Arun Shankar Narayanan

Video conferencing solution for medical applications in low-bandwidth networks

Use of telecommunication technology to tackle medical accessibility challenges, termed “Telemedicine”, is getting attention from researchers around the world. Realizing such a system in low bandwidth network is even more challenging; majorly due to the heavy data payload caused by video frames. This paper introduces some innovative features so that a regular video conferencing solution can be designed which will be able to function satisfactorily under low bandwidth networks. This work also focuses on categorizing the video transmission into different streaming priority classes based on parameters such as frame rate and resolution, which are important in varying medical applications, in order to achieve a minimum standard across all network speeds starting from as low as 128kbps. Analysis of these classes show that the innovative methods used in reducing the huge data payload of video data indeed are effective and help in making the telemedicine application in low-bandwidth networks a reality.

Mitigation of Vehicle Distribution in an EV Sharing Scheme for Last Mile Transportation

Last mile transportation, the movement of people and goods from a central hub to a final destination, is a challenging topic in implementing eco-friendly transport systems in modern cities. Much research has been focused on implementing a shared fleet of vehicles in achieving this goal. However, diverse commuter patterns as well as a large number of final destinations can lead to uneven distribution of the shared vehicles. In this paper, we propose and design a system platform for mitigation of vehicle distribution in an electric vehicle (EV) sharing scheme for last mile transportation by means of a remote driving approach. In this approach, a driver at a remote destination is enabled to maneuver the vehicle wirelessly and assist in the proper redistribution of the shared vehicle. Major technical challenges, such as handling wireless transmission latency, minimizing blind spots, and enhancing reliability, safety and security in the context of the remote driving system are identified and appropriate solutions are proposed and implemented. The developed system is validated with different performance-test measures and the outcomes are compared to that of normal driving. The results indicate that the proposed system platform can provide an adequate solution for last mile transportation through remote driving.

Extraction of spatial information for low-bandwidth telerehabilitation applications.

Telemedicine applications, based on two-dimensional (2D) video conferencing technology, have been around for the past 15 to 20 yr. They have been demonstrated to be acceptable for face-to-face consultations and useful for visual examination of wounds and abrasions. However, certain telerehabilitation assessments need the use of spatial information in order to accurately assess the patients condition and sending three-dimensional video data over low-bandwidth networks is extremely challenging. This article proposes an innovative way of extracting the key spatial information from the patients movement during telerehabilitation assessment based on 2D video and then presenting the extracted data by using graph plots alongside the video to help physicians in assessments with minimum burden on existing video data transfer. Some common rehabilitation scenarios are chosen for illustrations, and experiments are conducted based on skeletal tracking and color detection algorithms using the Microsoft Kinect sensor. Extracted data are analyzed in detail and their usability discussed.

MEETING ROOM - A secure multi-access, cross-platform telemedicine application

The high costs and inconvenience of visiting a doctor for medical advice have deterred a sizable number of elderly and needy from seeking proper medical treatment promptly and this may cause their conditions to deteriorate and possibly resulting in a more severe impact on their daily lives. Thus, this application is designed with the aim to bring more convenience and health care services to these less privileged segments of the community. In this paper a secure multi-access cross-platform telemedicine application, known as MEETING ROOM, has been designed and developed to provide easily accessible health care services. The MEETING ROOM application adopts a web-based approach in general to provide the flexibility to run on cross-platform devices. Computing devices with network connectivity can be placed in clinics, day care centers, community centers or right at their homes so that they can easily access the application with those devices. It is a hybrid application, comprising of a web portal and a video conferencing application. The web portal is used to manage the system and the users in a secure manner while the video conferencing application provides a convenient communication platform for the patients to consult a doctor on their conditions and for the doctors to hold online meetings. A web-based version and mobile Android version of the video conferencing application are developed to provide the flexibility.

Feasibility of adaptive streaming technologies in developing an integrated learning platform

Education system is going through a reform in terms of delivering lectures, with recent studies suggesting that shorter lectures help students to focus on the concepts thoroughly as well as effectively as they are found to be more engaging than the longer ones. However, making it a reality in traditional classroom settings is a big challenge. One possible alternative is to deliver lecture through short, bite-sized chunks of videos over the Internet which the students can access using their own devices at their own time, thus creating a flexible learning environment. This again posts another challenge in terms of its functionalities in bandwidth-scarce situations. This paper conducts a feasibility study of developing such a system, termed integrated learning platform, or iLEAP, by utilising adaptive streaming technology algorithms. iLEAP is intended to host lecture videos as well as discussion forums for students to engage in active discussions among themselves. This paper discusses the methods by which the data size can be reduced so as to enable the platform to work satisfactorily under varying network conditions. Evaluation of some of these techniques is done to show the viability of such a system which can enhance the learning experience of students. The paper concludes with further insights on the possibility of such techniques in other useful areas such as telemedicine.

