Feature Selection: Multi-source and Multi-view Data Limitations, Capabilities and Potentials

Cherrington, Marianne; Lu, Joan; Airehrour, David; Thabtah, Fadi; Xu, Qiang; Madanian, Samaneh

doi:10.1109/itnac46935.2019.9077992

Cited by 9 publications

(5 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, to reduce complexity, a subset of features may be selected instead of using all of them to develop the model. This may be needed, especially in more complex systems that use multiple input devices and modalities, and can therefore include many features irrelevant to the performed motions [42]. In simple cases, this process can be performed manually based on empirical knowledge.…”

Section: B Feature Extraction Engineering and Selectionmentioning

confidence: 99%

Assessing Human Motion During Exercise Using Machine Learning: A Literature Review

et al. 2022

View full text Add to dashboard Cite

The World Health Organization promotes healthy living through regular physical activities, such as exercise and sports, as well as access to healthcare and rehabilitation services for people with motor dysfunctions. However, there is a lack of specialized personnel and increased costs associated with such activities. These have led to the increased use of machine learning for the analysis and evaluation of human motion during exercise. To study the latest advancements in this area, a systematic literature review focusing on publications from 2017 to 2021 was performed. As a result, 88 relevant publications were identified, which developed both shallow machine learning and deep learning algorithms. The results indicated that algorithms for human motion assessment should provide personalized and informative assessments, with explainable and interpretable outcomes, that can be computed in real-time or concurrently with the execution of an exercise. Furthermore, they should be easy to adapt based on the needs of applications and should be able to perform with different motion capture systems. This has been challenging because of the usually small amount of collected data, the lack of large open datasets, and the unique characteristics of exercise motions. Based on the above findings, guidelines for the development of such algorithms are proposed and discussed. They relate to the selection of the type of assessment, handling data imbalances, selecting of motion capture technologies, balancing between accuracy and speed, selecting the right algorithm, performing concurrent assessment during an exercise, personalization and scalability, and evaluation.

show abstract

Section: B Feature Extraction Engineering and Selectionmentioning

confidence: 99%

Assessing Human Motion During Exercise Using Machine Learning: A Literature Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…According to Jiang et al (2017), the objective of artificial intelligence (AI) is to imitate human intelligence, and with ML, AI can augment human decision-making. A radical shift in healthcare is on the horizon, due to the increasing availability of digitised healthcare data via a variety of structured or unstructured sources that are linked in ways that were previously not viable (Cherrington et al, 2019a(Cherrington et al, , 2019b. The rapid advancement of ML techniques makes AI applications formidable and powerful tools.…”

Section: Artificial Intelligence Applications In Healthcarementioning

confidence: 99%

Improving New Zealand Health Outcomes with Artificial Intelligence

Sehgal¹,

Cherrington²

2021

Scope (Health and Wellbeing)

Self Cite

View full text Add to dashboard Cite

“…This method was sought, because data accuracy was an issue with the emerging COVID-19 pandemic; training using unsupervised, or semi-supervised machine learning and data smoothing techniques were used and regular updates were made available (Lampos, et al, 2020). Social media and communications applications can classify or cluster information that is rapidly changing, made especially difficult with mixed media content and semantic nuance (Cherrington et al, 2019b). Critical investigation of social media sites such as Weibo were used to disseminate information using natural language analysis to classify situational information .…”

Section: Technology Techniquesmentioning

confidence: 99%

Cracking the COVID-19 code: Cutting edge collaboration

Cherrington¹,

Dunn²,

Airehrour³

2021

Scope (Health and Wellbeing)

Self Cite

View full text Add to dashboard Cite

This paper was completed Easter Weekend, 2020 in Lockdown level 4. Looking back at that surreal 'moment in time', lockdown islands, burst bubbles and feelings of isolation have followed. Shifts in mindset are needed, and collaboration has been a means of survival, sustenance, support and sustainability. It is astounding how diverse the Covid-19 response has been in different countries and how the 'facts' have been interpreted. Research, data and facts should be a basis for making informed decisions; a vibrant research community is key. As we open and close our island nation with travel bubbles, it is worth thinking about healthy collaboration, but also reflecting on our well-being and the connectedness that makes us human. The answer is Connection.No man is an island entire of itself; every man is a piece of the continent, a part of the main.

show abstract

Feature Selection: Multi-source and Multi-view Data Limitations, Capabilities and Potentials

Cited by 9 publications

References 56 publications

Assessing Human Motion During Exercise Using Machine Learning: A Literature Review

Assessing Human Motion During Exercise Using Machine Learning: A Literature Review

Improving New Zealand Health Outcomes with Artificial Intelligence

Cracking the COVID-19 code: Cutting edge collaboration

Contact Info

Product

Resources

About