal weighting into a dynamic weighting algorithm, via the behavior analysis module; and
- generating a driver aggressiveness score by correlating the sensed data received from the sensor module with the road classifications using the dynamic weighting algorithm, via the behavior analysis module.
Additional aspects, advantages, features, and objects of the present disclosure would be made apparent from the drawings and the detailed description of the illustrative embodiments constructed in conjunction with the appended claims that follow.
It will be appreciated that features of the present disclosure are susceptible to being combined in various combinations without departing from the scope of the present disclosure as defined by the appended claims.
BRIEF DESCRIPTION OF DRAWINGS
The summary above, as well as the following detailed description of illustrative embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the present disclosure, exemplary constructions of the disclosure are shown in the drawings. However, the present disclosure is not limited to specific methods and instrumentalities disclosed herein. Moreover, those in the art will understand that the drawings are not to scale. Wherever possible, like elements have been indicated by identical numbers.
Embodiments of the present disclosure will now be described, by way of example only, with reference to the following diagrams wherein:
Figure 1 illustrates a block diagram of a system for determining a driving pattern of a driver of a vehicle, in accordance with an embodiment of the present disclosure.
Figure 2 illustrates a flow chart of a method for determining a driving pattern of a driver of a vehicle, in accordance with another embodiment of the present disclosure.
In the accompanying drawings, an underlined number is employed to represent an item over which the underlined number is positioned or an item to which the underlined number is adjacent. A non-underlined number relates to an item identified by a line linking the non-underlined number to the item. When a number is non-underlined and accompanied by an associated arrow, the non-underlined number is used to identify a general item at which the arrow is pointing.
DETAILED DESCRIPTION
The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practicing the present disclosure are also possible.
As used herein, the term “driving pattern” refers to a structured sequence of driver actions reflected through measurable operational parameters of a vehicle and correlated environmental influences. Specifically, the driving pattern represents the combined interaction of acceleration input, braking response, steering activity, torque demand, throttle variation, and vehicle speed fluctuations, integrated with classified road surface characteristics such as, but not limited to, smooth asphalt, rough terrain, or uneven gravel. Further, the driving pattern is derived by employing sensor data acquisition, road surface classification through frequency-based signal feature extraction, and behavior analysis using an adaptive statistical technique that applies a temporal weighting across varying conditions. Furthermore, the types of driving pattern include, but are not limited to, a conservative driving pattern characterized by smooth acceleration, controlled braking, and minimal steering deviation; moderate driving pattern characterized by balanced acceleration and deceleration with limited aggressive maneuvers; and aggressive driving pattern characterized by abrupt throttle inputs, heavy braking, rapid torque demand variations, and excessive steering corrections, often intensified on uneven or rough road classifications. Moreover, the determination of the driving pattern through correlation of the sensor data and the road classifications enables precise generation of a driver aggressiveness score, forming the basis of an advanced driving behavior analytics.
As used herein, the terms “vehicle”, “EV”, and “electric vehicle” are used interchangeably and refer to a mechanized transport unit designed for movement on land, powered by an energy source, and controlled through defined operational parameters. Specifically, the vehicle represents a structured assembly comprising, but not limited to, propulsion systems, steering mechanisms, braking systems, suspension components, and electronic control modules, operating together to achieve controlled mobility under varying road surface classifications. Further, the vehicle functions as the platform for the sensor modules that capture real-time data, such as, but not limited to, throttle position, brake application, steering angle, torque demand, and vibration, thereby enabling accurate determination of the driving pattern through correlation with the road classifier outputs and the behavior analysis. Furthermore, the types of vehicles include, but are not limited to, internal combustion engine vehicles that rely on fuel-powered propulsion, hybrid electric vehicles that combine fuel engines with battery-driven motors, and fully electric vehicles that depend exclusively on high-capacity rechargeable battery packs, each generating distinct sensor profiles during operation. Moreover, the integration of the vehicle data with adaptive statistical techniques and dynamic weighting algorithms allows precise modulation of the driver aggressiveness score, establishing a reliable framework for driving behavior assessment across the diverse vehicle categories.
As used herein, the terms “sensor module” and “sensor” are used interchangeably and refer to an integrated unit designed to capture measurable physical or mechanical parameters of a vehicle and convert the parameters into analyzable electronic signals. Specifically, the sensor module represents an assembly of one or more sensors configured to monitor the vehicle operational parameters such as, but not limited to the acceleration, braking force, throttle displacement, steering angle variation, torque demand fluctuation, velocity profile, and vibration intensity, with the sensed data transmitted to the road classifier module and the behavior analysis module for further processing. Further, the sensor module ensures synchronous acquisition of data streams that form the foundation for road surface classification and dynamic weighting in aggressiveness score generation. Furthermore, the types of sensor module include, but are not limited to, inertial measurement unit sensor modules that provide orientation and motion tracking, throttle position sensor modules that quantify acceleration intent, brake application sensor modules that measure braking force, torque demand sensor modules that evaluate propulsion requirements, steering angle sensor modules that monitor directional control, vehicle speed sensor modules that track velocity changes, and vibration sensor modules that capture road-induced oscillations. Moreover, the sensor module thereby establishes a precise and continuous interface between vehicle dynamics and the analytical framework of the driving pattern determination system.
As used herein, the term “operational parameter” refers to a measurable characteristic of the vehicle that defines driver input, vehicular response, or environmental influence during movement. Specifically, the operational parameter represents a quantifiable value derived from sensors integrated into the vehicle, describing aspects such as, but not limited to, throttle displacement, braking force application, steering angle adjustment, torque demand variation, velocity change, and vibration magnitude. Further, the operational parameter forms the primary dataset that is synchronized with classified road surface characteristics to generate a driver aggressiveness score through the dynamic weighting algorithm in the behavior analysis module. Furthermore, the types of operational parameters include, but is not limited to, kinematic parameters such as, but not limited to, speed, acceleration, and angular rotation; control parameters such as, but not limited to, throttle position, brake pressure, and steering angle; and dynamic response parameters such as, but not limited to, torque demand and vibration intensity. Moreover, the operational parameter functions as a critical input that enables adaptive statistical modeling and temporal weighting, establishing an accurate representation of driving behavior within the analytical framework of the invention.
