Writing applications using the Microsoft Kinect Sensorphildenoncourt
The document discusses writing applications using the Microsoft Kinect sensor, outlining the Kinect features such as motion sensing, RGB camera and depth sensor, and describing the Kinect SDK requirements and capabilities including access to video, depth and skeleton streams. It also covers limitations of the Kinect like lack of finger tracking and face recognition as well as possible application areas for the Kinect such as kiosks, security monitoring and video conferencing.
The Kinect sensor is an input device by Microsoft that uses cameras and microphones to track body movements and recognize gestures and voices. It consists of an RGB camera, depth sensor using infrared light, and 4-microphone array. The depth sensor uses structured light to measure distances by projecting a pattern and analyzing its distortion. Kinect can track up to 20 joints of the human body in real-time using skeletal tracking. It has applications in 3D scanning, sign language translation, augmented reality, robot control, and virtual fitting rooms due to its low-cost depth sensing capabilities.
Sensor fusion between car and smartphoneGabor Paller
This document discusses sensor fusion between a car and smartphone to enable new applications. It describes relevant sensors on each device - cars provide power, position and built-in sensors while phones contribute GPS, accelerometer, gyroscope and compass. Obtaining car data via OBDII is described, along with challenges like magnetic interference. Two use cases are proposed: dead reckoning navigation without GPS by combining car speed and phone direction, and vibration analysis using the phone's accelerometer to detect road conditions when driving. Overall, integrating car and phone sensors can provide richer data but also requires handling sensor limitations.
Better motion control using accelerometer/gyroscope sensor fusionGabor Paller
This document discusses using accelerometer and gyroscope sensor fusion to improve motion control. It begins by reviewing a previous presentation on using only an accelerometer for motion recognition. It then describes how each sensor - accelerometer, gyroscope, and compass - measures motion differently, with strengths and weaknesses. The main idea is to use a gyroscope to compensate for the gravity component detected by the accelerometer, allowing separation of gravity from motion acceleration. This allows more accurate motion recognition compared to using just acceleration. Implementation examples and conclusions are provided on potential applications and approaches to sensor fusion.
This document summarizes a presentation on methods for collecting spatial data in epidemiological research. It discusses tools for collecting location information like residential history questionnaires and GPS tracking. It presents the VERITAS online mapping questionnaire used to collect spatial data on regular destinations. An example of its use in the RECORD study is provided. A multisensor platform for real-time tracking of mobility, physical activity, and physiology is described. Issues around data processing and using spatial data to understand environmental exposures and health behaviors are also covered.
PAMS: A new position-aware multi-sensor dataset for human activity recognitio...Maynooth University
Nowadays smartphones are ubiquitous in various aspects of our lives. The processing power, communication bandwidth, and the memory capacity of these devices have surged considerably in recent years. Besides, the variety of sensor types, such as accelerometer, gyroscope, humidity sensor, and bio-sensors, which are embedded in these devices, opens a new horizon in self-monitoring of physical daily activities. One of the primary steps for any research in the area of detecting daily life activities is to test a detection method on benchmark datasets. Most of the early datasets limited their work to collecting only a single type of sensor data such as accelerometer data. While some others do not consider age, weight, and gender of the subjects who have participated in collecting their activity data. Finally, part of the previous works collected data without considering the smartphone's position. In this paper, we introduce a new dataset, called Position-Aware Multi-Sensor (PAMS). The dataset contains both accelerometer and gyroscope data. The gyroscope data boosts the accuracy of activity recognition methods as well as enabling them to detect a wider range of activities. We also take the user information into account. Based on the biometric attributes of the participants, a separate learned model is generated to analyze their activities. We concentrate on several major activities, including sitting, standing, walking, running, ascending/descending stairs, and cycling. To evaluate the dataset, we use various classifiers, and the outputs are compared to the WISDM. The results show that using the aforementioned classifiers, the average precision for all activities is above 88.5%. Besides, we measure the CPU, memory, and bandwidth usage of the application collecting data on the smartphone.
https://ieeexplore.ieee.org/document/8310680/
Writing applications using the Microsoft Kinect Sensorphildenoncourt
The document discusses writing applications using the Microsoft Kinect sensor, outlining the Kinect features such as motion sensing, RGB camera and depth sensor, and describing the Kinect SDK requirements and capabilities including access to video, depth and skeleton streams. It also covers limitations of the Kinect like lack of finger tracking and face recognition as well as possible application areas for the Kinect such as kiosks, security monitoring and video conferencing.
The Kinect sensor is an input device by Microsoft that uses cameras and microphones to track body movements and recognize gestures and voices. It consists of an RGB camera, depth sensor using infrared light, and 4-microphone array. The depth sensor uses structured light to measure distances by projecting a pattern and analyzing its distortion. Kinect can track up to 20 joints of the human body in real-time using skeletal tracking. It has applications in 3D scanning, sign language translation, augmented reality, robot control, and virtual fitting rooms due to its low-cost depth sensing capabilities.
Sensor fusion between car and smartphoneGabor Paller
This document discusses sensor fusion between a car and smartphone to enable new applications. It describes relevant sensors on each device - cars provide power, position and built-in sensors while phones contribute GPS, accelerometer, gyroscope and compass. Obtaining car data via OBDII is described, along with challenges like magnetic interference. Two use cases are proposed: dead reckoning navigation without GPS by combining car speed and phone direction, and vibration analysis using the phone's accelerometer to detect road conditions when driving. Overall, integrating car and phone sensors can provide richer data but also requires handling sensor limitations.
