1,720,978 research outputs found
Data Study Group Final Report: STC
No full textData Study Groups are week-long events at The Alan Turing Institute bringing together some of the country’s top talent from data science, artificial intelligence, and wider fields, to analyse real-world data science challenges.
Bandwidth allocation and understanding user behaviour
The main challenge was to understand the user behaviour of the stc users, the majority of which use a fraction of their assigned bandwidth. Thus, there is a significant potential for cost savings both for stc and their users.
To solve this problem, we need to complete the following tasks:
Identify customers, who underutilise their connection and identify cell phone towers which have spare capacity to accommodate the additional traffic
Map customers to cells with sufficient capacit
Data Study Group Final Report: Defence Science & Security Laboratory (DSTL) Using Topic Modelling to Discover New Trends in the Scientific Literature
No full textData Study Group Final Report: MRC Clinical Trials Unit, UCL
No full textData Study Groups are week-long events at The Alan Turing Institute bringing together some of the country’s top talent from data science, artificial intelligence, and wider fields, to analyse real-world data science challenges.
Monitoring in clinical trials: Identifying poor performance at recruitment sites
This Data Study Group (DSG) Challenge aimed to build a human-in-the-loop machine learning model that could assist the Medical Research Council Clinical Trials Unit (MRC CTU) at University College London, in identifying clinical trial sites that are performing poorly and require monitoring intervention. When running clinical trials, patient safety is the greatest priority, with robust operation a secondary but nevertheless key feature in ensuring successful outcome of the trial. Poor performance therefore relates to any trial conduct that could compromise safety or lead to variation in how a trial is conducted between sites, making monitoring trials a large and complex challenge.
The CTU is responsible for ensuring that all clinical trial sites gather quality data, while also protecting patient rights and well-being. Currently risk-based monitoring is used to evaluate whether individual sites are following trial protocol. This approach relies on pre-defined metrics, such as those measuring the correct and timely completion of trial forms, as indicators of site performance and uses a trigger system based on those indicators to alert the CTU when a site visit is considered necessary. However, a recent study found that the intuitively developed pre-defined metrics were not sufficient at discriminating sites requiring a site visit, where relevant features may have been missed.
The purpose of this DSG challenge was therefore to undertake an initial investigation into whether machine learning approaches can improve identification of poorly performing sites
Data Study Group Final Report: IEDE Acoustics Group, University College London Deep Learning Techniques for noise annoyance detection (DeLTA)
No full text
Reinforcement Learning Study Group Report – February 2021
No full textData Study Groups are week-long events at The Alan Turing Institute bringing together some of the country’s top talent from data science, artificial intelligence, and wider fields, to analyse real-world data science challenges.
Multi-agent reinforcement learning algorithm performance in unfamiliar domains
This document reports on an The Alan Turing Institute Data Study Group (DSG) investigating a Reinforcement Learning (RL) challenge posed by Defence Science and Technology Laboratory (Dstl).
Dstl is “the science inside UK defence and security.” As such, they provide evidence required by Defence to make effective decisions. For example, a planning exercise seeks to optimise the use of available resources to achieve a desired effect. Simulations and games can be helpful tools in answering the required questions.
Reinforcement learning (RL) has been shown to be able to generate effective (even super-human) agents to play games such as Go and Starcraft. Dstl would like to investigate RL in the context of games that are relevant in the defence sphere, and in particular whether RL can provide solutions which are adaptable to changes in the configuration o f the game. The aim of this DSG is thus to investigate the effectiveness of RL techniques when the rules of the game change between the training phase and the deployment phase
Environmental Investigation Agency (EIA) Identifying Tiger Stripes with Machine Learning
No full textReinforcement Learning Study Group Report – February 2021
No full textData Study Groups are week-long events at The Alan Turing Institute bringing together some of the country’s top talent from data science, artificial intelligence, and wider fields, to analyse real-world data science challenges.
Multi-agent reinforcement learning algorithm performance inunfamiliar domains
This document reports on an The Alan Turing Institute Data Study Group (DSG) investigating a Reinforcement Learning (RL) challenge posed by Defence Science and Technology Laboratory (Dstl).
Dstl is “the science inside UK defence and security.” As such, they provide evidence required by Defence to make effective decisions. For example, a planning exercise seeks to optimise the use of available resources to achieve a desired effect. Simulations and games can be helpful tools in answering the required questions.
Reinforcement learning (RL) has been shown to be able to generate effective (even super-human) agents to play games such as Go and Starcraft. Dstl would like to investigate RL in the context of games that are relevant in the defence sphere, and in particular whether RL can provide solutions which are adaptable to changes in the configuration o f the game. The aim of this DSG is thus to investigate the effectiveness of RL techniques when the rules of the game change between the training phase and the deployment phase
Data Study Group Final Report: Odin Vision
No full textData Study Groups are week-long events at The Alan Turing Institute bringing together some of the country’s top talent from data science, artificial intelligence, and wider fields, to analyse real-world data science challenges.
Exploring AI supported decisionmaking for early-stage diagnosis of colorectal cancer
The aim of this challenge is to explore methods that enhance the explainability of Odin-Vision’s current machine learning models to aid clinical decision-making. Their current capabilities include a real-time detection and classification model, deployed in a clinical setting, where a polyp is first imaged by a clinician and automatically classified as adenoma or non-adenoma; a binary classification task. The procedure is time sensitive and each polyp gets imaged approximately only once, with clinicians taking a few seconds for image capture and decision making. The aim of the machine learning model is to aid the clinician’s decision process, providing confidence in more ambiguous cases and substantially increase the reproduciblity of those decisions. The clinician’s trust in the model is also particularly important to encourage widespread uptake and acceptance of automated methods in a clinical setting
- …
