Search Results (286)

Early train detection is vital for ensuring the safety of railway personnel, particularly in remote locations where fixed signaling infrastructure is unavailable. Unlike many existing solutions that rely on high-power, high-cost sensors and compute platforms, this work presents a lightweight, low-cost, and portable framework designed to run entirely on resource-constrained microcontrollers with just kilobytes of Random Access Memory (RAM). The proposed system uses vibration data from low-cost accelerometers and employs a simple yet effective Linear Regression (LR) model for almost real-time prediction of train arrival times. To ensure feasibility on low-end hardware, a parallel-processing framework is introduced, enabling continuous data collection, Machine Learning (ML) inference, and wireless communication with strict timing and energy constraints. The decision-making process, including data preprocessing and ML prediction, completes in under 10 ms, and alerts are transmitted via LoRa, enabling kilometer-range communication. Field tests on active railway lines confirm that the system detects approaching trains 15 s in advance with no false negatives and a small number of explainable false positives. Power characterization demonstrates that the system can operate for more than 6 days on a 10 Ah battery, with potential for months of operation using wake-on-vibration modes. Full article

The rapid growth of the Internet of Things (IoT) has driven the need for ultra-low-power wireless communication systems. Wake-up receivers (WuRXs) have emerged as a key technology to enable energy-efficient, near-always-on operation for IoT devices. This review explores the state of the art in WuRXs design, focusing on low-power architectures, key trade-offs, and recent advancements. We discuss the challenges in achieving low power consumption while maintaining sensitivity, power consumption, and interference resilience. The review highlights the evolution from radio frequency (RF) envelope detection architectures to more complex heterodyne and subthreshold designs and concludes with future directions for WuRXs research. Full article

Background/Objectives: Breakfast skipping has been associated with a wide range of adverse health outcomes, including metabolic disorders, disrupted circadian rhythm, and impairments of memory and attention in adolescents and adults. Although partial associations between sleep and breakfast behaviors have been reported, few studies have examined multi-dimensional sleep health simultaneously in relation to breakfast skipping, especially comprehensive studies systematically examining this relationship, particularly under controlled social conditions, remain insufficient. Methods: We here demonstrate the association between sleep health and breakfast skipping among 2969 Japanese high school students. Participants provided between one and eight days of sleep diary data, including meal timing records; most (78.1%) completed all eight days, while the remainder contributed fewer days. Additionally, the Pittsburgh Sleep Quality Index (PSQI) was used to assess sleep quality, and the Pediatric Daytime Sleepiness Scale (PDSS) was used to evaluate daytime sleepiness. Results: Later wake-up times, lower sleep quality, and stronger daytime sleepiness were each associated with a higher likelihood of breakfast skipping. In additional analyses, no significant pairwise interactions were detected among wake-up time, PSQI, and PDSS, suggesting that these factors may be separately associated with breakfast skipping. Conclusions: These findings suggest that multi-dimensional sleep health, including wake-up time, sleep quality, and daytime sleepiness, is relevant to breakfast skipping. This study offers a novel contribution by linking multiple downstream indicators influenced by sleep health to breakfast behavior. Full article

The wire tightener is a critical tool in the construction and maintenance of power lines. Failure to detect tension overload in a timely manner may lead to plastic deformation or even breakage of the tool, potentially causing serious safety accidents. To address this issue, a force monitoring sensor was developed to track the real-time load on wire tighteners. In terms of hardware design, a foil strain gauge was integrated with an ultra-low-power mixed-signal microcontroller based on the mechanical characteristics of the wire tightener, enabling accurate acquisition and processing of load data. Low-power LoRa technology was employed for wireless data transmission, and an adaptive sleep–wake strategy was implemented to optimize power efficiency during data collection. The sensor’s material, geometry, and structure were tailored to the tool’s composition and working environment. Experimental results showed that the average relative error between the sensor readings and the reference values was less than 0.5%. The sensor has been successfully deployed in practical engineering applications, consuming approximately 4500 mWh over an 8 h continuous monitoring period. Full article

Hands-free computer interaction is a key topic in assistive technology, with camera-based and voice-based systems being the most common methods. Recent camera-based solutions leverage facial expressions or head movements to simulate mouse clicks or key presses, while voice-based systems enable control via speech commands, wake-word detection, and vocal gestures. However, existing systems often suffer from limitations in responsiveness and accuracy, especially under real-world conditions. In this paper, we present 3-Modal Human-Computer Interaction (3M-HCI), a novel interaction system that dynamically integrates facial, vocal, and eye-based inputs through a new signal processing pipeline and a cross-modal coordination mechanism. This approach not only enhances recognition accuracy but also reduces interaction latency. Experimental results demonstrate that 3M-HCI outperforms several recent hands-free interaction solutions in both speed and precision, highlighting its potential as a robust assistive interface. Full article