As used herein, the term “road classifier module” refers to a computational unit designed to evaluate and categorize surface conditions encountered by the vehicle using the processed sensor data. Specifically, the road classifier module represents an electronic subsystem communicably coupled to the sensor module, configured to extract the frequency-based signal features from the motion and vibration data, and to classify the surface characteristics of roads, such as, but not limited to, smooth asphalt, gravel, cobblestone, or uneven terrain. Further, the road classifier module provides contextual input that directly influences the behavior analysis module, enabling correlation of the operational parameters with real-world driving environments for precise aggressiveness score generation. Furthermore, the types of road classifier modules include, but are not limited to, frequency-domain classifier modules that analyze vibration patterns to identify surface roughness, time-domain classifier modules that assess signal amplitude variations for detecting abrupt road transitions, and hybrid classifier modules that integrate statistical and spectral features to deliver multi-dimensional surface characterization. Moreover, the road classifier module thereby ensures that driving pattern determination is not limited to vehicle input data but is enriched with environmental surface information, resulting in accurate and context-sensitive driver behavior analysis.
As used herein, the term “road surface characteristics” refers to the measurable physical attributes of a roadway that influence the vehicle dynamics, driver control, and sensor responses during operation. Specifically, the road surface characteristics represent the structural and textural properties of the driving surface that generate the distinctive vibration signatures and motion responses detectable through the frequency-based signal features extracted from the sensor data. Further, the road surface characteristics are classified by the road classifier module to provide contextual information that directly impacts the correlation of the operational parameters with the driving behavior, enabling precise modulation of the driver aggressiveness score. Furthermore, the types of road surface characteristics include, but are not limited to, smooth asphalt surfaces that yield low-frequency, low-amplitude vibration patterns; rough gravel surfaces that exhibit high-frequency, irregular vibration profiles; cobblestone surfaces that produce periodic oscillatory responses; and uneven terrain surfaces that generate variable vibration intensities with inconsistent spectral distribution. Moreover, the road surface characteristics serve as essential environmental inputs that, when integrated with the operational parameters, enable the behavior analysis module to distinguish between aggressive maneuvers driven by driver intent and those influenced by external surface conditions.
As used herein, the term “behavior analysis module” refers to a computational framework designed to interpret driver actions by processing operational parameters in correlation with the road surface classifications. Specifically, the behavior analysis module represents an adaptive analytical unit communicably linked to the sensor module and the road classifier module, configured to employ statistical modeling, temporal weighting, and dynamic algorithms to generate a quantified driver aggressiveness score. Further, the behavior analysis module integrates variable positioning of each operational parameter with the frequency-based surface classifications, ensuring that the scoring reflects both driver inputs and environmental influences in real time. Furthermore, the types of behavior analysis modules include, but are not limited to, rule-based modules that apply predefined thresholds for classifying driver actions, statistical modules that utilize probabilistic and regression-based modeling for dynamic correlation, and machine learning modules that continuously adapt weighting and feature relevance through iterative learning from sensor and road data. Moreover, the behavior analysis module functions as the central intelligence layer of the system, enabling precise determination of the driving pattern by dynamically balancing driver-induced variations with the surface-induced responses.
As used herein, the term “driver aggressiveness score” refers to a quantified metric that evaluates the intensity and style of the driver’s behavior during the vehicle operation. Specifically, the driver aggressiveness score refers to a numerical or categorical value generated by the behavior analysis module through correlation of the operational parameters, such as, but not limited to, throttle input, braking force, steering angle, torque demand, and vehicle speed, with the classified road surface characteristics obtained from the road classifier module. Further, the driver aggressiveness score is computed using the dynamic weighting algorithm that integrates the adaptive statistical techniques and the temporal weighting, ensuring that each operational parameter and road condition contributes proportionally to the final assessment. Furthermore, the types of driver aggressiveness score include, but are not limited to, low aggressiveness score associated with smooth acceleration, minimal braking, and stable steering control; moderate aggressiveness score associated with balanced throttle inputs, occasional abrupt braking, and moderate steering corrections; and high aggressiveness score associated with frequent rapid acceleration, heavy braking, sharp steering deviations, and amplified response on rough or uneven road surfaces. Moreover, the driver aggressiveness score functions as a definitive outcome of the system, enabling objective evaluation of driving patterns with high accuracy and contextual relevance.
As used herein, the term “dynamic weighting algorithm” refers to an adaptive computational method that assigns variable significance to multiple input parameters during analytical processing. Specifically, the dynamic weighting algorithm represents a data-driven approach employed by the behavior analysis module to correlate operational parameters such as, but not limited to, throttle position, braking intensity, steering angle, torque demand, vehicle speed, and vibration with classified road surface characteristics obtained from the road classifier module. Further, the dynamic weighting algorithm integrates the adaptive statistical techniques with temporal weighting, enabling continuous adjustment of parameter relevance based on changing driving conditions and the real-time sensor data. Furthermore, the types of dynamic weighting algorithms include, but are not limited to, statistical weighting algorithms that rely on probability distributions and regression models to allocate parameter influence, temporal weighting algorithms that modify weights according to time-varying changes in operational parameters, and hybrid adaptive weighting algorithms that combine statistical inference with iterative learning to optimize driver aggressiveness score generation. Moreover, the dynamic weighting algorithm establishes the computational foundation for precise modulation of driver behavior analysis, ensuring that each operational parameter and road classification contributes accurately to the overall driving pattern determination.
As used herein, the term “inertial measurement sensor” refers to a motion detection unit designed to quantify the orientation, acceleration, and angular velocity of the vehicle in real time. Specifically, the inertial measurement sensor represents an electromechanical sensing device that integrates accelerometers, gyroscopes, and magnetometers to capture multi-axis motion data, enabling accurate detection of linear acceleration, rotational dynamics, and positional shifts during vehicle operation. Further, the inertial measurement sensor forms a critical component of the sensor module, supplying high-resolution data that contributes to the classification of the road surface characteristics and the modulation of the driver aggressiveness score through the behavior analysis module. Furthermore, the types of inertial measurement sensors include, but are not limited to, accelerometer-based sensors that detect linear displacement and vibration intensity, gyroscope-based sensors that measure angular rotation and steering dynamics, and combined multi-sensor units that integrate accelerometers, gyroscopes, and magnetometers for complete six-degree-of-freedom motion tracking. Moreover, the inertial measurement sensor provides foundational data for both the road classifier and the behavior analysis modules, enabling precise recognition of driving patterns across the varied surface conditions.
