Search

Measurement of human body movement is an essential step in biomechanical analysis. The current standard for human motion capture systems uses infrared cameras to track reflective markers placed on the subject. While these systems can accurately track joint kinematics, the analyses are spatially limited to the lab environment. Though Inertial Measurement Unit (IMU) can eliminate the spatial limitations of the motion capture system, those systems are impractical for use in daily living due to the need for many sensors, typically one per body segment. Due to the need for practical and accurate estimation of joint kinematics, this study implements a reduced number of IMU sensors and employs machine learning algorithm to map sensor data to joint angles. Our developed algorithm estimates hip, knee, and ankle angles in the sagittal plane using two shoe-mounted IMU sensors in different practical walking conditions: treadmill, level overground, stair, and slope conditions. Specifically, we proposed five deep learning networks that use combinations of Convolutional Neural Networks (CNN) and Gated Recurrent Unit (GRU) based Recurrent Neural Networks (RNN) as base learners for our framework. Using those five baseline models, we proposed a novel framework, DeepBBWAE-Net, that implements ensemble techniques such as bagging, boosting, and weighted averaging to improve kinematic predictions. DeepBBWAE-Net predicts joint kinematics for the three joint angles under all the walking conditions with a Root Mean Square Error (RMSE) 6.93-29.0% lower than base models individually. This is the first study that uses a reduced number of IMU sensors to estimate kinematics in multiple walking environments.

Affective computing is a field of great interest in many computer vision applications, including video surveillance, behaviour analysis, and human-robot interaction. Most of the existing literature has addressed this field by analysing different sets of face features. However, in the last decade, several studies have shown how body movements can play a key role even in emotion recognition. The majority of these experiments on the body are performed by trained actors whose aim is to simulate emotional reactions. These unnatural expressions differ from the more challenging genuine emotions, thus invalidating the obtained results. In this paper, a solution for basic non-acted emotion recognition based on 3D skeleton and Deep Neural Networks (DNNs) is provided. The proposed work introduces three majors contributions. First, unlike the current state-of-the-art in non-acted body affect recognition, where only static or global body features are considered, in this work also temporal local movements performed by subjects in each frame are examined. Second, an original set of global and time-dependent features for body movement description is provided. Third, to the best of out knowledge, this is the first attempt to use deep learning methods for non-acted body affect recognition. Due to the novelty of the topic, only the UCLIC dataset is currently considered the benchmark for comparative tests. On the latter, the proposed method outperforms all the competitors.

Objective Whether a laryngeal mask airway (LMA) should be removed under deep anesthesia or after awakening from general anesthesia remains controversial. Among patients with special needs, removing an LMA after awakening might be difficult because they may be unable to follow instructions during LMA removal. Thus, requirements of patients with special needs must be taken into consideration while deciding on LMA removal. This study aimed to determine optimal timing of LMA removal after dental treatment under general anesthesia in disabled patients by comparing adverse event occurrence rates. Methods Between February and December 2018, we randomly categorized 80 disabled patients administered general anesthesia into two groups, namely, the Deep group (40 patients, LMA removed under deep anesthesia) or the Preawake group (40 patients, LMA removed in the Preawake state). Anesthesia in both groups comprised propofol (PROP) and remifentanil (RMFT), and flexible LMAs were used. Dental anesthesiologists assessed the frequency of adverse events, both during and immediately after LMA removal. Results Clenching, gross body movement, and difficult ventilation were more frequently seen in the Preawake group than in the Deep group (P Conclusions Among disabled patients requiring general anesthesia with PROP and RMFT for dental treatment, LMA should be removed under deep anesthesia to minimize adverse events.

The biosensors on a human body form a wireless body area network (WBAN) that can examine various physiological parameters, such as body temperature, electrooculography, electromyography, electroencephalography, and electrocardiography. Deep learning can use health information from the embedded sensors on the human body that can help monitoring diseases and medical disorders, including breathing issues and fever. In the context of communication, the links between the sensors are influenced by fading due to diffraction, reflection, shadowing by the body, clothes, body movement, and the surrounding environment. Hence, the channel between sensors and the central unit (CU), which collects data from sensors, is practically imperfect. Therefore, in this article, we propose a deep learning-based COVID-19 detection scheme using a WBAN setup in the presence of an imperfect channel between the sensors and the CU. Moreover, we also analyze the impact of correlation on WBAN by considering the imperfect channel. Our proposed algorithm shows promising results for real-time monitoring of COVID-19 patients.

Infants receiving care in the Neonatal Intensive Care Unit (NICU) experience several painful procedures during their hospitalization. Assessing neonatal pain is difficult because the current standard for assessment is subjective, inconsistent, and discontinuous. The intermittent and inconsistent assessment can induce poor treatment and, therefore, cause serious long-term outcomes. In this paper, we present a comprehensive pain assessment system that utilizes facial expressions along with crying sounds, body movement, and vital sign changes. The proposed automatic system generates a standardized pain assessment comparable to those obtained by conventional nurse-derived pain scores. The system achieved 95.56% accuracy using decision fusion of different pain responses that were recorded in a challenging clinical environment. In addition to the decision fusion, we present the performance of multimodal assessment using other fusion schemes as well as a unimodal assessment approach. We also discuss the impact of different factors (e.g., gestational age) on pain, propose several group-specific models for pain assessment (e.g., pre-term and full-term models), and compare the performance of these models with the performance of general models. While further research is needed, our results show that the automatic assessment of neonatal pain is a viable and more efficient alternative to the manual assessment.

OBJECTIVES The active factor along with light exercise can reduce static muscle work and increase muscle flexibility and endurance. Accordingly, this study aimed to design and prototype a new active footrest, implemented in conventional sitting workstations and to test its usability among office workers. METHODS The steps taken to design and prototype the active footrest were a) selection of an exercise appropriate for goals of ergonomic interventions, b) idea development, c) selection of the best conceptual design, d) design with SOLIDWORKS version 2016 software, and e) fabrication of a prototype. Afterward, the usability of the active footrest prototype was assessed among 20 office workers (10 females) using field data by the System Usability Scale. RESULTS Upon the completion of the design steps, the active footrest prototype was prototyped by taking into account design criteria (e.g. functionality, inclusive design, easy application, and reduction of additional body movement), anthropometric data and mechanical properties. The participants rated the usability of the active workstation as 89 ± 8.21 (out of 100) and indicating good usability results. CONCLUSION In this study, an active footrest was designed and prototyped to perform knee extension exercise with the capability of being implemented in conventional sitting workstations.

Patient motion during dynamic PET imaging can induce errors in myocardial blood flow (MBF) estimation. Motion correction for dynamic cardiac PET is challenging because the rapid tracer kinetics of 82Rb leads to substantial tracer distribution change across different dynamic frames over time, which can cause difficulties for image registration-based motion correction, particularly for early dynamic frames. In this paper, we developed an automatic deep learning-based motion correction (DeepMC) method for dynamic cardiac PET. In this study we focused on the detection and correction of inter-frame rigid translational motion caused by voluntary body movement and pattern change of respiratory motion. A bidirectional-3D LSTM network was developed to fully utilize both local and nonlocal temporal information in the 4D dynamic image data for motion detection. The network was trained and evaluated over motion-free patient scans with simulated motion so that the motion ground-truths are available, where one million samples based on 65 patient scans were used in training, and 600 samples based on 20 patient scans were used in evaluation. The proposed method was also evaluated using additional 10 patient datasets with real motion. We demonstrated that the proposed DeepMC obtained superior performance compared to conventional registration-based methods and other convolutional neural networks (CNN), in terms of motion estimation and MBF quantification accuracy. Once trained, DeepMC is much faster than the registration-based methods and can be easily integrated into the clinical workflow. In the future work, additional investigation is needed to evaluate this approach in a clinical context with realistic patient motion.

