Three-axis Acceleration Research Articles

The motion mechanism of a boulder transported by landslide

Various soil-rock mixed landslides occur in the natural environment. Carried along in the slide, boulders will eventually come to rest. The origin of boulder motion provides crucial constraints for inferring geological events. To overcome the challenges posed by the limited visibility within landslides and the subsequent difficulty in observing boulder motion, we propose a novel device to measure three-axis acceleration and angular velocity using Inertial Measurement Unit (IMU) technology. By comparing with the traditional high-speed camera, the efficacy of the IMU sphere is validated. In the study of boulder movements within landslides, we employ the IMU sphere to characterize boulders. Through experiments varying two key parameters—the initial position of the IMU sphere and the mass of fine particles—this study identifies three distinct final deposition states of the IMU sphere: separate, partially submerged, and completely submerged. By analyzing the potential and kinetic energy during the sliding process of the IMU sphere, we delve into the combined effects of motion enhancement due to landslide deformation and motion hindrance as the IMU sphere passes through fine particles, thereby revealing the underlying movement mechanisms of boulders within landslides. Analysis of leading wave heights indicates minimal sensitivity to the initial position of the IMU sphere, with the mass of fine particles exerting the primary influence. At last, through a comprehensive analysis of the IMU sphere's motion, a novel positional parameter is introduced, leading to the identification of motion mechanisms and distinct phase diagrams depicting deposition states.

High-fidelity analysis and experiments of a wireless sensor node with a built-in supercapacitor powered by piezoelectric vibration energy harvesting

A supercapacitor or an electric double layer capacitor (EDLC) is an essential component of a high-performance wireless sensor node (WSN) that can transmit the three-axis acceleration waveform data of structural vibrations and is powered by a piezoelectric vibration energy harvester (VEH). However, the intrinsically slow charging rate of the piezoelectric VEH triggers charging of extra capacitors formed inside the complex-shaped electrodes of the supercapacitor, which complicates the charging/discharging characteristics and thus estimation of the power generation and energy storage in the supercapacitor. Therefore, in this work, we establish an analytical methodology that allows accurate prediction of the charging/discharging characteristics of the supercapacitor built into the WSN powered by the piezoelectric VEH, considering (1) the nonlinear piezoelectricity, (2) a three-branch circuit model of the supercapacitor, and (3) the current–voltage relation equation for the diode. We develop a parameter identification technique for both the nonlinear piezoelectric VEH and the supercapacitor, and then establish a coupled analysis technique based on the differential algebraic equation (DAE). Using the DAE, we investigate the charging/discharging characteristics of the supercapacitor by considering the actual working steps of the WSN. We revealed that the second branch in the three-branch model contributes not only to an increase in the effective capacitance of the supercapacitor, but also to faster recovery of the voltage across the supercapacitor during WSN operation. We also revealed that a longer charging time led to more energy being stored in the capacitor in the third branch, from which it is difficult to extract energy within a short time period such as the WSN’s transmission process due to its long time constant. The contribution of the second and third branches must be considered to enable accurate prediction of the charging/discharging characteristics of the supercapacitor when built into the WSN powered by the piezoelectric VEH.

Continuous near-bit inclination measurement based on installation error correction

Abstract As the petroleum industry evolves, the challenges associated with petroleum exploration and development intensify, and the continuous measurement of well inclination has grown increasingly significant. Continuous near-bit inclination measurements can improve the accuracy of calculating wellbore trajectory and drilling efficiency. However, the vibration of the bottom drill bit seriously interferes with the inclination measurement, causing serious distortion of acceleration and inaccurate inclination measurement. When the well inclination measurement module is installed eccentrically, it is easy to cause installation errors. At the same time, the drill collar rotates, and the three-axis acceleration is affected by the centrifugal acceleration. The above factors will affect the accuracy of inclination measurement. This paper derives a three-axis acceleration measurement error model caused by installation error, and proposes a continuous measurement method based on this model. First, the vibration noise is filtered out by the Kalman filter. Then a multivariate linear regression model of three-axis acceleration is established, and the true inclination is calculated based on this model. After simulation verification, the continuous inclination error measured by this method is less than 0.2°.

Utilizing Inertial Measurement Units for Detecting Dynamic Stability Variations in a Multi-Condition Gait Experiment.

