Techniques for distributed theory synthesis in multiagent systems

Data sources are often dispersed geographically in real life applications. Finding a knowledge model may require to join all the data sources and to run a machine learning algorithm on the joint set. We present an alternative based on a Multi Agent System (MAS): an agent mines one data source in order to extract a local theory (knowledge model) and then merges it with the previous MAS theory using a knowledge fusion technique. This way, we obtain a global theory that summarizes the distributed knowledge without spending resources and time in joining data sources. New experiments have been executed including statistical significance analysis. The results show that, as a result of knowledge fusion, the accuracy of initial theories is significantly improved as well as the accuracy of the monolithic solution.

Distributed argumentation technology: advancing risk analysis and regulatory compliance of distributed ledger technologies for transaction and management of securities

Distributed argumentation technology is a computational approach incorporating argumentation reasoning mechanisms within multi-agent systems. For the formal foundations of distributed argumentation technology, in this thesis we conduct a principle-based analysis of structured argumentation as well as abstract multi-agent and abstract bipolar argumentation. The results of the principle-based approach of these theories provide an overview and guideline for further applications of the theories. Moreover, in this thesis we explore distributed argumentation technology using distributed ledgers. We envision an Intelligent Human-input-based Blockchain Oracle (IHiBO), an artificial intelligence tool for storing argumentation reasoning. We propose a decentralized and secure architecture for conducting decision-making, addressing key concerns of trust, transparency, and immutability. We model fund management with agent argumentation in IHiBO and analyze its compliance with European fund management legal frameworks. We illustrate how bipolar argumentation balances pros and cons in legal reasoning in a legal divorce case, and how the strength of arguments in natural language can be represented in structured arguments. Finally, we discuss how distributed argumentation technology can be used to advance risk management, regulatory compliance of distributed ledgers for financial securities, and dialogue techniques.

Integrated communication and learning towards autonomous mobile radio networks

The integration of distributed and ubiquitous intelligence has emerged over the last years as the mainspring of transformative advancements in mobile radio networks. As we approach the era of “mobile for intelligence”, next-generation wireless networks are poised to undergo significant and profound changes. Notably, the overarching challenge that lies ahead is the development and implementation of integrated communication and learning mechanisms that will enable the realization of autonomous mobile radio networks. The ultimate pursuit of eliminating human-in-the-loop constitutes an ambitious challenge, necessitating a meticulous delineation of the fundamental characteristics that artificial intelligence (AI) should possess to effectively achieve this objective. This challenge represents a paradigm shift in the design, deployment, and operation of wireless networks, where conventional, static configurations give way to dynamic, adaptive, and AI-native systems capable of self-optimization, self-sustainment, and learning. This thesis aims to provide a comprehensive exploration of the fundamental principles and practical approaches required to create autonomous mobile radio networks that seamlessly integrate communication and learning components. The first chapter of this thesis introduces the notion of Predictive Quality of Service (PQoS) and adaptive optimization and expands upon the challenge to achieve adaptable, reliable, and robust network performance in dynamic and ever-changing environments. The subsequent chapter delves into the revolutionary role of generative AI in shaping next-generation autonomous networks. This chapter emphasizes achieving trustworthy uncertainty-aware generation processes with the use of approximate Bayesian methods and aims to show how generative AI can improve generalization while reducing data communication costs. Finally, the thesis embarks on the topic of distributed learning over wireless networks. Distributed learning and its declinations, including multi-agent reinforcement learning systems and federated learning, have the potential to meet the scalability demands of modern data-driven applications, enabling efficient and collaborative model training across dynamic scenarios while ensuring data privacy and reducing communication overhead.

Extending the 2P-Kt ecosystem: CLP and Labelled LP

The ability to create hybrid systems that blend different paradigms has now become a requirement for complex AI systems usually made of more than a component. In this way, it is possible to exploit the advantages of each paradigm and exploit the potential of different approaches such as symbolic and non-symbolic approaches. In particular, symbolic approaches are often exploited for their efficiency, effectiveness and ability to manage large amounts of data, while symbolic approaches are exploited to ensure aspects related to explainability, fairness, and trustworthiness in general. The thesis lies in this context, in particular in the design and development of symbolic technologies that can be easily integrated and interoperable with other AI technologies. 2P-Kt is a symbolic ecosystem developed for this purpose, it provides a logic-programming (LP) engine which can be easily extended and customized to deal with specific needs. The aim of this thesis is to extend 2P-Kt to support constraint logic programming (CLP) as one of the main paradigms for solving highly combinatorial problems given a declarative problem description and a general constraint-propagation engine. A real case study concerning school timetabling is described to show a practical usage of the CLP(FD) library implemented. Since CLP represents only a particular scenario for extending LP to domain-specific scenarios, in this thesis we present also a more general framework: Labelled Prolog, extending LP with labelled terms and in particular labelled variables. The designed framework shows how it is possible to frame all variations and extensions of LP under a single language reducing the huge amount of existing languages and libraries and focusing more on how to manage different domain needs using labels which can be associated with every kind of term. Mapping of CLP into Labeled Prolog is also discussed as well as the benefits of the provided approach.