Wearable sensors demand flexible and concealable devices that can be seamlessly integrated with apparels and clothes. E-textile sensors and devices, built from specially functionalized fibers and yarns and constructed with embroidery and woven processes, provide an ideal solution for different wearable applications. In this article, we propose a textile-based, embroidered passive strain and displacement sensor functioned as a UHF RFID antenna that can be aesthetically integrated with garment fabrics. The antenna structure consists of a dipole arm and a coupling loop mounted with an RFID chip. The displacement between the loop and dipole arm will alter the impedance of the antenna and consequently modulate the backscattered signals from the RFID chip to the reader. The sensor is passive, i.e., no battery is needed on the sensor and the sensing information can be wirelessly retrieved by the reader from a few meters away. The structure is sensitive to strains and displacement caused by body movement. Our experiments demonstrate different applications for this sensor, i.e., when the sensor is embroidered on different locations on human body, such as breast, knees, and elbows, it can be used as a respiration monitor, gesture indicator, etc. to conveniently track and log various forms of body movements.

Computer vision is a significant component of human-computer interaction (HCI) processes in interactive control systems. In general, the interaction between humans and computers relies on the flexibility of the interactive visualization system. Electromyography (EMG) is a bioelectric signal used in HCI that can be captured noninvasively by placing electrodes on the human hand. Due to the impact of complex background, accurate recognition and analysis of human motion in real-time multitarget scenarios are considered challenging in HCI. Further, EMG signals of human hand motions are exceedingly nonlinear, and it is important to utilize a dynamic approach to address the noise problem in EMG signals. Hence, in this paper, the Optimized Noninvasive Human-Computer Interaction (ONIHCI) model has been proposed to predict human motion recognition. Average Intrinsic Mode Function (AIMF) has been used to reduce the noise factor in EMG signals. Furthermore, this paper introduces spatial thermographic imaging to overcome the conventional sensor problem, such as gesture recognition and human target identification in multitarget scenarios. The human motion behavior in spatial thermographic images is examined by target trajectory, and body movement kinematics is employed to classify human targets and objects. The experimental findings demonstrate that the proposed method reduces noise by 7.2% and improves accuracy by 97.2% in human motion recognition and human target identification.

Xianwen Liu,1 Baofeng Ding,2 Fu Shi,1 Yang Zhang,1 Lei Liu,1 Yongwei Sha,3 Tonghang Zhao1 1Department of Anaesthesiology, Liaocheng People’s Hospital, Liaocheng, Shandong, People’s Republic of China; 2Department of Anaesthesiology, Liaocheng Second People’s Hospital, Liaocheng, Shandong, People’s Republic of China; 3Department of Anaesthesiology, Guanxian Central Hospital, Liaocheng, Shandong, People’s Republic of ChinaCorrespondence: Tonghang Zhao Email lbzthgn@163.comObjective: The optimal sedation regime during endoscopy remains controversial, especially for elderly outpatients. In this study, we compared the efficacy and safety between remimazolam tosilate (RT) and etomidate-propofol (EP) in elderly outpatients undergoing colonoscopy.Methods: A total of 260 elderly outpatients undergoing sedative colonoscopy were randomized into two groups. Patients in the RT group received a 0.075-mg/kg maintenance dose of remimazolam following an initial dose of 0.15 mg/kg, whereas patients in the EP group (10 mL:20 mg etomidate plus 10 mL:100 mg propofol) received a 0.05-mL/kg maintenance dose following an initial dose of 0.1 mL/kg to maintain a Modified Observer’s Assessment of Alertness/Sedation score of ≤ 3 during the procedure. The primary endpoint was the success of the procedure. Secondary endpoints included time metrics, hemodynamics, consumption of fentanyl, etomidate, propofol, and remimazolam, intraoperative body movement, patient and endoscopist satisfaction scores, supplemental dose of sedative and fentanyl, and incidence and severity of adverse events.Results: The procedure success rate was 96.52% in the RT group and 100% in the EP group. The difference in procedure success rate between the RT and EP groups was − 3.48% (95% confidence interval: − 6.81%, − 0.15%). Four patients in the RT group required rescue midazolam. Compared with patients in the RT group, the onset time of the EP group was significantly lower (p < 0.05), whereas time to fully alert (p = 0.001), ready for discharge (p = 0.001), and hospital discharge (p = 0.002) were all significantly higher in the EP group. However, there were no significant differences in procedure time (p = 0.846) or cecal intubation time (p = 0.320) between the two groups. Although the frequency of intraoperative body movement was higher in the RT group, the difference was not significant (p = 0.508). There were no significant differences in patients’ demographic and baseline characteristics, supplemental doses of sedative and fentanyl, or patient and endoscopist satisfaction scores (p > 0.05). Muscular tremor and pain on injection were recorded more frequently in the EP group (p < 0.05). However, there were no significant differences in hypoxia, respiratory depression, or incidence of postoperative nausea and vomiting. The severity of adverse events was all mild (grade 1) across both groups.Conclusion: RT may have non-inferior efficacy and a higher safety profile than EP in elderly outpatients undergoing colonoscopy, which suggests that RT may be more suitable for elderly outpatients undergoing colonoscopy.Keywords: remimazolam tosilate, etomidate, propofol, elderly outpatients, colonoscopy

In health assessment and disease prevention, vital signs such as breathing rate, heartbeat rate, blood pressure and posturography play a critical role. Not only the elderly, but also young people need to pay attention to vital signs monitoring because more and more young people die of sudden diseases, such as sudden death and myocardial infarction. Traditional vital signs monitoring methods are invasive and inconvenient to use, especially for the elderly because these methods usually require users to wear some dedicated sensors. In recent years, some non-invasive vital signs monitoring methods based on wireless sensing have been proposed. Usually, these methods need the user to remain still. When the user walks around, these methods cannot work well. One of the challenges of mobile people breathing monitoring is that the small body chest displacement caused by breathing is disturbed by people’s walking. In this paper, we propose RF-RES, which is an accurate continuous breathing monitoring method based on RFID technology and uses a pair of tags to eliminate the influence of the user’s body movement. We merge the data of the tag pairs to eliminate the influence of the user’s entire body movement and propose an algorithm based on doppler frequency shift to track the user’s displacement during exercise. We conduct practical experiments to evaluate the performance with Impinj R420 and passive tags. The results show that RF-RES achieves accurate respiratory rate monitoring when estimating the respiratory rate of different users, with an average error of 0.54 BPM.

