Search Results (415)

Autonomous trains require reliable and accurate environmental perception to take over safety-critical tasks from the driver. This paper investigates the application of N-version architectures to rail track detection using Deep Neural Networks (DNNs) as a means to improve the safety of machine learning (ML)-enabled perception systems. We combine three different neural network architectures (WCID, VGG16-UNet, MobileNet–SegNet) in a 3M1I configuration. In this configuration, we apply two fusion methods to increase accuracy and to enable error detection: Maximum Confidence Voting (MCV), combining the DNN predictions at the image level, and Pixel Majority Voting (PMV), a novel approach for combining the predictions at the pixel level. In addition, we implement a new method for evaluating and combining prediction confidence values in the N-version architecture during runtime. We adjust the overall prediction confidence according to the conformity of all individual predictions, which is not possible with an individual network. Our results show that the N-version architecture not only enables a detection of erroneous predictions by utilizing those adjusted confidence values, but it can also partially improve the predictions by using the PMV combination algorithm. This work emphasizes the importance of model diversity and appropriate thresholds for an accurate assessment of prediction safety. These approaches can significantly improve the practical applicability of ML-based systems in safety-critical domains such as rail transportation. Full article

Accurate millet appearance quality assessment is critical for fair procurement pricing. Traditional manual inspection is time-consuming and subjective, necessitating an automated solution. This study proposes a machine-vision-based approach using deep learning for dense-scene millet detection and quality evaluation. High-resolution images of standardized millet samples were collected via smartphone and annotated into seven categories covering impurities, high-quality grains, and various defects. To address the challenges with small object detection and feature loss, the YOLO11s model with an overlap-partitioning strategy were introduced, dividing the high-resolution images into smaller patches for improved object representation. The experimental results show that the optimized model achieved a mean average precision (mAP) of 94.8%, significantly outperforming traditional whole-image detection with a mAP of 15.9%. The optimized model was deployed in a custom-developed mobile application, enabling low-cost, real-time millet inspection directly on smartphones. It can process full-resolution images (4608 × 3456 pixels) containing over 5000 kernels within 6.8 s. This work provides a practical solution for on-site quality evaluation in procurement and contributes to real-time agricultural inspection systems. Full article

The rapid advancement of sustainable materials has driven the need for high-performance polymer nanocomposites with superior mechanical, thermal, and structural properties. In this study, a novel RPET/PA-11/Joncryl^® nanocomposite reinforced with halloysite nanotubes (HNTs) is developed for the first time, marking a significant breakthrough in polymer engineering. Six different proportions of HNT (0, 1, 2, 3, 4, and 5 phr) are introduced to the blend of rPET/PA-11/Joncryl^® through a twin-screw extruder and injection moulding machine. The incorporation of HNTs into the RPET/PA-11 matrix, coupled with Joncryl^® as a compatibilizer, results in a synergistic enhancement of material properties through improved interfacial adhesion, load transfer efficiency, and nanoscale reinforcement. Comprehensive characterization reveals that the optimal formulation with 2 phr HNT (NCS-H2) achieves remarkable improvements in tensile strength (56.14 MPa), flexural strength (68.34 MPa), and Young’s modulus (895 MPa), far exceeding conventional polymer blends. Impact resistance reaches 243.46 J/m, demonstrating exceptional energy absorption and fracture toughness. Thermal analysis confirms enhanced stability, with an onset degradation temperature of 370 °C, attributing the improvement to effective matrix–filler interactions and restricted chain mobility. Morphological analysis through FESEM validates uniform HNT dispersion at optimal loading, eliminating agglomeration-induced stress concentrators and reinforcing the polymer network. The pioneering integration of HNT into RPET/PA-11/Joncryl^® nanocomposites not only bridges a critical gap in sustainable polymers but also establishes a new benchmark for polymer nanocomposites. This work presents an eco-friendly solution for engineering applications, offering mechanical robustness, thermal stability, and recyclability. The results form the basis for next-generation high-performance materials for industrial use in automotive, aerospace, and high-strength structural applications. Full article

