Search Results (19)

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

This study presents a novel method for detecting sleep posture changes—specifically tossing and turning—by monitoring variations in humidity using an array of humidity sensors embedded at regular intervals within a memory-foam pillow. Unlike previous approaches that rely primarily on temperature or pressure sensors, our method leverages the observation that humidity fluctuations are more pronounced during movement, enabling the more sensitive detection of posture changes. We demonstrate that dynamic patterns in humidity data correlate strongly with physical motion during sleep. To identify these transitions, we applied the Pruned Exact Linear Time (PELT) algorithm, which effectively segmented the time series based on abrupt changes in humidity. Furthermore, we converted humidity fluctuation curves into image representations and employed a transfer-learning-based model to classify sleep postures, achieving accurate recognition performance. Our findings highlight the potential of humidity sensing as a reliable modality for non-invasive sleep monitoring. In this study, we propose a novel method for detecting tossing and turning during sleep by analyzing changes in humidity captured by a linear array of sensors embedded in a memory foam pillow. Compared to temperature data, humidity data exhibited more significant fluctuations, which were leveraged to track head movement and infer sleep posture. We applied a rolling smoothing technique and quantified the cumulative deviation across sensors to identify posture transitions. Furthermore, the PELT algorithm was utilized for precise change-point detection. To classify sleep posture, we converted the humidity time series into images and implemented a transfer learning model using a Vision Transformer, achieving a classification accuracy of approximately 96%. Our results demonstrate the feasibility of a sleep posture analysis using only humidity data, offering a non-intrusive and effective approach for sleep monitoring. Full article

Non-visual techniques for identifying sleep postures have become essential for enhancing sleep health. Conventional methods depend on a costly professional medical apparatus that is challenging to adapt for domestic use. This study developed an economical airbag mattress and introduced a method for detecting sleeping positions via restricted body pressure data. The methodology relies on distributed body pressure data obtained from barometric pressure sensors positioned at various locations on the mattress. Two combinations of base learners were chosen based on the complementary attributes of the model, each of which can be amalgamated through a soft-voting strategy. Additionally, the architectures of Autoencoder and convolutional neural networks were integrated, collectively constituting the base learning layer of the model. Gradient enhancement was utilized in the meta-learner layer to amalgamate the output of the basic learning layer. The experimental findings indicate that the suggested holistic learning model has high classification accuracy of up to 95.95%, precision of up to 96.13%, and F1 index of up to 95.01% in sleep posture recognition assessments and possesses considerable merit. In the subsequent application, the sleep monitoring device identified the sleep posture and employed an air conditioner and an air purifier to create a more comfortable sleep environment. The user can utilize the sleep posture data to improve the quality of sleep and prevent related diseases. Full article

Sleep posture is a key factor in assessing sleep quality, especially for individuals with Obstructive Sleep Apnea (OSA), where the sleeping position directly affects breathing patterns: the side position alleviates symptoms, while the supine position exacerbates them. Accurate detection of sleep posture is essential in assessing and improving sleep quality. Automatic sleep posture detection systems, both wearable and non-wearable, have been developed to assess sleep quality. However, wearable solutions can be intrusive and affect sleep, while non-wearable systems, such as camera-based approaches and pressure sensor arrays, often face challenges related to privacy, cost, and computational complexity. The system in this paper proposes a microcontroller-based approach exploiting the execution of an embedded machine learning (ML) model for posture classification. By locally processing data from a minimal set of pressure sensors, the system avoids the need to transmit raw data to remote units, making it lightweight and suitable for real-time applications. Our results demonstrate that this approach maintains high classification accuracy (i.e., 0.90 and 0.96 for the configurations with 6 and 15 sensors, respectively) while reducing both hardware and computational requirements. Full article