As used herein, the term “throttle position sensor” refers to an electronic sensing device designed to measure the angular displacement of a throttle valve and translate the displacement into an electrical signal corresponding to the driver acceleration input. Specifically, the throttle position sensor represents a precision sensor integrated into the throttle body of the vehicle, configured to monitor the degree of the throttle plate opening and provide real-time data to the control systems for fuel injection, torque demand estimation, and acceleration profiling. Further, the throttle position sensor functions as part of the sensor module, supplying operational parameter data that directly reflects driver intent and contributes to the behavior analysis module for the accurate generation of the driver aggressiveness score. Furthermore, the types of throttle position sensors include, but are not limited to, potentiometric sensors that utilize resistive tracks to convert throttle angle into voltage variation, non-contact Hall effect sensors that rely on magnetic field displacement for signal generation, and inductive throttle position sensors that employ coil-based electromagnetic measurement for enhanced durability and precision. Moreover, the throttle position sensor provides critical input for correlating the driver acceleration behavior with classified road surface characteristics, enabling dynamic weighting within the aggressiveness scoring framework.
As used herein, the term “brake application sensor” refers to a sensing device designed to monitor braking activity by measuring the force, pressure, or displacement applied within the vehicle braking system. Specifically, the brake application sensor represents an electromechanical or electronic unit integrated into the brake pedal assembly or the hydraulic circuit, configured to generate real-time signals corresponding to the brake pedal actuation, hydraulic line pressure, or mechanical displacement. Further, the brake application sensor operates as part of the sensor module, delivering critical operational parameter data that reflects driver deceleration behavior, enabling the behavior analysis module to correlate the braking intensity with the classified road surface characteristics for precise aggressiveness score generation. Furthermore, the types of brake application sensors include, but are not limited to, pressure-based sensors that quantify hydraulic line pressure during braking, displacement-based sensors that detect pedal movement or stroke length, and force-based sensors that measure applied braking force directly through strain or load sensing elements. Moreover, the brake application sensor forms a fundamental input source for adaptive statistical modeling and temporal weighting, ensuring accurate identification of driving patterns within the analytical framework of the invention.
As used herein, the term “torque demand sensor” refers to a sensing unit designed to quantify the requested torque output from the vehicle propulsion system based on the driver input and load conditions. Specifically, the torque demand sensor represents the electronic measurement device that captures signals related to accelerator pedal displacement, engine control commands, or motor control inputs, translating the aforementioned signals into torque demand values that define propulsion requirements during vehicle operation. Further, the torque demand sensor functions as part of the sensor module, supplying essential operational parameter data that directly reflects propulsion intent and enabling the behavior analysis module to correlate torque fluctuations with the classified road surface characteristics for the accurate driver aggressiveness score generation. Furthermore, the types of torque demand sensors include, but are not limited to, pedal position-based sensors that calculate torque demand from accelerator displacement, current-based sensors that monitor electric motor input current to estimate torque requirements, and strain-based sensors that directly measure torque transmission through mechanical deformation of shafts or couplings. Moreover, the torque demand sensor establishes a critical feedback mechanism for the dynamic weighting, ensuring that the propulsion demand is accurately represented in the driving pattern analysis.
As used herein, the term “steering angle sensor” refers to a precision sensing device designed to measure the rotational position of the vehicle’s steering wheel and convert the angular displacement into an electronic signal for analysis. Specifically, the steering angle sensor represents an electromechanical or electronic transducer integrated within the steering column, configured to capture both the magnitude and direction of steering wheel rotation, as well as rotational velocity, enabling real-time monitoring of the driver's steering behavior and the vehicle's directional control. Further, the steering angle sensor operates as part of the sensor module, providing operational parameter data that reflects lane-keeping performance, cornering aggressiveness, and corrective maneuvers, which are further correlated with the road surface classifications by the behavior analysis module for the generation of the driver aggressiveness score. Furthermore, the types of steering angle sensors include, but are not limited to, potentiometric sensors that rely on variable resistance to measure angular position, optical sensors that use light interruption or reflection patterns to detect steering displacement, and magnetic Hall effect sensors that employ magnetic field variation to generate accurate angular position data with high durability. Moreover, the steering angle sensor functions as a vital input for adaptive statistical modeling and dynamic weighting, ensuring precise recognition of driving patterns across diverse surface conditions.
As used herein, the term “vehicle speed sensor” refers to an electronic sensing unit designed to measure the rotational speed of the vehicle’s wheels or transmission shaft and convert the measured data into a signal representing vehicle velocity. Specifically, the vehicle speed sensor refers to a transducer integrated within the drivetrain or the wheel hub assembly, configured to detect rotational frequency using the magnetic, optical, or inductive principles and generate real-time data for the vehicle control systems and analytical modules. Further, the vehicle speed sensor functions as a component of the sensor module, delivering operational parameter data that reflects longitudinal motion of the vehicle, which is further correlated with the classified road surface characteristics by the behavior analysis module for the accurate driver aggressiveness score generation. Furthermore, the types of vehicle speed sensors include, but are not limited to, variable reluctance sensors that detect changes in magnetic flux caused by gear tooth rotation, Hall effect sensors that measure wheel or shaft rotation using the magnetic field variations, and optical sensors that employ light interruption or reflection patterns to quantify rotational speed with high resolution. Moreover, the vehicle speed sensor establishes a critical measurement foundation for adaptive statistical modeling and dynamic weighting, ensuring reliable determination of driving patterns in real-time analysis.
As used herein, the term “vibration sensor” refers to a sensing element designed to detect oscillatory motion or mechanical disturbances experienced by a vehicle during operation. Specifically, the vibration sensor represents an electromechanical or piezoelectric device integrated into the sensor module, configured to capture amplitude, frequency, and phase characteristics of vibrations induced by the road surface irregularities, vehicle dynamics, or driver inputs, and convert the above-mentioned parameters into electrical signals suitable for analytical processing. Further, the vibration sensor provides critical data for the road classifier module, enabling the extraction of the frequency-based signal features that define the road surface characteristics and allowing the behavior analysis module to correlate the vibration intensity with the operational parameters for the precise driver aggressiveness score generation. Furthermore, the types of vibration sensors include, but are not limited to, piezoelectric sensors that utilize the crystalline deformation to generate a charge proportional to a vibration amplitude, capacitive sensors that measure variations in capacitance caused by oscillatory displacement, and microelectromechanical system (MEMS) sensors that integrate miniature mechanical structures and electronic circuits for high-sensitivity multi-axis vibration detection. Moreover, the vibration sensor establishes a direct link between the environmental surface conditions and the vehicle response, ensuring accurate contextual analysis within the dynamic weighting framework.