Free chlorine (FC) plays a crucial role in ensuring the safety of drinking water by effectively inactivating pathogenic microorganisms. However, traditional methods for measuring FC levels often require specialized equipment and laboratory settings, limiting their accessibility and practicality for on-site or point-of-use monitoring. QR Codes are powerful machine-readable patterns that are used worldwide to encode information (i.e., URLs or IDs), but their computer vision features allow QR Codes to act as carriers of other features for several applications. Often, this capability is used for aesthetics, e.g., embedding a logo in the QR Code. In this work, we propose using our technique to build back-compatible Color QR Codes, which can embed dozens of colorimetric references, to assist in the color correction to readout sensors. Specifically, we target two well-known products in the HORECA (hotel/restaurant/café) sector that qualitatively measure chlorine levels in samples of water. The two targeted methods were a BTB strip and a DPD powder. First, the BTB strip was a pH-based indicator distributed by Sensafe^®, which uses the well-known bromothymol blue as a base-reactive indicator; second, the DPD powder was a colorimetric test distributed by Hach^®, which employs diethyl-p-phenylenediamine (DPD) to produce a pink coloration in the presence of free chlorine. Custom Color QR Codes were created for both color palettes and exposed to several illumination conditions, captured with three different mobile devices and tested over different water samples. Results indicate that both methods could be correctly digitized in real-world conditions with our technology, rendering a 88.10% accuracy for the BTB strip measurement, and 84.62% for the DPD powder one. Full article

Traffic counts are essential for assessing road capacity to provide efficient, effective, and safe mobility. However, current methods for generating models for traffic count studies are often limited in their accuracy and applicability, which can lead to incorrect or imprecise estimates of traffic volume. This study focused on analyzing and predicting traffic conditions on Ikorodu Road in Lagos State. The analysis involved an examination of historical traffic data, specifically focusing on daily and hourly traffic volumes. The prediction involved the use of machine learning models, including decision trees, gradient boosting, and random forest classifiers. The results of this study revealed significant variations in traffic volume across different days of the week and times of the day, indicating peak and off-peak periods. The study also highlighted the need for a more comprehensive approach that includes additional factors, such as weather conditions, road work, and special events, which could significantly impact traffic volume. Full article

Industry 4.0 has revolutionized the way companies manufacture, improve, and distribute their products through the use of new technologies, such as artificial intelligence, robotics, and machine learning. Autonomous Mobile Robots (AMRs), especially, have gained a lot of attention, supporting workers with daily industrial tasks and boosting overall performance by delivering vital information about the status of the production line. To this end, this work presents the novel Q-CONPASS system that aims to introduce AMRs in production lines with the ultimate goal of gathering important information that can assist in production and safety control. More specifically, the Q-CONPASS system is based on an AMR equipped with a plethora of machine learning algorithms that enable the vehicle to safely navigate in a dynamic industrial environment, avoiding humans, moving machines, and stationary objects while performing important tasks. These tasks include the identification of the following: (i) missing objects during product packaging and (ii) extreme skeletal poses of workers that can lead to musculoskeletal disorders. Finally, the Q-CONPASS system was validated in a real-life environment (i.e., the lift manufacturing industry), showcasing the importance of collecting and processing data in real-time to boost productivity and improve the well-being of workers. Full article

