Agile ageing – A modifiable vital sign to mitigate the risk of falls in older adults?
- Authors: Ogilvie, Madeleine , Wallen, Matthew , Talpey, Scott
- Date: 2021
- Type: Text , Journal article
- Relation: Medical Hypotheses Vol. 148, no. (2021), p.
- Full Text:
- Reviewed:
- Description: Falls prevention in older adults is a targeted priority because a fall can lead to disability, institutionalisation and presents a signficant financial burden. Falls are multifactoral in nature however, impairments in both physical and cognitive functioning have been linked to their occurrence. Currently, testing and exercise training for falls prevention focuses on physical qualities such as balance and strength. Agility is a unique physical quality that couples an individuals perceptual cognitive ability with the ability to produce a quick and accurate movement. Agility is relatively well understood in a sporting context however, its application to falls prevention has been minimal. Because a fall may occur while an individual is perceiving information from the dynamic environment around them while attempting to execute a rapid and accurate movement it is hypothesised that concepts and methods used to assess and train agility in athlete populations can be use to improve practices related to the screening and training to mitigate the risk of a fall in an older adult. © 2021
Agoraphilic navigation algorithm in dynamic environment
- Authors: Hewawasam, Hasitha
- Date: 2021
- Type: Text , Thesis , PhD
- Full Text:
- Description: This thesis presents a novel Agoraphilic (free space attraction [FSA])-based navigation algorithm. This new algorithm is capable of undertaking local path planning for robot navigation in static and dynamic environments with the presence of a moving goal. The proposed algorithm eliminates the common weaknesses of the existing navigation approaches when operating in unknown dynamic environments while using the modified Agoraphilic concept. The Agoraphilic Navigation Algorithm in Dynamic Environment (ANADE) presented in this thesis does not look for obstacles (problems) to avoid; rather, it looks for free space (solutions) to follow. Therefore, this algorithm is also a human-like optimistic navigation algorithm. The proposed algorithm creates a set of Free Space Forces (FSFs) based on the current and future growing free space around the robot. These Free Space Forces are focused towards the current and future locations of a moving goal and finally generate a single attractive force. This attractive force pulls the robot through current free space towards the future growing free space leading to the goal. The new free space concept allows the ANADE to overcome many common problems of navigation algorithms. Several versions of the ANADE have been developed throughout this research to overcome the main limitation of the original Agoraphilic algorithm and address the common weaknesses of the existing navigation approaches. The ANADE I uses an object tracking method to identify the states (locations) of moving objects accurately. The ANADE II uses a dynamic obstacle prediction methodology to identify the robot’s future environments. In the ANADE III, a novel controller based on fuzzy logic was developed and combined with the new FSA concept to provide optimal navigational solutions at a low computational cost. In the ANADE III, the effectiveness of the ANADE II was further improved by incorporating the velocity vectors of the moving objects into decision-making. In the ANADE IV, a self-tuning system was successfully applied to the ANADE III to take advantage of the performances of free space attraction-based navigation algorithms. The proposed final version of the algorithm (ANADE V) comprises nine main modules. These modules are repeatedly used to create the robot’s driving force, which pulls the robot towards the goal (moving or static). An obstacle tracking module is used to identify the time-varying free spaces by tracking the moving objects. Further, a tracking system is also used to track the moving goal. The capacity of the ANADE was strengthened further by obstacle and goal path prediction modules. Future location prediction allowed the algorithm to make decisions by considering future environments around the robot. This is further supported by a self-tuning, machine learning–based controller designed to efficiently account for the inherent high uncertainties in the robot’s operational environment at a reduced computational cost. Experimental and simulation-based tests were conducted under dynamic environments to validate the algorithm. Further, the ANADE was benchmarked against other recently developed navigation algorithms. Those tests were focused on the behaviour of the algorithm under challenging environments with moving and static obstacles and goals. Further, the test results demonstrate that the ANADE is successful in navigating robots under unknown, dynamically cluttered environments.
