Questions related to Wearable Sensors
I`m organizing a testing campaign to evaluate a set tools designed for astronauts using VR (Virtual Reality). To measure the design performance we will use two well established performance evaluation methods, but they are both qualitative (NASA TLX and mSUS). I had the idea to add a quantitative control data layer to the experiment, using biometric feedbacks from wearable sensors.
Since I`m not a physician, I`m not sure which kind of data (and so sensors) will be best suited to measure stress and focus, and which indicators to look for. On the market there is a huge range of wearable sensors (hearth monitors, skin temperature and moisture, breathing levels, ECG).
Thank you for any suggestions or researches you can share on this topic.
We know cardiac diseases are among the deadliest diseases in the world and smart wearables are becoming more popular among people during their daily life. So, there is a lot of data collected from people. In addition, AI/ML models reach more accuracy when they are trained with larger datasets. It looks like it is a decent match. What are the challenges and difficulties in this regard in your opinion?
I am seeking Q1-ranked JCR journals in order to publish own datasets to make them publicly available to the community.
Datasets are about wearable sensor data from smartwatches, wristband and EEG headbands. And the topics are different: emotion recognition, activities of daily living of older adults...
Remote delivery of cardiac rehabilitation services using smartphones, the internet, or wearable sensors.
Can anyone recommend papers of the below time-series classification?
I have tried implementing a decision-making program.
The input variables include:
(1) time-series data measured by wearable sensors (numerical data)
(2) human data such as gender, birth, blood type, etc (categorical data).
The (1) was collected every 10ms and (2) was obtained every session.
(A session consists of 30 minutes)
The output variables are some gestures (multiple classes).
This problem has been defined as time-series classification.
I've read some time-series classification articles, but most classifiers deal with numerical time-series data only. (e.g. sensor data input, multiple classes output)
Public health is the art and science of promoting health, preventing diseases, and increasing health and lifespan through the organized efforts of society. It is believed that sport plays an important role in physical and mental health as it incorporates physical activity. Physical activities during sports are associated with risks for injury, such as concussions in contact sports and over-use injuries in sports requiring frequent repetition of the same movement.
Although sports injuries and their aftermath have been well-studied, less attention has been given to public health, especially using technology. The use of AI-enabled IoT devices in sports can reduce the risk of injuries and enhance the efficiency, capabilities, and fitness of athletes, spectators, coaches, and officials. The use of AI-enabled IoT devices in sports and public health has huge implications for research, businesses, and future activities of mankind. This is due to the fact that the IoT devices are required to extract an unprecedented amount of health data that can be filtered, processed, and analyzed using AI and machine learning. As a result, any system based on these technologies can obtain the benefits of collecting, processing, and analyzing highly valuable data of athletes, trainers, spectators, coaches, and officials. These technologies are beneficial for injury prevention, disease transmission, on-time diagnosis, and treatments for various diseases in an easy and cost-effective way.
The aim of this Special Issue is to identify public health concerns associated with sports using AI-enabled IoT devices and machine learning algorithms. Moreover, this Special Issue will address how the brain works during sports and analyze gait techniques and human activities and their effects on health. This Special Issue aims to motivate researchers from both academia and industry to investigate and analyze various aspects of AI-enabled IoT devices and their roles in sports and public health. Any pioneering methods and algorithms detailed in original research and review articles that offer improvements in sports and public health are welcome.
Potential topics include but are not limited to the following:
- Internet of Medical Things in sports and public health
- AI and IoT-assisted technology in human activity recognition during sports
- AI-enabled IoT applications in neurodegenerative health issues
- Analyzing cognitive abilities during sports
- Connecting the brain with sports and public health
- Deep learning-based processing and diagnostic analysis of biomedical sensor data
- Gait analysis based on group wearable sensors in sports
- Novel designs in machine learning and statistical applications in health informatics
- Intelligent monitoring of amputee behavior analysis using wearable technology
- Digital healthcare system for athletes using sensor-based technology
- Applications of wireless body area networks in sports
- Data- and model-driven intelligent and smart healthcare systems
- Novel designs of smart health services using big data analytics
- Novel application and evaluation study in sports and public health
My lab has openings for graduate research scholars. I am looking for a highly motivated students for leveraging advanced bioelectromagnetics approaches to design and develop the new generation of smarter wearable sensors that provide medically accurate data. The ideal candidate will be a recent and motivated undergraduate in Electrical Engineering or Biomedical Engineering with strong academic records. The candidate will be expected to develop state-of-the-art wearable technologies to sense, perceive and control biological systems at the University of Utah. This work will contribute to the development of novel electromagnetic technologies to create innovative and impactful solutions. Visit srl.ece.utah.edu if interested.
If so, we're hiring! - come and join our team to help develop the next generation of intelligent, wearable drug delivery devices. Research opportunities now available in microsensor integration, transdermal delivery and microfludics, and system electronics/communications. Further details available from Dr Conor O'Mahony - feel free to discuss with us!
I'm trying to synchronize imu sensor with the Motion Capture system. Is this possible? If so, how?
thanks for answering
I want to detect relative movement between fingers with wearable sensors. Which could be an appropriate technology for this?
Affective technologies are the interfaces concerning the emotional artificial intelligence branch known as affective computing (Picard, 1997). Applications such as facial emotion recognition technologies, wearables that can measure your emotional and internal states, social robots interacting with the user by extracting and perhaps generating emotions, voice assistants that can detect your emotional states through modalities such as voice pitch and frequency and so on...