Better motion control using accelerometer/gyroscope sensor fusionGabor Paller
This document discusses using accelerometer and gyroscope sensor fusion to improve motion control. It begins by reviewing a previous presentation on using only an accelerometer for motion recognition. It then describes how each sensor - accelerometer, gyroscope, and compass - measures motion differently, with strengths and weaknesses. The main idea is to use a gyroscope to compensate for the gravity component detected by the accelerometer, allowing separation of gravity from motion acceleration. This allows more accurate motion recognition compared to using just acceleration. Implementation examples and conclusions are provided on potential applications and approaches to sensor fusion.
This document summarizes a presentation on methods for collecting spatial data in epidemiological research. It discusses tools for collecting location information like residential history questionnaires and GPS tracking. It presents the VERITAS online mapping questionnaire used to collect spatial data on regular destinations. An example of its use in the RECORD study is provided. A multisensor platform for real-time tracking of mobility, physical activity, and physiology is described. Issues around data processing and using spatial data to understand environmental exposures and health behaviors are also covered.
PAMS: A new position-aware multi-sensor dataset for human activity recognitio...Maynooth University
Nowadays smartphones are ubiquitous in various aspects of our lives. The processing power, communication bandwidth, and the memory capacity of these devices have surged considerably in recent years. Besides, the variety of sensor types, such as accelerometer, gyroscope, humidity sensor, and bio-sensors, which are embedded in these devices, opens a new horizon in self-monitoring of physical daily activities. One of the primary steps for any research in the area of detecting daily life activities is to test a detection method on benchmark datasets. Most of the early datasets limited their work to collecting only a single type of sensor data such as accelerometer data. While some others do not consider age, weight, and gender of the subjects who have participated in collecting their activity data. Finally, part of the previous works collected data without considering the smartphone's position. In this paper, we introduce a new dataset, called Position-Aware Multi-Sensor (PAMS). The dataset contains both accelerometer and gyroscope data. The gyroscope data boosts the accuracy of activity recognition methods as well as enabling them to detect a wider range of activities. We also take the user information into account. Based on the biometric attributes of the participants, a separate learned model is generated to analyze their activities. We concentrate on several major activities, including sitting, standing, walking, running, ascending/descending stairs, and cycling. To evaluate the dataset, we use various classifiers, and the outputs are compared to the WISDM. The results show that using the aforementioned classifiers, the average precision for all activities is above 88.5%. Besides, we measure the CPU, memory, and bandwidth usage of the application collecting data on the smartphone.
https://ieeexplore.ieee.org/document/8310680/
Human Activity Recognition Using SmartphoneIRJET Journal
The document discusses human activity recognition using smartphone sensors. It proposes using a CNN-LSTM model to classify activities like walking, running, and sitting based on accelerometer and gyroscope sensor data from a smartphone. The CNN extracts features from the sensor data, while the LSTM recognizes sequences of activities over time. The model is implemented in an Android application that recognizes activities in real-time and also counts steps, distance, and calories burned. The application uses built-in smartphone sensors like accelerometer, gyroscope, and pedometer to recognize activities affordably and with high availability without external devices. The CNN-LSTM model achieves accurate activity recognition compared to other machine learning techniques.
VISION / AMBITION
-Australia the first drone-sensed nation (cm-scale)
-Pre-competitive data release for industry, environmental management, education & research
-Conventional survey & remote sensing techniques at ultra-high resolution and flexibility (time-series, rapid response etc)
-Next gen “UNDERCOVER” techniques (minerals and water resources)
Physiological monitoring has become increasingly popular with the availability of advanced technology. Techtiles aims to consolidate sensors that normally are not found together on one device to monitor a user's heart activity, breathing, and movement and process the data to compute heart rate, respiration rate, steps, distance, and energy burned. The prototype demonstrated accuracy within 17 beats/min for heart rate, 10 breaths/min for respiration, and was able to be worn comfortably for monitoring purposes.
Seminar given with Basile Chaix at London School of Hygiene and Tropical Medicine on Mobility and Exposure assessment for Epidemiological Modelling. Organisation: Steven Cummins & Daniel Lewis.
Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...Zohaib Riaz
Slides for our work presented at MobiQuitous 2017 Conference (http://mobiquitous.org/).
Full paper text: ftp://ftp.informatik.uni-stuttgart.de/pub/library/ncstrl.ustuttgart_fi/INPROC-2017-46/INPROC-2017-46.pdf
This paper focused on revealing weaknesses of existing location obfuscation approaches when an attacker possesses accurate or obfuscated location history information.
A benchmark dataset to evaluate sensor displacement in activity recognitionOresti Banos
This work introduces an open benchmark dataset to investigate inertial sensor displacement effects in activity recognition. While sensor position displacements such as rotations and translations have been recognised as a key limitation for the deployment of wearable systems, a realistic dataset is lacking. We introduce a concept of gradual sensor displacement conditions, including ideal, self-placement of a user, and mutual displacement deployments. These conditions were analysed in the dataset considering 33 fitness activities, recorded using 9 inertial sensor units from 17 participants. Our statistical analysis of acceleration features quantified relative effects of the displacement conditions. We expect that the dataset can be used to benchmark and compare recognition algorithms in the future.
This presentation illustrates part of the work described in the following article:
* Banos, O., Toth, M. A., Damas, M., Pomares, H., Rojas, I., Amft, O.: A benchmark dataset to evaluate sensor displacement in activity recognition. In: Proceedings of the 14th International Conference on Ubiquitous Computing (Ubicomp 2012), Pittsburgh, USA, September 5-8, (2012)
Sparse Mat: A Tale of Devising A Low-Cost Directional System for Pedestrian C...Tarik Reza Toha
Pedestrian counting is required in diversified places such as shopping malls, touristic spots, etc., however, a low-cost solution to this problem is yet to be proposed in the literature. Therefore, in this paper, we propose a new solution for pedestrian counting that exploits only a small number of COTS sensors (94% less than that used in the existing Eco-Counter solution). To do so, we propose detail designs and two different algorithms for separately sensing step-down and step-up phenomena that we find while walking. User evaluation of real implementations of both our algorithms confirms an average accuracy of up to 93% through sensing the step-up phenomena.
