Search Results (153)

In the proper management of construction, the use of BIM software allows for tracking of the entire lifecycle of buildings, enabling informed design and better management of the product lifecycle, easier collaboration among professionals, and a more efficient system. The combination of BIM tools and today’s information technologies allows the advantages of the BIM methodology to be amplified and expanded. In particular, creating a 3D model with BIM software and linking it to a data stream from sensors allows us to obtain a key component for a Digital Twin of a construction. By integrating BIM methodologies and Digital Twins, this manuscript describes the development of a Digital Twin prototype of a highway bridge, with a 3D model of the structure reproduced using BIM software serving as the core of the Digital Twin. To complete the Digital Twin architecture, an ADXL345 accelerometer sensor, a DTH22 humidity and temperature sensor, an ESP32 microcontroller, the Postgres database, Python (for communication between the backend and the frontend), and the JavaScript library CesiumJS were employed. This methodology produced a Digital Twin prototype capable of collecting vibration and temperature data from the previously mentioned sensors and displaying values through a graphical interface. It can be observed how this technology represents an expansion of the capabilities of BIM software, also highlighting the maintenance potential throughout the product lifecycle. Moreover, the technologies used make the methodology scalable, allowing additional BIMs to be added or the methodology to be applied in different contexts. Full article

This paper proposes a robust convolutional neural network (CNN) architecture for human activity recognition (HAR) using smartphone accelerometer data, evaluated on the WISDM dataset. We introduce two novel pooling mechanisms—Pooling A (Extrema Contrast Pooling (ECP)) and Pooling B (Center Minus Variation (CMV))—that enhance feature discrimination and noise robustness. ECP emphasizes sharp signal transitions through a nonlinear penalty based on the squared range between extrema, while CMV Pooling penalizes local variability by subtracting the standard deviation, improving resilience to noise. Input data are normalized to the [0, 1] range to ensure bounded and interpretable pooled outputs. The proposed framework is evaluated in two separate configurations: (1) a 1D CNN applied to raw tri-axial sensor streams with the proposed pooling layers, and (2) a histogram-based image encoding pipeline that transforms segment-level sensor redundancy into RGB representations for a 2D CNN with fully connected layers. Ablation studies show that histogram encoding provides the largest improvement, while the combination of ECP and CMV further enhances classification performance. Across six activity classes, the 2D CNN system achieves up to 96.84% weighted classification accuracy, outperforming baseline models and traditional average pooling. Under Gaussian, salt-and-pepper, and mixed noise conditions, the proposed pooling layers consistently reduce performance degradation, demonstrating improved stability in real-world sensing environments. These results highlight the benefits of redundancy-aware pooling and histogram-based representations for accurate and robust mobile HAR systems. Full article

This paper proposes an optical three-dimensional (3D) point cloud acquisition and sketching system, which is not limited by the measurement size, unlike traditional 3D object measurement techniques. The system employs an optical displacement sensor for surface displacement scanning and a six-axis inertial sensor (accelerometer and gyroscope) for spatial attitude perception. A microprocessor control unit (MCU) is responsible for acquiring, merging, and calculating data from the sensors, converting it into 3D point clouds. Butterworth filtering and Mahoney complementary filtering are used for sensor signal preprocessing and calculation, respectively. Furthermore, a human–machine interface is designed to visualize the point cloud and display the scanning path and measurement trajectory in real time. Compared to existing works in the literature, this system has a simpler hardware architecture, more efficient algorithms, and better operation, inspection, and observation features. The experimental results show that the maximum measurement error on 2D planes is 4.7% with a root mean square (RMS) error of 2.1%, corresponding to the reference length of 10.3 cm. For 3D objects, the maximum measurement error is 5.3% with the RMS error of 2.4%, corresponding to the reference length of 9.3 cm. Finally, it was verified that this system can also be applied to large-sized 3D objects for outlines. Full article