DEVELOPMENT OF A VIDEO STREAMING SYSTEM FOR TELEHEALTH APPLICATIONS

In this paper, the design of a video streaming system for telehealth applications is presented. Deviating from generalpurpose objectives of off-the-shelf teleconferencing solutions, the system is customized to enable doctors and patients to be virtually linked over a broad range of connection speeds yet maintaining a satisfactory video/audio streaming experience to carry out remote diagnosis and assessment. Specifically, a key objective is to maintain a frame rate of around 15 fps at various connection speeds through an appropriate selection and characterization of transport protocols, encoding technologies and other innovations. Through the use of the Microsoft’s Kinect sensor, under low bandwidth conditions, the system allows an optional streaming of human body structure in binary colour mode. Images are much smaller in size but sufficient for certain applications like tele-rehabilitation. The system also allows selective cropping for the user to discard the background but send only the useful information. Finally, through the use of adaptive streaming approach, the system is able to adapt the image quality to the network speed while maintaining the frame rate. Collectively, with these customized innovations incorporated, the system is able to perform video calls at frame rate of around 15 fps even in 128 kbps network.

Design and development of a secure multi-access, cross-platform telemedicine application – MEETING ROOM

Abstract The high costs and inconvenience of visiting a doctor for medical advice have deterred a sizable number of elderly and needy from seeking proper medical treatment promptly, and this may cause their conditions to deteriorate and possibly result in a more severe impact on their daily lives. Thus, this application is designed with the aim to bring about a more convenient form of health care services to these less-privileged segments of the community. In this paper, a secure multi-access cross-platform telemedicine application, known as MEETING ROOM, has been designed and developed to provide easily accessible health care services. The MEETING ROOM application adopts a web-based approach in general to provide the flexibility to run on cross-platform devices. Computing devices with network connectivity can be placed in clinics, day care centres, community centres or even right at the patients’ homes so that they can easily access the application with those devices. It is a hybrid application, comprising of a web portal and a video conferencing part. The web portal is used to manage the system and the users in a secure manner while the video conferencing application provides a convenient communication platform for the patients to consult a doctor on their conditions and for the doctors to hold online meetings. A web-based version and mobile Android version of the video conferencing application are developed to provide the flexibility.

A telerehabilitation application with pre-defined consultation classes

Advancements in telecommunication technologies have been instrumental for the past few decades in making human life easier. Development of telemedicine technology made access to better medical care for the rural population ever more possible. However, telemedicine systems for rehabilitation purposes which are designed to work under low-bandwidth network conditions are rare to find. This work focuses on developing a low-bandwidth telerehabilitation system with customised consultation classes for the user to select from, depending on the requirements. Each class, with its preset parameter values, is discussed in detail demonstrating relevant rehabilitation exercises. A novel bandwidth adaptation algorithm is also presented for optimal utilisation of the dynamic network conditions. Experiment results show that the system is able to perform effectively in each consultation scenario while performing the rehabilitation exercises. The proposed bandwidth adaptation algorithm is also verified for its ability in adapting the content quality and for effectively utilising the network under constrained conditions.

Adaptive streaming framework for control and monitoring applications

Advances in networking technologies have led to an increasing number of control systems with remote access functionalities. However, key challenges arise and remain in remote control and monitoring applications such as the need to prioritize different data types being transmitted over the same network with limited bandwidth; balancing streaming parameters in data intensive transmissions such as video streaming to meet a desired outcome at the receiving end, and synchronization of host and client processes. These issues can be specific to an application and need to be addressed to achieve effective data streaming. In this paper, we present an adaptive streaming framework allowing these issues to be addressed in a unified platform for specific applications. Samples of beneficiary applications are highlighted.

DEVELOPMENT OF AN INEXPENSIVE HEALTH MONITORING SYSTEM FOR THE LONE ELDERLY

This paper proposes the design and implementation of an intelligent health monitoring system, e-Guardian, which helps the elderly live independently and offers peace of mind to their family members. The heart of the system is a base station (BS) that acts as a gateway between GSM/GPRS and WSN. At seniors’ sides are a number of small and lightweight wearable devices (WDs) which are capable of automatically detecting accidental falls, inferring simple activities of daily livings (ADLs), monitoring body temperatures and heart rates, etc. WDs communicate with BS, possibly via range extenders (REs) in several hops. During an emergency, alert signals will be sent to family members or caregivers via SMS. To avoid network congestions, e-Guardian takes a decentralized approach by processing sensor data locally in WDs instead of streaming raw sensor data to the BS for processing. An interrupt-driven fall detection algorithm using a digital microelectromechanical-system (MEMS) accelerometer has been designed to allow host microcontroller units (MCUs) to process data only upon interrupts and sleep the rest of the time, thus achieving several months of standby time. The system consumes minimum bandwidth thus allows its network to scale easily to cover a large area. The scalability allows an e-Guardian system to be deployed in not only households but also care centers, hospitals and even entire village/community areas thus the cost per senior is further reduced.