This study proposes a wearable gait assessment method using inertial measurement units (IMUs) to evaluate gait ability in daily environments. By focusing on the estimation of the margin of stability (MoS), a key kinematic stability parameter, a method using a convolutional neural network, was developed to estimate the MoS from IMU acceleration time-series data. The relationship between MoS and other stability indices, such as the Lyapunov exponent and the multi-site time-series (MSTS) index, using data from five IMU sensors placed on various body parts was also examined. To simulate diverse gait conditions, treadmill speed was varied, and a knee-ankle-foot orthosis was used to restrict left knee extension, inducing gait asymmetry. The model achieved over 90% accuracy in classifying MoS in both forward and lateral directions using three-axis acceleration data from the IMUs. However, the correlation between MoS and the Lyapunov exponent or MSTS index was weak, suggesting that these indices may capture different aspects of gait stability.

The calculation and evaluation of acceleration errors produced by position movement of acceleration sensors on the seat of a human centrifuge

Abstract With the increasing requirement for pilot anti-overload ability training, the man-machine engineering problems caused by the existing seat on a human centrifuge are becoming increasingly prominent, making it challenging to meet actual requirements and needing to be upgraded. After upgrading, the seat can be quickly adjusted in front, back, up and down. Acceleration sensors fixed on the seat will also generate displacement, which will result in errors. Three-axis acceleration values are a crucial technical index in human centrifuge systems, and their errors need to be within a certain accuracy range in order to make the system operate normally. Otherwise, the system will produce serious consequences such as alarm and shutdown. Analysis shows that the position movement of acceleration sensors on the seat has no impact on the control system, mainly affecting the safety system. This study discusses the situation when acceleration errors in seat adjustment reach the maximum values, and calculates the three-axis acceleration errors in detail. It is observed whether the values are within the set limits by the safety system in order to evaluate whether they have an impact on the safety of the entire system. The result indicates that the acceleration errors caused by the adjustment of the upgraded seat are within a controllable range and will not have any adverse effect on the safety system of the human centrifuge. Therefore, the acceleration errors will not have any adverse effect on the safety of the whole system.

Human behavior recognition method based on wearable devices

Abstract Human behavior recognition remains a prevalent subject of inquiry in contemporary scientific studies. Behavior recognition technology has penetrated into every aspect of our lives, mainly in video surveillance, health monitoring, and smart homes. Aiming at some people who need behavioral monitoring to prevent danger, a human behavior recognition method based on wearable devices is proposed, which first acquires the three-axis acceleration data of behavioral activities of such people through wearable devices and then performs sliding window segmentation and feature extraction on the acquired data and finally inputs the obtained features into the dual-directional long and short term memory framework (BiLSTM) model to complete the identification of human behavior. To affirm the method’s reliability, we performed activity detection tests on a dataset from UCI featuring a non-powered wearable sensor used by the senior population. The outcomes indicate that the method is proficient in identifying the routine daily activities of this demographic, demonstrating its practical utility.

Tennis action recognition and evaluation with inertial measurement unit and SVM

Action recognition in tennis plays a crucial role for athletes and coaches, aiding in understanding and evaluating the players' skill levels to formulate more effective training plans and tactical strategies. To enhance the recognition and grading of tennis player actions, this study introduces the use of inertial measurement units and flexible resistive sensors for data collection. An improved Support Vector Machine is employed for data classification to achieve efficient action recognition. The results demonstrated that the proposed classification algorithm achieved an average accuracy of 95.35 % in recognizing actions of elite athletes, with the highest accuracy (96.38 %) observed in forehand strokes. In the case of sub-elite athletes, the algorithm achieved an impressive average accuracy of 97.67 %. For amateur enthusiasts, the algorithm exhibited an average accuracy of 94.08 %. Furthermore, elite athletes exhibited larger peak values in the three-axis acceleration waveform during ball striking. Specifically, the absolute peak value of acceleration in the Y-axis for elite athletes reached 78 m/s², representing an increase of 39 m/s² and 8 m/s² compared to the other two levels of athletes, respectively. Additionally, on the X and Z axes, elite athletes' acceleration peak values reached 59 m/s² and 78 m/s², significantly higher than those of sub-elite athletes and amateur enthusiasts. Moreover, the acceleration curves of elite athletes demonstrated a higher overall regularity. These findings indicate that the proposed action recognition method has a significant impact on recognition and evaluation, providing valuable insights for action recognition and assessment across various domains and advancing the application of artificial intelligence technology in the field of sports.