Accurate recognition of lower limb activities is essential for wearable rehabilitation systems and assistive robotics like exoskeletons and prosthetics. This study introduces SDALLE, a custom hardware data acquisition system that integrates surface electromyography sensors (EMGs) and inertial measurement sensors (IMUs) into a wireless, portable platform for locomotor monitoring. Using this system, data were collected from nine healthy subjects performing four fundamental locomotor activities: walking, jogging, stair ascent, and stair descent. The recorded signals underwent an offline structured preprocessing pipeline consisting of time-series augmentation (jittering and scaling) to increase data diversity, followed by wavelet-based denoising to suppress high-frequency noise and enhance signal quality. A temporal one-dimensional convolutional neural network (1D-TCNN) with three convolutional blocks and fully connected layers was trained on the prepared dataset to classify the four activities. Classification using IMU sensors achieved the highest performance, with accuracies ranging from 0.81 to 0.95. The gyroscope X-axis of the left Rectus Femoris achieved the best performance (0.95), while accelerometer signals also performed strongly, reaching 0.93 for the Vastus Medialis in the Y direction. In contrast, electromyography channels showed lower discriminative capability. These results demonstrate that the combination of SDALLE hardware, appropriate data preprocessing, and a temporal CNN provides an effective offline sensing and activity classification pipeline for lower limb activity recognition and offers an open-source dataset that supports further research in human activity recognition, rehabilitation, and assistive robotics. Full article

Recent advances in vibration-based pavement assessment have enabled the low-cost monitoring of road conditions using inertial sensors and machine learning models. However, most studies focus on isolated tasks, such as roughness classification, without integrating statistical validation, anomaly detection, or maintenance prioritization. This study presents a unified framework for road roughness severity classification and predictive maintenance using multi-axis accelerometer data collected from urban road networks in Pretoria, South Africa. The proposed pipeline integrates ISO-referenced labeling, ensemble and deep classifiers (Random Forest, XGBoost, MLP, and 1D-CNN), McNemar’s test for model agreement validation, feature importance interpretation, and GIS-based anomaly mapping. Stratified cross-validation and hyperparameter tuning ensured robust generalization, with accuracies exceeding 99%. Statistical outlier detection enabled the early identification of deteriorated segments, supporting proactive maintenance planning. The results confirm that vertical acceleration (accel_z) is the most discriminative signal for roughness severity, validating the feasibility of lightweight single-axis sensing. The study concludes that combining supervised learning with statistical anomaly detection can provide an intelligent, scalable, and cost-effective foundation for municipal pavement management systems. The modular design further supports integration with Internet-of-Things (IoT) telematics platforms for near-real-time road condition monitoring and sustainable transport asset management. Full article

Background/Objectives: Subcortical local field potentials (LFPs) provide a valuable in vivo window into the neurophysiology of the dystonia network. These signals can be recorded through Deep Brain Stimulation (DBS) devices and combined with whole-head techniques such as magnetoencephalography (MEG) to study cortical–subcortical interactions. However, simultaneous LFP-MEG acquisition poses challenges, including interference from the DBS device and synchronization issues. We present preliminary data on the feasibility and signal quality of concurrent LFP and MEG recordings in dystonia patients. Methods: We assessed simultaneous MEG-LFP recordings in 11 patients with inherited or idiopathic dystonia who underwent bilateral DBS lead implantation in the Globus Pallidus Internus (GPi). Two synchronization strategies were tested: (1) the Tapping method, using an accelerometer placed on the DBS device, and (2) the Stimulation method, which generated detectable artifacts during sham stimulation. Results: Both methods successfully aligned MEG and LFP signals with a mean temporal delay of 91 ± 22 ms for the Tapping method and 288 ± 166 ms for the Stimulation method. Post-implantation signal-to-noise ratio analysis revealed slight degradation but no significant impact on MEG quality (gradiometers: −0.12 ± 1.85 dB; magnetometers: −0.47 ± 2.03 dB). Conclusions: Simultaneous MEG-LFP recordings in dystonic patients are feasible, yielding high-quality signals, and reliable synchronization. Temporal alignment improved with practice, suggesting a short learning curve. This method opens new opportunities to study cortical-subcortical dynamics and strengthens the potential of combining MEG-LFP approaches for investigating dystonia. Full article

A vast number of boreholes in underground mining operations are often plagued by deviation issues, which severely impact both production efficiency and safety. The accurate and rapid acquisition of borehole trajectories is fundamental for subsequent deviation control and correction. However, existing inclinometers are limited by their operational efficiency and estimation accuracy, making them inadequate for large-scale measurement demands. To address this, this paper proposes a novel method for the rapid and accurate reconstruction of underground mine borehole trajectories using a robotic system. We employ a custom-designed robot equipped with an Inertial Measurement Unit (IMU) and a displacement sensor, which travels stably while collecting real-time attitude and depth information. Algorithmically, a complementary filter is used to fuse data from the gyroscope with that from the accelerometer and magnetometer, overcoming both integration drift and environmental disturbances. A cubic spline interpolation algorithm is then utilized to time-register the low-sampling-rate displacement data with the high-frequency attitude data, creating a time-synchronized sequence of ‘attitude–displacement increment’ pairs. Finally, the 3D borehole trajectory is accurately reconstructed by mapping the attitude quaternions to direction vectors and recursively accumulating the displacement increments. Comparative experiments demonstrate that the proposed method significantly improves efficiency. On a complex trajectory, the maximum and mean errors were reduced to 0.38 m and 0.18 m, respectively. This level of accuracy is far superior to that of the conventional static point-by-point measurement mode and effectively suppresses the accumulation of dynamic errors. This work provides a new solution for routine borehole trajectory surveying in mining operations. Full article