As used herein, the term “frequency-based signal feature” refers to represents the measurable attribute of the signal derived through spectral analysis that characterizes the distribution of energy or power across frequency components. Specifically, the frequency-based signal feature represents the computationally extracted parameter obtained by transforming time-domain vibration or motion signals into the frequency domain using analytical techniques such as, but not limited to, a Fourier transform or wavelet decomposition, enabling identification of patterns linked to road surface characteristics and vehicle responses. Further, the frequency-based signal feature serves as the primary input for the road classifier module, providing discriminative information that allows differentiation between smooth surfaces, rough terrains, and irregular patterns, which are further correlated with operational parameters by the behavior analysis module to generate the accurate driver aggressiveness scores. Furthermore, the types of frequency-based signal features include, but are not limited to, spectral centroid features that describe the weighted mean frequency of a signal, spectral bandwidth features that represent the spread of frequencies around the centroid, and peak frequency features that capture the dominant vibration frequency associated with specific surface conditions. Moreover, the frequency-based signal feature forms a critical analytical element that bridges the raw sensor data with the contextual road classification, ensuring precise integration of environmental influence into driving pattern analysis.
As used herein, the term “synchronous data exchange” refers to a communication process in which multiple system components transmit and receive information in a coordinated and time-aligned manner. Specifically, the synchronous data exchange represents a structured data transfer mechanism that ensures uniform sampling, consistent timestamps, and synchronized processing across modules such as, but not limited to, the sensor module, the road classifier module, and the behavior analysis module, enabling real-time correlation of operational parameters with the road surface classifications. Further, the synchronous data exchange is established through the network interface that maintains precise alignment of input streams, preventing latency-induced errors and ensuring accurate execution of the dynamic weighting algorithm for driver aggressiveness score generation. Furthermore, the types of synchronous data exchange include, but are not limited to, time-triggered exchange that operates on predefined clock cycles, event-triggered exchange that synchronizes data packets based on the specific sensor events, and hybrid synchronous exchange that integrates periodic timing with event-driven alignment to optimize bandwidth and responsiveness. Moreover, the synchronous data exchange provides the foundation for seamless integration of the sensor data and analytical processing, ensuring reliability and consistency in driving pattern determination.
As used herein, the term “network interface” refers to a hardware or software communication layer that enables structured data exchange between the interconnected modules. Specifically, the network interface represents an integrated communication framework that establishes connectivity between the sensor module, the road classifier module, and the behavior analysis module, ensuring synchronized transmission of the operational parameters, the road surface classifications, and the computed outputs required for the driving pattern determination. Further, the network interface supports synchronous data exchange by maintaining timing accuracy, data integrity, and minimal latency, thereby allowing precise execution of the dynamic weighting algorithm for the driver aggressiveness score generation. Furthermore, the types of network interfaces include, but are not limited to, wired interfaces such as, but not limited to, Controller Area Network (CAN) and Ethernet that provide high-reliability data transfer, wireless interfaces such as, but not limited to, Wi-Fi and Bluetooth that enable flexible short-range connectivity, and advanced vehicular interfaces such as, but not limited to, FlexRay and Automotive Ethernet that support high-speed, fault-tolerant, and real-time communication. Moreover, the network interface forms the backbone of modular integration, ensuring seamless interoperability and reliable coordination of analytical processes.
As used herein, the term “adaptive statistical technique” refers to a computational approach that dynamically modifies statistical parameters to reflect variations in the incoming data streams. Specifically, the adaptive statistical technique refers to a data-driven method employed by the behavior analysis module to assign variable positions to the operational parameters and the road classifications, adjusting the statistical weighting in real time according to the evolving vehicle dynamics and surface conditions. Further, the adaptive statistical technique ensures that the driver aggressiveness score generation remains contextually accurate by continuously recalibrating the influence of throttle position, braking force, steering angle, torque demand, speed, and vibration data against the classified road surface characteristics. Furthermore, the types of adaptive statistical techniques include, but are not limited to, regression-based adaptive modeling that modifies coefficient values as new data arrives, probabilistic adaptive modeling that updates likelihood estimations to reflect current conditions, and machine learning–oriented adaptive modeling that utilizes iterative optimization to refine parameter relevance over time. Moreover, the adaptive statistical technique provides the analytical flexibility required for precise modulation of the dynamic weighting algorithm, ensuring robust and real-time driving pattern analysis across diverse operational scenarios.
As used herein, the term “temporal weighting” refers to a computational process that assigns variable significance to data inputs based on their position within a time sequence. Specifically, the temporal weighting represents an analytical method applied by the behavior analysis module to adjust the influence of the operational parameters and the road classifications according to the temporal changes, ensuring that recent data holds greater relevance in the modulation of the driver aggressiveness score compared to the older data. Further, the temporal weighting enables continuous refinement of the dynamic weighting algorithm by aligning the aggressiveness assessment with evolving driving conditions and the sensor variations across time. Furthermore, the types of temporal weighting include, but are not limited to, exponential weighting that applies a decaying factor to the older data samples, sliding window weighting that limits computation to a defined temporal interval, and adaptive temporal weighting that dynamically alters the influence of the past and present data based on the variability of sensor inputs. Moreover, the temporal weighting establishes a time-sensitive analytical structure that ensures accuracy, responsiveness, and contextual alignment in driving pattern determination.
In accordance with a first aspect of the present disclosure, there is provided a system for determining a driving pattern of a driver of a vehicle, the system comprising:
- at least one sensor module configured to sense at least one operational parameter of the vehicle;
- at least one road classifier module communicably coupled to the at least one sensor module and configured to classify road surface characteristics based on the sensed data; and
- a behavior analysis module communicably coupled to the sensor module and the road classifier module,
wherein, the behavior analysis module is configured to generate a driver aggressiveness score by correlating the sensed data received from the sensor module with the road classifications received from the road classifier module via a dynamic weighting algorithm.
Referring to figure 1, in accordance with an embodiment, there is described a system 100 for determining a driving pattern of a driver of a vehicle 102 is described. The system 100 comprises at least one sensor module 104 configured to sense at least one operational parameter of the vehicle 102. Further, the system 100 comprises at least one road classifier module 106 communicably coupled to the at least one sensor module 104 and configured to classify road surface characteristics based on the sensed data. Furthermore, the system 100 comprises a behavior analysis module 108 communicably coupled to the sensor module 104 and the road classifier module 106. Moreover, the behavior analysis module 108 is configured to generate a driver aggressiveness score by correlating the sensed data received from the sensor module 104 with the road classifications received from the road classifier module 106 via a dynamic weighting algorithm.
