Mobile robots such as unmanned aerial vehicles (drones) can be used for surveillance, monitoring and data collection in buildings, infrastructure and environments. The importance of accurate and ...multifaceted monitoring is well known to identify problems early and prevent them escalating. This motivates the need for flexible, autonomous and powerful decision-making mobile robots. These systems need to be able to learn through fusing data from multiple sources. Until very recently, they have been task specific. In this paper, we describe a generic navigation algorithm that uses data from sensors on-board the drone to guide the drone to the site of the problem. In hazardous and safety-critical situations, locating problems accurately and rapidly is vital. We use the proximal policy optimisation deep reinforcement learning algorithm coupled with incremental curriculum learning and long short-term memory neural networks to implement our generic and adaptable navigation algorithm. We evaluate different configurations against a heuristic technique to demonstrate its accuracy and efficiency. Finally, we consider how safety of the drone could be assured by assessing how safely the drone would perform using our navigation algorithm in real-world scenarios.
Outlier detection has been used for centuries to detect and, where appropriate, remove anomalous observations from data. Outliers arise due to mechanical faults, changes in system behaviour, ...fraudulent behaviour, human error, instrument error or simply through natural deviations in populations. Their detection can identify system faults and fraud before they escalate with potentially catastrophic consequences. It can identify errors and remove their contaminating effect on the data set and as such to purify the data for processing. The original outlier detection methods were arbitrary but now, principled and systematic techniques are used, drawn from the full gamut of Computer Science and Statistics. In this paper, we introduce a survey of contemporary techniques for outlier detection. We identify their respective motivations and distinguish their advantages and disadvantages in a comparative review.
The three-dimensional swimming tracks of motile microorganisms can be used to identify their species, which holds promise for the rapid identification of bacterial pathogens. The tracks also provide ...detailed information on the cells' responses to external stimuli such as chemical gradients and physical objects. Digital holographic microscopy (DHM) is a well-established, but computationally intensive method for obtaining three-dimensional cell tracks from video microscopy data. We demonstrate that a common neural network (NN) accelerates the analysis of holographic data by an order of magnitude, enabling its use on single-board computers and in real time. We establish a heuristic relationship between the distance of a cell from the focal plane and the size of the bounding box assigned to it by the NN, allowing us to rapidly localise cells in three dimensions as they swim. This technique opens the possibility of providing real-time feedback in experiments, for example by monitoring and adapting the supply of nutrients to a microbial bioreactor in response to changes in the swimming phenotype of microbes, or for rapid identification of bacterial pathogens in drinking water or clinical samples.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
In this paper, we introduce a theoretical basis for a Hadoop-based neural network for parallel and distributed feature selection in Big Data sets. It is underpinned by an associative memory (binary) ...neural network which is highly amenable to parallel and distributed processing and fits with the Hadoop paradigm. There are many feature selectors described in the literature which all have various strengths and weaknesses. We present the implementation details of five feature selection algorithms constructed using our artificial neural network framework embedded in Hadoop YARN. Hadoop allows parallel and distributed processing. Each feature selector can be divided into subtasks and the subtasks can then be processed in parallel. Multiple feature selectors can also be processed simultaneously (in parallel) allowing multiple feature selectors to be compared. We identify commonalities among the five features selectors. All can be processed in the framework using a single representation and the overall processing can also be greatly reduced by only processing the common aspects of the feature selectors once and propagating these aspects across all five feature selectors as necessary. This allows the best feature selector and the actual features to select to be identified for large and high dimensional data sets through exploiting the efficiency and flexibility of embedding the binary associative-memory neural network in Hadoop.
A proposed Diagnostic AI System for Robot-Assisted Triage ("DAISY") is under development to support Emergency Department ("ED") triage following increasing reports of overcrowding and shortage of ...staff in ED care experienced within National Health Service, England ("NHS") but also globally. DAISY aims to reduce ED patient wait times and medical practitioner overload. The objective of this study was to explore NHS health practitioners' perspectives and attitudes towards the future use of AI-supported technologies in ED triage.