Wearable devices equipped with soft sensors provide a promising solution for body movement monitoring. Specifically, body movements like elbow flexion can be captured by monitoring the stretched soft sensors’ resistance changes. However, in addition to stretching, the resistance of a soft sensor is also influenced by its aging, which makes the resistance a less stable indicator of the elbow angle. In this paper, we leverage the recent progress in Deep Learning and address the aforementioned issue by formulating the aging-invariant prediction of elbow angles as a domain adaption problem. Specifically, we define the soft sensor data ( i.e. , resistance values) collected at different aging levels as different domains and adapt a regression neural network among them to learn domain-invariant features. However, unlike the popular pairwise domain adaptation problem that only involves one source and one target domain, ours is more challenging as it has “infinite” target domains due to the non-stop aging. To address this challenge, we novelly propose an output-level domain adaptation approach which builds on the fact that the elbow angles are in a fixed range regardless of aging. Experimental results show that our method enables robust and accurate prediction of elbow angles with aging soft sensors, which significantly outperforms supervised learning ones that fail to generalize to aged sensor data.

Background /objectives: For biomechanical studies using jump-landing tasks, many researchers set the criteria for judging success or failure of the trial. Failed trials are usually removed from the analysis. However, the kinetics and kinematics during tasks included in failed trials might be important for understanding the mechanisms and risk factors of non-contact sports injuries. However, few studies have attempted to analyze failed trials. Therefore, the main objective of this study was to investigate the characteristics associated with ground reaction force (GRF) and two-dimensional frontal body movements during a failed trial of single-leg lateral drop jump-landing. Methods Ten healthy women and 16 healthy men participated in this study. Spearman's rank correlation coefficients were calculated using the total number of failed trials and GRF data of successful trials. The association between frontal body movement and kinetics data was identified using correlation analyses. Wilcoxon signed-rank tests were performed to compare the GRF data of successful trials and failed trials of the same subject. Additionally, a two-way repeated measure analysis of variance was used to determine significant interactions of each trial and time after initial contact in the frontal body movement. Results A total of 137 trials including successful and failed trials were recorded. There were 59 failed jump trials. There was a significant negative correlation between the number of failed jump trials and the elapsed time from initial contact to peak vertical GRF (peak vGRF time) during successful trials (r = −0.427). The majority of failed trials were judged to be due to rearfoot movement patterns (rearfoot medial slip or rearfoot lateral slip). During rearfoot medial slip, we observed shorter peak vGRF time, larger trunk medial motions, and larger hip adduction movements after landing than that during successful trials. During rearfoot lateral slip, we observed larger trunk lateral motions and hip abduction movements after landing than that during successful trials. Conclusions Athletes who frequently failed during single-leg lateral drop jump-landing had poor skills absorbing jump-landing impact, which is related to various sports injuries. It is possible to identify the risk factors for sports injuries by analyzing failure patterns.

Radio frequency (RF) sensors such as radar are instrumental for continuous, contactless sensing of vital signs, especially heart rate (HR) and respiration rate (RR). However, decades of related research mainly focused on static subjects, because the motion artifacts from other body parts may easily overwhelm the weak reflections from vital signs. This paper marks a first step in enabling RF vital sign sensing under ambulant daily living conditions. Our solution is inspired by existing physiological research that revealed the correlation between vital signs and body movement. Specifically, we propose to combine direct RF sensing for static instances and indirect vital sign prediction based on movement power estimation. We design customized machine learning models to capture the sophisticated correlation between RF signal pattern, movement power, and vital signs. We further design an instant calibration and adaptive training scheme to enable cross-subjects generalization, without any explicit data labeling from unknown subjects. We prototype and evaluate the framework using a commodity radar sensor. Under a variety of moving conditions, our solution demonstrates an average estimation error of 5.57 bpm for HR and 3.32 bpm for RR across multiple subjects, which largely outperforms state-of-the-art systems.

Wireless body area networks (WBANs) are communication networks of sensors (and/or actuators), which can be placed on, inside, or around the body and represent a new generation of personal area networks. In contrast to the typical wireless sensor networks (WSNs), WBAN sensors are tiny and have limited power supply. Due to irregular human body movement and WBAN sensor distribution, fading can cause a lot of error, which can be determined by measuring the bit error rate (BER). A higher BER requires more power. Therefore, to reduce BER, power consumption (PC) and duty cycle (DC), a game theory-two master nodes-based cooperative protocol (GT-TMNCP) is proposed in this work. DC is enhanced by a further 13% using the proposed GT-TMNCP, leading to a BER reduction 3 times greater when compared to TMNCP, and PC improved by 14%, lower than with the TMNCP, for shadowing at 5 dB, critical index data (IC), IC = 3 and 5, representing maximum critical data. The results also demonstrate that BER is reduced up to 8 times, DC is enhanced by 8%, and PC by 7% for shadowing 9 dB, IC = 7, compared to the QoS optimisation approach and TMNCP.

Epilepsy is a risk factor for the development of psychogenic non-epileptic seizures (PNES) and comorbid epilepsy is recognized as a comorbidity in about 10–30% of patients with PNES. The combination of epileptic and nonepileptic seizures poses a particular diagnostic challenge. In patients with epilepsy, additional PNES may be suspected on the basis of their typical semiology. The possibility of additional PNES should also be considered if seizures fail to respond to antiepileptic drug treatment, in patients with frequent emergency admissions with seizures and in those who develop new types of seizures. The description of semiological details by patients and witnesses can suggest additional PNES. Home video recordings can support an initial diagnosis, however, especially in patients with mixed seizure disorders it is advisable to seek further diagnostic confirmation by capturing all habitual seizure types with video-EEG. The clinical features of PNES associated with epilepsy are similar to those in isolated PNES disorders and include longer duration, fluctuating course, asynchronous movements, pelvic thrusting, side-to-side head or body movement, persistently closed eyes and mouth, ictal crying, recall of ictal experiences and absence of postictal confusion. PNES can also present as syncope-like episodes with unresponsiveness and reduced muscle tone. There is no unique epileptological or brain pathology profile putting patients with epilepsy at risk of additional PNES. However, patients with epilepsy and PNES typically have lower educational achievements and higher levels of psychiatric comorbidities than patients with epilepsy alone. Psychological trauma, including sexual abuse, appears to be a less relevant aetiological factor in patients with mixed seizure disorders than those with isolated PNES, and the gender imbalance (i.e. the greater prevalence in women) is less marked in patients with PNES and additional epilepsy than those with PNES alone. PNES sometimes develop after epilepsy surgery. A diagnosis of ‘known epilepsy’ should never be accepted without (at least brief) critical review. This narrative review summarises clinical, electrophysiological and historical features that can help identify patients with epilepsy and additional PNES.

The purpose of this study was to explore the feasibility of a urination management system by developing a smart band-based algorithm that recognizes the urination interval of women. We designed a device that recognizes the time and interval of urination based on the patient’s specific posture and posture changes. The technology used for recognition applied the Radial Basis Function kernel-based Support Vector Machine, a teaching and learning method that facilitates multidimensional analysis by simultaneously judging the characteristics of complex learning data. In order to evaluate the performance of the proposed recognition technique, we compared actual urination and device-sensed urination. An experiment was performed to evaluate the performance of the recognition technology proposed in this study. The efficacy of smart band monitoring urination was evaluated in 10 female patients without urination problems. The entire experiment was performed over a total of 3 days. The average age of the participants was 28.73 years (26–34 years), and there were no signs of dysuria. The final accuracy of the algorithm was calculated based on clinical guidelines for urologists. The experiment showed a high average accuracy of 91.0%, proving the robustness of the proposed algorithm. This urination behavior recognition technique shows high accuracy and can be applied in clinical settings to characterize urination patterns in female patients. As wearable devices develop and become more common, algorithms that detect specific sequential body movement patterns that reflect specific physiological behaviors could become a new methodology to study human physiological behavior.