- Description: Doctor of Philosophy
AI and IoT-Enabled smart exoskeleton system for rehabilitation of paralyzed people in connected communities
- Authors: Jacob, Sunil , Alagirisamy, Mukil , Xi, Chen , Balasubramanian, Venki , Srinivasan, Ram
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Access Vol. 9, no. (2021), p. 80340-80350
- Full Text:
- Reviewed:
- Description: In recent years, the number of cases of spinal cord injuries, stroke and other nervous impairments have led to an increase in the number of paralyzed patients worldwide. Rehabilitation that can aid and enhance the lives of such patients is the need of the hour. Exoskeletons have been found as one of the popular means of rehabilitation. The existing exoskeletons use techniques that impose limitations on adaptability, instant response and continuous control. Also most of them are expensive, bulky, and requires high level of training. To overcome all the above limitations, this paper introduces an Artificial Intelligence (AI) powered Smart and light weight Exoskeleton System (AI-IoT-SES) which receives data from various sensors, classifies them intelligently and generates the desired commands via Internet of Things (IoT) for rendering rehabilitation and support with the help of caretakers for paralyzed patients in smart and connected communities. In the proposed system, the signals collected from the exoskeleton sensors are processed using AI-assisted navigation module, and helps the caretakers in guiding, communicating and controlling the movements of the exoskeleton integrated to the patients. The navigation module uses AI and IoT enabled Simultaneous Localization and Mapping (SLAM). The casualties of a paralyzed person are reduced by commissioning the IoT platform to exchange data from the intelligent sensors with the remote location of the caretaker to monitor the real time movement and navigation of the exoskeleton. The automated exoskeleton detects and take decisions on navigation thereby improving the life conditions of such patients. The experimental results simulated using MATLAB shows that the proposed system is the ideal method for rendering rehabilitation and support for paralyzed patients in smart communities. © 2013 IEEE. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Venki Balasubramanian” is provided in this record**
Alcohol consumption in aquatic settings: a mixed-method study exploring young adults’ attitudes and knowledge
- Authors: Calverley, Hannah , Petrass, Lauren , Blitvich, Jennifer
- Date: 2021
- Type: Text , Journal article
- Relation: Drugs: Education, Prevention and Policy Vol. 28, no. 6 (2021), p. 595-605
- Full Text: false
- Reviewed:
- Description: Retrospective studies have identified alcohol as a significant risk factor in drownings involving young adults. Few studies have explored this issue, therefore the current contextual understanding of alcohol consumption in aquatic settings is limited. This study used a survey (n = 182) and one-to-one and small group interviews (n = 23) to investigate knowledge and attitudes of United Kingdom and Australian young adults (aged 18–24 years) towards involvement in aquatic activity after consuming alcohol. Findings illustrated a poor level of general and aquatic-specific alcohol knowledge. Australian educated participants, and those self-reporting: stronger swimming competence; and/or completion of alcohol and water safety education; and/or participation in aquatic activity following alcohol consumption, achieved significantly higher knowledge scores. Most reported a neutral attitude, and those with previous experience of alcohol consumption in aquatic settings had more accepting attitudes of this behavior (p < 0.001). The aquatic activity, context and amount of alcohol consumed influenced attitudes. Participants reported a lack of alcohol-focused drowning prevention or water safety education for their age group, and many referred to their upbringing and parents’ behaviors as reference for what was safe. Drowning prevention practitioners should consider these results to ensure young adults understand the risks of consuming alcohol in all aquatic contexts. © 2020 Informa UK Limited, trading as Taylor & Francis Group.