Since these technologies are relatively invasive to our private sphere (feelings), I am trying to find influencing factors that might enhance user acceptance of these types of technologies in everyday life (I am measuring the effects with the TAM). Factors such as trust and privacy might be very obvious, but moderating factors such as gender and age are also very interesting. Furthermore, I need relevant literature which I can ground my work on since I am writing a literature review on this topic.
I am thankful for any kind of help!
I am working on activity recognition using wearable sensor data. Actually, I am confused to correctly specify the window size for my activities. Here, I am considering a sliding window technique for my work.
The accurate window size plays a vital role in the detection of activity; it affects the features, and whenever any features get affected, it directly hinders the performance of a classifier. I am working on four activities (Ac1, Ac2, Ac3, and Ac4), which are totally different in nature. In the AC1, the average person’s time is at least12 s, the maximum being 20 s, to complete one cycle of AC1. On the other hand, AC2 and AC3 activities are not regular activities compared to AC1. User lasts for 4 to 6 seconds to complete one circle of these two activities. In the Ac4, the average person time is 10 second to complete the activity.
So, my question is what should be my window size for this kind of activities to correctly process? A reply would be greatly appreciated.
For anyone that are working on all the interdisciplinary research topics involved in lifelog applications—data acquisition, semantic integration, data processing and mining, data categorization and summarization, and information retrieval data privacy and security, among others, there is an open call for manuscripts to the Applied Sciences journal by MDPI (Impact Factor 2.217).
Some keywords about the topic are:
- mobile/wearable sensors and devices remote heath monitoring
- data integration
- joint knowledge extraction
- semantic interoperability signal processing
- image processing
- data mining
- image and information retrieval sentiment analysis
- machine learning
- data privacy
You are welcome to contributions to this topic. Please bring scientific contributions to this topic.
My project is to design an antenna for wearable applications. Right now my substrate is PTFE (Teflon) but that is just plastic I think. I am looking for suggestions on the substrate. Can I use PTFE as a substrate for wearable applications or if I can have some suggestions on substrate material which is good for wearable applications.
I am working on sport activity recognition based on wearable sensor data specifically accelerometer and gyroscope. I would appreciate your cooperation if you share such dataset.
Hi, I need a wearable/fingertip health device to create a mobile application and measure the level of stress. I need at least 3 of these physiological factors: heart rate, respiratory rate, pulse oxygenation, blood pressure, HRV. In addition, I need a way to pass this data to my mobile application. Are there any devices that allow me to do that?
I am a new comer for the research of portable or wearable sensor for disease diagnose. If such sensor is integrated in smart phone, it will be promising. The current portable sensors are isolated from smart phone, but can be candidates for smart phone additives. Would you like to tell me about some companies, which already developed some portable sensors or detectors for health care.
Thank you very much!
Is there a software, standard or publications touching on how to keep track of where IoT devices are currently located?
Are there softwares, standards or publications touching on how to map them into a location and visually present them in their current location
I am currently an investigator in a CRT using gamification to reduce obesity. Part of the intervention is to provide schoolchildren and one family member with an activity tracker and reward those who exceed a threshold of steps with points.
For the pilot study, we purchased two activity trackers: Omron HJ-324U and Jawbone UP Move. The data cannot be extracted in bulk.
Do you have any guidance on which trackers allow bulk data extraction or how this can be done?
my descriptive model (task vs methods) for early development of a smart clothing design project for vital sign monitoring is available. In this project which did under supervision of an industrial designer, the model has drawn after completing the project.
(the model mostly illustrate an inspiration from Milton and Rodgers's (2013) book "research methods for product design" ; which termed an internal iteration within each phase. But have some addition for showing unknown condtions of project).
We're working a single lead ECG patch which we would like test in home environment for a long term period. What particular ECG electrode brands would you recommend for long term use (2-3 weeks)? What is the feedback you have heard from test subjects on comfort and usability with the same electrodes?
I am currently using foam based Ambu White sensor electrodes.
Exploring ways to integrate wearables and other sensors to track mobility and cognitive function for early development testing of drugs for Parkinson's Disease, Multiple Sclerosis, ALS, and Alzheimer's Disease
What is predicted to occur regarding the future (next 5 years) of wearable patches for healthcare?
Specifically how many of these patches will be sold to public commerce? As well, how many of these patches will incorporate 'smart' electronics vs. -only-chemistry (drug delivery) or will these patches have both?
I am looking for a wearable programmable accelerometer sensor. Something like the Shimmer platform (http://www.shimmersensing.com/shop/shimmer3), but not that expensive (max. 150 EUR).
The platform should allow creating custom firmware, so I can implement some algorithms for data analysis locally (on the sensor itself).
Also a wireless communication is needed (WiFi or Bluetooth).
If you have any suggestions please let me know.
Thanks in advance.
I am researching wearable/embeddable/ingestible technology for my MRP and am having trouble finding experts in the field of ingestibles. Any help in this area would be greatly appreciated.
I am searching for a device to measure ECG and EDA. Ideally the device should be worn on the wrist or the arm. I prefer not to use chest band or similar.
The monitoring of public spaces is a very sensitive issue as it entails the tracking and observing of people captured by a deployed network of video cameras. The monitoring may be dealt with at different levels of detail, depending on the type of technology employed, with regards to the dimensions of the monitored area, the topology of the sensor network, its location and the purpose of monitoring (security, crowd management, service delivery, etc.)
In particular face detection techniques joined with geotagging GPS Devices act as a distributed sensor node able to detect the identity, location, social connections, and more of any other person he encounters in public environment. In security surveillance perspective these ICT technologies are quite useful, but according to personal privacy the risk for abuse in such a system is substantial.