Between July and August 2022 a qualitative-exploratory research study was conducted to collect and capture the perceptions and attitudes of nine NHS healthcare practitioners to better understand the challenges and benefits of a DAISY deployment. The study was based on a thematic analysis of semi-structured interviews. The study involved qualitative data analysis of the interviewees' responses. Audio-recordings were transcribed verbatim, and notes included into data documents. The transcripts were coded line-by-line, and data were organised into themes and sub-themes. Both inductive and deductive approaches to thematic analysis were used to analyse such data.
Based on a qualitative analysis of coded interviews with the practitioners, responses were categorised into broad main thematic-types, namely: trust; current practice; social, legal, ethical, and cultural concerns; and empathetic practice. Sub-themes were identified for each main theme. Further quantitative analyses explored the vocabulary and sentiments of the participants when talking generally about NHS ED practices compared to discussing DAISY. Limitations include a small sample size and the requirement that research participants imagine a prototype AI-supported system still under development. The expectation is that such a system would work alongside the practitioner. Findings can be generalisable to other healthcare AI-supported systems and to other domains.
This study highlights the benefits and challenges for an AI-supported triage healthcare solution. The study shows that most NHS ED practitioners interviewed were positive about such adoption. Benefits cited were a reduction in patient wait times in the ED, assistance in the streamlining of the triage process, support in calling for appropriate diagnostics and for further patient examination, and identification of those very unwell and requiring more immediate and urgent attention. Words used to describe the system were that DAISY is a "good idea", "help", helpful, "easier", "value", and "accurate". Our study demonstrates that trust in the system is a significant driver of use and a potential barrier to adoption. Participants emphasised social, legal, ethical, and cultural considerations and barriers to DAISY adoption and the importance of empathy and non-verbal cues in patient interactions. Findings demonstrate how DAISY might support and augment human medical performance in ED care, and provide an understanding of attitudinal barriers and considerations for the development and implementation of future triage AI-supported systems.
This paper introduces a binary neural network-based prediction algorithm incorporating both spatial and temporal characteristics into the prediction process. The algorithm is used to predict ...short-term traffic flow by combining information from multiple traffic sensors (spatial lag) and time series prediction (temporal lag). It extends previously developed Advanced Uncertain Reasoning Architecture (AURA) k-nearest neighbour (k-NN) techniques. Our task was to produce a fast and accurate traffic flow predictor. The AURA k-NN predictor is comparable to other machine learning techniques with respect to recall accuracy but is able to train and predict rapidly. We incorporated consistency evaluations to determine whether the AURA k-NN has an ideal algorithmic configuration or an ideal data configuration or whether the settings needed to be varied for each data set. The results agree with previous research in that settings must be bespoke for each data set. This configuration process requires rapid and scalable learning to allow the predictor to be set-up for new data. The fast processing abilities of the AURA k-NN ensure this combinatorial optimisation will be computationally feasible for real-world applications. We intend to use the predictor to proactively manage traffic by predicting traffic volumes to anticipate traffic network problems.
In recent years, the range of sensing technologies has expanded rapidly, whereas sensor devices have become cheaper. This has led to a rapid expansion in condition monitoring of systems, structures, ...vehicles, and machinery using sensors. Key factors are the recent advances in networking technologies such as wireless communication and mobile ad hoc networking coupled with the technology to integrate devices. Wireless sensor networks (WSNs) can be used for monitoring the railway infrastructure such as bridges, rail tracks, track beds, and track equipment along with vehicle health monitoring such as chassis, bogies, wheels, and wagons. Condition monitoring reduces human inspection requirements through automated monitoring, reduces maintenance through detecting faults before they escalate, and improves safety and reliability. This is vital for the development, upgrading, and expansion of railway networks. This paper surveys these wireless sensors network technology for monitoring in the railway industry for analyzing systems, structures, vehicles, and machinery. This paper focuses on practical engineering solutions, principally, which sensor devices are used and what they are used for; and the identification of sensor configurations and network topologies. It identifies their respective motivations and distinguishes their advantages and disadvantages in a comparative review.