Alternative representations of the normal cone to the domain of supremum functions and subdifferential calculus
- Authors: Correa, R. , Hantoute, A. , López, Marco
- Date: 2021
- Type: Text , Journal article
- Relation: Set-Valued and Variational Analysis Vol. 29, no. 3 (2021), p. 683-699
- Relation: http://purl.org/au-research/grants/arc/DP180100602
- Full Text:
- Reviewed:
- Description: The first part of the paper provides new characterizations of the normal cone to the effective domain of the supremum of an arbitrary family of convex functions. These results are applied in the second part to give new formulas for the subdifferential of the supremum function, which use both the active and nonactive functions at the reference point. Only the data functions are involved in these characterizations, the active ones from one side, together with the nonactive functions multiplied by some appropriate parameters. In contrast with previous works in the literature, the main feature of our subdifferential characterization is that the normal cone to the effective domain of the supremum (or to finite-dimensional sections of this domain) does not appear. A new type of optimality conditions for convex optimization is established at the end of the paper. © 2021, The Author(s), under exclusive licence to Springer Nature B.V.
Amaranthus retroflexus L (redroot pigweed) : effects of elevated CO2 and soil moisture on growth and biomass and the effect of radiant heat on seed germination
- Authors: Weller, Sandra , Florentine, Singarayer , Welgama, Amali , Chadha, Aakansha , Turville, Christopher
- Date: 2021
- Type: Text , Journal article
- Relation: Agronomy Vol. 11, no. 4 (2021), p.
- Full Text:
- Reviewed:
- Description: Amaranthus retroflexus L. (Amaranthaceae), Redroot pigweed, is native to North America, but has become a weed of agriculture worldwide. Previous research into competition with food crops found it significantly reduces yields. Additionally, taxonomy, biomass allocation, physiological responses to light intensity, water stress, elevated CO2, and herbicide resistance have been inves-tigated. To extend other research findings, we investigated growth and biomass yield in response to (i) soil moisture stress, and (ii) drought and elevated CO2. Additionally, we investigated seed germination rates following exposure to three elevated temperatures for two different time periods. Overall, moisture stress reduced plant height, stem diameter, and number of leaves. Elevated CO2 (700 ppm) appeared to reduce negative impacts of drought on biomass productivity. Heating seeds at 120◦C and above for either 180 or 300 s significantly reduced germination rate. These results inform an understanding of potential responses of A. retroflexus to future climate change and will be used to predict future occurrence of this weed. The finding that exposing seeds to high temperatures retards germination suggests fire could be used to prevent seed germination from soil seed banks, particularly in no-till situations, and therefore may be used to address infestations or prevent further spread of this weed. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliates “Sandra Weller, Singarayer Florentine, Amali Welgama, Aakansha Chadha, Chrisopher Turville" are provided in this record**
An adaptive hierarchical sliding mode controller for autonomous underwater vehicles
- Authors: Van Vu, Quang , Dinh, Tuan , Van Nguyen, Thien , Tran, Hoang , Nguyen, Linh
- Date: 2021
- Type: Text , Journal article
- Relation: Electronics (Switzerland) Vol. 10, no. 18 (2021), p.
- Full Text:
- Reviewed:
- Description: The paper addresses a problem of efficiently controlling an autonomous underwater vehicle (AUV), where its typical underactuated model is considered. Due to critical uncertainties and nonlinearities in the system caused by unavoidable external disturbances such as ocean currents when it operates, it is paramount to robustly maintain motions of the vehicle over time as expected. Therefore, it is proposed to employ the hierarchical sliding mode control technique to design the closed-loop control scheme for the device. However, exactly determining parameters of the AUV control system is impractical since its nonlinearities and external disturbances can vary those parameters over time. Thus, it is proposed to exploit neural networks to develop an adaptive learning mechanism that allows the system to learn its parameters adaptively. More importantly, stability of the AUV system controlled by the proposed approach is theoretically proved to be guaranteed by the use of the Lyapunov theory. Effectiveness of the proposed control scheme was verified by the experiments implemented in a synthetic environment, where the obtained results are highly promising. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Linh Nguyen" is provided in this record**
An adaptive splitting algorithm for the sum of two generalized monotone operators and one cocoercive operator
- Authors: Dao, Minh , Phan, Hung
- Date: 2021
- Type: Text , Journal article
- Relation: Fixed Point Theory and Algorithms for Sciences and Engineering Vol. 2021, no. 1 (2021), p. 1-19
- Full Text:
- Reviewed:
- Description: Splitting algorithms for finding a zero of sum of operators often involve multiple steps which are referred to as forward or backward steps. Forward steps are the explicit use of the operators and backward steps involve the operators implicitly via their resolvents. In this paper, we study an adaptive splitting algorithm for finding a zero of the sum of three operators. We assume that two of the operators are generalized monotone and their resolvents are computable, while the other operator is cocoercive but its resolvent is missing or costly to compute. Our splitting algorithm adapts new parameters to the generalized monotonicity of the operators and, at the same time, combines appropriate forward and backward steps to guarantee convergence to a solution of the problem. © 2021, The Author(s).