Quality of Electrocardiography Recorded with Consumer Smart Shirts.

Smart wearables support continuous monitoring of vital signs for early detection of deteriorating health. However, the devices and sensors require sufficient quality to produce meaningful signals, in particular, if data is acquired in motion. In this study, we equipped 48 subjects with smart shirts recording one-lead electrocardiography (ECG), thoracic and abdominal respiratory inductance plethysmography, and three-axis acceleration. For 10 min each, the subjects sit, stand, walk, and run, with a resting period of 5 min in between each activity. We preprocessed the electrocardiogram and applied a signal quality index. We analyzed the signal quality index grouped by the activity and participants. For sitting, standing, walking, and running, the ECG signals provide acceptable quality over 73.20 %, 91.85 %, 12.26 %, and 13.14 % of the recording time. In conclusion, smart wearables may be useful for continuous health monitoring of people with a sedentary lifestyle, but rather not for sportive activities.

A novel method for measuring three-axis dynamic centrifugal acceleration field: the matrix transformation method

Abstract When a three-axis dynamic centrifuge is used to test the performance of inertial equipment (accelerometer, gyroscope, gyro-accelerometer, etc.), accurate estimating of the acceleration at the sensing position of the tested sensors is a key step. To solve the problem of the lack of relevant suitable methods, first, the principle of rigid body kinematics is used to prove that the acceleration of each point on a rigid body changes linearly with respect to the position. Subsequently, a matrix transformation method for accurately measuring the acceleration field on the three-axis dynamic centrifuge is presented. In this method, the distribution law (expressed by a 3×3 matrix) of the acceleration field is calculated based on the measured acceleration at multiple positions. After that the acceleration estimation value at any point on the centrifuge can be calculated. Finally, the uncertainty of the estimated acceleration value is analysed, and a verification experiment is carried out. The results show that the accuracy of this method is mainly limited by the accuracy of the acceleration measurements. The preliminary verification experiment system shows that the mean deviation of the estimated value error obtained by this method is less than 0.024 g, the standard uncertainty is less than 0.015 g, the left and right endpoints of the 95% probability inclusion interval are less than -0.026 g and 0.036 g, respectively, and the half width of the interval is less than 0.028 g. In all, this paper provides a powerful tool for examining the precision performance of inertial equipment on a three-axis dynamic centrifuge, and can also be used for calibration of this kind of centrifuge.

Data Quality Assessment of Gravity Recovery and Climate Experiment Follow-On Accelerometer.

Accelerometers are mainly used to measure the non-conservative forces at the center of mass of gravity satellites and are the core payloads of gravity satellites. All kinds of disturbances in the satellite platform and the environment will affect the quality of the accelerometer data. This paper focuses on the quality assessment of accelerometer data from the GRACE-FO satellites. Based on the ACC1A data, we focus on the analysis of accelerometer data anomalies caused by various types of disturbances in the satellite platform and environment, including thruster spikes, peaks, twangs, and magnetic torque disturbances. The data characteristics and data accuracy of the accelerometer in different operational states and satellite observation modes are analyzed using accelerometer observation data from different time periods. Finally, the data consistency of the accelerometer is analyzed using the accelerometer transplantation method. The results show that the amplitude spectral density of three-axis linear acceleration is better than the specified accuracy (above 10-1 Hz) in the accelerometer's nominal status. The results are helpful for understanding the characteristics and data accuracy of GRACE-FO accelerometer observations.

Design of Non-Intrusive Online Monitoring System for Traction Elevators

With the increase in elevator usage, more and more elevator real-time monitoring equipment is being applied to the operation of elevators. Traditional elevator monitoring equipment adopts a multi-sensor decentralized installation and layout, and the monitoring accuracy is low, which directly affects the effective alarm of the monitoring system; however, existing online monitoring systems cannot quickly alarm for faults. Aiming to solve the above problems, an elevator online monitoring system based on narrow-band Internet of Things (NB-IoT) is designed. The system is highly integrated with an STM32 main control chip, a six-axis acceleration gyroscope sensor, and an air pressure sensor to realize the edge calculation of the monitoring system. At the same time, this paper eliminates the temperature drift of the pressure sensor by using a temperature compensation algorithm and inputs the extracted characteristic parameters into the BP neural network for training to eliminate the zero drift so as to obtain the real-time height data of the elevator. The six-axis acceleration gyroscope sensor is used to calculate the posture so as to avoid the problem that a three-axis acceleration sensor or a three-axis gyroscope sensor alone cannot obtain accurate posture data. In order to further improve the monitoring accuracy, the peak-to-peak value of the signal is calculated by using a 95% confidence interval algorithm to reduce the suppression of the high-frequency components of the signal by noise and ensure that the signal has a large signal-to-noise ratio so that the obtained elevator car posture and vibration operation data are more accurate. Finally, the effectiveness of the proposed method is verified by experiments.