With the goal of implementing gesture interaction applications on wearable devices, this paper presents a comparative study on hand gesture recognition based on accelerometer (ACC) and photoplethysmography (PPG) sensors. Research is conducted on 14 hand gestures involving wrist and finger movements under four motion scenarios: sitting, walking, jogging, and running. When the participants perform the hand gestures, four channels of PPG signals and 3D ACC signals are collected. To effectively extract gesture repetitions from the continuous movements, a segmentation method based on PPG signal and motion noise is employed. The experimental results verify that the PPG signal is more suitable for implementing gesture interactions on wearable devices. At first, the signal-to-noise ratio analysis demonstrates that the ACC signals are much more affected by motion noise than the PPG signals. Then, the hand gesture recognition results in the four different motion scenarios demonstrate that the accuracies of both the ACC and PPG signals decrease with the intensity of body movement; however, the decrease of the PPG signals is significantly lower than that of the ACC signals, especially for finger-related gestures. A hand gesture recognition experiment with ratios of the samples between the training set and test set from 1:9 to 8:2 demonstrates that the PPG signal also has advantages in regards to reducing user’s training burden. Moreover, this research verifies that the green PPG signal is not the best choice for the implementation of gesture interactions. The research results provide a reliable foundation for promoting the development of gesture-based interactions in wearable devices.

Ultrasound-guided axillary brachial plexus block is increasingly used in preschool-age patients. However, the minimum effective volume of local anaesthetics has not been determined. With ethical committee approval and written informed consent from the guardians of all paediatric patients, we studied 27 consecutive patients aged 3 to 6 years who were scheduled for hand surgery. After general anaesthesia, eligible patients received a set volume of ultrasound-guided axillary brachial plexus block. We determined the volume of 0.2% ropivacaine for consecutive patients from the preceding patient’s outcome. The initial volume was 0.4 ml/kg. The testing interval was set at 0.05 ml/kg, and the lowest volume was 0.1 ml/kg. The following conditions were defined as a successful block: no heart rate changes, body movement, or ventilatory disorders during the operation; no use of fentanyl in the PACU; and a postoperative sensory block score

Sleep is a form of rest and getting enough sleep at the right times with suitable surrounding conditions is very important to maintain good health throughout life. The study aims to develop the end-user prototyping for a sleep monitoring system that measures the room ambient and body condition by using a wireless device utilizing Bluetooth Low Energy (BLE) embedded system. For the user interface, the Window application is used to display the collected data from separate ambient parameters and body condition embedded systems using Bluno Uno and Bluno Nano respectively. This sleep monitoring system also equipt with a video and audio based recording from the web camera and microphone of the built-in PC based unit. Capturing data from body monitoring and ambient monitoring separate units are then transferred to the Window based application by using the BLE connection and lastly, the captured data are log into the MySQL database with the date and time stamp. The ambient condition system captured the room temperature and humidity, light intensity and rate of CO2 concentration. The body condition system, it is measuring body temperature, heart rate and body movement. Based on the device testing on sleep monitoring, each of the parameters measured is optimized to choose the best possible occurrence of ambience setting selection for optimal sleep quality.

O Núcleo de Pesquisa e Extensão em Ciências do Movimento Corporal (NUPEM) do CEFD/UFES, representado por professores e pesquisadores elaborou conjuntamente uma carta aberta à comunidade. O grupo vislumbrou a importância de publicar estratégias de gerenciamento e manejo para a manutenção da atividade física e de cuidados de saúde e prevenção durante à pandemia do coronavírus (COVID-19). A pandemia tem alarmado a comunidade esportiva e praticantes de atividade física por seu potencial de transmissão, disseminação, hospitalização e letalidade, principalmente em populações mais vulneráveis, como aquelas com doenças crônicas e idosos. Além de informações gerais sobre a pandemia causada pelo COVID-19, o objetivo deste documento é fornecer informações e recomendações relacionadas à prática de atividade física (AF) para o esclarecimento de profissionais de saúde e pessoas ligadas ao esporte e da AF. Pretendemos assim auxiliar na educação e promoção da saúde por meio de estratégias de prevenção relacionadas à pandemia e à prática de atividade física. Nesta perspectiva, de acordo com as diretrizes atuais, recomenda-se evitar ao máximo o tempo de inatividade física e comportamentos sedentários. Ainda, é recomendada a prática de 150-300 min/semana de AF aeróbia de intensidade moderada e 2 sessões de atividades que envolvam treinamento de força muscular, contribuindo com a manutenção do estado de saúde. No entanto, um volume menor de AF produz também benefícios à saúde, ou seja, realizar alguma AF é melhor que nenhuma e movimentar mais e repousar menos também.

The increasing popularity of exergaming (exercise and gaming) has already emerged in the rehabilitation setting to help individuals develop, maintain, and restore maximum body movement and physical...

In chronic pain rehabilitation, physiotherapists adapt physical activity to patients' performance based on their expression of protective behavior, gradually exposing them to feared but harmless and essential everyday activities. As rehabilitation moves outside the clinic, technology should automatically detect such behavior to provide similar support. Previous works have shown the feasibility of automatic protective behavior detection (PBD) within a specific activity. In this paper, we investigate the use of deep learning for PBD across activity types, using wearable motion capture and surface electromyography data collected from healthy participants and people with chronic pain. We approach the problem by continuously detecting protective behavior within an activity rather than estimating its overall presence. The best performance reaches mean F1 score of 0.82 with leave-one-subject-out cross validation. When protective behavior is modelled per activity type, performance is mean F1 score of 0.77 for bend-down, 0.81 for one-leg-stand, 0.72 for sit-to-stand, 0.83 for stand-to-sit, and 0.67 for reach-forward. This performance reaches excellent level of agreement with the average experts' rating performance suggesting potential for personalized chronic pain management at home. We analyze various parameters characterizing our approach to understand how the results could generalize to other PBD datasets and different levels of ground truth granularity., 24 pages, 12 figures, 7 tables. Accepted by ACM Transactions on Computing for Healthcare

In view of the problems of low precision, poor quality, and long time of gait feature recognition due to the influence of human body movement environment on the recognition process of the current gait feature recognition method of human body movement blurred image, a new method of gait feature recognition based on graph neural network (GNN) method is proposed. The gait features of human movement blurred images were extracted, and the fusion clustering recognition of the GNN algorithm was used to locate the gait features of human movement blurred images. The gait features of human body movement blurred images were located by the GNN method. According to the contour feature point info of the human body movement blurred image, the standard deviation of gait feature location of the human body movement blurred image was calculated, the gait feature of the blurred image of human body movement was reconstructed, and the gait recognition of the human body movement blurred image was achieved. The results show that the extraction of human movement is good, with high positioning confidence, good recognition quality, average recognition accuracy of 92%, and greatly shortened recognition time.

In this paper, a bed-mounted vibration sensor-based system is proposed to monitor vital parameters during sleep, including heartbeat rate (HR) and respiratory rate (RR), body movements and sleep postures. Our system enables smart healthcare that monitors daily sleep in a ubiquitous and non-invasive manner. Besides, the system is contact-free, as no external wearable devices and physical contacts are required. Furthermore, the vibration-based approach also avoids the privacy violation caused by the usage of surveillance cameras. To effectively monitor sleep status, a robust stable signal mode decomposition based HR and RR estimation method is developed for the complicated and noisy vibration signals. Besides, algorithms for body movement and sleep posture identification are also proposed based on vibration signal features. A prototype system is demonstrated with system details, showing great potentials in monitoring sleep status in a real-time user-friendly manner. Experimental results of short term and long term experiments with different participants and beds show that our system achieves satisfying accuracy compared with dedicated commercial devices.