An adaptive splitting algorithm for the sum of two generalized monotone operators and one cocoercive operator
- Authors: Dao, Minh , Phan, Hung
- Date: 2021
- Type: Text , Journal article
- Relation: Fixed Point Theory and Algorithms for Sciences and Engineering Vol. 2021, no. 1 (2021), p.
- Full Text:
- Reviewed:
- Description: Splitting algorithms for finding a zero of sum of operators often involve multiple steps which are referred to as forward or backward steps. Forward steps are the explicit use of the operators and backward steps involve the operators implicitly via their resolvents. In this paper, we study an adaptive splitting algorithm for finding a zero of the sum of three operators. We assume that two of the operators are generalized monotone and their resolvents are computable, while the other operator is cocoercive but its resolvent is missing or costly to compute. Our splitting algorithm adapts new parameters to the generalized monotonicity of the operators and, at the same time, combines appropriate forward and backward steps to guarantee convergence to a solution of the problem. © 2021, The Author(s).
An AI-enabled lightweight data fusion and load optimization approach for internet of things
- Authors: Jan, Mian , Zakarya, Muhammad , Khan, Muhammad , Mastorakis, Spyridon , Balasubramanian, Venki
- Date: 2021
- Type: Text , Journal article
- Relation: Future Generation Computer Systems Vol. 122, no. (2021), p. 40-51
- Full Text: false
- Reviewed:
- Description: In the densely populated Internet of Things (IoT) applications, sensing range of the nodes might overlap frequently. In these applications, the nodes gather highly correlated and redundant data in their vicinity. Processing these data depletes the energy of nodes and their upstream transmission towards remote datacentres, in the fog infrastructure, may result in an unbalanced load at the network gateways and edge servers. Due to heterogeneity of edge servers, few of them might be overwhelmed while others may remain less-utilized. As a result, time-critical and delay-sensitive applications may experience excessive delays, packet loss, and degradation in their Quality of Service (QoS). To ensure QoS of IoT applications, in this paper, we eliminate correlation in the gathered data via a lightweight data fusion approach. The buffer of each node is partitioned into strata that broadcast only non-correlated data to edge servers via the network gateways. Furthermore, we propose a dynamic service migration technique to reconfigure the load across various edge servers. We assume this as an optimization problem and use two meta-heuristic algorithms, along with a migration approach, to maintain an optimal Gateway-Edge configuration in the network. These algorithms monitor the load at each server, and once it surpasses a threshold value (which is dynamically computed with a simple machine learning method), an exhaustive search is performed for an optimal and balanced periodic reconfiguration. The experimental results of our approach justify its efficiency for large-scale and densely populated IoT applications. © 2021 Elsevier B.V. *Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Venki Balasubramanian” is provided in this record**.