Homeoviscous adaptation (HVA) is a key cellular response by which fish protect their membranes against thermal stress. We investigated evolutionary HVA (long time scale) in Antarctic and ...non-Antarctic fish. Membrane lipid composition was determined for four Perciformes fish: two closely related Antarctic notothenioid species (
and
); a diversified related notothenioid Antarctic icefish (
); and a New Zealand species (
). The membrane lipid compositions were consistent across the three Antarctic species and these were significantly different from that of the New Zealand species. Furthermore, acclimatory HVA (short time periods with seasonal changes) was investigated to determine whether stenothermal Antarctic fish, which evolved in the cold, stable environment of the Southern Ocean, have lost the acclimatory capacity to modulate their membrane saturation states, making them vulnerable to anthropogenic global warming. We compared liver membrane lipid composition in two closely related Antarctic fish species acclimated at 0 °C (control temperature), 4 °C for a period of 14 days in
and 28 days for
and 6 °C for 7 days in both species. Thermal acclimation at 4 °C did not result in changed membrane saturation states in either Antarctic species. Despite this, membrane functions were not compromised, as indicated by declining serum osmolality, implying positive compensation by enhanced hypo-osmoregulation. Increasing the temperature to 6 °C did not change the membrane lipids of
However, in
thermal acclimation at 6 °C resulted in an increase of membrane saturated fatty acids and a decline in unsaturated fatty acids. This is the first study to show a homeoviscous response to higher temperatures in an Antarctic fish, although for only one of the two species examined.
► The paper considers pattern matching for intelligent decision support. ► Past flow patterns similar to today’s are sought to help with today’s decisions. ► An example shows that similarity between ...cumulatives of flows may be central. ► Also, on-street results obtained from a rule-based intervention system are given.
This paper considers signal plan selection; the main topic is the design of a system for utilising pattern matching to assist the timely selection of sound signal control plan changes. In this system, historical traffic flow data is continually searched, seeking traffic flow patterns similar to today’s. If, in one of these previous similar situations, (a) the signal plan utilised was different to that being utilised today and (b) it appears that the performance achieved was better than the performance likely to be achieved today, then the system recommends an appropriate signal plan switch. The heart of the system is “similarity”. Two traffic flow patterns (two time series of traffic flows arising from two different days) are said to be “similar” if the distance between them is small; similarity thus depends on how the metric or distance between two time series of traffic flows is defined. A simple example is given which suggests that utilising the standard Euclidean distance between the two sequences comprising cumulatives of traffic flow may be better than utilising the standard Euclidean distance between the original two sequences of traffic flow data. The paper also gives measured on-street public transport benefits which have arisen from using a simple rule-based (traffic-responsive) signal plan selection system, compared with a time-tabled signal plan selection system.
Competitive video game playing, an activity called esports, is increasingly popular to the point that there are now many professional competitions held for a variety of games. These competitions are ...broadcast in a professional manner similar to traditional sports broadcasting. Esports games are generally fast paced, and due to the virtual nature of these games, camera positioning can be limited. Therefore, knowing ahead of time where to position cameras, and what to focus a broadcast and associated commentary on, is a key challenge in esports reporting. This gives rise to moment-to-moment prediction within esports matches which can empower broadcasters to better observe and process esports matches. In this work we focus on this moment-to-moment prediction and in particular present techniques for predicting if a player will die within a set number of seconds for the esports title Dota 2. A player death is one of the most consequential events in Dota 2. We train our model on ‘telemetry’ data gathered directly from the game itself, and position this work as a novel extension of our previous work on the challenge. We use an enhanced dataset covering 9,822 Dota 2 matches. Since the publication of our previous work, new dataset parsing techniques developed by the WEAVR project enable the model to track more features, namely player status effects, and more importantly, to operate in real time. Additionally, we explore two new enhancements to the original model: one data-based extension and one architectural. Firstly we employ learnt embeddings for categorical features, e.g. which in game character a player has selected, and secondly we explicitly model the temporal element of our telemetry data using recurrent neural networks. We find that these extensions and additional features all aid the predictive power of the model achieving an F1 score of 0.54 compared to 0.17 for our previous model (on the new data). We improve this further by experimenting with the length of the time-series in the input data and find using 15 time steps further improves the F1 score to 0.62. This compares to F1 of 0.1 for a standard RNN on the same task. Additionally a deeper analysis of the Time to Die model is carried out to assess its suitability as a broadcast aid.
•Moment-to-moment prediction in esports is important for informing the audience.•We use neural networks to predict if a player will die in Dota 2 matches.•Our prediction uses ‘telemetry’ data gathered directly from the game itself.•We enhance our previous work using new data and a new neural architecture.•The new model works in real-time with an F1 score of 0.62 compared to 0.17 previously.