Internet of Things and the Value of Tracking EverythingPaul Barsch
This presentation was given to an executive MBA session at UCSD in April 2016. The session reviewed big data, internet of things, and how companies are gaining value from location, sensor, manufacturing and other data to make better business decisions.
Dr. Frederica Darema presents an overview of his program, Dynamic Data Driven Applications Systems (DDDAS), at the AFOSR 2013 Spring Review. At this review, Program Officers from AFOSR Technical Divisions will present briefings that highlight basic research programs beneficial to the Air Force.
Presentation Location and Context World, 2015. Palo Alto, CA November 3-4, 2015.
Abstract: Creating useful local context requires big data platforms and marketplaces. Contextual awareness is relevant to location based marketing, first responders, urban planners and many others. Location-aware mobile devices are revolutionizing how consumers and brands interact in the physical world. Situational awareness is a key element to efficiently handling any emergency response. In all cases, big data processing and high velocity streaming of location based data creates the richest contextual awareness. Data from many sources including IoT devices, sensor webs, surveillance and crowdsourcing are combined with semantically-rich urban and indoor data models. The resulting context information is delivered to and shared by mobile devices in connected and disconnected operations. Standards play a key role in establishing context platforms and marketplaces. Successful approaches will consolidate data from ubiquitous sensing technologies on a common space-time basis to enabled context-aware analysis of environmental and social dynamics.
IRJET- Surveillance of Object Motion Detection and Caution System using B...IRJET Journal
This document describes a proposed surveillance system using a block matching algorithm for motion detection. The system would use IP cameras to stream video that is monitored for unauthorized activity. Motion detection is performed by comparing frames using the block matching algorithm to detect changes in pixel intensity values, which would trigger an alarm. The block matching algorithm divides frames into blocks of pixels and validates the maximum and minimum intensity of each pixel. Comparing blocks between frames identifies motion if intensity values change beyond a threshold. If motion is detected in a designated sensitive area, the system saves the video and sends alerts by email and mobile notification to users.
Participatory Health Surveys – Sergiusz Pawlowicz et al, Centre for Geospatia...JISC GECO
The document summarizes a participatory health GIS project by the Centre for Geospatial Science at the University of Nottingham. The project aims to develop a dynamic surveying system using open source software and open standards to allow public participation in health surveys. Key goals are reusing data and software, having a dynamic surveying engine for real-time analysis, and ensuring interoperability, privacy, and real-time pre-diagnostics through a web-based system.
Aspects of Reproducibility in Earth ScienceRaul Palma
The document discusses aspects of reproducibility in earth science research within the European Virtual Environment for Research - Earth Science Themes (EVEREST) project. The key objectives of EVEREST are to establish an e-infrastructure to facilitate collaborative earth science research through shared data, models, and workflows. Research Objects (ROs) will be used to capture and share workflows, processes, and results to help ensure reproducibility and preservation of earth science research. An example RO is described for mapping volcano deformation using satellite imagery and other data sources. Issues around reproducibility related to data access, software dependencies, and manual intervention in workflows are also discussed.
IRJET- Doctors Assitive System using Augmentated Reality for Critical AnalysisIRJET Journal
This document discusses using augmented reality to assist doctors. It proposes a system that displays important patient medical information on semi-transparent glasses as part of an augmented reality headset. This allows doctors to view the information overlaid on the real world. The system aims to make patient data easily visible, portable, reduce time spent searching for data, and securely perform operations. It describes transmitting sensor data from a patient using sensors like heartbeat, temperature, and pressure sensors connected to a PIC microcontroller. The data is then sent using ZigBee transmission and viewed on the augmented reality glasses by the doctor for critical analysis during treatment.
Real-time human activity recognition from smart phone using linear support ve...TELKOMNIKA JOURNAL
The recognition of human activity (HAR) the use of cell devices embedded in its exten sively disbursed sensors affords guidance, instructions, and take care of citizens of smart cities. Consequently, it became essential to analyze human every day sports. To examine statistical models of human conduct, synthetic intelligence strategies such as machine studying can be used. Many studies have not studied type overall performance in real-time due to statistics series. To remedy this trouble, this paper proposes a structure primarily based on open supply technology and platforms consisting of Apache Kafka, for messages to flow over the internet, method them and provide shape for existing facts in real-time and formulates the trouble of identifying human pastime by using a smartphone tool as a type hassle using statistics collection by telephone sensors. The proposed version is skilled by some machine learning algorithms. The algorithm that has proven superior and quality results helps a linear vector machines.
Embedded Sensing and Computational Behaviour ScienceDaniel Roggen
Overview of the activities in the Sensor Technology Research Centre, University of Sussex, UK, in wearable technologies and computational behaviour science.
This study evaluated six machine learning classifiers for human activity recognition using smartphone sensor data. The classifiers - Decision Stump, Hoeffding Tree, Random Tree, J48, Random Forest, and REP Tree - were tested on a publicly available dataset containing accelerometer readings for six activities. Random Forest, J48, and REP Tree achieved statistically significantly better accuracy than Decision Stump and Hoeffding Tree according to measures like overall accuracy, precision, recall, F-measure, and kappa statistic. The results suggest these three classifiers are well-suited for human activity recognition from smartphone sensor data.
This study evaluated six machine learning classifiers for human activity recognition using smartphone sensor data. The classifiers - Decision Stump, Hoeffding Tree, Random Tree, J48, Random Forest, and REP Tree - were tested on a publicly available dataset containing accelerometer readings for six activities. Random Forest, J48, and REP Tree achieved statistically significantly better accuracy than Decision Stump and Hoeffding Tree according to measures like overall accuracy, precision, recall, F-measure, and kappa statistic. The results suggest these three classifiers are well-suited for human activity recognition from smartphone sensor data.
