British Columbia Institute of Technology

About: British Columbia Institute of Technology is a education organization based out in Burnaby, British Columbia, Canada. It is known for research contribution in the topics: Smart grid & Belief revision. The organization has 458 authors who have published 785 publications receiving 16140 citations.

Image-based Cell Phenotyping Using Deep Learning

Abstract: The ability to phenotype cells is fundamentally important in biological research and medicine. Current methods rely primarily on fluorescence labeling of specific markers. However, there are many situations where this approach is unavailable or undesirable. Machine learning has been used for image cytometry but has been limited by cell agglomeration and it is unclear if this approach can reliably phenotype cells indistinguishable to the human eye. Here, we show disaggregated single cells can be phenotyped with a high degree of accuracy using low-resolution bright-field and non-specific fluorescence images of the nucleus, cytoplasm, and cytoskeleton. Specifically, we trained a convolutional neural network using automatically segmented images of cells from eight standard cancer cell-lines. These cells could be identified with an average classification accuracy of 94.6%, tested using separately acquired images. Our results demonstrate the potential to develop an “electronic eye” to phenotype cells directly from microscopy images indistinguishable to the human eye.

Quantifying the effects of on-the-fly changes of seating configuration on the stability of a manual wheelchair

Abstract: In general, manual wheelchairs are designed with a fixed frame, which is not optimal for every situation. Adjustable on the fly seating allow users to rapidly adapt their wheelchair configuration to suit different tasks. These changes move the center of gravity (CoG) of the system, altering the wheelchair stability and maneuverability. To assess these changes, a computer simulation of a manual wheelchair was created with adjustable seat, backrest, rear axle position and user position, and validated with experimental testing. The stability of the wheelchair was most affected by the position of the rear axle, but adjustments to the backrest and seat angles also result in stability improvements that could be used when wheeling in the community. These findings describe the most influential parameters for wheelchair stability and maneuverability, as well as provide quantitative guidelines for the use of manual wheelchairs with on the fly adjustable seats.

Telehealth application in occupational health.

Abstract: While occupational health is a significant driver of population health, productivity, and well-being in Canadian society, most workers do not currently have adequate access to qualified occupational health services. A case study is used to demonstrate the utility of a telehealth approach to service delivery.

The validation and brokering of competence: Issues of trust and technology

Abstract: Campus Canada promotes lifelong learning through the articulation of workplace and other experiential learning for academic credit. This paper describes the recent re-development of the Record of Learning (RoL) component of the Campus Canada's e-Portfolio System. In matching the academic members' desires for provision of secure e-transcripts with learners' desires for validation of educational assertions, the RoL provides decentralized secure service without creating clerical log jams. The new RoL system paves the way for web services interoperability between registrar services and for automated creation of secure Records of Learning by workplace trainers. Further development is foreseen to establish the RoL as a separate service interoperable with a variety of e-portfolio and credentialing agencies.

Belief Manipulation: A Formal Model of Deceit in Message Passing Systems

Abstract: A dishonest participant in a message exchange is often interested in trying to convince others to hold particular, erroneous beliefs. While the study of belief change has a long history, to date there has not been a great deal of interest in modelling the conscious manipulation of others beliefs. In this paper, we introduce a formal definition of a belief manipulation problem. The definition relies on well-known concepts from Artificial Intelligence and the theory of belief change, and it is highly amenable to implementation using existing tools. We discuss applications of belief manipulation in two important domains: cryptographic protocol verification and Smart Grid security. In each of these domains, it is clear that many security problems can be abstracted and analyzed in terms of formal belief manipulation problems. The focus of this paper is on introducing a new problem of general interest in Security, and taking the first steps towards practical application.