In addition to characteristic and easily identifiable behavioural signs—namely epileptic seizures—electroencephalography (EEG) has long been a standard component of epilepsy diagnosis protocols. In veterinary practice, EEG is typically performed in a semi-invasive manner, using subcutaneous electrodes and sedation. Here, we propose that the non-invasive polysomnography protocol, originally developed for basic research, can serve as a more welfare-friendly yet informative alternative for assessing epileptic brain activity in dogs. In this study, N = 11 family dogs diagnosed with epilepsy underwent a single non-invasive polysomnography session. EEG-based evidence for epileptic activity was detected in two cases. Polysomnography data from these 11 epileptic dogs were further analysed to evaluate sleep structure parameters. Compared to a matched control group of N = 11 clinically healthy dogs, the epileptic group exhibited reduced sleep efficiency, increased sleep latency, more wakings after sleep onset, and less time spent in drowsiness and non-REM sleep. These findings support the potential utility of non-invasive brain monitoring techniques, such as polysomnography, in the diagnosis and management of epilepsy in veterinary medicine. Full article

Sleep is a vital physiological process for recovery and health. In people with knee osteoarthritis (OA), disrupted sleep is common and linked to worse clinical outcomes. Commercial sleep trackers provide an accessible option to monitor sleep in this population, but their accuracy for detecting sleep, wake, and sleep stages remains uncertain. This study compared nighttime sleep data from polysomnography (PSG) and Fitbit Sense in individuals with knee OA and insomnia. Data were collected from 53 participants (60.4% women, mean age 51 ± 8.2 years) over 62 nights using simultaneous PSG and Fitbit recording. Fitbit Sense showed high accuracy (85.76%) and sensitivity (95.95%) for detecting sleep but lower specificity (50.96%), indicating difficulty separating quiet wakefulness from sleep. Agreement with PSG was higher on nights with longer total sleep time, higher sleep efficiency, shorter sleep onset, and fewer awakenings, suggesting better performance when sleep is less fragmented. The device showed limited precision in classifying sleep stages, often misclassifying deep and REM sleep as light sleep. Despite these issues, Fitbit Sense may serve as a useful complementary tool for monitoring sleep duration, timing, and regularity in this population. However, sleep stage and fragmentation data should be interpreted cautiously in both clinical and research settings. Full article

Given the harsh working conditions of underwater pan-tilt systems, their energy consumption management is particularly crucial. This study proposes an underwater pan-tilt operation method with an automatic wake-up mechanism, which activates only upon target detection, replacing conventional timer-based triggering. Furthermore, departing from fixed-duration observation strategies, we introduce a Q-learning algorithm to optimize operational modes. The algorithm dynamically adjusts working modes based on surrounding biological activity frequency: employing a low-power mode (reduced energy consumption with lower monitoring intensity) during periods of sparse biological presence and switching to a high-performance mode (extended observation duration, higher energy consumption, and enhanced monitoring intensity) during frequent biological activity. Simulation results demonstrate that compared to fixed-duration observation schemes, the proposed optimization strategy achieves a 11.11% improvement in monitoring effectiveness while achieving 16.21% energy savings. Full article

In the wake of the continuous development of the international strategic petroleum reserve system, the tonnage and quantity of oil tankers have been increasing. This trend has driven the expansion of offshore oil exploration and transportation, resulting in frequent incidents of ship oil spills. Catastrophic impacts have been exerted on the marine environment by these accidents, posing a serious threat to economic development and ecological security. Therefore, there is an urgent need for efficient and reliable methods to detect oil spills in a timely manner and minimize potential losses as much as possible. In response to this challenge, a marine radar oil film segmentation method based on feature fusion and the artificial bee colony (ABC) algorithm is proposed in this study. Initially, the raw experimental data are preprocessed to obtain denoised radar images. Subsequently, grayscale adjustment and local contrast enhancement operations are carried out on the denoised images. Next, the gray level co-occurrence matrix (GLCM) features and Tamura features are extracted from the locally contrast-enhanced images. Then, the generalized least squares (GLS) method is employed to fuse the extracted texture features, yielding a new feature fusion map. Afterwards, the optimal processing threshold is determined to obtain effective wave regions by using the bimodal graph direct method. Finally, the ABC algorithm is utilized to segment the oil films. This method can provide data support for oil spill detection in marine radar images. Full article