An annotated catalog of Iranian Symphypleona and Neelipleona (Hexapoda: Collembola) : new records and key to species
- Authors: Mayvan, Mahmood , Sadeghi-Namaghi, Hussein , Shayanmehr, Masoumeh , Greenslade, Penelope
- Date: 2021
- Type: Text , Journal article
- Relation: Journal of Asia-Pacific Biodiversity Vol. 14, no. 4 (2021), p. 501-513
- Full Text:
- Reviewed:
- Description: This article provides an annotated catalog of the Symphypleona and Neelipleona (Hexapoda: Collembola) of Iran based on published literature and specimens recently collected from three different ecosystems in North Khorasan province (Forest, Rangeland, and Agricultural) of the years 2018 and 2019. Thirty-five species in seven families and 17 genera are listed. Among them, Megalothorax minimus and Bourletiella sp. are recorded for the first time from Iran. An updated key to the Iranian species and information on the biology and geographical distribution of each species is provided. © 2021 National Science Museum of Korea (NSMK) and Korea National Arboretum (KNA)
An augmented subgradient method for minimizing nonsmooth DC functions
- Authors: Bagirov, Adil , Hoseini Monjezi, Najmeh , Taheri, Sona
- Date: 2021
- Type: Text , Journal article
- Relation: Computational Optimization and Applications Vol. 80, no. 2 (2021), p. 411-438
- Relation: http://purl.org/au-research/grants/arc/DP190100580
- Full Text: false
- Reviewed:
- Description: A method, called an augmented subgradient method, is developed to solve unconstrained nonsmooth difference of convex (DC) optimization problems. At each iteration of this method search directions are found by using several subgradients of the first DC component and one subgradient of the second DC component of the objective function. The developed method applies an Armijo-type line search procedure to find the next iteration point. It is proved that the sequence of points generated by the method converges to a critical point of the unconstrained DC optimization problem. The performance of the method is demonstrated using academic test problems with nonsmooth DC objective functions and its performance is compared with that of two general nonsmooth optimization solvers and five solvers specifically designed for unconstrained DC optimization. Computational results show that the developed method is efficient and robust for solving nonsmooth DC optimization problems. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
An efficient adaptive sampling approach for mobile robotic sensor networks using proximal ADMM
- Authors: Le, Viet-Anh , Nguyen, Linh , Nghiem, Truong
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 American Control Conference, ACC 2021 Vol. 2021-May, p. 1101-1106
- Full Text: false
- Reviewed:
- Description: Adaptive sampling in a resource-constrained mobile robotic sensor network for monitoring a spatial phenomenon is a fundamental but challenging problem. In applications where a Gaussian Process is employed to model a spatial field and then to predict the field at unobserved locations, the adaptive sampling problem can be formulated as minimizing the negative log determinant of a predicted covariance matrix, which is a non-convex and highly complex function. Consequently, this optimization problem is typically addressed in a grid-based discrete domain, although it is combinatorial NP-hard and only a near-optimal solution can be obtained. To overcome this challenge, we propose using a proximal alternating direction method of multipliers (Px-ADMM) technique to solve the adaptive sampling optimization problem in a continuous domain. Numerical simulations using a real-world dataset demonstrate that the proposed PxADMM-based method outperforms a commonly used grid-based greedy method in the final model accuracy. © 2021 American Automatic Control Council.
An efficient approach for SIMO systems using adaptive fuzzy hierarchical sliding mode control
- Authors: Van Nguyen, Thien , Le, Hai , Tran, Hoang , Nguyen, Duc , Nguyen, Minh , Nguyen, Linh
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2021 p. 85-90
- Full Text: false
- Reviewed:
- Description: The paper addresses the problem of efficiently controlling a class of single input multiple output (SIMO) under-Actuated robotic systems such as a two dimensional inverted pendulum cart or a two dimensional overhead crane. It is first proposed to employ the hierarchical sliding mode control approach to design a control law, which guarantees stability and anti-swing of the vehicle when it is driven on a predefined trajectory. More importantly, the unknown and uncertain parameters of the system caused by its actuator nonlinearity and external disturbances are adaptively estimated and inferred by the proposed fuzzy logic mechanism, which results in the efficient operation of the SIMO under-Actuated system in real time. The proposed algorithm was then implemented in the synthetic environment, where the obtained results demonstrate its effectiveness. © 2021 IEEE.