This document describes a gait-based authentication system project. The project aims to authenticate individuals based on their unique walking gait using wearable sensors. It discusses implementing gait authentication using machine vision, floor sensors, or wearable sensors. The implementation phases include data gathering, feature extraction, modeling, training, and testing classifiers like neural networks and random forests to identify users based on their gait data. A web portal was created for data collection and evaluation of the gait authentication system.
Big&open data challenges for smartcity-PIC2014 ShanghaiVictoria López
This talk is about how both private enterprise and government wish to improve the value of their data and how they deal with this issue. The talk summarizes the ways we think about Big Data, Open Data and their use by organizations or individuals. Big Data is explained in terms of collection, storage, analysis and valuation. This data is collected from numerous sources including networks of sensors, government data holdings, company market databases, and public profiles on social networking sites. Organizations use many data analysis techniques to study both structured and unstructured data. Due to volume, velocity and variety of data, some specific techniques have been developed. MapReduce, Hadoop and other related as RHadoop are trendy topics nowadays.
In this talk several applications and case studies are presented as examples. Data which come from government sources must be open. Every day more and more cities and countries are opening their data. Open Data is then presented as a specific case of public data with a special role in Smartcity. The main goal of Big and Open Data in Smartcity is to develop systems which can be useful for citizens. In this sense RMap (Mapa de Recursos) is shown as an Open Data application, an open system for Madrid City Council, available for smartphones and totally developed by the researching group G-TeC (www.tecnologiaUCM.es).
Local Advanced Lung Cancer: Artificial Intelligence, Synergetics, Complex Sys...Oleg Kshivets
Overall life span (LS) was 1671.7±1721.6 days and cumulative 5YS reached 62.4%, 10 years – 50.4%, 20 years – 44.6%. 94 LCP lived more than 5 years without cancer (LS=2958.6±1723.6 days), 22 – more than 10 years (LS=5571±1841.8 days). 67 LCP died because of LC (LS=471.9±344 days). AT significantly improved 5YS (68% vs. 53.7%) (P=0.028 by log-rank test). Cox modeling displayed that 5YS of LCP significantly depended on: N0-N12, T3-4, blood cell circuit, cell ratio factors (ratio between cancer cells-CC and blood cells subpopulations), LC cell dynamics, recalcification time, heparin tolerance, prothrombin index, protein, AT, procedure type (P=0.000-0.031). Neural networks, genetic algorithm selection and bootstrap simulation revealed relationships between 5YS and N0-12 (rank=1), thrombocytes/CC (rank=2), segmented neutrophils/CC (3), eosinophils/CC (4), erythrocytes/CC (5), healthy cells/CC (6), lymphocytes/CC (7), stick neutrophils/CC (8), leucocytes/CC (9), monocytes/CC (10). Correct prediction of 5YS was 100% by neural networks computing (error=0.000; area under ROC curve=1.0).
More Related Content
Similar to Yan Kestens - Managing large cohorts and collecting data on mobility and health behaviour
Human Activity Recognition Using SmartphoneIRJET Journal
The document discusses human activity recognition using smartphone sensors. It proposes using a CNN-LSTM model to classify activities like walking, running, and sitting based on accelerometer and gyroscope sensor data from a smartphone. The CNN extracts features from the sensor data, while the LSTM recognizes sequences of activities over time. The model is implemented in an Android application that recognizes activities in real-time and also counts steps, distance, and calories burned. The application uses built-in smartphone sensors like accelerometer, gyroscope, and pedometer to recognize activities affordably and with high availability without external devices. The CNN-LSTM model achieves accurate activity recognition compared to other machine learning techniques.
VISION / AMBITION
-Australia the first drone-sensed nation (cm-scale)
-Pre-competitive data release for industry, environmental management, education & research
-Conventional survey & remote sensing techniques at ultra-high resolution and flexibility (time-series, rapid response etc)
-Next gen “UNDERCOVER” techniques (minerals and water resources)
Physiological monitoring has become increasingly popular with the availability of advanced technology. Techtiles aims to consolidate sensors that normally are not found together on one device to monitor a user's heart activity, breathing, and movement and process the data to compute heart rate, respiration rate, steps, distance, and energy burned. The prototype demonstrated accuracy within 17 beats/min for heart rate, 10 breaths/min for respiration, and was able to be worn comfortably for monitoring purposes.
Seminar given with Basile Chaix at London School of Hygiene and Tropical Medicine on Mobility and Exposure assessment for Epidemiological Modelling. Organisation: Steven Cummins & Daniel Lewis.
Conference talk: Understanding Vulnerabilities of Location Privacy Mechanisms...Zohaib Riaz
Slides for our work presented at MobiQuitous 2017 Conference (http://mobiquitous.org/).
Full paper text: ftp://ftp.informatik.uni-stuttgart.de/pub/library/ncstrl.ustuttgart_fi/INPROC-2017-46/INPROC-2017-46.pdf
This paper focused on revealing weaknesses of existing location obfuscation approaches when an attacker possesses accurate or obfuscated location history information.
A benchmark dataset to evaluate sensor displacement in activity recognitionOresti Banos
This work introduces an open benchmark dataset to investigate inertial sensor displacement effects in activity recognition. While sensor position displacements such as rotations and translations have been recognised as a key limitation for the deployment of wearable systems, a realistic dataset is lacking. We introduce a concept of gradual sensor displacement conditions, including ideal, self-placement of a user, and mutual displacement deployments. These conditions were analysed in the dataset considering 33 fitness activities, recorded using 9 inertial sensor units from 17 participants. Our statistical analysis of acceleration features quantified relative effects of the displacement conditions. We expect that the dataset can be used to benchmark and compare recognition algorithms in the future.
