For emergency departments (EDs) to maintain sustainable care of patients, hospital management must continually explore potential interventions to clinical practice. Agent-based modelling (ABM) can be a valuable tool to support this planning in a controlled environment. Existing approaches to ABM development are best suited for one-off models. However, conditions in EDs can change frequently, making the use of one-off models infeasible. Decision-makers must be able to trust simulations appropriately for them to be effective in intervention exploration. Domain-specific modelling languages (DSMLs) can address these challenges by offering a reusable library of appropriately abstract, domain-familiar, modelling concepts across case studies and automatic translation of these concepts into executable models. In this paper, we present a DSML to support repeated modelling exercises in the ED domain and illustrate the use and reuse of this DSML across two concrete case studies in London-based NHS emergency departments.

Given the distributed, heterogenous, and dynamic nature of service-based IoT systems, capturing circumstances data underlying service provisions becomes increasingly important for understanding process flow and tracing how outputs came about, thus enabling clients to make more informed decisions regarding future interaction partners. Whilst service providers are the main source of such circumstances data, they may often be reluctant to release it, e.g., due to the cost and effort required, or to protect their interests. In response, this article introduces a reputation-based framework, guided by intelligent software agents, to support the sharing of truthful circumstances information by providers. In this framework, assessor agents , acting on behalf of clients, rank and select service providers according to reputation, while provider agents , acting on behalf of service providers, learn from the environment and adjust provider’s circumstances provision policies in the direction that increases provider profit with respect to perceived reputation. The novelty of the reputation assessment model adopted by assessor agents lies in affecting provider reputation scores by whether or not they reveal truthful circumstances data underlying their service provisions, in addition to other factors commonly adopted by existing reputation schemes. The effectiveness of the proposed framework is demonstrated through an agent-based simulation including robustness against a number of attacks, with a comparative performance analysis against FIRE as a baseline reputation model.

Participatory agent-based modelling (ABM) can help bring the benefits of simulation to domain users by actively involving stakeholders in the development process. Collaboration in enterprise modelling can improve the model developer’s understanding of the domain and therefore improve the effectiveness of domain analysis. Where many agent-oriented methodologies focus on the development of one-off models, domain-specific modelling languages (DSML) can improve the re-use of concepts identified in domain analysis across multiple case studies and expose modelling concepts in domain-appropriate terms, increasing model accessibility. To realise the benefits of DSMLs we need to understand how DSML development can be incorporated into typical agent-based modelling. In this paper we discuss existing methodologies for ABM development and DSML development, and we discuss the benefits merging the two can bring. We present a methodology for DSML-assisted participatory agent-based modelling, and support the methodology with a case study—a modelling exercise conducted in collaboration with a hospital emergency department on the topic of infection control for COVID-19 and Influenza.

Current work on multi-agent systems at King's College London is extensive, though largely based in two research groups within the Department of Informatics: the Distributed Artificial Intelligence (DAI) thematic group and the Reasoning & Planning (RAP) thematic group. DAI combines AI expertise with political and economic theories and data, to explore social and technological contexts of interacting intelligent entities. It develops computational models for analysing social, political and economic phenomena to improve the effectiveness and fairness of policies and regulations, and combines intelligent agent systems, software engineering, norms, trust and reputation, agent-based simulation, communication and provenance of data, knowledge engineering, crowd computing and semantic technologies, and algorithmic game theory and computational social choice, to address problems arising in autonomous systems, financial markets, privacy and security, urban living and health. RAP conducts research in symbolic models for reasoning involving argumentation, knowledge representation, planning, and other related areas, including development of logical models of argumentation-based reasoning and decision-making, and their usage for explainable AI and integration of machine and human reasoning, as well as combining planning and argumentation methodologies for strategic argumentation.

