Search Results (5,274)

Remaining Useful Life (RUL) prediction for aeroengines represents a core challenge in Prognostics and Health Management (PHM), with significant implications for condition-based maintenance, operational cost reduction, and flight safety enhancement. Current deep learning-based approaches encounter three major limitations when handling multi-source sensor data: conventional convolution operations struggle to model heterogeneous sensor feature distributions, leading to computational redundancy; simplistic multimodal fusion strategies often induce semantic conflicts; and high model complexity hinders industrial deployment. To address these issues, this paper proposes a novel Partial Convolution Attention-enhanced CNN-LSTM Network (PALC-Net). We introduce a partial convolution mechanism that applies convolution to only half of the input channels while preserving identity mappings for the remainder. This design retains representational power while substantially lowering computational overhead. A dual-branch feature extraction architecture is developed: the temporal branch employs a PConv-CNN-LSTM architecture to capture spatio-temporal dependencies, while the statistical branch utilizes multi-scale sliding windows to extract physical degradation indicators—such as mean, standard deviation, and trend. Additionally, an adaptive fusion module based on cross-attention is designed, where heterogeneous features are projected into a unified semantic space via Query-Key-Value mappings. A sigmoid gating mechanism is incorporated to enable dynamic weight allocation, effectively mitigating inter-modal conflicts. Extensive experiments on the NASA C-MAPSS dataset demonstrate that PALC-Net achieves state-of-the-art performance across all four subsets. Notably, on the FD003 subset, it attains an MAE of 7.70 and an R² of 0.9147, significantly outperforming existing baselines. Ablation studies validate the effectiveness and synergistic contributions of the partial convolution, attention mechanism, and multimodal fusion modules. This work offers an accurate and efficient solution for aeroengine RUL prediction, achieving an effective balance between engineering practicality and algorithmic sophistication. Full article

To address the challenges of improving energy balance and extending the operational lifetime of wireless sensor networks for Automated Railway Track Fastener Maintenance Robots (ARTFMR) along railways, this paper proposes an enhanced LEACH protocol incorporating Particle Swarm Optimization (PSO). Initially, network nodes are deployed, and their energy consumption is calculated to formulate a non-uniform deployment model aimed at improving energy balance, followed by network clustering. Subsequently, a routing protocol is designed, where the cluster head election mechanism integrates two critical factors—dynamic residual energy and distance to the base station—to facilitate dynamic and distributed cluster head rotation. During the communication phase, a Time Division Multiple Access (TDMA) scheduling mechanism is employed in conjunction with an inter-cluster multi-hop routing scheme. Additionally, a joint data-volume and energy optimization strategy is implemented to dynamically adjust the transmission data volume based on the residual energy of each node. Finally, simulations were conducted using MATLAB, and the results indicate that the proposed energy-balanced non-uniform deployment optimization strategy improves network energy utilization, effectively extends network lifetime, and exhibits favorable scalability. Full article

Marine robots operating in low illumination and turbid waters require reliable measurement and control for surveying, inspection, and monitoring. This paper present a sensor-centric visual–inertial simultaneous localization and mapping (SLAM) pipeline that combines low-light enhancement, learned feature matching, and NeRF-based dense reconstruction to provide stable navigation states. A lightweight encoder–decoder with global attention improves signal-to-noise ratio and contrast while preserving feature geometry. SuperPoint and LightGlue deliver robust correspondences under severe visual degradation. Visual and inertial data are tightly fused through IMU pre-integration and nonlinear optimization, producing steady pose estimates that sustain downstream guidance and trajectory planning. An accelerated NeRF converts monocular sequences into dense, photorealistic reconstructions that complement sparse SLAM maps and support survey-grade measurement products. Experiments on AQUALOC sequences demonstrate improved localization stability and higher-fidelity reconstructions at competitive runtime, showing robustness to low illumination and turbidity. The results indicate an effective engineering pathway that integrates underwater image enhancement, multi-sensor fusion, and neural scene representations to improve navigation reliability and mission effectiveness in realistic marine environments. Full article

