Ho-Kyeong Ra

Kintense: a robust, accurate, real-time and evolving system for detecting aggressive actions from streaming 3D skeleton data

Kintense is a robust, accurate, real-time, and evolving system for detecting aggressive actions such as hitting, kicking, pushing, and throwing from streaming 3D skeleton joint coordinates obtained from Kinect sensors. Kintense uses a combination of: (1) an array of supervised learners to recognize a predefined set of aggressive actions, (2) an unsupervised learner to discover new aggressive actions or refine existing actions, and (3) human feedback to reduce false alarms and to label potential aggressive actions. This paper describes the design and implementation of Kintense and provides empirical evidence that the system is 11% - 16% more accurate and 10% - 54% more robust to changes in distance, body orientation, speed, and person when compared to standard techniques such as dynamic time warping (DTW) and posture based gesture recognizers. We deploy Kintense in two multi-person households and demonstrate how it evolves to discover and learn unseen actions, achieves up to 90% accuracy, runs in real-time, and reduces false alarms with up to 13 times fewer user interactions than a typical system.

Kintense: A robust, accurate, real-time and evolving system for detecting aggressive actions from streaming 3D skeleton data

Kintense is a robust, accurate, real-time, and evolving system for detecting aggressive actions such as hitting, kicking, pushing, and throwing from streaming 3D skeleton joint coordinates obtained from Kinect sensors. Kintense uses a combination of: (1) an array of supervised learners to recognize a predefined set of aggressive actions, (2) an unsupervised learner to discover new aggressive actions or refine existing actions, and (3) human feedback to reduce false alarms and to label potential aggressive actions. This paper describes the design and implementation of Kintense and provides empirical evidence that the system is 11% – 16% more accurate and 10% – 54% more robust to changes in distance, body orientation, speed, and person when compared to standard techniques such as dynamic time warping (DTW) and posture based gesture recognizers. We deploy Kintense in two multi-person households and demonstrate how it evolves to discover and learn unseen actions, achieves up to 90% accuracy, runs in real-time, and reduces false alarms with up to 13 times fewer user interactions than a typical system.

FADES: Behavioral detection of falls using body shapes from 3D joint data

Many efforts have been made to design classification systems that can aid the protection of elderly in a home environ- ment. In this work, we focus on an accident that is a great risk for seniors living alone, a fall. Specifically, we present FADES, which uses skeletal joint information collected from a 3D depth camera to accurately classify different types of falls facing various directions from a single camera and distinguish an actual fall versus a fall-like activity, even in the presence of partially occluding objects. The framework of FADES is designed using two different phases to classify the detection of a fall, a non-fall, or normal behavior. For the first phase, we use a classification method based on Support Vector Machine (SVM) to detect body shapes that appear during an interval of falling behavior. During the second phase, we aggregate the results of the first phase using a frequency-based method to determine the similarity between the behavior sequences trained for each of the behavior. Our system shows promising results that is comparable to state-of-the-art techniques such as Viterbi algorithm, revealing real time performance with latency of <45 ms and achieving the detection accuracy of 96.07% and 95.7% for falls and non-falls, respectively.

KinSpace: Passive Obstacle Detection via Kinect

Falls are a significant problem for the elderly living independently in the home. Many falls occur due to household objects left in open spaces. We present KinSpace, a passive obstacle detection system for the home. KinSpace employs the use of a Kinect sensor to learn the open space of an environment through observation of resident walking patterns. It then monitors the open space for obstacles that are potential tripping hazards and notifies the residents accordingly. KinSpace uses real-time depth data and human-in-the-loop feedback to adjust its understanding of the open space of an environment. We present a 5,000-frame deployment dataset spanning multiple homes and classes of objects. We present results showing the effectiveness of our underlying technical solutions in identifying open spaces and obstacles. The results for both lab testing and a deployment in an actual home show roughly 80% accuracy for both open space detection and obstacle detection even in the presence of many real-world issues. Consequently, this new technology shows great potential to reduce the risk of falls in the home due to environmental hazards.