The sleeping and eating behaviors of horses are important indicators of their health. With the development of the modern equine industry, timely monitoring and analysis of these behaviors can provide valuable data for assessing the physiological state of horses. To recognize horse behaviors in stalls, this study builds on the SlowFast algorithm, introducing a novel loss function to address data imbalance and integrating an SE attention module in the SlowFast algorithm’s slow pathway to enhance behavior recognition accuracy. Additionally, YOLOX is employed to replace the original target detection algorithm in the SlowFast network, reducing recognition time during the video analysis phase and improving detection efficiency. The improved SlowFast algorithm achieves automatic recognition of horse behaviors in stalls. The accuracy in identifying three postures—standing, sternal recumbency, and lateral recumbency—is 92.73%, 91.87%, and 92.58%, respectively. It also shows high accuracy in recognizing two behaviors—sleeping and eating—achieving 93.56% and 98.77%. The model’s best overall accuracy reaches 93.90%. Experiments show that the horse behavior recognition method based on the improved SlowFast algorithm proposed in this study is capable of accurately identifying horse behaviors in video data sequences, achieving recognition of multiple horses’ sleeping and eating behaviors. Additionally, this research provides data support for livestock managers in evaluating horse health conditions, contributing to advancements in modern intelligent horse breeding practices. Full article

This research presents a sleep posture monitoring system designed to assist the elderly and patient attendees. Monitoring sleep posture in real time is challenging, and this approach introduces hardware-based edge computation methods. Initially, we detected the postures using minimally optimized sensing modules and fusion techniques. This was achieved based on subject (human) data at standard and adaptive levels using posture-learning processing elements (PEs). Intermittent posture evaluation was performed with respect to static and adaptive PEs. The final stage was accomplished using the learned subject posture data versus the real-time posture data using posture classification. An FPGA-based Hierarchical Binary Classifier (HBC) algorithm was developed to learn and evaluate sleep posture in real time. The IoT and display devices were used to communicate the monitored posture to attendant/support services. Posture learning and analysis were developed using customized, reconfigurable VLSI architectures for sensor fusion, control, and communication modules in static and adaptive scenarios. The proposed algorithms were coded in Verilog HDL, simulated, and synthesized using VIVADO 2017.3. A Zed Board-based field-programmable gate array (FPGA) Xilinx board was used for experimental validation. Full article

Sleep position recognition plays a crucial role in enhancing individual sleep quality and addressing sleep-related disorders. However, the conventional non-invasive technology for recognizing sleep positions tends to be limited in its widespread application due to high production and computing costs. To address this issue, an enhanced stacking model is proposed based on a specific air bag mattress. Firstly, the hyperparameters of the candidate base model are optimized using the Bayesian optimization algorithm. Subsequently, the entropy weight method is employed to select extreme gradient boosting (XGBoost), support vector machine (SVM), and deep neural decision tree (DNDT) as the first layer of the enhanced stacking model, with logistic regression serving as the meta-learner in the second layer. Comparative analysis with existing machine learning techniques demonstrates that the proposed enhanced stacking model achieves higher classification accuracy and applicability. Full article

Recognizing sleep posture is crucial for the monitoring of people with sleeping disorders. Existing contact-based systems might interfere with sleeping, while camera-based systems may raise privacy concerns. In contrast, radar-based sensors offer a promising solution with high penetration ability and the capability to detect vital bio-signals. This study propose a deep learning method for human sleep pose recognition from signals acquired from single-antenna Frequency-Modulated Continuous Wave (FMCW) radar device. To capture both frequency features and sequential features, we introduce ResTCN, an effective architecture combining Residual blocks and Temporal Convolution Network (TCN) to recognize different sleeping postures, from augmented statistical motion features of the radar time series. We rigorously evaluated our method with an experimentally acquired data set which contains sleeping radar sequences from 16 volunteers. We report a classification accuracy of 82.74% on average, which outperforms the state-of-the-art methods. Full article

Background: Facial recognition systems utilizing deep learning techniques can improve the accuracy of facial recognition technology. However, it remains unclear whether these systems should be available for patient identification in a hospital setting. Methods: We evaluated a facial recognition system using deep learning and the built-in camera of an iPad to identify patients. We tested the system under different conditions to assess its authentication scores (AS) and determine its efficacy. Our evaluation included 100 patients in four postures: sitting, supine, and lateral positions, with and without masks, and under nighttime sleeping conditions. Results: Our results show that the unmasked certification rate of 99.7% was significantly higher than the masked rate of 90.8% (p < 0.0001). In addition, we found that the authentication rate exceeded 99% even during nighttime sleeping. Furthermore, the facial recognition system was safe and acceptable for patient identification within a hospital environment. Even for patients wearing masks, we achieved a 100% success rate for authentication regardless of illumination if they were sitting with their eyes open. Conclusions: This is the first systematical study to evaluate facial recognition among hospitalized patients under different situations. The facial recognition system using deep learning for patient identification shows promising results, proving its safety and acceptability, especially in hospital settings where accurate patient identification is crucial. Full article

