scholarly journals Identification of Suitable Biomarkers for Stress and Emotion Detection for Future Personal Affective Wearable Sensors

Biosensors ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 40 ◽  
Author(s):  
Abdulaziz Zamkah ◽  
Terence Hui ◽  
Simon Andrews ◽  
Nilanjan Dey ◽  
Fuqian Shi ◽  
...  
Keyword(s):  
Emotional Stress ◽  
Wearable Sensors ◽  
Biological Information ◽  
Current Status ◽  
Physiological Parameter ◽  
Stress Monitoring ◽  
Detection Systems ◽  
Primary Stress ◽  
Stress Biomarkers ◽  
Skin Conductivity

Skin conductivity (i.e., sweat) forms the basis of many physiology-based emotion and stress detection systems. However, such systems typically do not detect the biomarkers present in sweat, and thus do not take advantage of the biological information in the sweat. Likewise, such systems do not detect the volatile organic components (VOC’s) created under stressful conditions. This work presents a review into the current status of human emotional stress biomarkers and proposes the major potential biomarkers for future wearable sensors in affective systems. Emotional stress has been classified as a major contributor in several social problems, related to crime, health, the economy, and indeed quality of life. While blood cortisol tests, electroencephalography and physiological parameter methods are the gold standards for measuring stress; however, they are typically invasive or inconvenient and not suitable for wearable real-time stress monitoring. Alternatively, cortisol in biofluids and VOCs emitted from the skin appear to be practical and useful markers for sensors to detect emotional stress events. This work has identified antistress hormones and cortisol metabolites as the primary stress biomarkers that can be used in future sensors for wearable affective systems.

A Multi-User Multi-Task Model For Stress Monitoring From Wearable Sensors

2018 ◽  
Author(s):  
Oumayma Sakri ◽  
Christelle Godin ◽  
Gael Vila ◽  
Etienne Labyt ◽  
Sylvie Charbonnier ◽  
...  
Keyword(s):  
Wearable Sensors ◽  
Stress Monitoring ◽  
Task Model

scholarly journals UP-Fall Detection Dataset: A Multimodal Approach

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 1988 ◽  
Author(s):  
Lourdes Martínez-Villaseñor ◽  
Hiram Ponce ◽  
Jorge Brieva ◽  
Ernesto Moya-Albor ◽  
José Núñez-Martínez ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Community ◽  
Wearable Sensors ◽  
Fall Detection ◽  
Machine Learning Techniques ◽  
Elderly Persons ◽  
Negative Consequences ◽  
Detection Systems ◽  
Important Health ◽  
Experimental Use

Falls, especially in elderly persons, are an important health problem worldwide. Reliable fall detection systems can mitigate negative consequences of falls. Among the important challenges and issues reported in literature is the difficulty of fair comparison between fall detection systems and machine learning techniques for detection. In this paper, we present UP-Fall Detection Dataset. The dataset comprises raw and feature sets retrieved from 17 healthy young individuals without any impairment that performed 11 activities and falls, with three attempts each. The dataset also summarizes more than 850 GB of information from wearable sensors, ambient sensors and vision devices. Two experimental use cases were shown. The aim of our dataset is to help human activity recognition and machine learning research communities to fairly compare their fall detection solutions. It also provides many experimental possibilities for the signal recognition, vision, and machine learning community.

scholarly journals A Resilient and Hierarchical IoT-based Solution for Stress Monitoring in Everyday Settings

2021 ◽  
Author(s):  
Shiyi Jiang ◽  
Farshad Firouzi ◽  
Krishnendu Chakrabarty ◽  
Eric Elbogen
Keyword(s):  
Network Model ◽  
Wearable Sensors ◽  
Cost Effective ◽  
Health Concern ◽  
Stress Monitoring ◽  
Physical And Mental Health ◽  
Matching Network ◽  
Fisher Score ◽  
Edge Layer ◽  
Electrocardiogram Ecg

<div><div><div><p>Long-term stress is a global health concern because it impacts our physical and mental health. The emergence of Internet of Things (IoT) and Artificial Intelligence (AI) makes stress monitoring and treatment more accessible compared to today’s physician-centered healthcare system. However, existing solutions either fail to incorporate IoT technology or are not cost-effective. We propose a resilient, hierarchical IoT-based solution for stress monitoring to tackle the above problems. Multimodal data was collected from wearable sensors and underwent preprocessing, feature extraction, and multiple imputation. We applied three feature-selection methods prior to lightweight SVM classification at the edge layer, and utilized a CNN and a matching network model in the cloud layer. We obtained an accuracy of 86.7347% and an F1 score of 0.8725 at the edge using only 10 features selected based on the Fisher score. An accuracy of 98.9247% and an F1 score of 0.9876 was achieved by a matching network model based on electrocardiogram (ECG) data. The trade-off between the communication cost from the edge to the cloud and the overall accuracy was evaluated. Our hierarchical-IoT solution for stress-level evaluation provides insights into the potentiality of IoT and AI technology-based eHealth solutions.</p></div></div></div>

scholarly journals A Resilient and Hierarchical IoT-based Solution for Stress Monitoring in Everyday Settings