The system 100 for determining a driving pattern of a driver of a vehicle 102 operates through a structured interaction between the sensor module 104, the road classifier module 106, and the behavior analysis module 108. Specifically, the sensor module 104 senses operational parameters including, but not limited to, throttle position, brake application, torque demand, steering angle, vehicle speed, inertial changes, and vibration levels. Further, the sensed data is transmitted to the road classifier module 106, that performs classification of road surface characteristics by extracting the frequency-based features from motion and vibration signals. Furthermore, the classified road data is transferred to the behavior analysis module 108 along with the sensed operational parameters, creating a synchronized dataset for correlation. Moreover, the behavior analysis module 108 executes the dynamic weighting algorithm that associates each operational parameter with the corresponding road classification to derive the driver aggressiveness score. Additionally, the technique of operation involves sensing vehicle parameters, extracting signal features, and classifying road surfaces in real-time. Subsequently, the behavior analysis module 108 employs statistical mapping to assign weighted importance to each operational parameter in relation to the specific road classifications. Further, the adaptive statistical techniques regulate variable positions, enabling the weighting algorithm to differentiate between identical actions across distinct road surfaces. Furthermore, the temporal weighting embedded within the dynamic weighting algorithm adjusts the influence of sensed parameters over time, ensuring that persistent driving patterns carry greater impact on the aggressiveness score than transient fluctuations. Moreover, the final output is a quantified aggressiveness score that reflects both driver inputs and environmental road conditions. Consequently, precise driver behavior assessment is achieved through integration of the vehicle parameters with the road classification under the dynamic weighting framework. Additionally, the advantages include but are not limited to enhanced accuracy of aggressiveness measurement, improved reliability of behavioral profiling across diverse terrains, reduced misinterpretation of driver intent due to road-contextual analysis, and provision of a stable scoring mechanism resilient to short-term anomalies. Ultimately, the system 100 supports applications in fleet management, telematics, insurance risk assessment, and advanced driver assistance by offering a standardized and scalable framework for the driver behavior evaluation.
In an embodiment, the at least one sensor module 104 comprises one or more sensors selected from the group of sensors comprising inertial measurement unit sensors, throttle position sensors, brake application sensors, torque demand sensors, steering angle sensors, vehicle speed sensors, and vibration sensors. Specifically, each sensor generates raw signals that represent instantaneous operational states of the vehicle 102. Further, the inertial measurement unit sensor captures acceleration and angular velocity data, the throttle position sensor measures degree of throttle input, the brake application sensor registers pressure applied on braking components, the torque demand sensor evaluates load requested from the powertrain, the steering angle sensor provides turning position, the vehicle speed sensor measures velocity, and the vibration sensor records road-induced oscillations. Furthermore, the sensor module 104 integrates the sensed signals into a structured data set that is forwarded to the road classifier module 106 and the behavior analysis module 108 for subsequent processing. Moreover, the process of operation involves continuous acquisition of parameter values from the selected sensors with synchronized time stamping to ensure accurate correlation across modules. Additionally, the raw signals are subjected to preliminary filtering to reduce noise and enhance signal quality before transmission. Subsequently, each parameter holds defined significance in shaping the driver aggressiveness score. Further, the throttle and brake sensors highlight acceleration and deceleration tendencies, the torque demand indicates load response, the steering angle captures sharpness of directional changes, the vehicle speed reflects overall motion control, and the vibration, along with inertial measurement unit data, conveys external influences such as, but not limited to, bumps or irregular road conditions. Furthermore, the processed dataset serves as the input base for road classification and behavioral correlation, forming the backbone of the dynamic weighting algorithm implemented in the behavior analysis module 108. Consequently, accurate detection and representation of driver actions are achieved through specialized sensors capturing multi-dimensional operational parameters. Moreover, the plurality of sensors ensures precise driver aggressiveness evaluation by combining physical control actions with the vehicle dynamics and the environmental feedback. Additionally, the advantages include, but are not limited to, improved resolution of driver profiling, greater sensitivity to subtle variations in control behavior, enhanced robustness of aggressiveness scoring under diverse operating environments, and reduced error margins through the multi-sensor data fusion. Ultimately, the system 100 supports scalable deployment in connected vehicles and autonomous platforms by delivering a reliable, sensor-driven foundation for advanced driver behavior analytics.
In an embodiment, the road classifier module 106 is configured to classify road surface characteristics by extracting at least one frequency-based signal feature from motion and vibration data received from the sensor module 104. Specifically, the motion signals obtained from the inertial measurement unit sensors and the vibration signals captured from the vibration sensors are processed to identify dominant frequency components generated by the road irregularities. Further, the road classifier module 106 applies signal transformation techniques such as, but not limited to, a Fast Fourier Transform or a wavelet-based decomposition to convert time-domain signals into the frequency-domain representations. Furthermore, the extracted features, such as but not limited to amplitude, energy distribution, and peak frequency bands, are analyzed to distinguish between the smooth surfaces, gravel, potholes, and uneven terrains. Moreover, the classification results are transferred to the behavior analysis module 108 along with the synchronized operational parameters for contextual driver behavior assessment. Additionally, the procedure of operation involves systematic data acquisition from the motion and vibration sensors, preprocessing the acquired data through filtering algorithms to remove the extraneous noise, and segmentation of signals into defined analysis windows for the frequency extraction. Further, the feature extraction algorithms calculate specific indicators, including, but not limited to, spectral centroid, frequency variance, and harmonic ratios to quantify surface characteristics. Furthermore, the classification models within the road classifier module 106 map the extracted features to the predefined road categories through statistical clustering or machine learning algorithms. Moreover, each classification output is time-stamped and indexed to align with the operational parameters sensed by the vehicle 102, creating a precise correspondence between the road conditions and the driver actions. Additionally, the classified data enhances the behavior analysis module 108 by supplying the environmental context required for accurate aggressiveness scoring. Consequently, reliable road surface classification that supports contextual interpretation of the driver behavior under varying terrains is achieved. Further, the road classifier module 106 ensures that identical driving actions are interpreted differently based on the road type, thereby enhancing the accuracy of the aggressiveness evaluation. Additionally, the advantages include, but are not limited to, improved robustness of the driver scoring through integration of environmental context, reduction in the false positives for the aggressive behavior detection, enhanced adaptability across the diverse geographical regions, and higher accuracy in fleet management and telematics applications. Ultimately, the system 100 further contributes to safety and risk assessment systems by linking operational parameters with road condition influences through the frequency-based signal analysis.