An efficient force-feedback hand exoskeleton for haptic applications
- Authors: Le, Duy , Nguyen, Linh
- Date: 2021
- Type: Text , Journal article
- Relation: International Journal of Intelligent Robotics and Applications Vol. 5, no. 3 (2021), p. 395-409
- Full Text: false
- Reviewed:
- Description: In this paper, a study on wearable exoskeleton devices which are capable of delivering sensation to the fingers while interacting with the virtual objects in virtual reality environment has been conducted. A force-controllable hand exoskeleton system is proposed, which is able to apply force feedback to the fingertip while allowing natural finger motions. The linkage structure was inspired by the skeletal structure of a human finger. Moreover, a series elastic actuator (SEA) mechanism, which consisted of a linear motor, a spring and a potentiometer, was presented as an actuating system. The force transmission through linkage has been investigated to ensure the force feedback ability at the fingertip. By using a PID controller, the proposed actuator module could generate the desired force in two different modes: free mode and interaction mode. The experimental results show that the proposed system could effectively deliver forces to the fingertips. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.
An efficient hybrid system for anomaly detection in social networks
- Authors: Rahman, Md Shafiur , Halder, Sajal , Uddin, Ashraf , Acharjee, Uzzal
- Date: 2021
- Type: Text , Journal article
- Relation: Cybersecurity Vol. 4, no. 1 (2021), p.
- Full Text:
- Reviewed:
- Description: Anomaly detection has been an essential and dynamic research area in the data mining. A wide range of applications including different social medias have adopted different state-of-the-art methods to identify anomaly for ensuring user’s security and privacy. The social network refers to a forum used by different groups of people to express their thoughts, communicate with each other, and share the content needed. This social networks also facilitate abnormal activities, spread fake news, rumours, misinformation, unsolicited messages, and propaganda post malicious links. Therefore, detection of abnormalities is one of the important data analysis activities for the identification of normal or abnormal users on the social networks. In this paper, we have developed a hybrid anomaly detection method named DT-SVMNB that cascades several machine learning algorithms including decision tree (C5.0), Support Vector Machine (SVM) and Naïve Bayesian classifier (NBC) for classifying normal and abnormal users in social networks. We have extracted a list of unique features derived from users’ profile and contents. Using two kinds of dataset with the selected features, the proposed machine learning model called DT-SVMNB is trained. Our model classifies users as depressed one or suicidal one in the social network. We have conducted an experiment of our model using synthetic and real datasets from social network. The performance analysis demonstrates around 98% accuracy which proves the effectiveness and efficiency of our proposed system. © 2021, The Author(s).
An efficient multi-vehicle routing strategy for goods delivery services
- Authors: Le, Duy , Men, Ying , Luo, Yunkang , Zhou, Yixuan , Nguyen, Linh
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2021 Vol. 2021-July, p. 188-193
- Full Text: false
- Reviewed:
- Description: The paper addresses the problem of efficiently planning routes for multiple ground vehicles used in goods delivery services. Given popularity of today's e-commerce, particularly under the COVID-19 pandemic conditions, goods delivery services have been booming than ever, dominated by small-scaled (electric) bikes and promised by autonomous vehicles. However, finding optimal routing paths for multiple delivery vehicles operating simultaneously in order to minimize transportation cost is a fundamental but challenging problem. In this paper, it is first proposed to exploit the mixed integer programming paradigm to model the delivery routing optimization problem (DROP) for multiple simultaneously-operating vehicles given their energy constraints. The routing optimization problem is then solved by the multi-chromosome genetic algorithm, where the number of delivery vehicles can be optimized. The proposed approach was evaluated in a realworld experiment in which goods were expected to be delivered from a depot to 26 suburb locations in Canberra, Australia. The obtained results demonstrate effectiveness of the proposed algorithm. © 2021 IEEE.
An empirical analysis of sediment export dynamics from a constructed landform in the wet tropics
- Authors: Yavari, Shahla , McIntyre, Neil , Baumgartl, Thomas
- Date: 2021
- Type: Text , Journal article
- Relation: Water (Switzerland) Vol. 13, no. 8 (2021), p.