This presentation illustrates part of the work described in the following article:
* Banos, O., Toth, M. A., Damas, M., Pomares, H., Rojas, I., Amft, O.: A benchmark dataset to evaluate sensor displacement in activity recognition. In: Proceedings of the 14th International Conference on Ubiquitous Computing (Ubicomp 2012), Pittsburgh, USA, September 5-8, (2012)
Sparse Mat: A Tale of Devising A Low-Cost Directional System for Pedestrian C...Tarik Reza Toha
Pedestrian counting is required in diversified places such as shopping malls, touristic spots, etc., however, a low-cost solution to this problem is yet to be proposed in the literature. Therefore, in this paper, we propose a new solution for pedestrian counting that exploits only a small number of COTS sensors (94% less than that used in the existing Eco-Counter solution). To do so, we propose detail designs and two different algorithms for separately sensing step-down and step-up phenomena that we find while walking. User evaluation of real implementations of both our algorithms confirms an average accuracy of up to 93% through sensing the step-up phenomena.
Internet of Things and the Value of Tracking EverythingPaul Barsch
This presentation was given to an executive MBA session at UCSD in April 2016. The session reviewed big data, internet of things, and how companies are gaining value from location, sensor, manufacturing and other data to make better business decisions.
Dr. Frederica Darema presents an overview of his program, Dynamic Data Driven Applications Systems (DDDAS), at the AFOSR 2013 Spring Review. At this review, Program Officers from AFOSR Technical Divisions will present briefings that highlight basic research programs beneficial to the Air Force.
Presentation Location and Context World, 2015. Palo Alto, CA November 3-4, 2015.
Abstract: Creating useful local context requires big data platforms and marketplaces. Contextual awareness is relevant to location based marketing, first responders, urban planners and many others. Location-aware mobile devices are revolutionizing how consumers and brands interact in the physical world. Situational awareness is a key element to efficiently handling any emergency response. In all cases, big data processing and high velocity streaming of location based data creates the richest contextual awareness. Data from many sources including IoT devices, sensor webs, surveillance and crowdsourcing are combined with semantically-rich urban and indoor data models. The resulting context information is delivered to and shared by mobile devices in connected and disconnected operations. Standards play a key role in establishing context platforms and marketplaces. Successful approaches will consolidate data from ubiquitous sensing technologies on a common space-time basis to enabled context-aware analysis of environmental and social dynamics.
IRJET- Surveillance of Object Motion Detection and Caution System using B...IRJET Journal
This document describes a proposed surveillance system using a block matching algorithm for motion detection. The system would use IP cameras to stream video that is monitored for unauthorized activity. Motion detection is performed by comparing frames using the block matching algorithm to detect changes in pixel intensity values, which would trigger an alarm. The block matching algorithm divides frames into blocks of pixels and validates the maximum and minimum intensity of each pixel. Comparing blocks between frames identifies motion if intensity values change beyond a threshold. If motion is detected in a designated sensitive area, the system saves the video and sends alerts by email and mobile notification to users.
Participatory Health Surveys – Sergiusz Pawlowicz et al, Centre for Geospatia...JISC GECO
The document summarizes a participatory health GIS project by the Centre for Geospatial Science at the University of Nottingham. The project aims to develop a dynamic surveying system using open source software and open standards to allow public participation in health surveys. Key goals are reusing data and software, having a dynamic surveying engine for real-time analysis, and ensuring interoperability, privacy, and real-time pre-diagnostics through a web-based system.
Aspects of Reproducibility in Earth ScienceRaul Palma
The document discusses aspects of reproducibility in earth science research within the European Virtual Environment for Research - Earth Science Themes (EVEREST) project. The key objectives of EVEREST are to establish an e-infrastructure to facilitate collaborative earth science research through shared data, models, and workflows. Research Objects (ROs) will be used to capture and share workflows, processes, and results to help ensure reproducibility and preservation of earth science research. An example RO is described for mapping volcano deformation using satellite imagery and other data sources. Issues around reproducibility related to data access, software dependencies, and manual intervention in workflows are also discussed.
IRJET- Doctors Assitive System using Augmentated Reality for Critical AnalysisIRJET Journal
This document discusses using augmented reality to assist doctors. It proposes a system that displays important patient medical information on semi-transparent glasses as part of an augmented reality headset. This allows doctors to view the information overlaid on the real world. The system aims to make patient data easily visible, portable, reduce time spent searching for data, and securely perform operations. It describes transmitting sensor data from a patient using sensors like heartbeat, temperature, and pressure sensors connected to a PIC microcontroller. The data is then sent using ZigBee transmission and viewed on the augmented reality glasses by the doctor for critical analysis during treatment.
Real-time human activity recognition from smart phone using linear support ve...TELKOMNIKA JOURNAL
The recognition of human activity (HAR) the use of cell devices embedded in its exten sively disbursed sensors affords guidance, instructions, and take care of citizens of smart cities. Consequently, it became essential to analyze human every day sports. To examine statistical models of human conduct, synthetic intelligence strategies such as machine studying can be used. Many studies have not studied type overall performance in real-time due to statistics series. To remedy this trouble, this paper proposes a structure primarily based on open supply technology and platforms consisting of Apache Kafka, for messages to flow over the internet, method them and provide shape for existing facts in real-time and formulates the trouble of identifying human pastime by using a smartphone tool as a type hassle using statistics collection by telephone sensors. The proposed version is skilled by some machine learning algorithms. The algorithm that has proven superior and quality results helps a linear vector machines.