Impulse-radio ultra-wideband (IR-UWB) radar devices can be used to monitor vital signs, such as respiratory and cardiac rates. For this purpose, the phase of an echo signal received from the chest or back of a human is usually used; subsequently, respiratory rate estimation (RRE) and cardiac rate estimation (CRE) can be achieved by estimating two fundamental frequencies corresponding to the respiratory and cardiac rates, respectively. However, the interference caused by undesirable terms would inevitably be induced in an echo signal; thus, the cardiac rate information contained in the phase of the received signal is often smeared and destroyed. Among several sources of interference such as high-order harmonics of respiratory rate, random body movement of an individual, and system noise, the body movement of an individual is the most critical for reliable CRE, making it a very challenging task. To address this problem, we herein propose a new framework comprising four steps: 1) RRE via differentiation and spectrum analysis for an unwrapped phase of received signal, 2) coarse estimation of cardiac rate candidates, 3) selection of three promising candidates for the desired cardiac rate based on a histogram of several candidates, and 4) determination of the desired cardiac rate via a fuzzy logic rule-based method. In experiments using 7.29 GHz IR-UWB radar hardware, we observed that our proposed framework is capable of performing accurate and robust real-time CRE even in the presence of body movement.

A Study to Assess the Effectiveness of Oral Sucrose on Level of Pain during DPT Immunization among Infants at a Selected Hospital, Salem. Objectives:To assess the level of pain during DPT immunization among infants in experimental and control group. To determine the effectiveness of oral sucrose on level of pain during DPT immunization among infants in experimental and control group. To associate the level of pain during DPT immunization among infants in experimental and control group with their selected demographic variables. Operational Definitions Effectiveness Effectiveness refers to the reduced level of pain among infants in experimental group when compared to control group as measured by modified REILY infant pain Assessment Scale. Oral sucrose Oral sucrose refers to 24% sucrose solution (2ml) given to infants prior to administration of DPT immunization. DPT Immunization It is a vaccine administered intra muscularly in vastus lateralis to prevent DPT. Pain Pain refers to an unpleasant experience observed in the infant during injection as measured by using modified REILY infant pain assessment scale (facial expression, body movement, activity, cry, consolability). Infants Infants refer to the babies of 6 - 14 weeks of age receiving DPT immunization. Hypotheses H1: There will be significant difference in level of pain among infants in experimental and control group after oral sucrose administration during DPT immunization at P < 0.05 level. H2: There will be significant association between the level of pain during DPT immunization among infants in experimental and control group with their selected demographic variables at p

Thomas Balanis, Bernd Sanner Internal Medicine, Agaplesion Bethesda Hospital, Wuppertal, GermanyCorrespondence: Thomas BalanisInternal Medicine, Agaplesion Bethesda Hospital, Wuppertal, GermanyEmail thomasmpalanis@gmail.comPurpose: Atrial fibrillation (AF) is the most common arrhythmia and is associated with an increased risk of complications. A screening test has the potential to prevent AF-related complications. This study investigated the diagnostic accuracy of an automated device for home blood pressure (BP) monitoring, which implements an algorithm for AF detection.Patients and Methods: A modified, automated oscillometric device for home BP monitoring (Omron BP785N (HEM-7321-Z), Omron Healthcare) with an AF detector was used to measure the BP in patients. During each BP measurements, the electrocardiogram (ECG) was recorded simultaneously. Simultaneous BP measurements and ECG recordings were obtained from 99 subjects.Results: Twenty out of 20 patients with atrial fibrillation were correctly recognized by the device and the device correctly identified 67 patients with sinus rhythm as “Not-AF”. On the other hand, 12 patients with basic rhythm: sinus rhythm were incorrectly referred to as “atrial fibrillation”. In summary, the device has a diagnostic accuracy of 87.88% with a sensitivity of 100% and a specificity of 84.8%. On the other hand, in 23 patients, the raw data of the device showed that a body movement occurred during the measurement of the blood pressure. If these subjects were excluded of the analysis, then the diagnostic accuracy of the device would be even better, namely 90.79%. The sensitivity would be 100% and the specificity 89.5%.Conclusion: These data suggest that an automated device for home blood pressure has an excellent diagnostic accuracy for detecting an AF and could be used as a reliable screening test for early diagnosis of atrial fibrillation. Body movements have an impact of the accuracy and specificity of a blood pressure monitor.Keywords: atrial fibrillation detection, blood pressure measurement, Omron BP785N

Healthcare systems are a very important part of the economy of any country and for the public health. The IoT-based monitoring system for patients with paralysis, which helps to promote the health condition of a patient with paralysis, in addition to the day-to-day life. India has suffered a stroke, the incidence is much higher than that of the more developed countries, it is home to around 2.1 million Indians suffered from the boom of the (lame) per year. If a patient is suffering from a paralysis attack in all or any part of the body can be turned off in order to move in, which means that their movement is restricted and they can barely communicate with anyone at all, because they can't talk like a normal person. Raccoons will find it difficult to understand what they are saying, and help them deal with their day-to-day needs, such as food, water, etc.). At present, work is in progress on the review of the motion parameters on the legs, arms, and head of the paralytics. This paper investigates the development of an integrated and portable prototype is a model of a system for the monitoring of the various movements of the body, spinal cord injuries, with the help of sensors. The tests were carried out by placing the sensors on the head, arm, and leg of the paralyzed patient the data received from these sensors are sent to the raspberry pi 3 model. In the Android app, you'll receive a verbal warning, and if the patient is in need of help via Bluetooth, which, in turn, is connected to the raspberry pi.

Breathing is one of the vital signs used to assess the physical health of a subject. Non-contact-based measurements of both breathing rate and changes in breathing rate help monitor health condition of subjects more flexibly. In this paper, we present an improved real-time camera-based adaptive breathing monitoring system, which includes real time (1) adaptive breathing motion detection, (2) adaptive region of interest detection to eliminate environmental noise, (3) breathing and body movement classification, (4) respiration rate estimation, (5) monitor change in respiration rate to examine overall health of an individual, and (6) online adaptation to lighting. The proposed system does not pose any positional and postural constraint. For evaluation, 30 videos of 15 animals are tested with drugs to simulate various medical conditions and breathing patterns, and the results from the proposed system are compared with the outputs of an existing FDA-approved invasive medical system for patient monitoring. The results show that the proposed method performs significantly correlated RR results to the reference medical device with the correlation coefficient equal to 0.92 and p-value less than 0.001, and more importantly the proposed video-based method is demonstrated to produce alarms 10 to 20 s earlier than the benchmark medical device. Graphical abstract The proposed system flowchart to extract the respiratory pattern from video.