Non-contact multimodal indoor human monitoring systems: A survey

Indoor human monitoring systems are integral in various applications. They leverage a wide range of sensors, including cameras, radio devices, and inertial measurement units, to collect extensive data from users and the environment. These sensors contribute distinct data modalities, encompassing video feeds from cameras, received signal strength indicators and channel state information from WiFi devices, and three-axis acceleration data from accelerometers. In this context, we present a comprehensive survey of multimodal approaches applied to indoor human monitoring systems, with a specific focus on their relevance in elderly care. Our survey primarily highlights non-contact technologies, particularly cameras and radio devices, as key components in the development of indoor human monitoring systems. Throughout this article, we explore well-established techniques for extracting features from multimodal data sources. Our exploration extends to methodologies for fusing these features and harnessing multiple modalities to improve the accuracy and robustness of machine learning models. Furthermore, we conduct comparative analysis across different data modalities in diverse human monitoring tasks and undertake a comprehensive examination of existing multimodal datasets. This extensive survey not only highlights the significance of indoor human monitoring systems but also emphasizes their versatile applications. In particular, we emphasize their critical role in enhancing the quality of elderly care, offering valuable insights into the development of non-contact monitoring solutions tailored to the needs of aging populations.

Deep Learning-Based Road Pavement Inspection by Integrating Visual Information and IMU

This study proposes a deep learning method for pavement defect detection, focusing on identifying potholes and cracks. A dataset comprising 10,828 images is collected, with 8662 allocated for training, 1083 for validation, and 1083 for testing. Vehicle attitude data are categorized based on three-axis acceleration and attitude change, with 6656 (64%) for training, 1664 (16%) for validation, and 2080 (20%) for testing. The Nvidia Jetson Nano serves as the vehicle-embedded system, transmitting IMU-acquired vehicle data and GoPro-captured images over a 5G network to the server. The server recognizes two damage categories, low-risk and high-risk, storing results in MongoDB. Severe damage triggers immediate alerts to maintenance personnel, while less severe issues are recorded for scheduled maintenance. The method selects YOLOv7 among various object detection models for pavement defect detection, achieving a mAP of 93.3%, a recall rate of 87.8%, a precision of 93.2%, and a processing speed of 30–40 FPS. Bi-LSTM is then chosen for vehicle vibration data processing, yielding 77% mAP, 94.9% recall rate, and 89.8% precision. Integration of the visual and vibration results, along with vehicle speed and travel distance, results in a final recall rate of 90.2% and precision of 83.7% after field testing.

Cow Behavior Recognition Based on Wearable Nose Rings.

This study introduces a novel device designed to monitor dairy cow behavior, with a particular focus on feeding, rumination, and other behaviors. This study investigates the association between the cow behaviors and acceleration data collected using a three-axis, nose-mounted accelerometer, as well as the feasibility of improving the behavioral classification accuracy through machine learning. A total of 11 cows were used. We utilized three-axis acceleration sensors that were fixed to the cow's nose, and these devices provided detailed and unique data corresponding to their activity; in particular, a recorder was installed on each nasal device to obtain acceleration data, which were then used to calculate activity levels and changes. In addition, we visually observed the behavior of the cattle. The characteristic acceleration values during feeding, rumination, and other behavior were recorded; there were significant differences in the activity levels and changes between different behaviors. The results indicated that the nose ring device had the potential to accurately differentiate between eating and rumination behaviors, thus providing an effective method for the early detection of health problems and cattle management. The eating, rumination, and other behaviors of cows were classified with high accuracy using the machine learning technique, which can be used to calculate the activity levels and changes in cattle based on the data obtained from the nose-mounted, three-axis accelerometer.