With the existing pressure sensors, it is difficult to achieve the unification of wide pressure response range and high sensitivity. Furthermore, the preparation of pressure sensors with excellent performance for sleep health monitoring has become a research difficulty. In this paper, based on material and microstructure synergistic enhancement mechanism, a hybrid pressure sensor (HPS) integrating triboelectric pressure sensor (TPS) and piezoelectric pressure sensor (PPS) is proposed. For the TPS, a simple, low-cost, and structurally controllable microstructure preparation method is proposed in order to investigate the effect of carbon nano-onions (CNOs) and hierarchical composite microstructures on the electrical properties of CNOs@Ecoflex. The PPS is used to broaden the pressure response range and reduce the pressure detection limit of HPS. It has been experimentally demonstrated that the HPS has a high sensitivity of 2.46 V/10⁴ Pa (50–600 kPa) and a wide response range of up to 1200 kPa. Moreover, the HPS has a low detection limit (10 kPa), a high stability (over 100,000 cycles), and a fast response time. The sleep monitoring system constructed based on HPS shows remarkable performance in breathing state recognition and sleeping posture supervisory control, which will exhibit enormous potential in areas such as sleep health monitoring and potential disease prediction. Full article

Migraine is a chronic neurological disorder that frequently coexists with different vestibular and cochlear symptoms (sudden hearing loss, tinnitus, otalgia, aural fullness, hyperacusis, dizziness, imbalance, and vertigo) and disorders (recurrent benign positional vertigo, persistent postural perceptual dizziness, mal de debarquement, and Menière’s disease). Despite evidence of an epidemiological association and similar pathophysiology between migraine and these vestibulocochlear disorders, patients suffering from migraine-related symptoms are usually underdiagnosed and undertreated. Current migraine treatment options have shown success in treating vestibulocochlear symptoms. Lifestyle and dietary modifications (reducing stress, restful sleep, avoiding migraine dietary triggers, and avoiding starvation and dehydration) and supplements (vitamin B2 and magnesium) offer effective first-line treatments. Treatment with migraine prophylactic medications such as tricyclic antidepressants (e.g., nortriptyline), anticonvulsants (e.g., topiramate), and calcium channel blockers (e.g., verapamil) is implemented when lifestyle and dietary modifications are not sufficient in improving a patient’s symptoms. We have included an algorithm that outlines a suggested approach for addressing these symptoms, taking into account our clinical observations. Greater recognition and understanding of migraine and its related vestibular and cochlear symptoms are needed to ensure the appropriate diagnosis and treatment of affected patients. Full article

Traffic command and scheduling are the core monitoring aspects of railway transportation. Detecting the fatigued state of dispatchers is, therefore, of great significance to ensure the safety of railway operations. In this paper, we present a multi-feature fatigue detection method based on key points of the human face and body posture. Considering unfavorable factors such as facial occlusion and angle changes that have limited single-feature fatigue state detection methods, we developed our model based on the fusion of body postures and facial features for better accuracy. Using facial key points and eye features, we calculate the percentage of eye closure that accounts for more than 80% of the time duration, as well as blinking and yawning frequency, and we analyze fatigue behaviors, such as yawning, a bowed head (that could indicate sleep state), and lying down on a table, using a behavior recognition algorithm. We fuse five facial features and behavioral postures to comprehensively determine the fatigue state of dispatchers. The results show that on the 300 W dataset, as well as a hand-crafted dataset, the inference time of the improved facial key point detection algorithm based on the retina–face model was 100 ms and that the normalized average error (NME) was 3.58. On our own dataset, the classification accuracy based the an Bi-LSTM-SVM adaptive enhancement algorithm model reached 97%. Video data of volunteers who carried out scheduling operations in the simulation laboratory were used for our experiments, and our multi-feature fusion fatigue detection algorithm showed an accuracy rate of 96.30% and a recall rate of 96.30% in fatigue classification, both of which were higher than those of existing single-feature detection methods. Our multi-feature fatigue detection method offers a potential solution for fatigue level classification in vital areas of the industry, such as in railway transportation. Full article