This study introduces an innovative and scalable approach for automated road surface assessment by integrating Mobile Mapping System (MMS)-based LiDAR data analysis with an open-source WebGIS platform. In a U.S.-based case study, over 20 datasets were collected along Interstate I-65 in West Lafayette, Indiana, using the Purdue Wheel-based Mobile Mapping System—Ultra High Accuracy (PWMMS-UHA), following Indiana Department of Transportation (INDOT) guidelines. Preprocessing included noise removal, resolution reduction to 2 cm, and ground/non-ground separation using the Cloth Simulation Filter (CSF), resulting in Bare Earth (BE), Digital Terrain Model (DTM), and Above Ground (AG) point clouds. The optimized BE layer, enriched with intensity and color information, enabled crack detection through Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Random Forest (RF) classification, with and without intensity normalization. DBSCAN parameter tuning was guided by silhouette scores, while model performance was evaluated using precision, recall, F1-score, and the Jaccard Index, benchmarked against reference data. Results demonstrate that RF consistently outperformed DBSCAN, particularly under intensity normalization, achieving Jaccard Index values of 94% for longitudinal and 88% for transverse cracks. A key contribution of this work is the integration of geospatial analytics into an interactive, open-source WebGIS environment—developed using Blender, QGIS, and Lizmap—to support predictive maintenance planning. Moreover, intervention thresholds were defined based on crack surface area, aligned with the Pavement Condition Index (PCI) and FHWA standards, offering a data-driven framework for infrastructure monitoring. This study emphasizes the practical advantages of comparing clustering and machine learning techniques on 3D LiDAR point clouds, both with and without intensity normalization, and proposes a replicable, computationally efficient alternative to deep learning methods, which often require extensive training datasets and high computational resources. Full article

Fifth-generation (5G) networks are the fifth generation of mobile networks and are regarded as a global standard, following 1G, 2G, 3G, and 4G networks. Fifth-generation, with its large available bandwidth provided by mmWave, not only provides the end user with higher spectrum efficiency, massive capacity, low latency, and high speed but is also a network designed to connect virtually everyone and everything together, including machines, objects, and devices. Therefore, studies of such systems’ performance evaluation and capacity bounds are critical for the research community. Furthermore, the performance of these systems should be investigated in realistic contexts while considering signal strength and restricted uplink power to maintain system coverage and capacity, which are also affected by the environment and the value of the service factor parameter. However, any proposed application should include a multiservice case to reflect the true state of 5G systems. As an extension of previous work, the capacity bounds for 5G networks are derived and analyzed in this research, considering both single and multiservice cases with mobility. In addition, the influence of different parameters on network performance, such as the interference, service factor, and non-orthogonality factors, and cell radii, is also discussed. The numerical findings and analysis reveal that the type of environment and service factor parameters have the greatest influence on system capacity and coverage. Subsequently, it is shown that the investigated parameters have a major impact on cell performance and therefore can be considered key indicators for mobile designers and operators to consider in planning and designing future networks. To validate these findings, some results are evaluated against ITU-T standards, while others are compared with related studies from the literature. Full article

Recent European policies fostering sustainable mobility target urban proximity as a core strategy for a modal shift towards low-carbon modes. Urban proximity, as a characteristic of the built environment, can be studied as a sub-thread of a broad and complex body of literature which associates urban factors such as density or land use mix with observed travel behavior, so as to address their relative influence on the latter. Building on this previous knowledge, the present work addresses the importance of a diverse set of factors on local travel modal choice between walking and other modes, according to the 2018 Household Mobility Survey of the Metropolitan Region of Madrid, and a large variety of demographic and built environment characteristics. The work proposes to address this importance through a workflow on a set of Machine Learning models, filtering different distance thresholds and purposes of the trips, going through a strict feature selection process, and executing under different schema definitions. The resulting models are inspected for accuracy, feature importance, and composition. Results suggest that even small changes in distance thresholds exert a great impact on all models; sociodemographic variables are slightly more important in most models, yet building age, along with other street layout factors, pervasively obtain fairly accurate predictions too. Full article