Investigating the coupled hydrodynamic and thermal wakes induced by underwater vehicles is vital for non-acoustic detection and environmental monitoring. Here, the standard SUBOFF model is simulated under eight operating conditions—speeds of 10, 15, and 20 kn; depths of 10, 20, and 30 m; and both with and without thermal discharge—using Delayed Detached Eddy Simulation (DDES) coupled with the Volume of Fluid (VOF) method. Results indicate that, under heat emission conditions, higher speeds accelerate wake temperature decay, making the thermal wake difficult to detect downstream; without heat emission, turbulent mixing dominates the temperature field, and speed effects are minor. With increased speed, wake vorticity at a fixed location grows by about 30%, free-surface wave height rises from 0.05 to 0.15 m, and wavelength remains around 1.8 m, all positively correlated with speed. Dive depth is negatively correlated with wave height, decreasing from 0.15 to 0.04 m as depth increases from 5 to 20 m, while wavelength remains largely unchanged. At a 10 m submergence depth, the thermal wake is clearly detectable on the surface but becomes hard to detect beyond 20 m, indicating a pronounced depth effect on its visibility. These results not only confirm the positive correlation between vessel speed and wake vorticity reported in earlier studies but also extend those findings by providing the first quantitative evaluation of how submergence depth critically limits thermal wake visibility beyond 20 m. This research provides quantitative evaluations of wake characteristics under varying speeds, depths, and heat emissions, offering valuable insights for stealth navigation and detection technologies. Full article

Wind farm performance monitoring has traditionally relied on deterministic models, such as power curves or machine learning approaches, which often fail to account for farm-wide behavior and the uncertainty quantification necessary for the reliable detection of underperformance. To overcome these limitations, we propose a probabilistic methodology for turbine-level active power prediction and uncertainty estimation using high-frequency SCADA data and farm-wide autoregressive information. The method leverages a Stochastic Variational Gaussian Process with a Linear Model of Coregionalization, incorporating physical models like manufacturer power curves as mean functions and enabling flexible modeling of active power and its associated variance. The approach was validated on a wind farm in the Belgian North Sea comprising over 40 turbines, using only 15 days of data for training. The results demonstrate that the proposed method improves predictive accuracy over the manufacturer’s power curve, achieving a reduction in error measurements of around 1%. Improvements of around 5% were seen in dominant wind directions (200°–300°) using 2 and 3 Latent GPs, with similar improvements observed on the test set. The model also successfully reconstructs wake effects, with Energy Ratio estimates closely matching SCADA-derived values, and provides meaningful uncertainty estimates and posterior turbine correlations. These results demonstrate that the methodology enables interpretable, data-efficient, and uncertainty-aware turbine-level power predictions, suitable for advanced wind farm monitoring and control applications, enabling a more sensitive underperformance detection. Full article

Sleep position recognition plays a crucial role in diagnosing and managing various health conditions, such as sleep apnea, pressure ulcers, and musculoskeletal disorders. Accurate monitoring of body posture during sleep can provide valuable insights for clinicians and support the development of intelligent healthcare systems. This research presents a comparative analysis of sleep position recognition using two distinct approaches: image-based deep learning and accelerometer-based classification. There are five classes: prone, supine, right side, left side, and wake up. For the image-based method, the Visual Geometry Group 16 (VGG16) convolutional neural network was fine-tuned with data augmentation strategies including rotation, reflection, scaling, and translation to enhance model generalization. The image-based model achieved an overall accuracy of 93.49%, with perfect precision and recall for “right side” and “wakeup” positions, but slightly lower performance for “left side” and “supine” classes. In contrast, the accelerometer-based method employed a feedforward neural network trained on features extracted from segmented accelerometer data, such as signal sum, standard deviation, maximum, and spike count. This method yielded superior performance, reaching an accuracy exceeding 99.8% across most sleep positions. The “wake up” position was particularly easy to detect due to the absence of body movements such as heartbeat or respiration when the person is no longer in bed. The results demonstrate that while image-based models are effective, accelerometer-based classification offers higher precision and robustness, particularly in real-time and privacy-sensitive scenarios. Further comparisons of the system characteristics, data size, and training time are also carried out to offer crucial insights for selecting the appropriate technology in clinical, in-home, or embedded healthcare monitoring applications. Full article