Sleep posture has a crucial impact on the incidence and severity of obstructive sleep apnea (OSA). Therefore, the surveillance and recognition of sleep postures could facilitate the assessment of OSA. The existing contact-based systems might interfere with sleeping, while camera-based systems introduce privacy concerns. Radar-based systems might overcome these challenges, especially when individuals are covered with blankets. The aim of this research is to develop a nonobstructive multiple ultra-wideband radar sleep posture recognition system based on machine learning models. We evaluated three single-radar configurations (top, side, and head), three dual-radar configurations (top + side, top + head, and side + head), and one tri-radar configuration (top + side + head), in addition to machine learning models, including CNN-based networks (ResNet50, DenseNet121, and EfficientNetV2) and vision transformer-based networks (traditional vision transformer and Swin Transformer V2). Thirty participants (n = 30) were invited to perform four recumbent postures (supine, left side-lying, right side-lying, and prone). Data from eighteen participants were randomly chosen for model training, another six participants’ data (n = 6) for model validation, and the remaining six participants’ data (n = 6) for model testing. The Swin Transformer with side and head radar configuration achieved the highest prediction accuracy (0.808). Future research may consider the application of the synthetic aperture radar technique. Full article

In-bed posture monitoring has become a prevalent area of research to help minimize the risk of pressure sore development and to increase sleep quality. This paper proposed 2D and 3D Convolutional Neural Networks, which are trained on images and videos of an open-access dataset consisting of 13 subjects’ body heat maps captured from a pressure mat in 17 positions, respectively. The main goal of this paper is to detect the three main body positions: supine, left, and right. We compare the use of image and video data through 2D and 3D models in our classification. Since the dataset was imbalanced, three strategies were evaluated, i.e., down sampling, over sampling, and class weights. The best 3D model achieved accuracies of 98.90 ± 1.05% and 97.80 ± 2.14% for 5-fold and leave-one-subject-out (LOSO) cross validations, respectively. To compare the 3D model with 2D, four pre-trained 2D models were evaluated, where the best-performing model was the ResNet-18 with accuracies of 99.97 ± 0.03% for 5-fold and 99.62 ± 0.37% for LOSO. The proposed 2D and 3D models provided promising results for in-bed posture recognition and can be used in the future to further distinguish postures into more detailed subclasses. The outcome of this study can be used to remind caregivers at hospitals and long-term care facilitiesto reposition their patients if they do not reposition themselves naturally to prevent pressure ulcers. In addition, the evaluation of body postures and movements during sleep can help caregivers understand sleep quality. Full article

Emerging sleep health technologies will have an impact on monitoring patients with sleep disorders. This study proposes a new deep learning model architecture that improves the under-blanket sleep posture classification accuracy by leveraging the anatomical landmark feature through an attention strategy. The system used an integrated visible light and depth camera. Deep learning models (ResNet-34, EfficientNet B4, and ECA-Net50) were trained using depth images. We compared the models with and without an anatomical landmark coordinate input generated with an open-source pose estimation model using visible image data. We recruited 120 participants to perform seven major sleep postures, namely, the supine posture, prone postures with the head turned left and right, left- and right-sided log postures, and left- and right-sided fetal postures under four blanket conditions, including no blanket, thin, medium, and thick. A data augmentation technique was applied to the blanket conditions. The data were sliced at an 8:2 training-to-testing ratio. The results showed that ECA-Net50 produced the best classification results. Incorporating the anatomical landmark features increased the F1 score of ECA-Net50 from 87.4% to 92.2%. Our findings also suggested that the classification performances of deep learning models guided with features of anatomical landmarks were less affected by the interference of blanket conditions. Full article