In an embodiment, the sensor module 104, the road classifier module 106, and the behavior analysis module 108 are configured to synchronize data exchange via a network interface 110. Specifically, the network interface 110 enables structured transmission of the sensed operational parameters, the classified road surface data, and the correlated behavioral outputs with minimal latency. Further, the sensor module 104 streams real-time data from the throttle position sensors, the brake application sensors, the steering angle sensors, the torque demand sensors, the vehicle speed sensors, the inertial measurement unit sensors, and the vibration sensors into the network interface 110. Furthermore, the road classifier module 106 accesses the motion and vibration data over the same interface for the frequency-domain feature extraction and the surface classification. Moreover, the behavior analysis module 108 receives both the operational data and the road classifications via the network interface 110, ensuring synchronized alignment for the correlation within the dynamic weighting algorithm. Additionally, the process of operation involves packetization of the sensor data streams, encoding of the classified road features, and the transmission through the network interface 110 with precise timestamping. Subsequently, the synchronization protocols embedded in the network interface 110 ensure that operational data from the sensor module 104 and the road classifications from the road classifier module 106 remain temporally aligned. Further, the data buffering and the clock synchronization mechanisms compensate for transmission delays, thereby maintaining coherence between the datasets across modules. Furthermore, the behavior analysis module 108 integrates received inputs without desynchronization, allowing the dynamic weighting algorithm to process temporally consistent values. Moreover, the resulting driver aggressiveness score is computed with full preservation of the timing relationship between the driver actions and the road conditions. Consequently, real-time, synchronized, and reliable communication between sensing and analysis components is established, thereby ensuring that the behavioral interpretation is contextually accurate. Additionally, the advantages include, but are not limited to, improved precision of aggressiveness scoring through time-aligned data fusion, enhanced robustness of system 100 performance under high data throughput, reduced error in correlation due to minimized latency, and scalability across distributed vehicular platforms. Ultimately, the system 100 further supports integration into the connected vehicle ecosystems by delivering a network-enabled foundation for continuous behavioral profiling with consistent synchronization of multi-source data streams.
In an embodiment, the behavior analysis module 108 is configured to modulate the driver aggressiveness score based on the received real-time data of each sensed operational parameter and road classification. Specifically, the sensor module 104 delivers instantaneous throttle position, brake application, torque demand, steering angle, vehicle speed, vibration, and inertial data to the behavior analysis module 108. Further, the road classifier module 106 transmits the corresponding road surface classifications derived from the frequency-based feature extraction. Furthermore, the behavior analysis module 108 processes the received inputs and assigns variable significance to each parameter in accordance with the prevailing road conditions, ensuring that the aggressiveness score dynamically adapts to both the driver actions and the environmental influences. Moreover, the process of operation involves continuous sensing and classification, followed by real-time weighting and modulation. Additionally, the operational parameters are normalized and mapped to the defined behavioral indices, whereas the classified road surfaces are incorporated as contextual multipliers. Subsequently, the behavior analysis module 108 integrates the aforementioned inputs into the dynamic weighting algorithm, adjusting the driver aggressiveness score for every instance of new data. For instance, rapid acceleration measured on a smooth surface generates a higher modulation value compared to the same acceleration detected on a rough surface, due to the reduced likelihood of external disturbance. Further, the algorithm thereby maintains consistent scoring across varied terrains by contextualizing every driver action within the corresponding road classification. Consequently, the driver aggressiveness score is produced that reflects both the instantaneous driving behavior and the prevailing road conditions, ensuring precision in the behavioral assessment. Furthermore, the advantages include but are not limited to improved accuracy of the aggressiveness measurement through dynamic modulation, reduction of misclassification by distinguishing the driver intent from the environmental impact, enhanced adaptability across diverse terrains, and provision of stable yet responsive scoring suitable for telematics, fleet monitoring, and insurance analytics. Ultimately, the system 100 further strengthens safety evaluation systems by ensuring that aggressive behavior is assessed within the correct environmental context.
In an embodiment, the behavior analysis module 108 is configured to employ an adaptive statistical technique to assign a variable position to each operational parameter and road classification during the modulation process. Specifically, the sensor module 104 delivers the operational data, including, but not limited to, throttle position, brake application, steering angle, torque demand, vehicle speed, vibration, and inertial values. Simultaneously, the road classifier module 106 provides the road surface classifications derived from the frequency-domain signal features. Further, the behavior analysis module 108 applies the adaptive statistical mapping that dynamically allocates positional weights to the received inputs. Further, the variable positions signify the relative importance of each parameter and classification in shaping the aggressiveness score, ensuring that each contributing factor is weighted according to contextual influence rather than fixed, pre-determined values. Furthermore, the process of operation involves real-time acquisition of the vehicle parameters, preprocessing of data, and extraction of road features, followed by statistical assignment within the behavior analysis module 108. Moreover, the adaptive statistical techniques, such as, but not limited to, the regression-based weighting, probabilistic modeling, or clustering, assign variable positions based on correlation strength, variance, and predictive contribution of each input. For instance, the steering angle data gains a higher positional significance on the winding terrains classified by the road classifier module 104, whereas the throttle and brake application data assume greater weight on smoother road classifications. Additionally, the variable positions are recalibrated continuously, allowing the dynamic weighting algorithm to reflect evolving conditions and maintain contextual accuracy. Subsequently, the modulation process ensures that no parameter dominates across all conditions, maintaining balance across multiple influencing factors. Consequently, the driver aggressiveness score is produced with enhanced precision and contextual fidelity through adaptive positioning of operational parameters and road classifications. Further, the advantages include, but are not limited to, increased robustness of behavioral evaluation by preventing fixed-weight biases, improved adaptability of scoring across diverse driving environments, reduction of error caused by non-contextual parameter dominance, and provision of a dynamic framework that scales efficiently with additional sensors or road features. Furthermore, the system 100 strengthens the accuracy of driver profiling systems deployed in telematics, fleet monitoring, and insurance risk assessment by aligning statistical weighting with real-world driving variability.