Receiver-initiated MAC protocols, such as the IEEE 802.15.4e RIT scheme, are promising for energy-efficient communication in multi-hop wireless sensor networks. However, their practical use requires a better understanding of how multiple contention-avoidance mechanisms interact under realistic network conditions. This study develops an ns-3 implementation of an RIT-compliant receiver-initiated MAC protocol together with a flexible evaluation framework that enables selective activation of representative enhancement strategies, including carrier-sensing options for data and beacon transmissions and randomization of beacon intervals. Four realistic network scenarios were designed to simulate practical deployment settings. Simulation results revealed that the effectiveness of these enhancement strategies varied significantly depending on network load and topology. In particular, beacon interval randomization, although often assumed to improve robustness, was found to degrade performance under low-load conditions, indicating that even widely adopted mechanisms may behave differently depending on operational environments. Conversely, CSMA-based approaches provided consistent improvements in transmission reliability. These observations highlight the importance of considering environmental factors and parameter configurations when enabling enhancement mechanisms. Overall, the proposed platform provides a reproducible and unified environment for fair comparison of receiver-initiated MAC protocols and their optional mechanisms, offering practical insights for selecting appropriate configurations in real sensor network deployments. Full article

Intelligent driving cabins operated by artificial intelligence technology are evolving into the third living space. They aim to integrate perception, analysis, decision making, and intervention. By using multimodal biosignal acquisition technologies (flexible sensors and non-contact sensing), it is possible to monitor the physiological indicators of heart rate and blood pressure in real time. Leveraging the benefits of domain controllers in the vehicle and edge computing helps the AI platform reduce data latency and enhance real-time processing capabilities, as well as integrate the cabin’s internal and external data through machine learning. Its aim is to build tailored health baselines and high-precision risk prediction models (e.g., CNN, LSTM). This system can initiate multi-level interventions such as adjustments to the environment, health recommendations, and ADAS-assisted emergency parking with telemedicine help. Current issues consist of sensor precision, AI model interpretation, security of data privacy, and whom to attribute legal liability to. Future development will mainly focus on cognitive digital twin construction, L4/L5 autonomous driving integration, new biomedical sensor applications, and smart city medical ecosystems. Full article

RFID (Radio Frequency Identification) technology has become an essential instrument in numerous industrial sectors, enhancing process efficiency and streamlining operations, allowing for the automated tracking of goods and equipment without the need for manual intervention. Nevertheless, the deployment of industrial IoT systems necessitates the establishment of complex sensor networks to enable detailed multi-parameter monitoring of items. Despite these advancements, challenges remain in item-level sensing, data analysis, and the management of power consumption. To mitigate these shortcomings, this study presents a holistic AI-assisted, semi-passive RFID-integrated multi-sensor system designed for robust food quality monitoring. The primary contributions are threefold: First, a compact (45 mm ∗ 38 mm) semi-passive UHF RFID tag is developed, featuring a rechargeable lithium battery to ensure long-term operation and extend the readable range up to 10 m. Second, a dedicated IoT cloud platform is implemented to handle big data storage and visualization, ensuring reliable data management. Third, the system integrates machine learning algorithms (LSTM) to analyze sensing data for real-time food quality assessment. The system’s efficacy is validated through real-world experiments on food products, demonstrating its capability for low-cost, long-distance, and intelligent quality control. This technology enables low-cost, timely, and sustainable quality assessments over medium and long distances, with battery life extending up to 27 days under specific conditions. By deploying this technology, quantified food quality assessment and control can be achieved. Full article

Air pollution from ship operations can pose a significant challenge for coastal cities, particularly where ports are closely integrated into the urban fabric. This study examines the influence of ship docking on PM_2.5 concentrations in Chios, Greece, a medium size island city where the port directly borders densely populated neighbourhoods. Calibrated PurpleAir sensors were installed at urban and suburban sites to measure PM_2.5, with data analysed alongside ship call records and meteorological observations. An event-based concentration enhancement metric (%ΔC) was estimated to compare PM_2.5 during docking with the preceding 3 h background for 170 ship arrivals in February and August 2022. The results showed that under prevailing northerly winds in August, PM_2.5 at the downwind urban site increased on average by 5.0 µg m⁻³ (48%), whereas winter increments were smaller (6.1%) due to higher background variability. When both seasons and all wind directions were pooled, the urban site exhibited a mean enhancement of 1.7 µg m⁻³ (19%), while impacts at the suburban site remained minor (3%). Median-based uncertainty analysis confirmed robust enhancements under northerly winds only. Wind direction and wind speed were the primary controls on %ΔC, whereas ship engine power and time at berth had limited influence. The results suggest that ship-related PM_2.5 impacts are detectable but remain spatially and temporally limited in coastal urban environments, including medium-sized islands characterised by relatively low shipping activity. Full article

