Showing 10-18 of 35 results
Food Image Recognition
Goal Estimate ‘what people eat’ with machine learning based on images or videos of plates. Methodology We can start small by e.g. aiming to estimate portion sizes, in- or exclusion of vegetables at dinnertime or in-or exclusion of fruits in breakfasts. We could ask students to collect both experimental data…
Road Scan Data
DATAST is a company that works to make maintaining and servicing the public space as efficient as possible. DATAST has a lot of data they get from different sources which they have to store. And they have different clients that only have access to certain parts of the data. DATAST…
Behavior Features
We have data from one day (7-22.00) regarding physical activity of 15 patients, comprising two types of data: Type 1: Accelerometry: % of time lying/sitting, standing, walking, running, cycling. Type 2: Behavioral mapping: 3 hourly observations during one day (approximately 45 observations per patient) – what – how – with…
Auto Exercise Planning
Using string data from the electronic patient record to compose an eHealth exercise program, what is needed and how feasible is it, what can be the potential outcome? Composing a digital exercise program is time consuming. Is it feasible to compose a exercise program by subsequently: Linking data from the…
Public Health Data
The trigger The COVID-19 pandemic triggered the demand for data driven decision making amongst policy makers in the public health sector. Registration data on test results and vaccination status were extensively used to create meaningful data analytics. The paradox This health crisis also revealed a remarkable paradox. Whereas governmental researchers…
Risk signaling
The aim of this research program is to contribute to prevention by better identifying suspicious abnormalities by paramedics. Subsequently, upon identification, to advise more effectively to ask for medical care. Embedding enhanced risk signaling and secondary prevention in skin therapeutic care Cancer is one of the diseases that cause…
Infant Blink Detection
Distributed machine learning is becoming a popular model-training method due to privacy, computational scalability, and bandwidth capacities. In this work, we explore scalable distributed-training versions of two algorithms commonly used in object detection. A novel distributed training algorithm using Mean Weight Matrix Aggregation (MWMA) is proposed for Linear Support Vector…
AR for deaf students
Hearing loss is a global problem that many people deal with and the percentage of people with a hearing impairment will only keep growing. It is projected that we will reach a global population of 8 billion people in 2022 . Of these 8 billion people it is estimated that…
Digital Health Challenges
Background: Digital health is well-positioned in low and middle-income countries (LMICs) to revolutionize health care due, in part, to increasing mobile phone access and internet connectivity. This paper evaluates the underlying factors that can potentially facilitate or hinder the progress of digital health in Pakistan. Objective: The objective of this…