Interventions to increase active commuting have been recommended as a method to increase population physical activity, but evidence is mixed. Social norms related to travel behaviour may influence the uptake of active commuting interventions but are rarely considered in their design and evaluation. In this study we develop an agent-based model that incorporates social norms related to travel behaviour and demonstrate the utility of this through implementing car-free Wednesdays. A synthetic population of Waltham Forest, London, UK was generated using a microsimulation approach with data from the UK Census 2011 and UK HLS datasets. An agent-based model was created using this synthetic population which modelled how the actions of peers and neighbours, subculture, habit, weather, bicycle ownership, car ownership, environmental supportiveness, and congestion affect the decision to trave. The developed model (MOTIVATE) is a configurable agent-based model where social norms related to travel behaviour are used to provide a more realistic representation of the socio-ecological systems in which active commuting interventions may be deployed. The utility of this model is demonstrated using car-free days as a hypothetical intervention. In the control scenario, the odds of active travel were plausible at 0.091 (89% HPDI: [0.091, 0.091]). Compared to the control scenario, the odds of active travel were increased by 70.3% (89% HPDI: [70.3%, 70.3%]), in the intervention scenario, on non-car-free days; the effect is sustained to non-car-free days. The model is a useful tool for investigating the effect of how social networks and social norms influence the effectiveness of various interventions. If configured using real-world built environment data, it may be useful for investigating how social norms interact with the built environment to cause the emergence of commuting conventions.

Resource allocation and task prioritisation are key problem domains in the fields of autonomous vehicles, networking, and cloud computing. The challenge in developing efficient and robust algorithms comes from the dynamic nature of these systems, with many components communicating and interacting in complex ways. The multi-group resource allocation optimisation (MG-RAO) algorithm we present uses multiple function approximations of resource demand over time, alongside reinforcement learning techniques, to develop a novel method of optimising resource allocation in these multi-agent systems. This method is applicable where there are competing demands for shared resources, or in task prioritisation problems. Evaluation is carried out in a simulated environment containing multiple competing agents. We compare the new algorithm to an approach where child agents distribute their resources uniformly across all the tasks they can be allocated. We also contrast the performance of the algorithm where resource allocation is modelled separately for groups of agents, as to being modelled jointly over all agents. The MG-RAO algorithm shows a 23 - 28% improvement over fixed resource allocation in the simulated environments. Results also show that, in a volatile system, using the MG-RAO algorithm configured so that child agents model resource allocation for all agents as a whole has 46.5% of the performance of when it is set to model multiple groups of agents. These results demonstrate the ability of the algorithm to solve resource allocation problems in multi-agent systems and to perform well in dynamic environments.

In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5x better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.

Patient flow in emergency departments (EDs) is notoriously difficult to manage efficiently. While much of the attention has focused on the procedures, protocols and pathways in which patients receive their first hours of care, less attention has been paid to the relational factors that make it happen. Our study is the first, to our knowledge, to consider the role of interprofessional barriers, defined as suboptimal ways of working, as perceived by ED staff in patient flow management. Drawing on 19 interviews with hospital staff in an acute tertiary trauma center hospital in England, we established three flow-related types of interprofessional barriers: ED teamwork barriers, performance-driven coordination barriers, and referral-related collaborative barriers. Knotworking was recognized as a form of interactions and asset to teamworking, coordination, and collaboration. Identifying processes such as chasing, escalating, and advocating enabled our investigation to highlight a very complex set of interprofessional interactions, and signpost what the suboptimal practices of flow management are. Our analysis holds promise for hospitals beyond the National Health Service in England.

