Search

Monitoring sleep posture is important for avoiding bedsores after surgery, reducing apnea events, tracking the progression of Parkinson's disease, and even alerting epilepsy patients to potentially fatal sleep postures. Today, there is no easy way to track sleep postures. Past work has proposed installing cameras in the bedroom, mounting accelerometers on the subject's chest, or embedding pressure sensors in their bedsheets. Unfortunately, such solutions jeopardize either the privacy of the user or their sleep comfort. In this paper, we introduce BodyCompass, the first RF-based system that provides accurate sleep posture monitoring overnight in the user's own home. BodyCompass works by studying the RF reflections in the environment. It disentangles RF signals that bounced off the subject's body from other multipath signals. It then analyzes those signals via a custom machine learning algorithm to infer the subject's sleep posture. BodyCompass is easily transferable and can apply to new homes and users with minimal effort. We empirically evaluate BodyCompass using over 200 nights of sleep data from 26 subjects in their own homes. Our results show that, given one week, one night, or 16 minutes of labeled data from the subject, BodyCompass's corresponding accuracy is 94%, 87%, and 84%, respectively.

Accurate and low-cost sleep measurement tools are needed in both clinical and epidemiological research. To this end, wearable accelerometers are widely used as they are both low in price and provide reasonably accurate estimates of movement. Techniques to classify sleep from the high-resolution accelerometer data primarily rely on heuristic algorithms. In this paper, we explore the potential of detecting sleep using Random forests. Models were trained using data from three different studies where 134 adult participants (70 with sleep disorder and 64 good healthy sleepers) wore an accelerometer on their wrist during a one-night polysomnography recording in the clinic. The Random forests were able to distinguish sleep-wake states with an F1 score of 73.93% on a previously unseen test set of 24 participants. Detecting when the accelerometer is not worn was also successful using machine learning ($$\hbox {F1-score} > 93.31\%$$ F1-score > 93.31 % ), and when combined with our sleep detection models on day-time data provide a sleep estimate that is correlated with self-reported habitual nap behaviour ($$\hbox {r}=.60$$ r = . 60 ). These Random forest models have been made open-source to aid further research. In line with literature, sleep stage classification turned out to be difficult using only accelerometer data.

A vast majority of nursing home residents suffer from health issues such as incontinence, night wandering and pressure ulcers. The workload of nurses is noticeably increasing because of these problems. Previous research has shown that many of these complaints can be associated with specific movements in bed. This paper proposes the usage of accelerometer sensors in a non-invasive manner to detect these movements. Using deep learning on the edge, the discussed method provides immediate feedback to nurses to assist them with their care tasks.

Falls are a significant threat to the health and independence of elderly people and represent an enormous burden on the healthcare system. Successfully predicting falls could be of great help, yet this requires a timely and accurate fall risk assessment. Gait abnormalities are one of the best predictive signs of underlying locomotion conditions and precursors of falls. The advent of wearable sensors and wrist-worn devices provides new opportunities for continuous and unobtrusive monitoring of gait during daily activities, including the identification of unexpected changes in gait. To this end, we present in this paper a novel method for determining gait abnormalities based on a wrist-worn device and a deep neural network. It integrates convolutional and bidirectional long short-term memory layers for successful learning of spatiotemporal features from multiple sensor signals. The proposed method was evaluated using data from 18 subjects, who recorded their normal gait and simulated abnormal gait while wearing impairment glasses. The data consist of inertial measurement unit (IMU) sensor signals obtained from smartwatches that the subjects wore on both wrists. Numerous experiments showed that the proposed method provides better results than the compared methods, achieving 88.9% accuracy, 90.6% sensitivity, and 86.2% specificity in the detection of abnormal walking patterns using data from an accelerometer, gyroscope, and rotation vector sensor. These results indicate that reliable fall risk assessment is possible based on the detection of walking abnormalities with the use of wearable sensors on a wrist.

