The use of Spindle Feature Vectors in Wearable Devices for Sleep Monitoring and Analysis

2020 ◽  
Author(s):  
Ioannis Krilis ◽  
Theodore Antonakopoulos
Keyword(s):  
Wearable Devices ◽  
Sleep Monitoring ◽  
Feature Vectors

scholarly journals 1197 Utility of Fitbit Charge 2 for Sleep Monitoring in Patients With Obstructive Sleep Apnea

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A458-A458
Author(s):  
D Kim ◽  
W Shin ◽  
J Byun
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Total Sleep Time ◽  
Sleep Stage ◽  
Sleep Time ◽  
Wearable Devices ◽  
Sleep Stages ◽  
Sleep Monitoring ◽  
Obstructive Sleep ◽  
Single Center Observational Study

Abstract Introduction The wearable device may be useful in monitoring sleep. Many studies reported reliable data in detecting sleep-wake states and sleep stage proportion in healthy adults, However, only a few validation studies were performed evaluating sleep using the wearable devices in patients with obstructive sleep apnea(OSA), which showed insufficient accuracy. We aimed to evaluate the reliability of multi-sensory wristband (Fitbit Charge 2) in patients with OSA. Methods This was a preliminary analysis of a prospective single-center observational study. Consecutive patients underwent standard Polysomnography (PSG) for evaluation of OSA with Fitbit Charge 2. Sleep data from PSG and Fitbit charge 2 were compared using paired t-tests and Bland-Altman plots. Results A total of eighty-six patients were analyzed. Four of them had poor data quality, 18 of them did not show sleep stages. Compared with the PSG, Fitbit Charge 2 showed higher total sleep time (419.1±194.0 vs 269.8±22.6, p<0.001) and sleep efficiency (95.8±2.5 vs 84.6±7.1, p<0.001). Those with sleep stage data showed higher sleep efficacy (87.7±5.5 vs 82.37.5, p=0.024) and a lower proportion of N1 sleep (33.7±19.9 vs 65.3±38.8, p=0.01). Conclusion Fitbit Charge 2 showed limited utility in monitoring sleep in patients with obstructive sleep apnea. Support none

New Feature Vectors using GFCC for Speaker Identification

2018 ◽  
Vol 6 (8) ◽  
pp. 243
Author(s):  
A. Nagesh
Keyword(s):  
Speaker Recognition ◽  
Speaker Identification ◽  
Signal To Noise Ratio ◽  
Main Idea ◽  
Extraction Methods ◽  
Identification System ◽  
Identification Performance ◽  
Feature Vectors ◽  
Overall Performance ◽  
New Feature

The feature vectors of speaker identification system plays a crucial role in the overall performance of the system. There are many new feature vectors extraction methods based on MFCC, but ultimately we want to maximize the performance of SID system.  The objective of this paper to derive Gammatone Frequency Cepstral Coefficients (GFCC) based a new set of feature vectors using Gaussian Mixer model (GMM) for speaker identification. The MFCC are the default feature vectors for speaker recognition, but they are not very robust at the presence of additive noise. The GFCC features in recent studies have shown very good robustness against noise and acoustic change. The main idea is  GFCC features based on GMM feature extraction is to improve the overall speaker identification performance in low signal to noise ratio (SNR) conditions.

Improving the Computational Cost for Copied Region Detection in Forensic Images

2016 ◽  
Vol 2 (1) ◽  
pp. 55
Author(s):  
Tu Huynh-Kha ◽  
Thuong Le-Tien ◽  
Synh Ha ◽  
Khoa Huynh-Van
Keyword(s):  
Wavelet Transform ◽  
Euclidean Distance ◽  
Research Work ◽  
Computational Cost ◽  
Correlation Coefficients ◽  
Zernike Moments ◽  
Computational Time ◽  
Discrete Wavelet ◽  
Feature Vectors ◽  
Region Detection

This research work develops a new method to detect the forgery in image by combining the Wavelet transform and modified Zernike Moments (MZMs) in which the features are defined from more pixels than in traditional Zernike Moments. The tested image is firstly converted to grayscale and applied one level Discrete Wavelet Transform (DWT) to reduce the size of image by a half in both sides. The approximation sub-band (LL), which is used for processing, is then divided into overlapping blocks and modified Zernike moments are calculated in each block as feature vectors. More pixels are considered, more sufficient features are extracted. Lexicographical sorting and correlation coefficients computation on feature vectors are next steps to find the similar blocks. The purpose of applying DWT to reduce the dimension of the image before using Zernike moments with updated coefficients is to improve the computational time and increase exactness in detection. Copied or duplicated parts will be detected as traces of copy-move forgery manipulation based on a threshold of correlation coefficients and confirmed exactly from the constraint of Euclidean distance. Comparisons results between proposed method and related ones prove the feasibility and efficiency of the proposed algorithm.