Recently, the inherent piezoelectric properties of the 2D transition-metal dichalcogenides (TMDs) tin monosulfide (SnS) and tin disulfide (SnS2) have attracted much attention. Thus the piezoelectricity of these materials has been theoretically and experimentally investigated for energy-harvesting devices. However, the piezoelectric output performance of the SnS2- or SnS-based 2D thin film piezoelectric nanogenerator (PENG) is still relatively low, and the fabrication process is not suitable for practical applications. Here we report the formation of the SnS2/SnS heterostructure thin film for the enhanced output performance of a PENG using atomic layer deposition (ALD). The piezoelectric response of the heterostructure thin film was increased by ∼40% compared with that of the SnS2 thin film, attributed to large band offset induced by the heterojunction formation. Consequently, the output voltage and current density of the heterostructure PENG were 60 mV and 11.4 nA/cm2 at 0.6% tensile strain, respectively. In addition, thickness-controllable large-area uniform thin-film deposition via ALD ensures that the reproducible output performance is achieved and that the output density can be lithographically adjusted depending on the applications. Therefore, the SnS2/SnS heterostructure PENG fabricated in this work can be employed to develop a flexible energy-harvesting device or an attachable self-powered sensor for monitoring pulse and human body movement.

Worldwide, 16.7 million people die each year due to cardiovascular disease. These statistics raise demand of devices like sensor-based pacemakers (PM) which are not just doing heart rate augmentation but also capable to transmit information via wireless link to on body sensor and support remote monitoring of such patients. As per the world health organization WHO reports there are more than 3 million functioning PMs and about 600,000 pacemakers are implanted each year in world. On an average, 70–80% of PMs are implanted in aged patients around 65 years or older. In addition to continuous monitoring of cardiovascular parameters, detection of physical movement of such patients may be helpful to assess their well-being. This paper has been formulated with an aim to highlight an approach which may be used to detect the physical movement of the patient using information signal received from implanted PM. The transmitted signal will experience a pathloss offered by wireless human body channel, which will affect the link quality parameters namely Signal to Noise Ratio (SNR) and Bit Error Rate (BER) and received signal strength indicator (RSSI). In the current work mathematical model has been formulated considering in body and on body channel propagation conditions and received power, received energy, pathloss, SNR, BER, bit rate, energy per bit and RSSI have been evaluated using IEEE802.15.6 channel models CM2 and CM3. Data set has been created and human body movement has been detected using Machine Learning (ML) techniques. Prediction accuracy of Multilayer Perceptron (MLP), k-Nearest Neighbours (kNN) and Random Forest have been compared. The analysis performed depicts that human body movement can be detected using different channel models and ML techniques such as MLP, kNN and Random Forest with an accuracy of 65.3%, 72.8% and 93.4% respectively. The critical comparison of the result indicates that the performance of Random Forest is better than MLP and kNN. This approach will be helpful in remote detection of human body movement of patients.

Parkinson’s disease is a neurodegenerative disorder that progresses slowly and its symptoms appear over time, so its early diagnosis is not easy. A neurologist can diagnose Parkinson's by reviewing the patient's medical history and repeated scans. Besides, body movement analysts can diagnose Parkinson's by analyzing body movement. Recent research work has shown that changes in speech can be used as a measurable indicator for early Parkinson’s detection. In this work, the authors propose a speech signal-based hybrid Parkinson's disease diagnosis system for its early diagnosis. To achieve this, the authors have tested several combinations of feature selection approaches and classification algorithms and designed the model with the best combination. To formulate various combinations, three feature selection methods such as mutual information gain, extra tree, and genetic algorithm and three classifiers namely naive bayes, k-nearest-neighbors, and random forest have been used. To analyze the performance of different combinations, the speech dataset available at the UCI (University of California, Irvine) machine learning repository has been used. As the dataset is highly imbalanced so the class balancing problem is overcome by the synthetic minority oversampling technique (SMOTE). The combination of genetic algorithm and random forest classifier has shown the best performance with 95.58% accuracy. Moreover, this result is also better than the recent work found in the literature.

Introduction The development and well-being of children are directly linked to several aspects. Among those aspects, physical activity, an adequate nutrition, and a healthy mind, seem to be of crucial importance. Psychopathologies, such as anxiety and depression, have a negative impact on life, especially when co-occurring (mixed-anxiety depression disorder/cothymia), and the clinical implications include a higher risk of suicide and psychiatric hospitalization, elevated disability, decreased compliance with medical treatment, and considerably increased usage of medical services. Thus, research in conventional and nonconventional modalities is necessary to address this issue. The main objective of this study was to understand if TJQ and QG could be effective as a mindfulness cognitive-behavioural based therapeutic tool with body movement, for the treatment of children suffering from cothymia. Methods In this small study, six selected children, four males and two females aged between 7 and 11 years old, were taught a set of exercises of TaijiQuan (TJQ) and Qi Gong (QG). To obtain the results, the Achenbach Teacher's Report Form (TRF) was applied at the beginning of the experimental period, as well as at the ending of the experimental period. The resulting scores were analysed to observe the difference between both moments of evaluation. Results Results showed some improvements in symptoms, with an average improvement of 46%. Conclusion TJQ and QG seem to be a promising complementary therapeutic tool in cognitive-behavioural approaches for children who suffer from cothymia, as well as prevention and control for children who may not display symptoms at a clinical level. However, further research is needed in order to understand the full potential of these therapeutic exercises.

Background The frequency of new-onset HIV-associated seizure in the HIV-infected patient is estimated to be between 2 and 11%. Identifying the underlying etiology of new-onset seizure will have a vital impact on the mortality and morbidity of patients living with HIV infection. Case presentation We report a 34-year old newly diagnosed HIV+ male patient presented with abnormal body movement (ABM) involving his right hemibody associated with loss of consciousness lasting few minutes of two weeks duration. The ABM occurred frequently (> five times per week) and associated with frothy and excessive salivation. He reported headache following each spells. Brain magnetic resonance imaging (MRI) showed bilateral frontal T2 and FLAIR hyperintensity and T1 hypointensity; post contrast study showed bilateral small ring enhancing lesion with perilesional oedema, the biggest one on the left hemisphere, with a 10 mm diameter; considering patient advanced immunosuppression and underlying HIV infection, the brain MRI findings were consistent with cerebral toxoplasmosis. Bipolar montage electroencephalography (EEG) study showed generalized background slowing, prominent in the left fronto-centeral region. Patient was managed with combination antiretroviral therapy, anti-toxoplasmosis medication, and anticonvulsant. On follow up, the frequency of seizure attack has significantly reduced. Conclusion Considering the high prevalence of HIV infection and associated seizure among people living with HIV in sub-Saharan Africa, this case fairly highlights on the importance of utilizing advanced imaging techniques such as MRI and EEG in identifying the underlying causes of HIV-associated seizures.

BACKGROUND The study of clusters of risk factors for elevated blood pressure (EBP) among adolescents from low- middle-income countries has received little research attention. The objective of the study was to identify clusters of EBP precursors (i.e., overweight, physical fitness, risk diet, and body movement) and to analyze its associations with EBP. METHODS This a cross-sectional study conducted in a sample of 965 secondary schools' students aged between 12 and 17 years-old from Colombia. Measurements included blood pressure, sociodemographic information, and four EBP precursors: Overweight, body movement, risk diet, and physical fitness. Cluster analysis was applied with the two-step method to identify the patterns of EBP precursors, and logistic regression models were used to analyze the association between clusters and EBP. RESULTS Findings indicate that EBP was present in 28.9% of the students, approximately 20% of adolescents had desirable profile (normal weight, normal-high physical fitness, low-risk diet, and middle-high body movement), and 16% of them had the four EBP precursors. The cluster solution revealed five clusters, formed according to the accumulation of EBP precursors, this is, characterized by having zero, one (low body movement), two (low body movement and high-risk diet), three (low body movement, high risk diet, and low fitness), or four (low body movement, high risk diet, low fitness, and overweight) EBP precursors. The cluster with four EBP precursors had a higher risk of having EBP. CONCLUSIONS According to these findings, it is necessary to implement programs that simultaneously address multiple health-related behaviors to promote health in adolescents.