BACKGROUND:Although alarm safety is a critical issue that needs to be addressed to improve patient care, hospitals have not given serious consideration about how their staff should be using, setting, and responding to clinical alarms. Studies have indicated that 80%-99% of alarms in hospital units are false or clinically insignificant and do not represent real danger for patients, leading caregivers to miss relevant alarms that might indicate significant harmful events. The lack of use of any intelligent filter to detect recurrent, irrelevant, and/or false alarms before alerting health providers can culminate in a complex and overwhelming scenario of sensory overload for the medical team, known as alarm fatigue.OBJECTIVE:This paper's main goal is to propose a solution to mitigate alarm fatigue by using an automatic reasoning mechanism to decide how to calculate false alarm probability (FAP) for alarms and whether to include an indication of the FAP (ie, FAP_LABEL) with a notification to be visualized by health care team members designed to help them prioritize which alerts they should respond to next.METHODS:We present a new approach to cope with the alarm fatigue problem that uses an automatic reasoner to decide how to notify caregivers with an indication of FAP. Our reasoning algorithm calculates FAP for alerts triggered by sensors and multiparametric monitors based on statistical analysis of false alarm indicators (FAIs) in a simulated environment of an intensive care unit (ICU), where a large number of warnings can lead to alarm fatigue.RESULTS:The main contributions described are as follows: (1) a list of FAIs we defined that can be utilized and possibly extended by other researchers, (2) a novel approach to assess the probability of a false alarm using statistical analysis of multiple inputs representing alarm-context information, and (3) a reasoning algorithm that uses alarm-context information to detect false alarms in order to decide whether to notify caregivers with an indication of FAP (ie, FAP_LABEL) to avoid alarm fatigue.CONCLUSIONS:Experiments were conducted to demonstrate that by providing an intelligent notification system, we could decide how to identify false alarms by analyzing alarm-context information. The reasoner entity we described in this paper was able to attribute FAP values to alarms based on FAIs and to notify caregivers with a FAP_LABEL indication without compromising patient safety.

Alarm Fatigue is a scenario experienced by an overwhelmed and fatigued healthcare team that is desensitized and slow to respond to alarms. The most common alarm-related issues that may lead to Alarm Fatigue include the excessive number of alarms, a number of alarms generated by many different types of alarm devices, and the high percentage of false alarms (80%-99%). All of these alerts have to be processed by the healthcare teams who are consistently under pressure: they should analyze the high volume of inputs they are receiving in order to answer to them quickly and correctly, by making decisions in real-time about the response to the next alarm. Under alarm fatigue conditions, the staff may ignore and/or silence alarms, putting patients in risky situations. This paper’s main goal is to propose a feasible solution for mitigating alarm fatigue by using an automatic reasoning mechanism to choose the best caregiver to be assigned to a given notification within the set of available caregivers in an Intensive Care Unit. Our main contribution in this work consists of an algorithm that decides who is the best caregiver to notify in an ICU. We formalized this problem as a Constraint-Satisfaction Problem and we present one example of how it can be solved. We designed a case study where patients’ vital signs were collected through a vital signs’ generator that also triggers alarms. We conducted five experiments to test our algorithm considering different situations for an ICU. The evaluation of our algorithm was made through the comparison between the results of the choices made by our reasoning algorithm and another strategy that we call “blind” strategy, which randomly assigns caregivers to notifications. Experiments are used to demonstrate that providing a reasoning system we could decide who is the best caregiver to receive a notification. By comparing the choices made by our reasoning algorithm and the “blind” strategy, our reasoning algorithm achieved a better result in terms of prioritizing the assignments we wanted to make based on our defined criteria: patient’s severity, the distance between caregivers and patients, caregivers’ experience, the probability of a notification to be false, and the number of notifications caregivers have received. The experimental results strongly suggest that this reasoning algorithm is a useful strategy for mitigating alarm fatigue. We showed, in our experiments, that caregivers with higher levels of experience received more notifications than the ones with lower levels. Our future work is to deal with resource negotiation and to evaluate the distribution of the notifications to the caregivers’ teams made by the algorithms.