Introduction: The monitoring of autonomic nervous balance during childhood remains underexplored. However, heart rate variability (HRV) is widely recognized as a biomarker of health risk across the lifespan. Juvenile idiopathic arthritis (JIA), a group of chronic inflammatory joint disorders, is associated with persistent inflammation and pain, both of which contribute to increased cardiovascular risk, commonly linked to reduced HRV. Among HRV parameters, very-low frequency (VLF) components have been associated with physiological recovery processes. This study aimed to assess HRV during sleep in patients with JIA. Methods: We studied 10 patients with JIA and 10 age-, gender-, and Tanner stage-matched healthy controls. All participants underwent polysomnographic monitoring following an adaptation night in the sleep laboratory. HRV was analyzed using standard time and frequency domain measures over 5 min epochs across all sleep stages. Frequency components were classified into low- and high-frequency bands, and time domain measures included the standard deviation of the beat-to-beat intervals. Group differences in HRV parameters were assessed using nonparametric tests for independent samples, with a significance level set at p < 0.05. Results: JIA exhibited greater sleep disruption than controls, including reduced NREM sleep, longer total sleep time, and increased wake time after sleep onset. HRV analyses in both time and frequency domains revealed significant differences between groups across all stages of sleep. In JIA patients, the standard deviation of the normal-to-normal interval during slow wave sleep (SWS) and total power across all sleep stages (p < 0.05) was reduced. In JIA patients, the standard deviation of the normal-to-normal interval during slow wave sleep and total power across all sleep stages were significantly reduced (p < 0.05). VLF power was also significantly lower in JIA patients across all sleep stages (p = 0.002), with pronounced reductions during N2 and SWS (p = 0.03 and p = 0.02, respectively). A group effect was observed for total power across all stages, mirroring the VLF findings. Additionally, group differences were detected in LF/HF ratio analyses, although values during N2, SWS, and REM sleep did not differ significantly between groups. Notably, the number of affected joints showed a moderate positive correlation with the parasympathetic HRV parameter. Conclusions: Patients with JIA exhibited sleep disruption and alterations in cardiovascular autonomic functioning during sleep. Reduced HRV across all sleep stages in these patients suggests underlying autonomic nervous dysfunction. Addressing sleep disturbances in patients with chronic pain may serve as an effective strategy for managing their cardiovascular risk. Full article

Enhancing the detection capabilities of marine vessels is crucial for maritime security and intelligence acquisition. However, accurately identifying small ships in complex oceanic environments remains a significant challenge, as these targets are frequently obscured by ocean waves and other disturbances, compromising recognition accuracy and stability. To address this issue, we propose YOLO-ssboat, a novel small-target ship recognition algorithm based on the YOLOv8 framework. YOLO-ssboat integrates the C2f_DCNv3 module to extract fine-grained features of small vessels while mitigating background interference and preserving critical target details. Additionally, it employs a high-resolution feature layer and incorporates a Multi-Scale Weighted Pyramid Network (MSWPN) to enhance feature diversity. The algorithm further leverages an improved multi-attention detection head, Dyhead_v3, to refine the representation of small-target features. To tackle the challenge of wake waves from moving ships obscuring small targets, we introduce a gradient flow mechanism that improves detection efficiency under dynamic conditions. The Tail Wave Detection Method synergistically integrates gradient computation with target detection techniques. Furthermore, adversarial training enhances the network’s robustness and ensures greater stability. Experimental evaluations on the Ship_detection and Vessel datasets demonstrate that YOLO-ssboat outperforms state-of-the-art detection algorithms in both accuracy and stability. Notably, the gradient flow mechanism enriches target feature extraction for moving vessels, thereby improving detection accuracy in wake-disturbed scenarios, while adversarial training further fortifies model resilience. These advancements offer significant implications for the long-range monitoring and detection of maritime vessels, contributing to enhanced situational awareness in expansive oceanic environments. Full article

Valerian root extracts are widely used as mild sedatives to promote sleep, with clinical studies confirming their efficacy. Their sleep-promoting effects are associated with the adenosine A1 receptor (A1AR), a key regulator of sleep through neural activity inhibition. Adenosine, a neuromodulator that accumulates during wakefulness, activates A1ARs to facilitate sleep transitions. Using advanced analytics, we detected adenosine at 0.05% in the valerian extract Ze 911, supporting direct A1AR activation in vitro. Additionally, we explored A1ARs’ allosteric sites for modulatory activity. Valerenic acid and pinoresinol, key constituents of Ze 911, were identified as positive allosteric modulators (PAMs) of A1ARs. Valerenic acid exhibited strong PAM activity, with high cooperativity (αβ = 4.79 for adenosine and αβ = 23.38 for CPA) and intrinsic efficacy (τB = 5.98 for adenosine and τB = 3.14 for CPA). Pinoresinol displayed weaker PAM activity, with moderate cooperativity (αβ = 3.42 for adenosine and αβ = 0.79 for CPA) and limited efficacy (τB = 0.93 for adenosine and τB = 1.66 for CPA). The allosteric modulation observed in valerian extract Ze 911 suggests a mechanism of action in which valerenic acid and pinoresinol enhance receptor activation through allosteric interactions, potentially amplifying the effects of endogenous adenosine. By targeting A1ARs’ allosteric sites, valerian extract Ze 911 offers increased therapeutic selectivity and reduced off-target effects, emphasizing its potential for managing sleep disorders. Full article