The central purpose of this study is to develop and validate an advanced numerical model capable of simulating the vibrational behavior of the operator’s seat in a tractor-type agricultural vehicle designed for operation in protected horticultural environments, such as vegetable greenhouses. The three-dimensional (3D) model of the seat was created using SolidWorks 2023, while its dynamic response was investigated through Finite Element Analysis (FEA) in Altair SimSolid, enabling a detailed evaluation of the natural vibration modes within the 0–80 Hz frequency range. Within this interval, eight significant natural frequencies were identified and correlated with the real structural behavior of the seat assembly. For experimental validation, direct time-domain measurements were performed at a constant speed of 5 km/h on an uneven, grass-covered dirt track within the research infrastructure of INMA Bucharest, using the TE-0 self-propelled electric tractor prototype. At the operator’s seat level, vibration data were collected considering the average anthropometric characteristics of a homogeneous group of subjects representative of typical tractor operators. The sample of participating operators, consisting exclusively of males aged between 27 and 50 years, was selected to ensure representative anthropometric characteristics and ergonomic consistency for typical agricultural tractor operators. Triaxial accelerometer sensors (NexGen Ergonomics, Pointe-Claire, Canada, and Biometrics Ltd., Gwent, UK) were strategically positioned on the seat cushion and backrest to record accelerations along the X, Y, and Z spatial axes. The recorded acceleration data were processed and converted into the frequency domain using Fast Fourier Transform (FFT), allowing the assessment of vibration transmissibility and resonance amplification between the floor and seat. The combined numerical–experimental approach provided high-fidelity validation of the seat’s dynamic model, confirming the structural modes most responsible for vibration transmission in the 4–8 Hz range—a critical sensitivity band for human comfort and health as established in previous studies on whole-body vibration exposure. Beyond validating the model, this integrated methodology offers a predictive framework for assessing different seat suspension configurations under controlled conditions, reducing experimental costs and enabling optimization of ergonomic design before physical prototyping. The correlation between FEA-based modal results and field measurements allows a deeper understanding of vibration propagation mechanisms within the operator–seat system, supporting efforts to mitigate whole-body vibration exposure and improve long-term operator safety in horticultural mechanization. Full article

This study focuses on human awareness, a critical component in human–robot interaction, particularly within agricultural environments where interactions are enriched by complex contextual information. The main objective is identifying human activities occurring during collaborative harvesting tasks involving humans and robots. To achieve this, we propose a novel and lightweight deep learning model, named 1D-ResNeXt, designed explicitly for recognizing activities in agriculture-related human–robot collaboration. The model is built as an end-to-end architecture incorporating feature fusion and a multi-kernel convolutional block strategy. It utilizes residual connections and a split–transform–merge mechanism to mitigate performance degradation and reduce model complexity by limiting the number of trainable parameters. Sensor data were collected from twenty individuals with five wearable devices placed on different body parts. Each sensor was embedded with tri-axial accelerometers, gyroscopes, and magnetometers. Under real field conditions, the participants performed several sub-tasks commonly associated with agricultural labor, such as lifting and carrying loads. Before classification, the raw sensor signals were pre-processed to eliminate noise. The cleaned time-series data were then input into the proposed deep learning network for sequential pattern recognition. Experimental results showed that the chest-mounted sensor achieved the highest F1-score of 99.86%, outperforming other sensor placements and combinations. An analysis of temporal window sizes (0.5, 1.0, 1.5, and 2.0 s) demonstrated that the 0.5 s window provided the best recognition performance, indicating that key activity features in agriculture can be captured over short intervals. Moreover, a comprehensive evaluation of sensor modalities revealed that multimodal fusion of accelerometer, gyroscope, and magnetometer data yielded the best accuracy at 99.92%. The combination of accelerometer and gyroscope data offered an optimal compromise, achieving 99.49% accuracy while maintaining lower system complexity. These findings highlight the importance of strategic sensor placement and data fusion in enhancing activity recognition performance while reducing the need for extensive data and computational resources. This work contributes to developing intelligent, efficient, and adaptive collaborative systems, offering promising applications in agriculture and beyond, with improved safety, cost-efficiency, and real-time operational capability. Full article