. Two key tasks in argument mining (AM) are classification of argument components and identification of relations between argument components. Approaches to solving the argument component classification problem typically take a supervised learning approach, however a lack of suitable datasets makes this a challenge for identification of ar-gument component relations. We propose a pipeline with a recurrent, branched structure that combines supervised learning of argument component classifications with NLP approaches to identification of argument component relations, with the aim of improving both classification of argument components (i

An increase in volumes of data and a shift towards live data enabled a stronger focus on resource-intensive tasks which run continuously over long periods. A Grid has potential to offer the required resources for these tasks, while considering a fair and balanced allocation of resources among multiple client agents. Taking this into account, a Grid might be unwilling to allocate its resources for long time, leading to task interruptions. This problem becomes even more serious if an interruption of one task may lead to the interruption of dependent tasks. Here, we discuss a new strategy for resource re-allocation which is utilized by a client with the aim to prevent too long interruptions by re-allocating resources between its own tasks. Those re-allocations are suggested by a client agent, but only a Grid can re-allocate resources if agreed. Our strategy was tested under the different Grid settings, accounting for the adjusted coefficients, and demonstrated noticeable improvements in client utilities as compared to when it is not considered. Our experiment was also extended to tests with environmental modelling and realistic Grid resource simulation, grounded in real-life Grid studies. These tests have also shown a useful application of our strategy.

Background Informed estimates claim that 80% to 99% of alarms set off in hospital units are false or clinically insignificant, representing a cacophony of sounds that do not present a real danger to patients. These false alarms can lead to an alert overload that causes a health care provider to miss important events that could be harmful or even life-threatening. As health care units become more dependent on monitoring devices for patient care purposes, the alarm fatigue issue has to be addressed as a major concern for the health care team as well as to enhance patient safety. Objective The main goal of this paper was to propose a feasible solution for the alarm fatigue problem by using an automatic reasoning mechanism to decide how to notify members of the health care team. The aim was to reduce the number of notifications sent by determining whether or not to group a set of alarms that occur over a short period of time to deliver them together, without compromising patient safety. Methods This paper describes: (1) a model for supporting reasoning algorithms that decide how to notify caregivers to avoid alarm fatigue; (2) an architecture for health systems that support patient monitoring and notification capabilities; and (3) a reasoning algorithm that specifies how to notify caregivers by deciding whether to aggregate a group of alarms to avoid alarm fatigue. Results Experiments were used to demonstrate that providing a reasoning system can reduce the notifications received by the caregivers by up to 99.3% (582/586) of the total alarms generated. Our experiments were evaluated through the use of a dataset comprising patient monitoring data and vital signs recorded during 32 surgical cases where patients underwent anesthesia at the Royal Adelaide Hospital. We present the results of our algorithm by using graphs we generated using the R language, where we show whether the algorithm decided to deliver an alarm immediately or after a delay. Conclusions The experimental results strongly suggest that this reasoning algorithm is a useful strategy for avoiding alarm fatigue. Although we evaluated our algorithm in an experimental environment, we tried to reproduce the context of a clinical environment by using real-world patient data. Our future work is to reproduce the evaluation study based on more realistic clinical conditions by increasing the number of patients, monitoring parameters, and types of alarm.

Typically, recommender systems focus solely on individual preferences of users or small groups of users, but recommendations can have effects on the wider social structure. Social considerations are there- fore necessary in recommendation generation. In this paper, we identify gaps in literature relevant to socially responsible recommendation sys- tems, and present a number of challenges. Finally, we present a vision for an architecture capable of generating socially responsible recommen- dations and encouraging their acceptance via incentives and rationales.

Reputation is crucial to enabling human or software agents to select among alternative providers. Although several effective reputation assessment methods exist, they typically distil reputation into a numerical representation, with no accompanying explanation of the rationale behind the assessment. Such explanations would allow users or clients to make a richer assessment of providers, and tailor selection according to their preferences and current context. In this paper, we propose an approach to explain the rationale behind assessments from quantitative reputation models, by generating arguments that are combined to form explanations. Our approach adapts, extends and combines existing approaches for explaining decisions made using multi-attribute decision models in the context of reputation. We present example argument templates, and describe how to select their parameters using explanation algorithms. Our proposal was evaluated by means of a user study, which followed an existing protocol. Our results give evidence that although explanations present a subset of the information of trust scores, they are sufficient to equally evaluate providers recommended based on their trust score. Moreover, when explanation arguments reveal implicit model information, they are less persuasive than scores.