Accurate prediction of the performance of an internal combustion engine is an essential step towards achieving efficiency and complying with emission standards. This study presents an artificial neural network (ANN) model that uses sensor-derived parameters, such as design power, wheel power, torque, and rotational speed, to predict engine load. Data were collected from a dynamometer and a hardware-in-the-loop (HiL) setup to ensure realistic, sensor-based measurements. The proposed ANN architecture achieved high accuracy (99%) in multiclass classification and strong regression performance ($R^2\approx 0.98$), demonstrating its ability to model complex engine load relationships under normal operating conditions. Performance was validated using 5-fold stratified cross-validation, achieving an average accuracy of $0.988\pm 0.011$, macro-F1 of $0.984\pm 0.011$, and regression $R^2$ of $0.962\pm 0.052$, confirming strong generalization and robustness. The model can be extended to include additional sensor inputs and adapted for use with other powertrain systems, allowing it to be used in a range of automotive and industrial applications. Full article

This study critically examines the technological feasibility, regulatory challenges, and societal acceptance of Pilotless Passenger Aircraft (PPAs) in commercial aviation. A mixed-methods design integrated quantitative passenger surveys (n = 312) and qualitative pilot interviews (n = 15), analyzed using SPSS and NVivo to capture both statistical and thematic perspectives. Results show moderate public awareness (58%) but limited willingness to fly (23%), driven by safety (72%), cybersecurity (64%), and human judgement (60%) concerns. Among pilots, 93% agreed automation improves safety, yet 80% opposed removing human pilots entirely, underscoring reliance on human adaptability in emergencies. Both groups identified regulatory assurance, demonstrable reliability, and human oversight as prerequisites for acceptance. Technologically, this paper synthesizes advances in AI-driven flight management, multi-sensor navigation, and high-integrity control systems, including Airbus’s ATTOL and NASA’s ICAROUS, demonstrating that pilotless flight is technically viable but has yet to achieve the airline-grade reliability target of 10⁻⁹ failures per flight hour. Regulatory analysis of FAA, EASA, and ICAO frameworks reveals maturing but fragmented approaches to certifying learning-enabled systems. Ethical and economic evaluations indicate unresolved accountability, job displacement, and liability issues, with potential 10–15% operational cost savings offset by certification, cybersecurity, and infrastructure expenditures. Integrated findings confirm that PPAs represent a socio-technical challenge rather than a purely engineering problem. This study recommends a phased implementation roadmap: (1) initial deployment in cargo and low-risk missions to accumulate safety data; (2) hybrid human–AI flight models combining automation with continuous human supervision; and (3) harmonized international certification standards enabling eventual passenger operations. Policy implications emphasize explainable-AI integration, workforce reskilling, and transparent public engagement to bridge the trust gap. This study concludes that pilotless aviation will not eliminate the human element but redefine it, achieving autonomy through partnership between human judgement and machine precision to sustain aviation’s uncompromising safety culture. Full article

This research presents a study on enhancing the localization and orientation accuracy of indoor Autonomous Guided Vehicles (AGVs) operating under a centralized, camera-based control system. We investigate and compare the performance of two Extended Kalman Filter (EKF) configurations: a standard EKF and a novel Blended EKF. The research methodology comprises four primary stages: (1) Sensor bias correction for the camera (CAM), Dead Reckoning, and Inertial Measurement Unit (IMU) to improve raw data quality; (2) Calculation of sensor weights using the Inverse-Variance Weighting principle, which assigns higher confidence to sensors with lower variance; (3) Multi-sensor data fusion to generate a stable state estimation that closely approximates the ground truth (GT); and (4) A comparative performance evaluation between the standard EKF, which processes sensor updates independently, and the Blended EKF, which fuses CAM and DR (Dead Reckoning) measurements prior to the filter’s update step. Experimental results demonstrate that the implementation of bias correction and inverse-variance weighting significantly reduces the Root Mean Square Error (RMSE) across all sensors. Furthermore, the Blended EKF not only achieved a lower RMSE in certain scenarios but also produced smooth trajectories similar to or less than the standard EKF in some weightings. These findings indicate the significant potential of the proposed approach in developing more accurate and robust navigation systems for AGVs in complex indoor environments. Full article