In this paper, the rail mean vertical alignment is estimated through double integration of wheel–rail contact forces measured using dynamometric wheelsets on a dedicated track recording vehicle (TRV). A simplified three degrees of freedom (DOF) linear model of half a train coach has been developed for this purpose. The model’s ability to simulate the average left and right longitudinal level has been tested using vertical contact force recordings from a constant speed track section, as measured by the TRV. The results are compared with available track geometry (TG) data, recorded by the optical system of the same vehicle, used for condition monitoring of the Italian railway infrastructure. Model parameters, such as masses, stiffness, and damping of the suspensive system have been optimized. An error analysis has been conducted on results. A good agreement is found between simulated and recorded vertical alignment at the D1 level, suggesting the feasibility of using contact forces measured with instrumented wheelsets for railway TG condition monitoring. This computationally efficient approach highlights the potential of strain gauges and instrumented wheelsets as alternative or complementary technologies to the widely adopted accelerometers, rate gyros, and optical devices for railway condition monitoring. Given its low computational cost, embedded and real-time TG estimation could be further investigated. Full article

The increasing concern for road safety has driven the development of advanced driver behavior analysis systems. This study presents a comprehensive review of various techniques to detect unsafe driving behaviors, with a particular emphasis on using smartphone sensors. By leveraging data from accelerometers, gyroscopes, and GPS, these methods allow for the detection of aggressive driving patterns, which may result from factors such as driver distraction or drowsiness. Modern sensor technology plays a crucial role in real-time monitoring and has significant potential to enhance vehicle safety systems. A Long Short-Term Memory (LSTM) network combined with a Conv1D layer was trained to analyze driving patterns using a sliding window technique. As technology continues evolving, its application in driver behavior analysis holds great promise for reducing traffic accidents and improving driving habits. Furthermore, the ability to gather and analyze large amounts of data from drivers in various conditions opens new opportunities for more personalized and adaptive safety solutions. This research offers insights into the future direction of driver monitoring systems and the growing impact of mobile and sensor-based solutions in transportation safety. Full article

Visible Light Positioning (VLP), leveraging Light-Emitting Diodes (LEDs) and smartphone CMOS cameras, provides a high-precision solution for indoor localization. However, existing systems face challenges in accuracy, latency, and robustness due to line-of-sight (LOS) limitations and inefficient signal encoding. To overcome these constraints, this paper introduces a real-time VLP framework that integrates Multi-Pulse Position Modulation (MPPM) with smartphone multi-sensor fusion. By employing MPPM, a high-efficiency encoding scheme, the proposed system transmits LED identifiers (LED-IDs) with reduced inter-symbol interference, enabling robust signal detection even under dynamic lighting conditions and at extended distances. The smartphone’s camera is a receiver that decodes the MPPM-encoded LED-ID, while accelerometer and magnetometer data compensate for device orientation and motion-induced errors. Experimental results demonstrate that the MPPM-driven approach achieves a decoding success rate of over 97% at distances up to 2.4 m, while maintaining a frame processing rate of 30 FPS and sub-35 ms latency. Furthermore, the method reduces angular errors through sensor fusion, yielding 2D positioning accuracy below 10 cm and vertical errors under 16 cm across diverse smartphone orientations. The synergy of MPPM’s spectral efficiency and multi-sensor correction establishes a new benchmark for VLP systems, enabling scalable deployment in real-world environments without requiring complex infrastructure. Full article

Rowing is a cyclic sport that consists of repetitive biomechanical actions, with performance being influenced by the balance between propulsive and resistive forces. The current study aimed to assess the relationships between intracycle velocity variation (IVV) and key biomechanical and performance variables in male and female single scullers. Twenty-three experienced rowers (10 females) completed a 2000 m rowing competition, during which boat position and velocity were measured using a 15 Hz GPS, while cycle rate was derived from the integrated triaxial accelerometer sampling at 100 Hz. From these data, it was possible to calculate distance per cycle, IVV, the coefficient of velocity variation (CVV), and technical index values. Males presented higher mean, maximum and minimum velocity, distance per cycle, CVV, and technical index values than females (15.40 ± 0.81 vs. 13.36 ± 0.88 km/h, d = 0.84; 21.39 ± 1.68 vs. 18.77 ± 1.52 km/h, d = 1.61; 11.15 ± 1.81 vs. 9.03 ± 0.85 km/h, d = 1.45; 7.68 ± 0.32 vs. 6.89 ± 0.97 m, d = 0.69; 14.13 ± 2.02 vs. 11.64 ± 1.93%, d = 2.06; and 34.25 ± 4.82 vs. 26.30 ± 4.23 (m²/s·cycle), d = 4.56, respectively). An association between mean velocity and intracycle IVV, CVV, and cycle rate (r = 0.68, 0.74 and 0.65, respectively) was observed in males but not in female single scullers (which may be attributed to anthropometric specificities). In female single scullers, mean velocity was related with distance per cycle and was associated with technical index in both males and females (r = 0.76 and 0.66, respectively). Despite these differences, male and female single scullers adopted similar pacing strategies and CVV remained constant throughout the 2000 m race (indicating that this variable might not be affected by fatigue). Differences were also observed in the velocity–time profile, with men reaching peak velocity first and having a faster propulsive phase. Data provided new information on how IVV and CVV relate to commonly used biomechanical variables in rowing. Technical index (r = 0.87): distance per cycle was associated with technical index in both males and females (r = 0.76 and 0.66, respectively). Future studies should include other boat classes and other performance variables such as the power output and arc length. Full article