Agent based simulation as a novel decision support tool for retail managers

Intelligent agents offer a new and exciting way of understanding the world of work. We apply agent-based simulation to investigate a set of problems in a retail context. Specifically, we are working to understand the relationship between human resource management practices and retail productivity. Our multi-disciplinary research team draws upon expertise from work psychologists and computer scientists. Our research so far has led us to conduct case study work with a top ten UK retailer. Based on our case study experience and data we are developing a simulator that can be used to investigate the impact of management practices (e.g. training, empowerment, teamwork) on customer satisfaction and retail productivity.

Comparing simulation output accuracy of discrete event and agent based models: a quantitative approach

In our research we investigate the output accuracy of discrete event simulation models and agent based simulation models when studying human centric complex systems. In this paper we focus on human reactive behaviour as it is possible in both modelling approaches to implement human reactive behaviour in the model by using standard methods. As a case study we have chosen the retail sector, and here in particular the operations of the fitting room in the women wear department of a large UK department store. In our case study we looked at ways of determining the efficiency of implementing new management policies for the fitting room operation through modelling the reactive behaviour of staff and customers of the department. First, we have carried out a validation experiment in which we compared the results from our models to the performance of the real system. This experiment also allowed us to establish differences in output accuracy between the two modelling methods. In a second step a multi-scenario experiment was carried out to study the behaviour of the models when they are used for the purpose of operational improvement. Overall we have found that for our case study example both, discrete event simulation and agent based simulation have the same potential to support the investigation into the efficiency of implementing new management policies.

Six thinking hats for electricity markets simulation: adapting meeting tools to agent decision

In almost all industrialized countries, the energy sector has suffered a severe restructuring that originated a greater complexity in market players’ interactions. The complexity that these changes brought made way for the creation of decision support tools that facilitate the study and understanding of these markets. MASCEM – “Multiagent Simulator for Competitive Electricity Markets” arose in this context providing a framework for evaluating new rules, new behaviour, and new participants in deregulated electricity markets. MASCEM uses game theory, machine learning techniques, scenario analysis and optimisation techniques to model market agents and to provide them with decision-support. ALBidS is a multiagent system created to provide decision support to market negotiating players. Fully integrated with MASCEM it considers several different methodologies based on very distinct approaches. The Six Thinking Hats is a powerful technique used to look at decisions from different perspectives. This tool’s goal is to force the thinker to move outside his habitual thinking style. It was developed to be used mainly at meetings in order to “run better meetings, make faster decisions”. This dissertation presents a study about the applicability of the Six Thinking Hats technique in Decision Support Systems, particularly with the multiagent paradigm like the MASCEM simulator. As such this work’s proposal is of a new agent, a meta-learner based on STH technique that organizes several different ALBidS’ strategies and combines the distinct answers into a single one that, expectedly, out-performs any of them.

Distributed, Agent-Based Intelligent System for Demand Response Program Simulation in Smart Grids

A distributed, agent-based intelligent system models and simulates a smart grid using physical players and computationally simulated agents. The proposed system can assess the impact of demand response programs.

System Level Simulation and Radio Resource Management for Distributed Antenna Systems with Cognitive Radio and Multi-Cell Cooperation

4th International Conference on Future Generation Communication Technologies (FGCT 2015), Luton, United Kingdom.

Simulation Environment for Multi-Robot Cooperative 3D Target Perception

4th International Conference, SIMPAR 2014, Bergamo, Italy, October 20-23, 2014

Simulation of masonry out-of-plane failure modes by multi-body dynamics

The seismic assessment of the local failure modes in existing masonry buildings is currently based on the identification of the so-called local mechanisms, often associated with the out-of-plane wall behavior, whose stability is evaluated by static force-based approaches and, more recently, by some displacement-based proposals. Local mechanisms consist of kinematic chains of masonry portions, often regarded as rigid bodies, with geometric nonlinearity and concentrated nonlinearity in predefined contact regions (unilateral no-tension behavior, possible sliding with friction). In this work, the dynamic behavior of local mechanisms is simulated through multi-body dynamics, to obtain the nonlinear response with efficient time history analyses that directly take into account the characteristics of the ground motion. The amplification/filtering effects of the structure are considered within the input motion. The proposed approach is validated with experimental results of two full-scale shaking-table tests on stone masonry buildings: a sacco-stone masonry façade tested at Laboratório Nacional de Engenharia Civil and a two-storey double-leaf masonry building tested at European Centre for Training and Research in Earthquake Engineering (EUCENTRE).