2021 ◽  
Author(s):  
Shiyi Jiang ◽  
Farshad Firouzi ◽  
Krishnendu Chakrabarty ◽  
Eric Elbogen
Keyword(s):  
Network Model ◽  
Wearable Sensors ◽  
Cost Effective ◽  
Health Concern ◽  
Stress Monitoring ◽  
Physical And Mental Health ◽  
Matching Network ◽  
Fisher Score ◽  
Edge Layer ◽  
Electrocardiogram Ecg

<div><div><div><p>Long-term stress is a global health concern because it impacts our physical and mental health. The emergence of Internet of Things (IoT) and Artificial Intelligence (AI) makes stress monitoring and treatment more accessible compared to today’s physician-centered healthcare system. However, existing solutions either fail to incorporate IoT technology or are not cost-effective. We propose a resilient, hierarchical IoT-based solution for stress monitoring to tackle the above problems. Multimodal data was collected from wearable sensors and underwent preprocessing, feature extraction, and multiple imputation. We applied three feature-selection methods prior to lightweight SVM classification at the edge layer, and utilized a CNN and a matching network model in the cloud layer. We obtained an accuracy of 86.7347% and an F1 score of 0.8725 at the edge using only 10 features selected based on the Fisher score. An accuracy of 98.9247% and an F1 score of 0.9876 was achieved by a matching network model based on electrocardiogram (ECG) data. The trade-off between the communication cost from the edge to the cloud and the overall accuracy was evaluated. Our hierarchical-IoT solution for stress-level evaluation provides insights into the potentiality of IoT and AI technology-based eHealth solutions.</p></div></div></div>

Early prediction of efficacy of endocrine therapy in breast cancer (BC): Pilot study and validation with 18F fluoroestradiol (18F-FES) PET/CT.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. TPS649-TPS649
Author(s):  
Alessandra Gennari ◽  
Dino Amadori ◽  
Etienne Brain ◽  
Javier Cortes ◽  
Nadia Harbeck ◽  
...  
Keyword(s):  
Treatment Options ◽  
Endocrine Resistance ◽  
Drop Out ◽  
Biological Information ◽  
Current Status ◽  
Predictive Score ◽  
First Line ◽  
Pet Ct ◽  
Er Expression

TPS649 Background: Almost 70% of early BC are endocrine responsive, as defined by estrogen receptor (ER) expression; however roughly 30% of ER+ BC patients will relapse despite adjuvant ET. Moreover, 10 to 20% of BC metastases lose ER expression. The upfront administration of ET in ER+ women with MBC is recommended by major guidelines. However, the early identification of endocrine resistance might improve systemic treatment options, sparing unnecessary toxicities and inactive drugs. 18F-FES, an oestradiol analogue labeled with 18F, may allow to test the performance of ERs, by testing their in vivo linkage ability. In MBC, 18F-FES uptake has been proposed to be a better predictor of response to ET than ER expression itself. The aim of the ET-FES study is to validate the predictive value of 18F-FES uptake at PET/CT scan in metastatic ER+ patients. Methods: This is aphase II, multicentric european comparative study of first line ET vs CT in ER+ MBC with low 18F- FES uptake. The primary endpoint is disease control rate (DCR). Correlative studies include: 1. Optimization of 18F-FES production; 2. Association between gene alterations in ESR1/ESR2 genes and 18F- FES uptake; 3. Development of a predictive score of endocrine responsiveness based on 18F-FES SUV value and clinical and biological information. All patients with ER+ MBC candidate to first line ET will receive a 18F-FES CT/PET at baseline, in addition to standard staging. Patients with 18F-FES uptake (SUV) > 2 will receive ET. Patients with 18F-FES SUV < 2 will be randomized to ET until disease progression (control arm) or CT (single agents) until PD. A total of 220 patients with ER+ MBC will be enrolled. Of these, approximately 50% (n=110) will show a 18F-FES SUV < 2 and will be randomized to ET or CT. The study will have 85% power to detect an absolute 20% difference in the DCR between arms after 3 months of therapy, assuming a 5% two-sided alpha level and a 10% drop-out rate. Current status: The ET-FES study was approved for funding by the ist Join TRANSCAN European call. 18F-FES production is currently on final development (GMP), and the clinical protocol is being finalized for EC approval in the different EU countries. Clinical trial information: 2013-000287-29.