In an embodiment, the behavior analysis module 108 is configured to update weighting to the variable positions based on temporal changes in sensor data received from the sensor module 104. Specifically, the sensor module 104 delivers continuous data streams including, but not limited to, the throttle position, the brake application, the torque demand, the steering angle, the vehicle speed, the vibration levels, and the inertial measurements. Further, the behavior analysis module 108 monitors variations in the aforementioned parameters across defined time intervals and recalibrates the weighting applied to each variable position in the dynamic weighting algorithm. Furthermore, the temporal updating process ensures that gradual shifts in driving style, repetitive patterns, or sustained behavioral tendencies exert a proportionate influence on the driver's aggressiveness score. The process of operation involves temporal segmentation of the incoming sensor data into analysis windows, extraction of statistical features such as, but not limited to, mean, variance, and trend gradients, and dynamic adjustment of weighting coefficients assigned to each operational parameter and road classification. Moreover, the behavior analysis module 108 tracks short-term fluctuations separately from the long-term behavioral consistency, enabling differentiation between the isolated aggressive maneuvers and persistent aggressive driving patterns. For instance, a single sudden brake application receives a lower temporal weighting compared to repeated braking events recorded over a defined period, resulting in a more accurate modulation of the aggressiveness score. Additionally, the weighting updates occur continuously, ensuring that the scoring process reflects both instantaneous inputs and evolving temporal behavior. Consequently, the driver aggressiveness score is delivered, and that accounts for time-dependent variations in operational parameters, enhancing behavioral accuracy by distinguishing transient events from the long-term driving tendencies. Subsequently, the advantages include, but are not limited to, improved reliability of the driver profiling through incorporation of the temporal dynamics, reduced distortion of scores by short-lived anomalies, greater contextual fidelity in the aggressiveness evaluation across extended driving sessions, and enhanced adaptability of the system in fleet monitoring, insurance telematics, and safety applications. Ultimately, the system 100 ensures that driver assessment remains stable yet sensitive to genuine behavioral patterns through temporal updating of the variable weighting positions.
In an embodiment, the behavior analysis module 108 integrates the adaptive statistical technique and temporal weighting into the dynamic weighting algorithm to modulate the driver aggressiveness score based on the operational parameters and road classifications. Specifically, the sensor module 104 provides data streams of the throttle position, brake application, steering angle, torque demand, vehicle speed, inertial signals, and vibration levels, and the road classifier module 106 supplies the classified road surfaces derived from the frequency-based signal features. Further, the behavior analysis module 108 employs adaptive statistical mapping to assign variable positions to each parameter and road classification, and the temporal weighting continuously adjusts the positions based on the time-dependent changes. Furthermore, the integration ensures that driver actions are interpreted with statistical adaptability and temporal consistency, producing the aggressiveness score that reflects both the immediate and sustained behavioral patterns under varying road conditions. The process of operation involves sequential processing of the operational data and the road classifications through the adaptive statistical modeling, where each input receives the variable position determined by the correlation strength and the contextual significance. Moreover, the temporal weighting is applied across the defined analysis windows, recalibrating the influence of the operational parameters and the road classifications according to the persistence and recurrence over time. For instance, the repeated high torque demand on a smooth road classification receives a higher weight compared to a single instance of torque demand, whereas frequent steering corrections on an uneven road classification are emphasized more strongly than isolated corrections. Additionally, the dynamic weighting algorithm processes both the adaptive statistical allocation and temporal adjustment in unison, generating the modulated aggressiveness score that captures real-time variability while maintaining stability across extended driving intervals. Consequently, the driver aggressiveness score is produced with enhanced precision, stability, and contextual fidelity through the integration of the adaptive statistical positioning and temporal weighting. Additionally, the advantages include, but are not limited to, reduction of inaccuracies by preventing overemphasis on single events, improved robustness of the aggressiveness evaluation across diverse terrains and driving durations, enhanced differentiation between the occasional aggressive actions and sustained aggressive driving, and greater scalability for advanced telematics, insurance, and fleet applications. Ultimately, the system 100 ensures that the aggressiveness scoring maintains responsiveness to immediate driver actions while embedding long-term behavioral consistency into the evaluation process.
In an exemplary embodiment, the system 100 for determining a driving pattern of a driver of a vehicle 102 incorporates a sensor module 104 that includes an inertial measurement unit, a throttle position sensor, a brake application sensor, a steering angle sensor, a torque demand sensor, a vehicle speed sensor, and a vibration sensor. The inertial measurement unit records acceleration and angular velocity values with a sampling rate of 200 Hz, the throttle position sensor measures throttle input in a range of 0 to 100%, the brake application sensor records hydraulic pressure levels in bar units, the steering angle sensor captures wheel angle in degrees, the torque demand sensor records engine or motor torque values in Newton-meters, the vehicle speed sensor measures speed in kilometres per hour, and the vibration sensor records surface-induced oscillations in g-force values. The road classifier module 106 receives vibration and motion data and extracts frequency-based signal features; for instance, a dominant vibration frequency of 20 Hz with amplitude exceeding 0.7 g corresponds to a rough gravel surface, whereas a dominant vibration frequency of 5 Hz with amplitude below 0.2 g corresponds to smooth asphalt. The behavior analysis module 108 synchronously receives operational parameters and road classifications through a network interface 110. The dynamic weighting algorithm correlates aggressive driver actions with road classifications by assigning real-time weights. For instance, sudden throttle input rising from 10% to 80% within 2 seconds on asphalt receives an aggressiveness weight of 0.3, while the same maneuver on gravel receives an aggressiveness weight of 0.7 due to higher associated risk. A hard braking event with hydraulic pressure exceeding 60 bar within 1.5 seconds receives a base weight of 0.5 on asphalt and 0.9 on cobblestone. The adaptive statistical technique assigns variable positions to each operational parameter, and the algorithm updates the weights based on temporal patterns. Repeated sharp braking events detected three times within a 5-minute interval increase the cumulative aggressiveness weight by 25% to reflect consistent aggressive behavior. The behavior analysis module 108 integrates adaptive statistical modeling with temporal weighting and generates the driver aggressiveness score. A representative output for a 20-minute urban drive indicates a score of 72 on a scale of 0 to 100, where values above 65 signify high aggressiveness. The score results from combining throttle surges, frequent harsh braking, and tight steering inputs on uneven surfaces with respective weighted values. The generated aggressiveness score provides actionable insights for driver monitoring systems, insurance-based risk assessments, and fleet management optimization.
In accordance with another aspect of the present disclosure, there is provided a method for determining a driving pattern of a driver of a vehicle, the method comprising:
- sensing at least one operational parameter of the vehicle, via at least one sensor module;
- classifying road surface characteristics by extracting at least one frequency-based signal feature, via a road classifier module;
- employing an adaptive statistical technique to assign variable position to each operational parameter and road classification, via a behavior analysis module;
- integrating the adaptive statistical technique and temporal weighting into a dynamic weighting algorithm, via the behavior analysis module; and
- generating a driver aggressiveness score by correlating the sensed data received from the sensor module with the road classifications using the dynamic weighting algorithm, via the behavior analysis module.