Turbocharged diesel engines are widely used for the propulsion and as the generators for powering auxiliary systems in marine applications. Many works were published on the development of diagnosis tools for the engines using data from simulation models or from experiments on a sophisticated engine test bench. However, the simulation data varies a lot with actual operational data, and the available sensor data on the actual vessel is much less compared to the data from test benches. Therefore, it is necessary to develop anomaly prediction and fault diagnosis models from limited data available from the engines. In this paper, an artificial intelligence (AI)-based anomaly detection model and machine learning (ML)-based fault diagnosis model were developed using the actual data acquired from a diesel engine of a cargo vessel. Unlike the previous works, the study uses operational, thermodynamic, and vibration data for the anomaly detection and fault diagnosis. The paper provides the overall architecture of the proposed predictive maintenance system including details on the sensorization of assets, data acquisition, edge computation, and AI model for anomaly prediction and ML algorithm for fault diagnosis. Faults with varying severity levels were induced in the subcomponents of the engine to validate the accuracy of the anomaly detection and fault diagnosis models. The unsupervised stacked autoencoder AI model predicts the engine anomalies with 87.6% accuracy. The balanced accuracy of supervised fault diagnosis model using Support Vector Machine algorithm is 99.7%. The proposed models are vital in marching towards sustainable shipping and have potential to deploy across various applications. Full article

This study details the design, fabrication, and experimental validation of a wearable, non-invasive microwave sensor for continuous blood glucose monitoring. It incorporates a crescent-loaded elliptical patch antenna with a complementary split-ring resonator (CSRR) tag unit to greatly improve sensing sensitivity. The sensor operates across multiple resonant frequencies, enabling broadband dielectric characterization of glucose-dependent blood permittivity. Incorporation of the CSRR tag unit leads to a marked improvement in electromagnetic coupling and field confinement, resulting in a substantial increase in sensitivity, achieving 1.14 MHz/mg/dL in resonant frequency shift and 0.015 dB/mg/dL in reflection coefficient sensitivity compared to conventional designs. The sensor was fabricated on an FR-4 substrate and experimentally characterized using a vector network analyzer (VNA), showing strong agreement between simulated and measured S11 responses, with minimal frequency deviations and consistent resonance behavior. Experimental results confirmed improved sensitivity in response to glucose concentration variations over the range of 0–500 mg/dL, validating the sensor’s performance under realistic conditions. Furthermore, a physics-informed deep learning (PI-DL) model was developed to predict glucose concentration directly from measured S11 data. The model achieved enhanced prediction accuracy, with a mean absolute error below 1 mg/dL and a strong generalization across unseen samples, demonstrating the power of combining physical modeling with data-driven approaches. These results confirm that the proposed sensor, enhanced with the CSRR tag unit and supported by a PI-DL framework, offers a promising pathway toward next-generation non-invasive, accurate, and wearable glucose monitoring solutions. Full article

The rapid evolution of modern vehicles into intelligent and interconnected systems presents new complexities in both functional safety and cybersecurity. In this context, ensuring the reliability and integrity of critical sensor data, such as wheel speed inputs for anti-lock brake systems (ABS), is essential. Effective detection of wheel speed sensor faults not only improves functional safety, but also plays a vital role in keeping system resilience against potential cyber–physical threats. Although data-driven approaches have gained popularity for system development due to their ability to extract meaningful patterns from historical data, a major limitation is the lack of diverse and representative faulty datasets. This study proposes a novel dual learning model, based on Temporal Convolutional Networks (TCN), designed to accurately distinguish between normal and faulty wheel speed sensor behavior within a hardware-in-the-loop (HIL) simulation platform implemented on an FPGA. To address dataset limitations, a TruckSim–MATLAB/Simulink co-simulation environment is used to generate realistic datasets under normal operation and eight representative fault scenarios, yielding up to 5000 labeled sequences (balanced between normal and faulty behaviors) at a sampling rate of 60 Hz. Two TCN models are trained independently to learn normal and faulty dynamics, and fault decisions are made by comparing the reconstruction errors (MSE and MAE) of both models, thus avoiding manually tuned thresholds. On a test set of 1000 sequences (500 normal and 500 faulty) from the 5000 sample configuration, the proposed dual TCN framework achieves a detection accuracy of 97.8%, a precision of 96.5%, a recall of 98.2%, and an F1-score of 97.3%, outperforming a single TCN baseline, which achieves 91.4% accuracy and an 88.9% F1-score. The complete dual TCN architecture is implemented on a Xilinx ZCU102 FPGA evaluation kit (AMD, Santa Clara, CA, USA), while supporting real-time inference in the HIL loop. These results demonstrate that the proposed approach provides accurate, low-latency fault detection suitable for safety-critical ABS applications and contributes to improving both functional safety and cyber-resilience of braking systems. Full article