Central to explanatory simulation models is their capability to not just show that but also why particular things happen. Explanation is closely related with the detection of causal relationships and is, in a simulation context, typically done by means of controlled experiments. However, for complex simulation models, conventional “blackbox” experiments may be too coarse-grained to cope with spurious relationships. We present an intervention-based causal analysis methodology that exploits the manipulability of computational models, and detects and circumvents spurious effects. The core of the methodology is a formal model that maps basic causal assumptions to causal observations and allows for the identification of combinations of assumptions that have a negative impact on observability. First, experiments indicate that the methodology can successfully deal with notoriously tricky situations involving asymmetric and symmetric overdetermination and detect fine-grained causal relationships between events in the simulation. As illustrated in the article, the methodology can be easily integrated into an existing simulation environment.

Due to their immense complexity, large-scale multi-agent systems are often not amenable to exhaustive formal verification. Statistical approaches that focus on the verification of individual traces can provide an interesting alternative that circumvents combinatorial explosion. However, due to its focus on finite execution paths, trace-based verification is inherently limited to certain types of correctness properties. We show how, by combining sampling with the idea of trace fragmentation, statistical verification can be used to answer interesting quantitative correctness questions about multi-agent systems at different observational levels. The usefulness of the verification approach is illustrated with a simple case study from the area of swarm robotics.

A bottleneck, in general, is a point of congestion in a system which impacts its efficiency, productivity and may lead to delays. Identifying and then fixing bottlenecks is an important step in maintaining and improving a system. To detect bottlenecks, we must understand the flow of processes, and dependencies between resources. Thus provenance information is an appropriate form of input to address this matter. In this paper, bottleneck patterns based on provenance graphs are proposed. These patterns are used to define the structures bottlenecks may take based on their classification, and offer a way to detect possible bottlenecks. An example from soybeans distribution is used to illustrate this preliminary work.

Quality of Service (QoS) properties play an important role in distinguishing between functionally equivalent services and accommodating the different expectations of users. However, the subjective nature of some properties and the dynamic and unreliable nature of service environments may result in cases where the quality values advertised by the service provider are either missing or untrustworthy. To tackle this, a number of QoS estimation approaches have been proposed, using the observation history available on a service to predict its performance. Although the context underlying such previous observations (and corresponding to both user and service related factors) could provide an important source of information for the QoS estimation process, it has only been used to a limited extent by existing approaches. In response, we propose a context‐aware quality learning model, realized via a learning‐enabled service agent, exploiting the contextual characteristics of the domain to provide more personalized, accurate, and relevant quality estimations for the situation at hand. The experiments conducted demonstrate the effectiveness of the proposed approach, showing promising results (in terms of prediction accuracy) in different types of changing service environments.

Trust and reputation allow agents to make informed decisions about potential interactions. Trust in an agent is derived from direct experience with that agent, while reputation is determined by the experiences reported by other witness agents with potentially differing viewpoints. These experiences are typically aggregated in a trust and reputation model, of which there are several types that focus on different aspects. Such aspects include handling subjective perspectives of witnesses, dishonesty, or assessing the reputation of new agents. In this paper, we distil reputation systems into their fundamental aspects, discussing first how trust and reputation information is represented and second how it is disseminated among agents. Based on these discussions, a unifying abstraction is presented for trust and reputation systems, which is demonstrated by instantiating it with a broad range of reputation systems found in the literature. The abstraction is then instantiated to combine the range of capabilities of existing reputation systems in the Machine Learning Reputation System, which is evaluated using a marketplace simulation.