Wearable self-powered sensors represent a theme of interest in the literature due to the progress in the Internet of Things and implantable devices. The integration of different materials to harvest energy from body movement or the environment to power up sensors or act as an active component of the detection of analytes is a frontier to be explored. This review describes the most relevant studies of the integration of nanogenerators in wearables based on the interaction of piezoelectric and triboelectric devices into more efficient and low-cost harvesting systems to power up batteries or to use the generated power to identify multiple analytes in self-powered sensors and biosensors.

Background and Objectives: Body Mass Index (BMI) is a parameter established by WHO (World Health Organization) as a ratio of body weight to body height squared. Physical activity according to WHO is any body movement produced by skeletal muscles that require energy. Lack of physical activity) is an independent risk factor for chronic disease, and is thought to cause death globally. The aim of this study was to determine the relationship between BMI and physical activity. Methods: This study is a descriptive research design. The data was collected by using a questionnaire. The data of this study were categorical variables from 2 groups so it used the Chi-Square test. Reference results were entered into the Mendeley application using the Vancouver system. Results: total sample was 104 people with a mean age of 21-23 years. 21 years 22 people (21.2%), 22 years 46 people (44.2%), 23 years 23 people (22.1%). Based on gender, it was found that there were 37 men (35.6%) and 67 women (64.4%). Based on BMI, it was found that 13 people were underweight (12.5%), 45 people were normal (43.3%), 24 people were overweight (23.1%), 20 people were obese 1 (19.2%), and 2 people were obese 2 ( 1.9%). Conclusion: There is no relationship between BMI and physical activity.

This study investigated the effects of dopaminergic drugs on the EEG mu power during motor imagery, action observation, and execution. This is a double-blind, crossover study with a sample of 15 healthy adults under placebo vs. methylphenidate vs. risperidone conditions during motor imagery, action observation, and execution tasks. The participants had drug dosage adjustment based on body weight/dose (mg/kg). We also analyzed the mu band power by electroencephalography during the study steps. The main result is the interaction between the condition and task factors for the C3 and C4 electrodes, with decreasing EEG mu power in the methylphenidate when compared to risperidone (p ≤ 0.0083). Our results can indicate that the methylphenidate decreases the neurophysiological activity in the central cortical regions during the perceptual experience of tasks with or without body movement.

The continuous development of 802.11ad technology provides new opportunities in wireless sensing. In this work, we propose ViMo, a calibration-free remote vital sign monitoring system that can detect stationary/nonstationary users and estimate the respiration rates (RRs) as well as heart rates (HRs) built upon a commercial 60-GHz WiFi. The design of ViMo consists of two key components. First, we design an adaptive object detector that can identify static objects, stationary human subjects, and human in motion without any calibration. Second, we devise a robust HR estimator, which eliminates the respiration signal from the phase of the channel impulse response (CIR) to remove the interference of the harmonics from breathing and adopts dynamic programming (DP) to resist the random measurement noise. The influence of different settings, including the distance between a human and the device, user orientation and incidental angle, blockage material, body movement, and conditions of multiuser separation is investigated by extensive experiments. The experimental results show that ViMo monitors user’s vital signs accurately, with a median error of 0.19 and 0.92 breaths per minute (BPM), respectively, for RR and HR estimation.

Vital signs (e.g., respiration rate or heartbeat rate) sensing is of great importance to implement pervasive in-home healthcare. Traditional vital signs monitoring approaches usually require users to wear some dedicated sensors. These approaches are intrusive and inconvenient to use, especially for elderly people. Some non-intrusive vital signs monitoring approaches based on wireless sensing have been proposed in recent years. However, these approaches require the target user to be in situ during the monitoring process, which greatly limits their utilization in practical scenarios where the target users usually move around. In this paper, we propose RF-RMM, an RFID-based approach to accurate and continuous respiration monitoring for mobile users. The major challenge in respiration monitoring for moving people is that the tiny body displacement caused by the user’s respiration is overwhelmed by the user’s entire body movement. To address this issue, we propose a novel approach that uses a pair of tags to eliminate the effect of the user’s body movement. We fuse the data from the paired tags to cancel the effect of the user’s entire body movement and retain only the displacement caused by the user’s respiration. Another challenging issue in implementing RF-RMM is how to resolve the phase ambiguity problem when the target user moves around, which becomes more serious than in the static case. We propose a distance tracking algorithm to track the phase transition during the user’s movement, according to which the phase ambiguity problem can be well handled. We implement RF-RMM on commercial RFID devices and conduct extensive real-world experiments to evaluate its performance. The results show that RF-RMM achieves accurate respiration rate monitoring with an average error of 0.54 BPM in estimating different users’ respiration rate and an average relative error of less than 13% in estimating the user’s individual breath length.

Parkinson’s disease is a slowly progressing neurodegenerative disorder that is not easy to diagnose at the early stages because of delayed symptoms. The most usual ways to diagnose this disease is either by reviewing the medical history of the patient and looking at the computerized tomography scans along with the magnetic resonance imaging by a neurologist or by analyzing the body movements of the patient by the body movement analysts. However, recent research work indicates that Parkinson’s can be effectively diagnosed at an early stage by measuring the changes in handwriting. In this work, the authors have proposed a Parkinson’s disease diagnosis system by analyzing the kinematic features extracted from the handwritten spirals drawn by patients. The publicly available University of California, Irvine Parkinson’s disease spiral drawings using digitized graphics tablet dataset is used in this study. A total of 29 kinematics features are extracted from the dataset. The class imbalance problem in the dataset is handled by the synthetic minority oversampling technique because the dataset is highly imbalanced. Relevant features are selected using the genetic algorithm and mutual information gain feature selection methods. The performance of four classifiers support vector machine, random forest, AdaBoost and XGBoost are analyzed in terms of accuracy, sensitivity, specificity, precision, F-measure, and area under ROC curve. Tenfold cross-validation method is used for validating the results. The combination of mutual information gain feature selection method with AdaBoost classifiers outperforms with 96.02% accuracy.

Motion artifact (MA) contamination with electrocardiogram (ECG) signal is a common issue caused by body movement or sensor loosening, resulting in distortion of clinical features of ECG. In this work, the Monte Carlo filter (MCF)-based MA removal from single-channel ECG signal is proposed, assisting in real-time telecardiology systems. Initially, after R-peak detection and beat extraction, principal component (PC) analysis was performed upon clean ECG beats, and PC, with the highest energy, was assumed to be the feature beat. Using this feature beat, MA corrupted beats were denoised successively to achieve a clean pattern of ECG using MCF. A new approach of weight calculation and resampling was also proposed for better performance of the MCF. Performance of the proposed algorithm was tested on the IEEE Signal Processing Cup Challenge 2015 ECG database and MIT-BIH arrythmia records, with an improvement of signal-to-noise ratio between 10 and 15 dB, after MA removal. The proposed work was also tested on real-time ECG data collected from ten healthy volunteers using the AD8232 ECG module and Raspberry Pi, resulting in correlation coefficient higher than 0.99, between the original and denoised signals. The proposed algorithm was able to remove MA from any single-channel MA corrupted ECG signal, irrespective of lead category, using features of clean beats. A comparative study of the obtained result with previously published works ensured the superior performance on MA removal from ECG in the proposed work, along with real-time data collection, processing, and transmission.