- Full Text:
- Reviewed:
- Description: Although plot-scale erosion experiments are numerous, there are few studies on constructed landforms. This limits the understanding of their long-term stability, which is especially important for planning mined land rehabilitation. The objective of this study was to gain insight into the erosion processes in a 30 × 30 m trial plot on a mine waste rock dump in tropical northern Australia. The relationships between rainfall, runoff and suspended and bedload sediment export were assessed at annual, seasonal, inter-event and intra-event timescales. During a five-year study period, 231 rainfall– runoff–sediment export events were examined. The measured bedload and suspended sediments (mainly represented in nephelometric turbidity units (NTU)) showed the dominance of the wet season and heavy rainfall events. The bedload dominated the total mass, although the annual bedload diminished by approximately 75% over the five years, with greater flow energy required over time to mobilise the same bedload. The suspended load was more sustained, though it also exhibited an exhaustion process, with equal rainfall and runoff volumes and intensities, leading to lower NTU values over time. Intra-event NTU dynamics, including runoff-NTU time lags and hysteretic behaviours, were somewhat random from one event to the next, indicating the influence of the antecedent distribution of mobilisable sediments. The value of the results for supporting predictive modelling is discussed. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
An evaluation methodology for interactive reinforcement learning with simulated users
- Authors: Bignold, Adam , Cruz, Francisco , Dazeley, Richard , Vamplew, Peter , Foale, Cameron
- Date: 2021
- Type: Text , Journal article
- Relation: Biomimetics Vol. 6, no. 1 (2021), p. 1-15
- Full Text:
- Reviewed:
- Description: Interactive reinforcement learning methods utilise an external information source to evaluate decisions and accelerate learning. Previous work has shown that human advice could significantly improve learning agents’ performance. When evaluating reinforcement learning algorithms, it is common to repeat experiments as parameters are altered or to gain a sufficient sample size. In this regard, to require human interaction every time an experiment is restarted is undesirable, particularly when the expense in doing so can be considerable. Additionally, reusing the same people for the experiment introduces bias, as they will learn the behaviour of the agent and the dynamics of the environment. This paper presents a methodology for evaluating interactive reinforcement learning agents by employing simulated users. Simulated users allow human knowledge, bias, and interaction to be simulated. The use of simulated users allows the development and testing of reinforcement learning agents, and can provide indicative results of agent performance under defined human constraints. While simulated users are no replacement for actual humans, they do offer an affordable and fast alternative for evaluative assisted agents. We introduce a method for performing a preliminary evaluation utilising simulated users to show how performance changes depending on the type of user assisting the agent. Moreover, we describe how human interaction may be simulated, and present an experiment illustrating the applicability of simulating users in evaluating agent performance when assisted by different types of trainers. Experimental results show that the use of this methodology allows for greater insight into the performance of interactive reinforcement learning agents when advised by different users. The use of simulated users with varying characteristics allows for evaluation of the impact of those characteristics on the behaviour of the learning agent. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
An evidence-based checklist for improving scoping review quality
- Authors: Cooper, Simon , Cant, Robyn , Kelly, Michelle , Levett-Jones, Tracy , McKenna, Lisa
- Date: 2021
- Type: Text , Journal article
- Relation: Clinical Nursing Research Vol. 30, no. 3 (2021), p. 230-240
- Full Text: false
- Reviewed:
- Description: A scoping review aims to systematically explore and map the research available from a wide range of sources. The objective of this study was to produce a scoping review checklist to guide future scoping studies to enable rigorous review and critique of phenomena of interest. The methods used included a review of literature, expert consensus group meetings, a modified Delphi survey and, finally, verification against recent scoping study examples. Results showed that the checklist was able to identify key elements of scoping reviews. The 22-item Scoping Review Checklist (SRC), which includes two optional stakeholder consultation items, has been developed using rigorous recommended approaches. The checklist can be used to guide the conduct and critique of scoping studies. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Simon Cooper and Robyn Cant” is provided in this record**