Electrochemical Affinity Assays/Sensors: Brief History and Current Status

2021 ◽  
Vol 14 (1) ◽  
pp. 109-131
Author(s):  
Kenneth R. Wehmeyer ◽  
Ryan J. White ◽  
Peter T. Kissinger ◽  
William R. Heineman
Keyword(s):  
Quantum Dots ◽  
Early Development ◽  
Electrochemical Detection ◽  
Wearable Sensors ◽  
Lab On A Chip ◽  
Ease Of Use ◽  
Current Status ◽  
The Past ◽  
User Friendly

The advent of electrochemical affinity assays and sensors evolved from pioneering efforts in the 1970s to broaden the field of analytes accessible to the selective and sensitive performance of electrochemical detection. The foundation of electrochemical affinity assays/sensors is the specific capture of an analyte by an affinity element and the subsequent transduction of this event into a measurable signal. This review briefly covers the early development of affinity assays and then focuses on advances in the past decade. During this time, progress on electroactive labels, including the use of nanoparticles, quantum dots, organic and organometallic redox compounds, and enzymes with amplification schemes, has led to significant improvements in sensitivity. The emergence of nanomaterials along with microfabrication and microfluidics technology enabled research pathways that couple the ease of use of electrochemical detection for the development of devices that are more user friendly, disposable, and employable, such as lab-on-a-chip, paper, and wearable sensors.

scholarly journals Investigation of Polyurethane Matrix Membranes for Salivary Nitrate ISFETs to Prevent the Drift

Sensors ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 2713
Author(s):  
Shuto Osaki ◽  
Takuya Kintoki ◽  
Takayo Moriuchi-Kawakami ◽  
Kenichi Kitamura ◽  
Shin-ichi Wakida
Keyword(s):  
Field Effect Transistors ◽  
Wearable Sensors ◽  
Single Drop ◽  
Stress Monitoring ◽  
Stress Markers ◽  
Whole Saliva ◽  
Selective Membrane ◽  
Human Stress ◽  
Polyurethane Matrix ◽  
Matrix Membranes

We have investigated human-stress monitoring by making use of salivary nitrate, which can be a candidate for stress markers, with ion-selective field-effect transistors (ISFETs). ISFETs are suitable for on-site single-drop analysis of salivary nitrate within 10 s. However, when ISFETs are used for salivary nitrate, ISFETs have a problem that is called the initial drift. The initial drift makes accurate nitrate monitoring difficult. Thus, the purpose of this study is to prevent the initial drift and to search for a new, simple polymer to possess a better performance of sensor responses than conventional matrix membranes, such as PVC. In this research, we investigated ISFETs using specific matrix membranes, for example KP-13, Pellethane®­­, and P7281-PU. The initial drift was evaluated from the fluctuations of the response values generated by the ISFETs when immersed in saliva or aqueous solution. As a result, P7281-PU showed a prevention effect on the initial drift, both in the whole saliva and in various solutions. Furthermore, the cause of drift may be H+ diffusion, and the drift prevention effect of P7281-PU may be affected by urethane bond capturing H+ in the ion-selective membrane. This result suggests that a continuous nitrate monitoring is feasible and may be applied to wearable sensors.

scholarly journals On Crowd-verification of Biological Networks

2013 ◽  
Vol 7 ◽  
pp. BBI.S12932 ◽  
Author(s):  
Sam Ansari ◽  
Jean Binder ◽  
Stephanie Boue ◽  
Anselmo Di Fabio ◽  
William Hayes ◽  
...  
Keyword(s):  
Biological Networks ◽  
Network Models ◽  
Biological Information ◽  
Current Status ◽  
Biological Knowledge ◽  
Web Based ◽  
Domain Experts ◽  
Graphical Interfaces ◽  
Continuous Use ◽  
Complexity Increase

Biological networks with a structured syntax are a powerful way of representing biological information generated from high density data; however, they can become unwieldy to manage as their size and complexity increase. This article presents a crowd-verification approach for the visualization and expansion of biological networks. Web-based graphical interfaces allow visualization of causal and correlative biological relationships represented using Biological Expression Language (BEL). Crowdsourcing principles enable participants to communally annotate these relationships based on literature evidences. Gamification principles are incorporated to further engage domain experts throughout biology to gather robust peer-reviewed information from which relationships can be identified and verified. The resulting network models will represent the current status of biological knowledge within the defined boundaries, here processes related to human lung disease. These models are amenable to computational analysis. For some period following conclusion of the challenge, the published models will remain available for continuous use and expansion by the scientific community.

Sign in / Sign up

Export Citation Format

Share Document