Open-pit mining involves the use of vehicles with high load capacity and satisfactory mobility. As experience shows, these requirements are fully met by pneumatic wheeled dump trucks, the traction drives of which can be made using thermal or electric machines. The latter are preferable due to their environmental friendliness. Unlike dump trucks with thermal engines, which require fuel to be injected into them, electric trucks can be powered by various options of a power supply: centralized, autonomous, and combined. This paper highlights the advantages and disadvantages of different power supply systems depending on their schematic solutions and the quarry parameters for all the variants of the power supply of the dumper. Each quantitative indicator of each factor was changed under conditions consistent with the others. The steepness of the road elevation in the quarry and its length were the factors under study. The studies conducted show that the energy consumption for dump truck movement for all variants of a power supply practically does not change. Another group of factors consisted of electric energy sources, which were accumulator batteries and double electric layer capacitors. The analysis of energy efficiency and the regenerative braking system reveals low efficiency of regeneration when lifting the load from the quarry. In the process of lifting from the lower horizons of the quarry to the dump and back, kinetic energy is converted into heat, reducing the efficiency of regeneration considering the technological cycle of works. Taking these circumstances into account, removing the regenerative braking systems of open-pit electric dump trucks hauling soil or solid minerals from an open pit upwards seems to be economically feasible. Eliminating the regenerative braking system will simplify the design, reduce the cost of a dump truck, and free up usable volume effectively utilized to increase the capacity of the battery packs, allowing for longer run times without recharging and improving overall system efficiency. The problem of considering the length of the path for energy consumption per given gradient of the motion profile was solved. Full article

The automation of mining mobile equipment is a topic of considerable interest, as it has the potential to significantly reduce the number of accidents and implement the so-called zero-entry mining concept, which would eliminate the need for any human presence on the mine site. Nevertheless, the current state of robotics and automation technology does not yet meet the requirements for the implementation of fully autonomous operations in mines. Autonomous mining equipment continues to operate under the supervision of humans, and a considerable number of mining equipment has not yet been automated. This indicates the necessity of identifying novel strategies to increase the safety of mining operations through the utilization of robotics and automation technologies. One potential solution to address this challenge is to increase the involvement of humans in autonomous mining operations. This could entail integrating human decision-makers into the decision-making loops of autonomous mining equipment. To this end, we propose the paradigm of autonomous collaborative mining, wherein humans and autonomous machines work together in a collaborative manner to increase the safety and efficiency of mining operations. We analyze the enabling factors required to implement this paradigm and present the case of autonomous loading using LHDs based on the autonomous collaborative mining paradigm. Full article

The applications of machine learning in wireless and mobile communication net-works have been receiving increasing attention, especially in the new era of big data and the Internet of Things (IoT), where data mining and data analysis technologies are effective approaches to solving wireless system issues [...] Full article

Unmanned Aerial Vehicles (UAVs) are integral to the development of smart city infrastructures, enabling essential services such as real-time surveillance, urban traffic regulation, and cooperative environmental monitoring. UAV-to-UAV communication networks, despite their adaptability, have significant limits stemming from onboard battery constraints, inclement weather, and variable flight trajectories. This work presents a thorough examination of energy and spectral efficiency in UAV-to-UAV communication over four frequency bands: 2.4 GHz, 5.8 GHz, 28 GHz, and 60 GHz. Our MATLAB R2023a simulations include classical free-space path loss, Rayleigh/Rician fading, and real-time mobility profiles, accommodating varied heights (up to 500 m), flight velocities (reaching 15 m/s), and fluctuations in the path loss exponent. Low-frequency bands (e.g., 2.4 GHz) exhibit up to 50% reduced path loss compared to higher mmWave bands for distances exceeding several hundred meters. Energy efficiency (${\eta }_e$) is evaluated by contrasting throughput with total power consumption, indicating that 2.4 GHz initiates at around 0.15 bits/Joule (decreasing to 0.02 bits/Joule after 10 s), whereas 28 GHz and 60 GHz demonstrate markedly worse ${\eta }_e$ (as low as ${10}^{-3}$–${10}^{-4}\mathrm{bits}/\mathrm{Joule}$), resulting from increased path loss and oxygen absorption. Similarly, sub-6 GHz spectral efficiency can attain $4\times {10}^{-12}\mathrm{bps}/\mathrm{Hz}$ in near-line-of-sight scenarios, whereas 60 GHz lines encounter significant attenuation at distances above 200–300 m without sophisticated beamforming techniques. Polynomial-fitting methods indicate that the projected ${\eta }_e$ diverges from actual performance by less than 5% after 10 s of flight, highlighting the feasibility of machine-learning-based techniques for real-time power regulation, beam steering, or multi-band switching. While mmWave UAV communication can provide significant capacity enhancements (100–500 MHz bandwidth), energy efficiency deteriorates markedly without meticulous flight planning or adaptive protocols. We thus advocate using multi-band radios, adaptive modulation, and trajectory optimisation to equilibrate power consumption, ensure connection stability, and meet high data-rate requirements in densely populated, dynamic urban settings. Full article