A Single-Leg Vertical Hop Test Is an Effective Tool to Measure Functional Performance after Anterior Cruciate Ligament (ACL) Reconstruction

This study evaluated the single-leg vertical hop test (SLVHT), using digital sensor technology, for the functional assessment of rehabilitation progress in patients after ACL reconstruction (ACL-R). Between January 2019 and June 2022, 143 patients (26.6 (8.9) years, m/f 66/34%) completed return-to-sport testing at 3 and 6 months after ACL-R. The jump height during SLVHT was quantified with a digital motion sensor, containing a three-axis acceleration gyroscope sensor, and the limb symmetry index (LSI) (injured/non-injured leg ratio) was calculated. Three months postoperatively, the jump height of the injured leg was 59.6% (13.5 (5.5) cm) that of the non-injured leg (22.9 (6.2) cm; p < 0.01). After 6 months, the jump height of the injured leg (18.4 (6.9) cm) improved by 44.1% compared to that at the 3-month follow-up but was still lower than the non-injured leg jump height (23.2 (7.0) cm, p < 0.001; LSI = 79.6%). Men jumped higher than women, but their LSI was not different at 3 (59.6 vs. 59.5%) and 6 months (80.6 vs. 77.8%). Regression analysis identified the non-injured leg jump height as the primary independent predictor of the jump height of the injured leg (β = 0.776, T = 51.506, p < 0.001). SLVHT, using digital sensor technology, is a simple and cost-effective functional test to assess rehabilitation progress after ACL-R, with the potential for multi-centre data analysis.

Exploring Physical Activity Levels in Patients with Cardiovascular Disease-A Preliminary Study.

Increased physical activity may prevent disease onset and severity in individuals with cardiovascular disease. However, studies evaluating physical activity in people with cardiovascular disease are limited. This prospective observational study aimed to objectively assess the level of physical activity in patients with cardiovascular disease and determine the actual extent of physical activity in their daily lives. Participants aged 20 years or older with cardiovascular disease at a cardiology clinic were included. Physical activity was measured using an activity meter with a three-axis acceleration sensor. Overall, 58 patients were included in the study. Household activities were found to be more frequent sources of physical activity. The step count was related to age and housework, while total physical activity and household activity were related to age and work. Locomotive activity was related to sex and housework. Total physical and household activities tended to decrease with age. These findings indicate the influence of work and household chores on physical activity and suggest that physical activity may be underestimated if household activity is not also assessed. These fundamental findings may provide clinical evidence to underpin physical activity for patients with cardiovascular disease.

A Study on the Problem-Solving Performance of Sixth-Grade Elementary School Students from Urban and Rural Areas and Students of Different Genders in the Unit of Ratio and Proportion

<p>本研究旨在探討國小六年級不同性別的城鄉學童在比與比值單元中的解題表現，透過對整體和不同向度的解題表現進行分析，以瞭解城鄉和性別之間的差異。研究選擇以紙筆測驗方式收集量化資料，樣本包括臺南市城市地區的5個班級共125位學童以及鄉村地區的8個班級共112位學童。研究使用研究者自編的「比與比值成就測驗」進行施測，並運用統計分析工具SPSS 21.0進行描述性統計、t檢定、二因子變異數分析，進一步分析城鄉和不同性別的解題表現及交互作用。</p> <p> </p><p>The purpose of this study was to explore the problem-solving performance of sixth-grade elementary school students from urban and rural areas and students of different genders in the unit of ratio and proportion, analyzed gender difference and disparity of urban and rural from the entirety and different dimensions of problem-solving performance in this unit. This study adopted paper-and-pencil tests to collect quantitative data. The sample consisted of 125 students from five classes in urban elementary schools in Tainan City and 112 students from eight classes in rural elementary schools in Tainan City. The students were tested by the researcher’s self-edited ""Ratio and Proportion Achievement Test."", and analyzed descriptive statistics, t-test, and two-way ANOVA by statistical software SPSS21.0. Subsequently, analyzed the interaction between urban and rural areas and different genders. The research results are as follows: 1.There was a statistical significance in the performance of urban and rural students from the entirety and the irreducible ratio dimension, but there was no statistical significance in the performance of urban and rural students from the definition of ratio, the definition of proportion, the equivalent ratio ,and the application of the ratio dimensions. 2.There was no statistical significance in the performance of students of different genders from the entirety and different dimensions. 3.There was no significant interaction between students of urban and rural areas and different genders from the entirety and different dimensions performance.vibration and skidding, etc. If the tire is abnormal, if the driver is negligent, it will cause serious harm. Therefore, we design a set of smart tire system, through the measurement of inertial sensing information during tire operation, including: three-axis acceleration, angular velocity, absolute direction, combined with the identification technology of AI algorithm, dynamically detect abnormal tire conditions, and Realize the design of the following IoT platform components: 1. The hardware device installed on the wheel frame can detect abnormal values during tire travel. 2. It has real-time monitoring and abnormal reminders, maintenance suggestions, and a discussion platform for riders, etc. Functional mobile phone application, 3. Based on deep learning neural network technology to identify various tire abnormalities, 4. Establish a cross-platform smart tire web interface for professional fleets to manage parking lots. According to the experimental test results, the AI interpretation accuracy rate of this system is as high as 99.17%.</p> <p> </p>