In the context of aging populations, it has become necessary to develop new methods and devices for the daily home-based self-rehabilitation of elderly people. To this end, this paper proposes and evaluates the use of an easy-to-use single battery-powered device including a 3D accelerometer and a 3D gyroscope, where light algorithms, such as the complementary filter and the Kalman filter, are implemented to estimate the elbow joint angle. During experiments, a robotic arm and a human arm were used to obtain an error interval for each tested algorithm; the robotic arm allows for reproducible movements and reproducible results, which allows us to independently verify the impact of parameters such as the sensor’s movement speed on the algorithm precision. The experimental results show that the algorithm that uses only accelerometer data is one of the most relevant since it allows us to obtain a Root Mean Square Error between 1.83° and 5.52° at a sensor data rate of 100 Hz, which is similar to the results obtained using the data fusion algorithms tested. Nevertheless, it has a lower power consumption since it requires only 58 cycles when using an ARM Cortex-M4 processor (which is lower than that of the other data fusion algorithms tested by a factor of at least two), and it does not necessitate the additional sensor required by the other data fusion algorithms tested (such as a gyroscope or a magnetometer). The algorithm using only accelerometer data also seems to be the algorithm with the lowest power consumption and should be preferred. Moreover, its power consumption can be reduced by more than the increase in the error when reducing the rate of the data output by the sensor. In this work, a reduction in the data rate from 100 Hz to 10 Hz increased the RMSE by a factor of 1.8 but could reduce the power consumption associated with the sensor and the algorithm’s computation by a factor of 10. Finally, the experimental results show that the higher the speed of the sensor’s motion, the higher the error obtained using only accelerometer data. Nevertheless, the algorithm that uses only accelerometer data remains well suited to rehabilitation exercises or mobility evaluations since the speed of the sensor’s movement is also moderate. Full article

Background/Objectives: Nonverbal synchrony—the temporal coordination of physical behaviors such as head movement and gesture—is a critical component of effective social communication. Individuals with autism spectrum disorder (ASD) are often described as having impairments in such synchrony, but objective and scalable tools to measure these disruptions remain limited. This study aims to assess body motion synchrony in ASD using phase-based features as potential markers of social timing impairments. Methods: We applied a phase difference detection algorithm to high-resolution triaxial accelerometer data obtained during structured, unidirectional verbal communication. A total of 72 participants (36 typically developing TD–TD and 36 TD–ASD) were divided into dyads. ASD participants always assumed the listener role, enabling the isolation of receptive synchrony. Four distribution-based features—synchrony activity, directionality, variability, and coherence—were extracted from the phase difference data to assess synchrony dynamics. Results: Compared to the TD group, the ASD group exhibited significantly lower synchrony activity (ASD: 5.96 vs. TD: 9.63 times/min, p = 0.0008, Cohen’s d = 1.23), greater temporal variability (ASD: 384.4 ms vs. TD: 311.1 ms, p = 0.0036, d = 1.04), and reduced coherence (ASD: 0.13 vs. TD: 0.81, p = 0.036, d = 0.73). Although the mean phase difference did not differ significantly between groups, the ASD group displayed weaker and more irregular synchrony patterns, indicating impaired temporal stability. Conclusions: Our findings highlight robust impairments in nonverbal head motion synchrony in ASD, not only in frequency but also in terms of temporal stability and convergence. The use of phase-based synchrony features provides a continuous, high-resolution, language-independent metric for social timing. These metrics offer substantial potential as behavioral biomarkers for diagnostic support and intervention monitoring in ASD. Full article