Health problems due to poor posture is becoming increasingly common among every age group in today's time. Sedentary workstyle, lack of physical exercise, unsupported or unbalanced sitting conditions are some of the factors that cause posture-related problems. The correct or inappropriate posture of the human body can be detected using a wearable sensor system, as discussed in this paper. In this work, three tri-axial accelerometers placed at the back of the subject were used to classify nine different postures in sitting and standing positions. A novel combined deep learning model consisting of a fully convolutional network (FCN) and long short-term model (LSTM) is proposed for posture classification. Experimental results show that combined FCN-LSTM network yields the highest average classification accuracy of 99.91%, whereas the individual FCN and LSTM networks yield classification accuracies of 97.88% and 88.47%, respectively. The models are also compared in terms of complexity and execution time.

The use of marijuana is now legal for medical purposes in 39 of the 50 United States. Eleven of these 39 states have also legalized marijuana for non-medical usage. Marijuana impairs the motor skills of users, making Driving Under the Influence of Marijuana (DUIM) a growing public health concern. There are currently few accessible and accurate methods to assess the impairment levels of drivers who have used marijuana. Current assessment methods include self-reports and testing urine, oral fluid, and blood. However, self-reports are often biased and biological tests are cumbersome to perform in situ. In this paper, we investigate whether dose-dependent changes in participants gait (walk) can be detected using data gathered from their smartphone motion sensors (accelerometer and gyroscope). We envision WeedGait, a smartphone sensing system that will assess the gait of marijuana users passively and warn them when they are too impaired to drive safely. To the best of our knowledge, this is the first study on using smartphones to assess marijuana-induced gait impairment. Gait data was collected from 10 subjects and pre-processing steps included low pass filtering, step cycle detection and segmentation, and normalization. We present a novel gait analysis approach that analyzes normalized, single-step segments to achieve higher accuracy than prior approaches. We compared the classification results of various machine and deep learning models, and found that Long Short Time Memory (LSTM) and Support Vector Machines performed best, discriminating the gait of subjects after smoking either marijuana with 3% or 7.2% THC versus smoking a placebo marijuana cigarette with an accuracy of 92.1%. These results suggest that smartphone-based marijuana testing is more accurate than urine-based tests but slightly less accurate than oral fluid based testing. Moreover, smartphone sensing of marijuana is completely passive and hence more convenient, which facilitates pervasive testing in natural settings and could have massive impact due to the near-ubiquity of smartphones.

Essential tremor (ET), a common neurological movement disorder, is typically measured with rating scales by neurologists during a clinical visit. This method undervalues the tremor fluctuations during patients' daily activities. This paper proposes an ET severity evaluation system based on advanced deep learning algorithms. We combine the convolutional neural network (CNN) and long short-term memory (LSTM) to build the multi-layer ET evaluation model (Eval-net). Experiments based on acceleration data gathered from 20 ET patients and five healthy subjects are conducted to verify the feasibility of the proposed method. Experimental results show that the Eval-net model can classify six typical activities and four levels of ET severity with better performance than previous approaches in recognition accuracy. This study demonstrates that the proposed method makes improvements in recognizing human activities and evaluating tremor severity based on acceleration data.

The ballistocardiography (BCG) signal is a measurement of the vibrations of the center of mass of the body due to the cardiac cycle and can be used for noninvasive hemodynamic monitoring. The seismocardiography (SCG) signals measure the local vibrations of the chest wall due to the cardiac cycle. While BCG is a more well-known modality, it requires the use of a modified bathroom scale or a force plate and cannot be measured in a wearable setting, whereas SCG signals can be measured using wearable accelerometers placed on the sternum. In this paper, we explore the idea of finding a mapping between zero mean and unit $\ell _{2}$ -norm SCG and BCG signal segments such that, the BCG signal can be acquired using wearable accelerometers (without retaining amplitude information). We use neural networks to find such a mapping and make use of the recently introduced UNet architecture. We trained our models on 26 healthy subjects and tested them on ten subjects. Our results show that we can estimate the aforementioned segments of the BCG signal with a median Pearson correlation coefficient of 0.71 and a median absolute deviation (MAD) of 0.17. Furthermore, our model can estimate the R-I, R-J and R-K timing intervals with median absolute errors (and MAD) of 10.00 (8.90), 6.00 (5.93), and 8.00 (5.93), respectively. We show that using all three axis of the SCG accelerometer produces the best results, whereas the head-to-foot SCG signal produces the best results when a single SCG axis is used.

Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which is characterized by inattention, hyperactivity and impulsive behaviors. In particular, children have difficulty keeping still exhibiting increased fine and gross motor activity. This paper focuses on analyzing the data obtained from two tri-axial accelerometers (one on the wrist of the dominant arm and the other on the ankle of the dominant leg) worn during school hours by a group of 22 children (11 children with ADHD and 11 paired controls). Five of the 11 ADHD diagnosed children were not on medication during the study. The children were not explicitly instructed to perform any particular activity but followed a normal session at school alternating classes of little or moderate physical activity with intermediate breaks of more prominent physical activity. The tri-axial acceleration signals were converted into 2D acceleration images and a Convolutional Neural Network (CNN) was trained to recognize the differences between non-medicated ADHD children and their paired controls. The results show that there were statistically significant differences in the way the two groups moved for the wrist accelerometer (t-test p-value &lt, 0.05). For the ankle accelerometer statistical significance was only achieved between data from the non-medicated children in the experimental group and the control group. Using a Convolutional Neural Network (CNN) to automatically extract embedded acceleration patterns and provide an objective measure to help in the diagnosis of ADHD, an accuracy of 0.875 for the wrist sensor and an accuracy of 0.9375 for the ankle sensor was achieved.

Parkinson’s disease (PD) is a chronic neurodegenerative condition that affects a patient’s everyday life. Authors have proposed that a machine learning and sensor-based approach that continuously monitors patients in naturalistic settings can provide constant evaluation of PD and objectively analyse its progression. In this paper, we make progress toward such PD evaluation by presenting a multimodal deep learning approach for discriminating between people with PD and without PD. Specifically, our proposed architecture, named MCPD-Net, uses two data modalities, acquired from vision and accelerometer sensors in a home environment to train variational autoencoder (VAE) models. These are modality-specific VAEs that predict effective representations of human movements to be fused and given to a classification module. During our end-to-end training, we minimise the difference between the latent spaces corresponding to the two data modalities. This makes our method capable of dealing with missing modalities during inference. We show that our proposed multimodal method outperforms unimodal and other multimodal approaches by an average increase in F1-score of 0.25 and 0.09, respectively, on a data set with real patients. We also show that our method still outperforms other approaches by an average increase in F1-score of 0.17 when a modality is missing during inference, demonstrating the benefit of training on multiple modalities.

The final publication is available at Springer via https://doi.org/10.1007/978-3-319-59147-6_30 Freezing of gait (FOG) is one of the most incapacitating symptoms among the motor alterations of Parkinson’s disease (PD). Manifesting FOG episodes reduce patients’ quality of life and their autonomy to perform daily living activities, while it may provoke falls. Accurate ambulatory FOG assessment would enable non-pharmacologic support based on cues and would provide relevant information to neurologists on the disease evolution. This paper presents a method for FOG detection based on deep learning and signal processing techniques. This is, to the best of our knowledge, the first time that FOG detection is addressed with deep learning. The evaluation of the model has been done based on the data from 15 PD patients who manifested FOG. An inertial measurement unit placed at the left side of the waist recorded tri-axial accelerometer, gyroscope and magnetometer signals. Our approach achieved comparable results to the state-of-the-art, reaching validation performances of 88.6% and 78% for sensitivity and specificity respectively.