Accumulation of salts in irrigated soils can be detrimental not only to growing crops but also to groundwater quality. Soil salinity should be regularly monitored, and appropriate irrigation at the required leaching rate should be applied to prevent excessive salt accumulation in the root zone, thereby improving soil fertility and crop production. We combined two frequency domain electromagnetic induction (FD-EMI) mono-channel sensors (EM31 and EM38) and operated them at different heights and with different coil orientations to monitor the vertical distribution of soil salinity in a salt-affected irrigated area in Kairouan (central Tunisia). Multiple measurement heights and coil orientations were used to enhance depth sensitivity and thereby improve salinity predictions from this type of proximal sensor. The resulting multi-configuration FD-EMI datasets were used to derive soil salinity information via inverse modeling with a recently developed in-house laterally constrained inversion (LCI) approach. The collected apparent electrical conductivity (ECa) data were inverted to predict the spatial and temporal distribution of soil salinity. The results highlight several findings about the distribution of salinity in relation to different irrigation systems using brackish water, both in the short and long term. The expected transfer of salinity from the surface to deeper layers was systematically observed by our FD-EMI surveys. However, the intensity and spatial distribution of soil salinity varied between different crops, depending on the frequency and amount of drip or sprinkler irrigation. Furthermore, our results show that vertical salinity transfer is also influenced by the wet or dry season. The study provides insights into the effectiveness of combining two different FD-EMI sensors, EM31 and EM38, for monitoring soil salinity in agricultural areas, thereby contributing to the sustainability of irrigated agricultural production. The inversion approach provides a more detailed representation of soil salinity distribution across spatial and temporal scales at different depths, and across irrigation systems, compared to the classical method based on soil samples and laboratory analysis, which is a point-scale measurement. It provides a more extensive assessment of soil conditions at depths up to 4 m with different irrigation systems. For example, the influence of local drip irrigation was imaged, and the history of a non-irrigated plot was evaluated, confirming the potential of this method. Full article

Traditionally, sea fog detection technologies have relied primarily on in situ observations. However, point-based observations suffer from limitations in extensive monitoring in marine environments due to the scarcity of observation stations and the limited nature of measurement data. Satellites effectively address these issues by covering vast areas and operating across multiple spectral channels, enabling precise detection and monitoring of sea fog. Despite the increasing adoption of deep learning in this field, achieving further improvements in accuracy and reliability necessitates the simultaneous use of multiple satellite datasets rather than relying on a single source. Therefore, this study aims to achieve higher accuracy and reliability in sea fog detection by employing a deep learning-based advanced co-registration technique for multi-satellite image fusion and autotuning-based optimization of State-of-the-Art (SOTA) semantic segmentation models. We utilized data from the Advanced Meteorological Imager (AMI) sensor on the Geostationary Korea Multi-Purpose Satellite 2A (GK2A) and the GOCI-II sensor on the Geostationary Korea Multi-Purpose Satellite 2B (GK2B). Swin Transformer, Mask2Former, and SegNeXt all demonstrated balanced and excellent performance across overall metrics such as IoU and F1-score. Specifically, Swin Transformer achieved an IoU of 77.24 and an F1-score of 87.16. Notably, multi-satellite fusion significantly improved the Recall score compared to the single AMI product, increasing from 88.78 to 92.01, thereby effectively mitigating the omission of disaster information. Ultimately, comparisons with the officially operational GK2A AMI Fog and GK2B GOCI-II Marine Fog (MF) products revealed that our deep learning approach was superior to both existing operational products. Full article