In the field of sustainable mobility, this study highlights the importance of using machine learning for predictive modeling based on real traffic data collected from instrumented bicycles. The advent of advanced technologies like sustainable mobility apps, sensors, and advanced data analysis methods led to the ability to collect data from various sources, which enabled researchers to estimate battery state of charge (SOC) accurately. Most current research uses them in the lab experiments for data collection. In this work, we use real-time sensors data to construct data-driven models for lithium-ion battery SOC estimation. This research integrates both electric bicycle battery, environmental and route variables to achieve the following goals: (1) Collect a multimodal data set including operational, topography, vehicle, and external variables, (2) Preprocess data obtained from sensors installed on the electric bicycle battery, (3) Create models of lithium-ion battery SOC based on electric bicycle battery and environmental variables, and (4) Assess data-driven models and compare their performance for lithium-ion battery SOC with high accuracy. To achieve that, we conducted a real study to predict the Remaining Useful Life (RUL), as a measure of state of charge, of electric bicycle battery. The study was carried out on a 15 km cycle route in Medellín, Colombia, for 28 days. To estimate the RUL, we used four different machine learning algorithms: Long Short-Term Memory (LSTM), Support Vector Regression (SVR), AdaBoost, and Gradient Boost. Notably, data preprocessing techniques played a pivotal role, with a particular focus on smoothing sensor data using Convolutional Neural Networks (CNN). The results showed a significant improvement in prediction accuracy when using data preprocessing, confirming its importance in improving model performance. Furthermore, the comparison of network performance facilitated the selection of the most effective model for the test data. This study underscores the value of using real-world data to develop and validate predictive models in the pursuit of sustainable mobility solutions, and highlights the critical role of data-driven methodologies in addressing today’s urban transportation challenges. Full article

Restoring strength, function, and mobility following an illness, accident, or surgery is the primary goal of upper arm rehabilitation. Exoskeletons offer adaptable support, enhancing patient engagement and accelerating recovery. This work proposes an adjustable, wearable robotic exoskeleton powered by electromyography (EMG) data for upper arm rehabilitation. Three activation levels—low, medium, and high—were applied to the EMG data to forecast the Pulse Width Modulation (PWM) based on the range of motion (ROM) angle. Conventional machine learning (ML) models, including K-Nearest Neighbor Regression (K-NNR), Support Vector Regression (SVR), and Random Forest Regression (RFR), were compared with neural network approaches, including Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) to determine the best ML model for the ROM angle prediction. The LSTM model emerged as the best predictor with a high accuracy of 0.96. The system achieved 0.89 accuracy in exoskeleton control and 0.85 accuracy in signal categorization. Additionally, the proposed exoskeleton demonstrated a 0.97 performance in ROM correction compared to conventional methods (p = 0.097). These findings highlight the potential of EMG-based, LSTM-enabled exoskeleton systems to deliver accurate and adaptive upper arm rehabilitation, particularly for senior citizens, by providing personalized and effective support. Full article