Embedded Sensing and Computational Behaviour ScienceDaniel Roggen
Overview of the activities in the Sensor Technology Research Centre, University of Sussex, UK, in wearable technologies and computational behaviour science.
This study evaluated six machine learning classifiers for human activity recognition using smartphone sensor data. The classifiers - Decision Stump, Hoeffding Tree, Random Tree, J48, Random Forest, and REP Tree - were tested on a publicly available dataset containing accelerometer readings for six activities. Random Forest, J48, and REP Tree achieved statistically significantly better accuracy than Decision Stump and Hoeffding Tree according to measures like overall accuracy, precision, recall, F-measure, and kappa statistic. The results suggest these three classifiers are well-suited for human activity recognition from smartphone sensor data.
This study evaluated six machine learning classifiers for human activity recognition using smartphone sensor data. The classifiers - Decision Stump, Hoeffding Tree, Random Tree, J48, Random Forest, and REP Tree - were tested on a publicly available dataset containing accelerometer readings for six activities. Random Forest, J48, and REP Tree achieved statistically significantly better accuracy than Decision Stump and Hoeffding Tree according to measures like overall accuracy, precision, recall, F-measure, and kappa statistic. The results suggest these three classifiers are well-suited for human activity recognition from smartphone sensor data.
This document describes a gait-based authentication system project. The project aims to authenticate individuals based on their unique walking gait using wearable sensors. It discusses implementing gait authentication using machine vision, floor sensors, or wearable sensors. The implementation phases include data gathering, feature extraction, modeling, training, and testing classifiers like neural networks and random forests to identify users based on their gait data. A web portal was created for data collection and evaluation of the gait authentication system.
Big&open data challenges for smartcity-PIC2014 ShanghaiVictoria López
This talk is about how both private enterprise and government wish to improve the value of their data and how they deal with this issue. The talk summarizes the ways we think about Big Data, Open Data and their use by organizations or individuals. Big Data is explained in terms of collection, storage, analysis and valuation. This data is collected from numerous sources including networks of sensors, government data holdings, company market databases, and public profiles on social networking sites. Organizations use many data analysis techniques to study both structured and unstructured data. Due to volume, velocity and variety of data, some specific techniques have been developed. MapReduce, Hadoop and other related as RHadoop are trendy topics nowadays.
In this talk several applications and case studies are presented as examples. Data which come from government sources must be open. Every day more and more cities and countries are opening their data. Open Data is then presented as a specific case of public data with a special role in Smartcity. The main goal of Big and Open Data in Smartcity is to develop systems which can be useful for citizens. In this sense RMap (Mapa de Recursos) is shown as an Open Data application, an open system for Madrid City Council, available for smartphones and totally developed by the researching group G-TeC (www.tecnologiaUCM.es).
Similar to Yan Kestens - Managing large cohorts and collecting data on mobility and health behaviour (20)
Local Advanced Lung Cancer: Artificial Intelligence, Synergetics, Complex Sys...Oleg Kshivets
Overall life span (LS) was 1671.7±1721.6 days and cumulative 5YS reached 62.4%, 10 years – 50.4%, 20 years – 44.6%. 94 LCP lived more than 5 years without cancer (LS=2958.6±1723.6 days), 22 – more than 10 years (LS=5571±1841.8 days). 67 LCP died because of LC (LS=471.9±344 days). AT significantly improved 5YS (68% vs. 53.7%) (P=0.028 by log-rank test). Cox modeling displayed that 5YS of LCP significantly depended on: N0-N12, T3-4, blood cell circuit, cell ratio factors (ratio between cancer cells-CC and blood cells subpopulations), LC cell dynamics, recalcification time, heparin tolerance, prothrombin index, protein, AT, procedure type (P=0.000-0.031). Neural networks, genetic algorithm selection and bootstrap simulation revealed relationships between 5YS and N0-12 (rank=1), thrombocytes/CC (rank=2), segmented neutrophils/CC (3), eosinophils/CC (4), erythrocytes/CC (5), healthy cells/CC (6), lymphocytes/CC (7), stick neutrophils/CC (8), leucocytes/CC (9), monocytes/CC (10). Correct prediction of 5YS was 100% by neural networks computing (error=0.000; area under ROC curve=1.0).
Does Over-Masturbation Contribute to Chronic Prostatitis.pptxwalterHu5
In some case, your chronic prostatitis may be related to over-masturbation. Generally, natural medicine Diuretic and Anti-inflammatory Pill can help mee get a cure.
8 Surprising Reasons To Meditate 40 Minutes A Day That Can Change Your Life.pptxHolistified Wellness
We’re talking about Vedic Meditation, a form of meditation that has been around for at least 5,000 years. Back then, the people who lived in the Indus Valley, now known as India and Pakistan, practised meditation as a fundamental part of daily life. This knowledge that has given us yoga and Ayurveda, was known as Veda, hence the name Vedic. And though there are some written records, the practice has been passed down verbally from generation to generation.
Here is the updated list of Top Best Ayurvedic medicine for Gas and Indigestion and those are Gas-O-Go Syp for Dyspepsia | Lavizyme Syrup for Acidity | Yumzyme Hepatoprotective Capsules etc
- Video recording of this lecture in English language: https://youtu.be/kqbnxVAZs-0
- Video recording of this lecture in Arabic language: https://youtu.be/SINlygW1Mpc
- Link to download the book free: https://nephrotube.blogspot.com/p/nephrotube-nephrology-books.html
- Link to NephroTube website: www.NephroTube.com
- Link to NephroTube social media accounts: https://nephrotube.blogspot.com/p/join-nephrotube-on-social-media.html
Adhd Medication Shortage Uk - trinexpharmacy.comreignlana06
The UK is currently facing a Adhd Medication Shortage Uk, which has left many patients and their families grappling with uncertainty and frustration. ADHD, or Attention Deficit Hyperactivity Disorder, is a chronic condition that requires consistent medication to manage effectively. This shortage has highlighted the critical role these medications play in the daily lives of those affected by ADHD. Contact : +1 (747) 209 – 3649 E-mail : sales@trinexpharmacy.com
Cell Therapy Expansion and Challenges in Autoimmune DiseaseHealth Advances
There is increasing confidence that cell therapies will soon play a role in the treatment of autoimmune disorders, but the extent of this impact remains to be seen. Early readouts on autologous CAR-Ts in lupus are encouraging, but manufacturing and cost limitations are likely to restrict access to highly refractory patients. Allogeneic CAR-Ts have the potential to broaden access to earlier lines of treatment due to their inherent cost benefits, however they will need to demonstrate comparable or improved efficacy to established modalities.