Smart technology-assisted Home Nursing Care Program for Persons with Dementia or Hip Fracture: Implementation Difficulties: Thematic Analysis (Preprint)

2020 ◽  
Author(s):  
Yea-Ing Shyu ◽  
Chung-Chih Lin ◽  
Ching-Tzu Yang ◽  
Pei-Ling Su ◽  
Jung-Ling Hsu
Keyword(s):  
Hip Fracture ◽  
Family Caregivers ◽  
Nursing Care ◽  
Care Program ◽  
Wearable Devices ◽  
Elderly Persons ◽  
Home Nursing ◽  
Smart Technology ◽  
Smart Clothing ◽  
Home Nursing Care

BACKGROUND Wearable devices have been developed and implemented to improve data collection in remote health care and smart care. Wearable devices have the advantage of always being with individuals, enabling easy detection of their movements. In this study, we developed and implemented a smart-care system using smart clothing for persons with dementia and with hip fracture. We conducted a preliminary study to understand family caregivers’ and care receivers’ experiences of receiving a smart technology-assisted (STA) home-nursing care program. OBJECTIVE This paper reports the difficulties we encountered and strategies we developed during the feasibility phase of studies on the effectiveness of our STA home-nursing care program for persons with dementia and hip fracture. METHODS Our care model, a STA home-nursing care program for persons with dementia and those with hip fracture included a remote-monitoring system for elderly persons wearing smart clothing was used to facilitate family caregivers’ detection of elderly persons’ movements. These movements included getting up at night, staying in the bathroom for more than 30 minutes, not moving more than 2 hours during the day, leaving the house, and daily activities. Participants included 13 families with 5 patients with hip fracture and 7 with dementia. Research nurses documented the difficulties they encountered during the process. RESULTS Difficulties encountered in this smart-care study were categorized into problems setting up the smart-care environment, problems running the system, and problems with participant acceptance/adherence. These difficulties caused participants to drop out, the system to not function or delayed function, inability to collect data, extra costs of manpower, and financial burden. Strategies to deal with these problems are also reported. CONCLUSIONS During the implementation of smart care at home for persons with dementia or hip fracture, different aspects of difficulties were found and strategies were taken. The findings of this study can provide a reference for future implementation of similar smart-home devices.

Comparisons of physical activity and sedentary behavior between owners and non-owners of commercial wearable devices

2021 ◽  
Vol 141 (2) ◽  
pp. 89-96
Author(s):  
Hsin-Yen Yen ◽  
Hao-Yun Huang
Keyword(s):  
Physical Activity ◽  
Sleep Quality ◽  
Sedentary Behavior ◽  
Sedentary Time ◽  
Short Form ◽  
Wearable Devices ◽  
Wearable Device ◽  
World Health ◽  
World Health Organization Quality ◽  
Quality Of Life Scale

Aims: Wearable devices are a new strategy for promoting physical activity in a free-living condition that utilizes self-monitoring, self-awareness, and self-determination. The main purpose of this study was to explore health benefits of commercial wearable devices by comparing physical activity, sedentary time, sleep quality, and other health outcomes between individuals who used and those that did not use commercial wearable devices. Methods: The research design was a cross-sectional study using an Internet survey in Taiwan. Self-administered questionnaires included the International Physical Activity Questionnaire–Short Form, Pittsburgh Sleep Quality Index, Health-Promoting Lifestyle Profile, and World Health Organization Quality-of-Life Scale. Results: In total, 781 participants were recruited, including 50% who were users of wearable devices and 50% non-users in the most recent 3 months. Primary outcomes revealed that wearable device users had significantly higher self-reported walking, moderate physical activity, and total physical activity, and significantly lower sedentary time than non-users. Wearable device users had significantly better sleep quality than non-users. Conclusion: Wearable devices inspire users’ motivation, engagement, and interest in physical activity through habit formation. Wearable devices are recommended to increase physical activity and decrease sedentary behavior for promoting good health.

scholarly journals Wearable Technologies in Field Hockey Competitions: A Scoping Review

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5242
Author(s):  
Jolene Ziyuan Lim ◽  
Alexiaa Sim ◽  
Pui Wah Kong
Keyword(s):  
Heart Rate ◽  
Inertial Sensors ◽  
Wearable Devices ◽  
Field Hockey ◽  
Heart Rate Monitors ◽  
Search Terms ◽  
Physiological Demands ◽  
And Performance ◽  
Future Work ◽  
Skin Temperatures

The aim of this review is to investigate the common wearable devices currently used in field hockey competitions, and to understand the hockey-specific parameters these devices measure. A systematic search was conducted by using three electronic databases and search terms that included field hockey, wearables, accelerometers, inertial sensors, global positioning system (GPS), heart rate monitors, load, performance analysis, player activity profiles, and competitions from the earliest record. The review included 39 studies that used wearable devices during competitions. GPS units were found to be the most common wearable in elite field hockey competitions, followed by heart rate monitors. Wearables in field hockey are mostly used to measure player activity profiles and physiological demands. Inconsistencies in sampling rates and performance bands make comparisons between studies challenging. Nonetheless, this review demonstrated that wearable devices are being used for various applications in field hockey. Researchers, engineers, coaches, and sport scientists can consider using GPS units of higher sampling rates, as well as including additional variables such as skin temperatures and injury associations, to provide a more thorough evaluation of players’ physical and physiological performances. Future work should include goalkeepers and non-elite players who are less studied in the current literature.

Enabling Batteryless Wearable Devices by Transferring Power Through The Human Body

2021 ◽  
Vol 24 (3) ◽  
pp. 30-34
Author(s):  
Rishi Shukla ◽  
Neev Kiran ◽  
Rui Wang ◽  
Jeremy Gummeson ◽  
Sunghoon Ivan Lee
Keyword(s):  
Energy Source ◽  
Low Power ◽  
Human Body ◽  
Wearable Sensors ◽  
Primary Energy ◽  
Wearable Devices ◽  
Ultra Low Power ◽  
The Past ◽  
Key Barrier

Over the past few decades, we have witnessed tremendous advancements in semiconductor and MEMS technologies, leading to the proliferation of ultra-miniaturized and ultra-low-power (in micro-watt ranges) wearable devices for wellness and healthcare [1]. Most of these wearable sensors are battery powered for their operation. The use of an on-device battery as the primary energy source poses a number of challenges that serve as the key barrier to the development of novel wearable applications and the widespread use of numerous, seamless wearable sensors [5].

Sign in / Sign up

Export Citation Format

Share Document