The aim of this paper is to show how compact mmWave radar systems, attached to a person, can take advantage of their movements, in order to significantly improve the image resolution by means of synthetic aperture radar (SAR) techniques. Thus, high resolution imaging becomes possible even with tiny on-chip systems, opening up a horizon of possibilities to assist visually impaired people. The approach is illustrated for movements in terms of arm swings. For this purpose, it is firstly shown that the information from an inertial measurement unit (IMU) can be used to provide a trajectory estimation, which is enough to apply synthetic aperture radar processing. As a consequence, the resolution of the radar is greatly improved when compared with that achieved considering a single position. In order to avoid the continuously growing position error, commonly observed in dead-reckoning systems relying just on IMU, zero velocity updates (ZUPT) will be systematically applied. For doing so, two different zero velocity detectors (ZVD) are considered, one based on acceleration data and other on velocity estimation. Although the positioning information is extracted from the IMU, demonstrating the enhanced obstacle detection capabilities obtained with this approach, other sensors that can be carried by a person and that are capable of providing trajectory estimations to combine measurements acquired with compact mmWave radars could have been used. The system is tested using different targets and a good performance comparable to the one achieved by using a high accuracy reference positioning system is attained. The compactness of the system enables the possibility of using it as a wearable device, e.g., attached to the wrist. This shows that an IMU is enough for tracking relatively simple movements, though more complex positioning systems can be used for more general actions.

Gait recognition refers to the identification of individuals based on features acquired from their body movement during walking. Despite the recent advances in gait recognition with deep learning, variations in data acquisition and appearance, namely camera angles, subject pose, occlusions, and clothing, are challenging factors that need to be considered for achieving accurate gait recognition systems. In this paper, we propose a network that first learns to extract gait convolutional energy maps (GCEM) from frame-level convolutional features. It then adopts a bidirectional recurrent neural network to learn from split bins of the GCEM, thus exploiting the relations between learned partial spatiotemporal representations. We then use an attention mechanism to selectively focus on important recurrently learned partial representations as identity information in different scenarios may lie in different GCEM bins. Our proposed model has been extensively tested on two large-scale CASIA-B and OU-MVLP gait datasets using four different test protocols and has been compared to a number of state-of-the-art and baseline solutions. Additionally, a comprehensive experiment has been performed to study the robustness of our model in the presence of six different synthesized occlusions. The experimental results show the superiority of our proposed method, outperforming the state-of-the-art, especially in scenarios where different clothing and carrying conditions are encountered. The results also revealed that our model is more robust against different occlusions as compared to the state-of-the-art methods., Comment: Accepted in IEEE Transactions on Biometrics, Behavior, and Identity Science (T-BIOM)

Long-term person re-identification (re-ID) aims to build identity correspondence of the Target Subject of Interest (TSI) exposed under surveillance cameras over a long time interval. Compared to the conventional short-term re-ID studied by most existing works, it suffers an additional problem: significant dressing change observed with time lapsing. Unfortunately, this variation in long-term person re-ID case contradicts the assumption of prior short-term re-ID approaches, and thus causes significant difficulties if conventional short-term re-ID methods are applied. To address the problem, this paper proposes to learn hybrid feature representation via a two-stream network named SpTSkM, including a spatial-temporal stream and a skeleton motion stream. The former performs directly on image sequences, which tends to learn identity-related spatial-temporal patterns such as body geometric structure and body movement. The latter operates on normalized 3D skeletons by adapting graph convolutional network, which tends to learn pure motion patterns from skeleton sequences. Both streams extract fine-grained level time-gap stable information that is robust to appearance changes in long-term re-ID and meanwhile maintains sufficient discriminability to differentiate different people. The final matching metric is obtained by mixing information of the two streams in a score-level fusion strategy. In addition, we collect a Cloth-Varying vIDeo re-ID (CVID-reID) dataset particularly for long-term re-ID. It contains video tracklets of celebrities posted on the Internet. These videos are snapshots under extremely different scenarios that include highly dynamic background, diverse camera views and abundant cloth variations on each TSI. These factors cause CVID-reID more complicated and closer to practice. Our experiments demonstrate the difficulty of long-term person re-ID and also validate the effectiveness of the proposed SpTSkM, showing the best performance.

Internet of things (IoT) and machine learning based systems incorporating smart wearable technology are rapidly evolving to monitor and manage healthcare and physical activities. This paper is focused on the proposition of a fog-centric wireless, real-time, smart wearable and IoT-based framework for ubiquitous health and fitness analysis in a smart gym environment. The proposed framework aims to aid in the health and fitness industry based on body vitals, body movement and health related data. The framework is expected to assist athletes, trainers and physicians with the interpretation of multiple physical signs and raise alerts in case of any health hazard. We proposed a method to collect and analyze exercise specific data which can be used to measure exercise intensity and its benefit to athlete’s health and serve as recommendation system for upcoming athletes. We determined the validity of the proposed framework by giving a six weeks workout plan with six days a week for workout activity targeting all muscles followed by one day for recovery. We recorded the electrocardiogram, heart rate, heart rate variability, breath rate, and determined athlete’s movement using a 3D-acceleration. The collected data in the research is used in two modules. A Health zone module implemented on body vitals data which categorizes athlete’s health state into various categories. Hzone module is responsible for health hazards identification and alarming. Outstandingly, the Hzone module is able to identify an athlete’s physical state with 97% accuracy. A gym activity recognition (GAR) module is implemented to recognize workout activity in real-time using body movements and body vitals data. The purpose of the GAR module is to collect and analyze exercise specific data. The GAR module achieved an accuracy of above 89% on athlete independent model based on muscle group.

Lumbar-pelvic movements (LPMs) are generally performed in the clinical setting to identify limitations in a range of movements. Continuous monitoring of these movements can provide real-time feedback to both patients and medical experts with the potential of identifying activities that may precipitate symptoms of low back pain (LBP) as well as improving therapy by providing a personalised approach. Recent advances in mobile computing technology and wearable sensors have paved the way for developing mobile physical activity monitoring applications with more advanced and complex algorithms, such as deep neural network (DNN) based models. However, there is a lack of prior studies that focus on real-time LPMs detection with multimodal sensory data. Meanwhile, most research in the area of body movement detection do not consider the potential transition logic of the constituent low-level body movements (e.g., LPMs) within their corresponding high-level physical activity. This information could significantly increase accuracy of detection results. Further, current studies mainly perform deep learning-based movement detection in the cloud (or a backend server) that could increase network bandwidth and response time. To address these limitations, this paper proposes a novel LPMs detection approach using an enhanced and adapted hybrid DNN model, which includes a convolutional neural network followed by a long-short term memory recurrent network (CNN-LSTM), and performs detection locally on the mobile device. The results of a comparative evaluation of the proposed model and baseline models are described. We also introduce a set of domain-specific pre-defined rules, based on the transition logic information, to reconstruct the detection outputs to further improve the detection accuracy.