In addition to infrastructure and capacity constraints, CAR-Ts face a very different risk-benefit dynamic in autoimmune compared to oncology, highlighting the need for tolerable therapies with low adverse event risk. CAR-NK and Treg-based therapies are also being developed in certain autoimmune disorders and may demonstrate favorable safety profiles. Several novel non-cell therapies such as bispecific antibodies, nanobodies, and RNAi drugs, may also offer future alternative competitive solutions with variable value propositions.
Widespread adoption of cell therapies will not only require strong efficacy and safety data, but also adapted pricing and access strategies. At oncology-based price points, CAR-Ts are unlikely to achieve broad market access in autoimmune disorders, with eligible patient populations that are potentially orders of magnitude greater than the number of currently addressable cancer patients. Developers have made strides towards reducing cell therapy COGS while improving manufacturing efficiency, but payors will inevitably restrict access until more sustainable pricing is achieved.
Despite these headwinds, industry leaders and investors remain confident that cell therapies are poised to address significant unmet need in patients suffering from autoimmune disorders. However, the extent of this impact on the treatment landscape remains to be seen, as the industry rapidly approaches an inflection point.
Yan Kestens - Managing large cohorts and collecting data on mobility and health behaviour
1. Managing large cohorts and
collecting data on mobility and
health behaviour :
Novel solutions and challenges
Yan Kestens
Montreal University, Social and Preventive Medicine
Montreal Hospital University Research Center (CRCHUM)
SPHERE Lab .org
Paris, France
21th May 2013
2. Aim
Presentation of tools/methods that facilitate the
collection of data in large cohorts (with a focus on
spatial data)
Three tools that have been pilot tested or implemented
in existing cohort studies
– Tool 1: Study Management Application
– Tool 2: VERITAS interactive mapping questionnaire
– Tool 3: Multisensor platform for real-time tracking
3. Managing a cohort
Large cohorts All kinds of challenges!
Recruitment
Participants
Interviewers
Questionnaires
Devices
Database
Attrition
Residential
moves
Confidentiality
Coordinators
Participation
rate
Bias
Investigators
Data collection
Tracking
Data linkage
GIS
6. Tool 1: Cohort Management
Application
Use of a study management application to manage
– People
– Procedures
– Questionnaires
– Devices
– Procedures
7.
8.
9.
10.
11.
12.
13.
14. Study Management Application
• A comprehensive application to manage cohorts
• Facilitates the process
• Keeps track of activities
• Integrates questionnaires
15. Tool 2: Spatial data collection tool
• Environmental determinants increasingly at stake,
both as a cause of disease, social health inequalities,
and as a target for intervention
• Current shift to improve integration of daily mobility
and multiple exposures in epidemiological models
16. Collecting spatial information
• Tools to collect location information include:
– Residential history questionnaires – lifecourse
– Travel surveys – often one day of detailed mobility
– Activity space questionnaires – asking people’s
regular destinations
– Real-time tracking using GPS receivers
17. Spatial data used in health research
Place of
residence /
Residential
history
21. Spatial data used in health research
Attribute data:
Frequency
Attachment
Perception
Travel mode
Constraints
With whom
Etc.
22. VERITAS, an online mapping
questionnaire
• Uses an interactive map to collect spatial data
• Can be administered or self-administered
• Flexible and scalable
• Allows to collect information on locations, routes,
spaces and related qualitative assessment
• Is linked to mapping and search APIs to facilitate the
process and increase validity (Openstreetmap,
Google Map, etc.)
23. VERITAS
A series of questions which can be answered on a map
through creation of:
– A point location (marker)
– A line (polyline)
– An area (polygon)
Map searching capabilities / streetview
functionalities can help identifying known
locations/destinations.
25. VERITAS RECORD
• Illustration: VERITAS in the RECORD Study
• RECORD Study: Large Paris area cohort on Cardiovascular
health (n = 8,000)
• Wave 1 in 2007-2008, Wave 2 in 2012-2014
• VERITAS RECORD administered to some 4,800 participants as
of today
• 27 spatial questions including destinations for food shopping,
sport activities, leisure, friends, family, etc.