KinSpace: to provide fall prevention using Kinect

Falls are a significant problem for the elderly living independently in the home. Many falls occur due to household objects left in open spaces. We present KinSpace, a system that uses real-time depth data and human-in-the-loop feedback to adjust its understanding of the open space of an environment. We present results showing the effectiveness of our underlying technical solutions in identifying open spaces and obstacles. The results for both lab testing and a small deployment in an actual home show over 80% accuracy for open space detection and 70% accuracy in obstacle detection even in the presence of many real world issues.

HealthNode: Software Framework for Efficiently Designing and Developing Cloud-Based Healthcare Applications

With the exponential improvement of software technology during the past decade, many efforts have been made to design remote and personalized healthcare applications. Many of these applications are built on mobile devices connected to the cloud. Although appealing, however, prototyping and validating the feasibility of an application-level idea is yet challenging without a solid understanding of the cloud, mobile, and the interconnectivity infrastructure. In this paper, we provide a solution to this by proposing a framework called HealthNode, which is a general-purpose framework for developing healthcare applications on cloud platforms using Node.js. To fully exploit the potential of Node.js when developing cloud applications, we focus on the fact that the implementation process should be eased. HealthNode presents an explicit guideline while supporting necessary features to achieve quick and expandable cloud-based healthcare applications. A case study applying HealthNode to various real-world health applications suggests that HealthNode can express architectural structure effectively within an implementation and that the proposed platform can support system understanding and software evolution.

Poster: KinFrame: Framework for Large Scale Surveillance of Vulnerable People using Depth Camera

With the advancement of technology in various domains, many efforts have been made to design advanced classification engines using depth cameras. Being inspired by its potential of providing information at the skeleton level using a non-invasive infrared camera, many studies have been done to aid vulnerable people such as children, elderly, and people that physically or mentally ill. However, most of these studies focus on the algorithms and processing of a single camera, and do not consider large scale issues that are found in practical deployments. We present KinFrame, a framework that: (1) considers challenges and requirements that are necessary in design a practical system for vulnerable people and allow application developers to easily setup multiple depth camera deployment, (2) adapts a flow control method to solve large scale bandwidth issues that exist while streaming data from multiple devices, and (3) uses a data management technique to control constant flow of realtime information and efficiently structure data storage. For improved usability of the system, we also design an alerting mechanism for quick emergency reports to parents and caregivers, and layout a user interface for them to verify emergency situations or analyze behavioral patterns of the vulnerable person being monitored. In this paper, we give an overview of KinFrame and demonstrate with an example of how it can be utilized in a real-world environment.

Poster: Software Architecture for Efficiently Designing Cloud Applications using Node.js

We propose a practical solution for cloud application development using Node.js and Express library by presenting: (1) a software architecture which utilizes two standard inheritance pattern techniques, the top-down and divide and conquer approaches, to effectively organize the structure of the application for improved maintainability and extensibility in the long-run, and (2) an easy-to-follow guideline that instructs the implementation procedures for developing Node.js cloud applications.

Accurately Measuring Heart Rate Using Smart Watch: Poster Abstract

Smart watches are increasingly being used in various applications to monitor heart rate for exercise and health care purposes. It is crucial that the readings from these devices are accurate so that users can take proper actions according to the intensity of the heart rate. Taking actions from inaccurate readings can negatively impact the health of the user. In this work, we run a preliminary study that verifies the accuracy of wearable platforms by comparing the measurements with a clinically-grade device.

Framework for Surveillance of Vulnerable People Using Depth Camera

With the advancement of technology in various domains, many efforts have been made to design state-of-the-art classification engines using depth cameras. Being inspired by its potential of providing information at the skeleton level using a non-invasive infrared camera, many studies have been done to aid vulnerable people such as children, elderly, and people that are physically or mentally ill. However, most of these studies focus on the algorithms and processing of a single camera, and do not consider issues that are found in practical deployments. We present KinFrame, a framework that considers challenges and requirements of designing practical systems for vulnerable people and allows application developers to easily and efficiently setup large scale, multiple depth camera deployment.