Evaluation of Fatigue in Older Drivers Using a Multimodal Medical Sensor and Driving Simulator

In recent years, the spread of wearable medical sensors has made it possible to easily measure biological signals such as pulse rate and body acceleration (BA), and from these biological signals, it is possible to evaluate the degree of biological stress and autonomic nervous activity in daily life. Accumulated fatigue due to all-day work and lack of sleep is thought to be a contributing factor to distracted driving, and technology to estimate fatigue from biological signals during driving is desired. In this study, we investigated fatigue evaluation during a driving simulator (DS) using biological information on seven older subjects. A DS experiment was performed in the morning and afternoon, and no significant differences were observed in the change over time of heart rate variability and skin temperature. On the other hand, in the afternoon DS, changes in arousal and body movements were observed based on BA calculated from the three-axis acceleration sensor and fingertip reaction time in a psychomotor vigilance test. It is suggested that by combining biological information, it may be possible to evaluate the degree of fatigue from the presence or absence of arousal and changes in body movements while driving.

Fabrication and Characterization of Monolithic Integrated Three-Axis Acceleration/Pressure/Magnetic Field Sensors.

In order to realize the measurement of three-axis acceleration, pressure, and magnetic field, monolithic integrated three-axis acceleration/pressure/magnetic field sensors are proposed in this paper. The proposed sensors were constructed with an acceleration sensor consisting of four L-shaped double beams, two masses, middle double-beams, and twelve piezoresistors, a pressure sensor made of a square silicon membrane, and four piezoresistors, as well as a magnetic field sensor composed of five Hall elements. COMSOL software and TCAD-Atlas software were used to simulate characteristics of integrated sensors, and analyze the working principles of the sensors in measuring acceleration, pressure, and magnetic field. The integrated sensors were fabricated by using micro-electro-mechanical systems (MEMS) technology and packaged by using inner lead bonding technology. When applying a working voltage of 5 V at room temperature, it is possible for the proposed sensors to achieve the acceleration sensitivities of 3.58 mV/g, 2.68 mV/g, and 9.45 mV/g along the x-axis, y-axis, and z-axis (through an amplifying circuit), and the sensitivities towards pressure and magnetic field are 0.28 mV/kPa and 22.44 mV/T, respectively. It is shown that the proposed sensors can measure three-axis acceleration, pressure, and magnetic field.

Research on Vibration Comfort of Non-Motorized Lane Riding Based on Three-Axis Acceleration

To enhance cycling comfort, a critical investigation of vibration effects in non-motorized bicycle riding is essential, focusing on road characteristics and traffic features. The analysis of how these elements influence cycling vibrations identified 13 key factors. This study utilized non-motorized bicycle lanes in Wuhan City for empirical research. Three-axis accelerometers were attached to riders’ torsos to measure vibration comfort levels. The observed road segments ranged from slightly to relatively uncomfortable. This study employed the random forest algorithm and logistic regression to analyze the influencing factors further. Six factors emerged as significant in affecting cycling comfort: the existence of dedicated non-motorized bicycle lanes, the lack of a physical barrier between non-motorized and motorized traffic, cycling speed, road surface irregularities, parking areas within non-motorized lanes, and bicycle type. This research offers valuable insights into non-motorized bicycle lane usage and contributes to the development of urban non-motorized bicycle infrastructure, supporting sustainable urban transportation.