• Over 65,000 locations collected – Median of 14 locations
collected per participant
• Median completion time of 20 minutes
26. VERITAS RECORD
• Rich spatial information on regular destinations which can
serve to identify multiple environmental exposures and
inequalities
• Spatial information transformed into spatial indicators to feed
epidemiological models (Activity space size, maximum
distance, concentration etc.) (Camille Perchoux, Ph.D.
candidate)
• Interesting information to monitor spatial health inequalities,
mobility behaviour and guide intervention in the distribution
of resources/infrastructures
27. Tool 3: A multisensor platform for real-
time tracking
• Self-reported locations vs. objective measures
• Multisensor device for tracking of:
– Mobility (GPS, RFID)
– Physical activity (Accelerometer)
– Physiology (Various sensors)
36. SenseDoc Multisensor Device
CAPTURE
Accelerometer
Marie-Lyse Bélanger, M.Sc. Student in kinesiology
Accelerometer validation using indirect calorimetry
Lab – 14 controlled exercises from sedentary to vigouros PA
Eleven adult subjects
Calculation of Vertical Magnitude Acceleration (VMAG)
Testing of various bandpass filters
Comparison with Actigraph GT3X performence
Best results obtained with Bandpass filter 0.1 Hz – 3.5 Hz
Modelling of Energy Expenditure: Adj. R-square of .79
Use of Vector Body Dynamic Acceleration (VEDBA)
37. SenseDoc Multisensor Device
CAPTURE
Battery life
Strong battery (3200 mAh)
Axelle Chevallier, M.Sc. Student in
Electrical Engineering
Mohamad Sawan, Professor,
Electrical Engineering
Battery optimisation algorithm
- Movement
- Location and movement
39. SenseDoc Multisensor Device
CAPTURE
Data transmission
GPS Data sent over the air (cellphone network) every 30 minutes
Possible alerts depending on
- Location
- Activity
- Time
Connection to other sensors (2.4 GHz ANT+) Heart rate monitor,
footpod, RFID tags, etc.
40. Issues in data processing
PROCES
SING
Transforming raw GPS data into meaningful and useful
information, combining with accelerometry
- ‘Putting things into context’
- Activity locations
- Trips between locations
SPHERELAB GPS
ARCTOOLBOX
www.spherelab.org/tools
41. Usage
Using GPS/Accel to locate behaviour and assess exposure
Improve the understanding of mechanisms linking
environments to health behaviours and profiles
Use GPS to prompt recall and gain additional insight
Use GPS to support qualitative studies (go-along, geo-
ethnography, geo-tagged photos, environmental
perception, etc.)
Use GPS/Accel data to assist clinical practice (mHealth)
USAGE
42. UsageUSAGE
RECORD GPS Study, Paris
191 participants wearing GPS & Accelerometer for 7 days
Estimates of:
• Number of steps walked
• Energy expenditure
• Moderate to Vigorous physical activity
• Sedentary time
Analyses possible at the trip level and by travel mode
43. UsageUSAGE
During wear time, transportation was responsible for:
• 39% of steps walked
• 32% of total energy expenditure
• 33% of MVPA
• 15% of sedentary time
46. Spherelab GPS studies
RECORD-GPS Study, Paris, Basile Chaix
BIXI bikesharing study, Montreal, Lise Gauvin
Ste-Justine CIRCUIT Pediatric Intervention, Montréal, Mélanie
Henderson
Novel Real-Time Measurement of Physical Activity Patterns in Type 2
Diabetes and Hypertension through GPS Monitoring and Accelerometry,
Kaberi Dasgupta
Healthy Aging in Urban Environments, Montreal, Paris, Luxembourg; Yan
Kestens, Basile Chaix, Philippe Gerber
47. CURHA Project
Develop an international platform and research
agenda to collect and analyse detailed data on daily
mobility and health outcomes among older adults
living in contrasted urban settings
Use of novel methods to capture daily mobility to
better understand interactions between
environments, mobility and health
48. Objectives
Provide evidence about how characteristics of urban
environments relate to active mobility and social
participation
Disentangle the complex people-environment
interactions that link urban local contexts healthy
aging
49. Methods
Trois cohortes, 450 participants par site:
Montréal/Sherbrooke: Cohorte NuAge
Paris: Cohorte RECORD
Luxembourg: Nouvelle cohorte avec SHARE
50. Methods
VERITAS
(Questionnaire on
regular destinations)
VERITAS
(Questionnaire on
regular destinations)
Canada LuxembourgFrance
Existing
questionnaires (ex:
individual SES)
Existing
questionnaires (ex:
individual SES)
Existing
questionnaires (ex:
individual SES)
Novel GPS/Accelerometry mobility protocol
Novel qualitative assessment of place experience
Existing GIS Existing GIS Existing GIS
NOVEL PROCEDURES TO BE
SHARED AND APPLIED TO
ALL SETTINGS, DRAWING
ON EXISTING EXPERTISE IN
DIFFERENT SETTINGS
EXAMPLES OF EXISTING
COMMON RESSOURCES IN
ALL SETTINGS (Need for
cross-validation of DB to
ensure comparability)
VERITAS
QUESTIONNAIRE
(Activity spaces)
EXAMPLES OF
EXPERTISE/TOOLS EXISTING
IN ONE SETTING TO BE
EXTENDED TO OTHER
SETTINGS
MULTISENSOR
PLATFORM
MULTISENSOR
PLATFORM
MULTISENSOR DEVICE
AND SERVER
PLATFORM
QUALITATIVE
ASSESSMENT OF
MOBILITY
QUALITATIVE
ASSESSMENT OF
MOBILITY
QUALITATIVE
ASSESSMENT OF
MOBILITY
TOOLS/PROCEDURES SHARING CONFIGURATIONS
Novel spatio-temporal modelling
51. Data
Mobility assessment will resort to:
• Activity space questionnaires
• Continuous 7-days monitoring of location
• Physical activity using wearable sensors
• Qualitative assessment of participants’ experiences
and meanings of his/her activity space, mobility, and
home territories.
52. Data
Behavioural outcomes of focus:
• Active living (including active transportation, walking
and sedentary behaviour)
• Social participation
• Spatial behaviour (activity space, modes of
transportation, relation to places)
GIS for environmental exposure measures
53. Analyses
Liens entre contextes urbains (SIG), mobilité, activité
physique, participation sociale
54. Conclusion
“Design for the young, and you
exclude the old;
design for the old and you
include everyone”
Bernard Isaacs, in G. Miller, G. Harris and I. Ferguson,
“Mobility Under Attack”.