Victor Foo

Analysis and comparison of sleeping posture classification methods using pressure sensitive bed system

Pressure ulcers are common problems for bedridden patients. Caregivers need to reposition the sleeping posture of a patient every two hours in order to reduce the risk of getting ulcers. This study presents the use of Kurtosis and skewness estimation, principal component analysis (PCA) and support vector machines (SVMs) for sleeping posture classification using cost-effective pressure sensitive mattress that can help caregivers to make correct sleeping posture changes for the prevention of pressure ulcers.

Health and wellness monitoring through wearable and ambient sensors: exemplars from home-based care of elderly with mild dementia

Monitoring and timely intervention are extremely important in the continuous management of health and wellness among all segments of the population, but particularly among those with mild dementia. In relation to this, we prescribe three design principles for the construction of services and applications. These are ambient intelligence, service continuity, and micro-context. In this paper, we provide three exemplars from our research and development activities that illustrate the use of these design principles in the construction of services and applications. All the applications are drawn from the field of care for mild dementia patients in their living quarters.

2-layer Erroneous-Plan Recognition for dementia patients in smart homes

People with dementia lose their ability to learn, solve problems, and communicate. And they are all around us. To potentially replace some of their diminished memory and problem-solving abilities, Erroneous-Plan Recognition (EPR) aims to detect defects or faults in the execution of correct plans by the dementia patient, and send timely audio and visual prompts to the dementia patient and caregiver in order to correct these faults. The scope of this work is for the patient who lives alone in a smart home. One challenge is that the definition of plan can be very subjective. It is necessary to regard a plan as an Activity of Daily Living (ADL), choose the ADLs to monitor, and deploy available sensors to acquire data. With the sensor data, there can be activity recognition, followed by plan recognition. Another challenge is the highly random and erroneous behaviour of dementia patients. Multiple, sequential, and independent layers of error detection can be arranged in a prioritised manner to detect specific errors first, and provide an error probability if no specific errors are detected. On the whole, most of the EPR results are very good as they are at least 0.9, indicating that the data is linearly separable. The 2-layer EPR system, which uses the blacklist and whitelist as Layer 1 and naive Bayes classifier as Layer 2, is significantly more accurate than each individual layer. In fact, 5 out of 6 actors have an accuracy above 0.9. With the encouraging results, there will be more technical and domain challenges which we can address in the near future.

Multi-modal sensing smart spaces embedded with WSN based image camera

In this paper we discuss the use of low frame rate image cameras on a WSN in order to gather micro-context information in the context of smart homes and smart living spaces for the elderly. These simple devices are an attractive alternative to their more heavy duty counterparts since they can gather ambient image data at a rate that is amenable to the ambient space that they are in without much infrastructural support or modification. We propose their use in a multi-modal sensing environment where information from other ambient sensors may be mixed and matched in order to provide intelligence about the space and the activities of the subjects within the space. Their compelling use case, which includes their light weight and ease of mobility makes them a good candidate for a multi-modal sensing smart space. In this paper we introduce our work on architecture of the smart space and the implementation of the feature extraction using the image camera.

Sensor based micro context for mild dementia assistance

Due to decline in their cognitive function, elderly people with mild dementia living alone at home are at risk of making errors in their activities of daily living (ADLs). In order to help such people, most activity recognition systems for assistive living in smart homes attempt to classify activities from coarse grained context such as location or time of day. Location by itself however, does not provide adequate context information for the recognition of ADLs and instrumental ADLs. It does not help to know that a person is in the kitchen if we are interested in knowing whether or not he has taken his meal (ADL) or prepared it (iADL). Additional information about the activity is needed. In this paper micro-context is introduced as a key aspect both for activity recognition as well as for prompted correction. Initial results from our laboratory experiments are presented herein, and it is shown that micro-context is useful for both activity recognition and prompted error correction.

Design of a Smart Continence Management System Based on Initial User Requirement Assessment

Those with dementia need closer attention and monitoring when they develop incontinence. Incontinence can lead to medical complications such as skin breakdown, places greater demands on caregivers, and strips the patients of their dignity. We have taken a step towards building a smart continence management system (SCMS) by automating the detection of events and forwarding details of these events to caregivers. Besides reducing bedsores and concomitant ill-effects of the elderly remaining in soiled diapers for prolonged periods, SCMS also benefits caregivers, helping them improve visitation schedules and time management. In the user-requirements generationphase, a cohort of people were interviewed. Subsequently the user-requirements were translated into technical specifications,based on which, a product survey was conducted. The system was designed, implemented, deployed and is being evaluated at a nursing home in Singapore. Initial results are encouraging. A planned usability study/overall system evaluationwill provide new requirements for the second version.

WDM optical network testbed and distributed storage application

In this article we present the details of a generalized multiprotocol label switching controlled wavelength-division multiplexing (WDM) optical network developed under the Optical Network Focused Interest Group (ONFIG) program in Singapore. The WDM network is controlled through a GMPLS control plane that consists of CR-LDP, LMP, and OSPF-TE. We conducted various field trials on the GMPLS-capable WDM optical network testbed with the main focus on distributed storage service application. We developed and evaluated a distributed storage services application on the WDM optical network testbed and demonstrated that incorporating a lightweight data transport protocol with optical network control could be an efficient approach for data-intensive storage applications by exploiting the dynamic connection establishment and backup protection features.