Referring to figure 2, in accordance with an embodiment, there is described a method 200 for determining a driving pattern of a driver of a vehicle 102. At step 202, the method 200 comprises sensing at least one operational parameter of the vehicle 102, via at least one sensor module 104. At step 204, the method 200 comprises classifying road surface characteristics by extracting at least one frequency-based signal feature, via a road classifier module 106. At step 206, the method 200 comprises employing an adaptive statistical technique to assign variable position to each operational parameter and road classification, via a behavior analysis module 108. At step 208, the method 200 comprises integrating the adaptive statistical technique and temporal weighting into a dynamic weighting algorithm via the behavior analysis module 108. At step 210, the method 200 comprises generating a driver aggressiveness score by correlating the sensed data received from the sensor module 104 with the road classifications using the dynamic weighting algorithm, via the behavior analysis module 108.
In an embodiment, the method 200 comprises sensing at least one operational parameter of the vehicle 102, via at least one sensor module 104. Further, the method 200 comprises classifying road surface characteristics by extracting at least one frequency-based signal feature, via a road classifier module 106. Furthermore, the method 200 comprises employing an adaptive statistical technique to assign variable position to each operational parameter and road classification, via a behavior analysis module 108. Moreover, the method 200 comprises integrating the adaptive statistical technique and temporal weighting into a dynamic weighting algorithm, via the behavior analysis module 108. Additionally, the method 200 comprises generating a driver aggressiveness score by correlating the sensed data received from the sensor module 104 with the road classifications using the dynamic weighting algorithm, via the behavior analysis module 108.
The system for determining a driving pattern of a driver of a vehicle, as described in the present disclosure, is advantageous in terms of producing a context-sensitive aggressiveness score by integrating operational parameters with road surface classifications, ensuring accurate driver behavior assessment. Further, the system uses adaptive statistical technique that provides dynamic weighting of sensor data, resulting in a more reliable evaluation under varying conditions. Furthermore, the system uses temporal weighting to enhance long-term accuracy by capturing repetitive aggressive maneuvers across multiple driving intervals. Moreover, the system architecture enables seamless deployment in connected vehicles and supports integration with telematics and fleet management platforms. Additionally, the enhanced precision in driver profiling supports safety optimization, insurance risk evaluation, and predictive maintenance strategies.
It would be appreciated that all the explanations and embodiments of the system 100 also apply mutatis-mutandis to the method 200.
In the description of the present invention, it is also to be noted that, unless otherwise explicitly specified or limited, the terms “disposed,” “mounted,” and “connected” are to be construed broadly, and may for example be fixedly connected, detachably connected, or integrally connected, either mechanically or electrically. They may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Modifications to embodiments and combinations of different embodiments of the present disclosure described in the foregoing are possible without departing from the scope of the present disclosure as defined by the accompanying claims. Expressions such as “including”, “comprising”, “incorporating”, “have”, and “is” used to describe and claim the present disclosure are intended to be construed in a non-exclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is also to be construed to relate to the plural where appropriate.
Although embodiments have been described with reference to a number of illustrative embodiments thereof, it should be understood that numerous other modifications and embodiments can be devised by those skilled in the art that will fall within the spirit and scope of the principles of this disclosure. More particularly, various variations and modifications are possible in the component parts and/or arrangements of the subject combination arrangement within the scope of the present disclosure, the drawings, and the appended claims. In addition to variations and modifications in the component parts and/or arrangements, alternative uses will also be apparent to those skilled in the art.
,CLAIMS:WE CLAIM:
1. A system (100) for determining a driving pattern of a driver of a vehicle (102), the system (100) comprising:
- at least one sensor module (104) configured to sense at least one operational parameter of the vehicle (102);
- at least one road classifier module (106) communicably coupled to the at least one sensor module (104) and configured to classify road surface characteristics based on the sensed data; and
- a behavior analysis module (108) communicably coupled to the sensor module (104) and the road classifier module (106),
wherein, the behavior analysis module (108) is configured to generate a driver aggressiveness score by correlating the sensed data received from the sensor module (104) with the road classifications received from the road classifier module (106) via a dynamic weighting algorithm.

2. The system (100) as claimed in claim 1, wherein the at least one sensor module (104) comprises one or more sensors selected from the group of sensors comprising inertial measurement unit sensors, throttle position sensors, brake application sensors, torque demand sensors, steering angle sensors, vehicle speed sensors, and vibration sensors.

3. The system (100) as claimed in claim 1, wherein the road classifier module (106) is configured to classify road surface characteristics by extracting at least one frequency-based signal feature from motion and vibration data received from the sensor module (104).

4. The system (100) as claimed in claim 1, wherein the sensor module (104), the road classifier module (106), and the behavior analysis module (108) are configured to synchronous data exchange via a network interface (110).

5. The system (100) as claimed in claim 1, wherein the behavior analysis module (108) is configured to modulate the driver aggressiveness score based on the received real-time data of each sensed operational parameter and road classification.

6. The system (100) as claimed in claim 1, wherein the behavior analysis module (108) is configured to employ an adaptive statistical technique to assign variable position to each operational parameter and road classification during the modulation process.

7. The system (100) as claimed in claim 1, wherein the behavior analysis module (108) is configured to update weighting to the variable positions based on temporal changes in sensor data received from the sensor module (104).

8. The system (100) as claimed in claim 1, wherein the behavior analysis module (108) integrates the adaptive statistical technique and temporal weighting into the dynamic weighting algorithm to modulate the driver aggressiveness score based on the operational parameters and road classifications.

9. The method (200) for determining a driving pattern of a driver of a vehicle (102), the method (200) comprising:
- sensing at least one operational parameter of the vehicle, via at least one sensor module (104);
- classifying road surface characteristics by extracting at least one frequency-based signal feature, via a road classifier module (106);
- employing an adaptive statistical technique to assign variable position to each operational parameter and road classification, via a behavior analysis module (108);
- integrating the adaptive statistical technique and temporal weighting into a dynamic weighting algorithm, via the behavior analysis module (108); and
- generating a driver aggressiveness score by correlating the sensed data received from the sensor module with the road classifications using the dynamic weighting algorithm, via the behavior analysis module (108).