Agent-based parking occupancy simulation

The existing parking simulations, as most simulations, are intended to gain insights of a system or to make predictions. The knowledge they have provided has built up over the years, and several research works have devised detailed parking system models. This thesis work describes the use of an agent-based parking simulation in the context of a bigger parking system development. It focuses more on flexibility than on fidelity, showing the case where it is relevant for a parking simulation to consume dynamically changing GIS data from external, online sources and how to address this case. The simulation generates the parking occupancy information that sensing technologies should eventually produce and supplies it to the bigger parking system. It is built as a Java application based on the MASON toolkit and consumes GIS data from an ArcGis Server. The application context of the implemented parking simulation is a university campus with free, on-street parking places.

Agent based simulation to optimise emergency departments

Nowadays, many of the health care systems are large and complex environments and quite dynamic, specifically Emergency Departments, EDs. It is opened and working 24 hours per day throughout the year with limited resources, whereas it is overcrowded. Thus, is mandatory to simulate EDs to improve qualitatively and quantitatively their performance. This improvement can be achieved modelling and simulating EDs using Agent-Based Model, ABM and optimising many different staff scenarios. This work optimises the staff configuration of an ED. In order to do optimisation, objective functions to minimise or maximise have to be set. One of those objective functions is to find the best or optimum staff configuration that minimise patient waiting time. The staff configuration comprises: doctors, triage nurses, and admissions, the amount and sort of them. Staff configuration is a combinatorial problem, that can take a lot of time to be solved. HPC is used to run the experiments, and encouraging results were obtained. However, even with the basic ED used in this work the search space is very large, thus, when the problem size increases, it is going to need more resources of processing in order to obtain results in an acceptable time.

Regional-scale integration of multi-scale hydrological and geophysical data using a two-step Bayesian sequential simulation approach

Significant progress has been made with regard to the quantitative integration of geophysical and hydrological data at the local scale for the purpose of improving predictions of groundwater flow and solute transport. However, extending corresponding approaches to the regional scale still represents one of the major challenges in the domain of hydrogeophysics. To address this problem, we have developed a regional-scale data integration methodology based on a two-step Bayesian sequential simulation approach. Our objective is to generate high-resolution stochastic realizations of the regional-scale hydraulic conductivity field in the common case where there exist spatially exhaustive but poorly resolved measurements of a related geophysical parameter, as well as highly resolved but spatially sparse collocated measurements of this geophysical parameter and the hydraulic conductivity. To integrate this multi-scale, multi-parameter database, we first link the low- and high-resolution geophysical data via a stochastic downscaling procedure. This is followed by relating the downscaled geophysical data to the high-resolution hydraulic conductivity distribution. After outlining the general methodology of the approach, we demonstrate its application to a realistic synthetic example where we consider as data high-resolution measurements of the hydraulic and electrical conductivities at a small number of borehole locations, as well as spatially exhaustive, low-resolution estimates of the electrical conductivity obtained from surface-based electrical resistivity tomography. The different stochastic realizations of the hydraulic conductivity field obtained using our procedure are validated by comparing their solute transport behaviour with that of the underlying ?true? hydraulic conductivity field. We find that, even in the presence of strong subsurface heterogeneity, our proposed procedure allows for the generation of faithful representations of the regional-scale hydraulic conductivity structure and reliable predictions of solute transport over long, regional-scale distances.

A Multi-Center Phase II Study (SAKK 36/06) of Single Agent Everolimus (RAD001) In Patients with Relapsed or Refractory Mantle Cell Lymphoma

Introduction: Mantle cell lymphoma (MCL) accounts for 6% of all B-cell lymphomas and remains incurable for most patients. Those who relapse after first line therapy or hematopoietic stem cell transplantation have a dismal prognosis with short response duration after salvage therapy. On a molecular level, MCL is characterised by the translocation t[11;14] leading to Cyclin D1 overexpression. Cyclin D1 is downstream of the mammalian target of rapamycin (mTOR) kinase and can be effectively blocked by mTOR inhibitors such as temsirolimus. We set out to define the single agent activity of the orally available mTOR inhibitor everolimus (RAD001) in a prospective, multi-centre trial in patients with relapsed or refractory MCL (NCT00516412). The study was performed in collaboration with the EU-MCL network. Methods: Eligible patients with histologically/cytologically confirmed relapsed (not more than 3 prior lines of systemic treatment) or refractory MCL received everolimus 10 mg orally daily on day 1 - 28 of each cycle (4 weeks) for 6 cycles or until disease progression. The primary endpoint was the best objective response with adverse reactions, time to progression (TTP), time to treatment failure, response duration and molecular response as secondary endpoints. A response rate of 10% was considered uninteresting and, conversely, promising if 30%. The required sample size was 35 pts using the Simon's optimal two-stage design with 90% power and 5% significance. Results: A total of 36 patients with 35 evaluable patients from 19 centers were enrolled between August 2007 and January 2010. The median age was 69.4 years (range 40.1 to 84.9 years), with 22 males and 13 females. Thirty patients presented with relapsed and 5 with refractory MCL with a median of two prior therapies. Treatment was generally well tolerated with anemia (11%), thrombocytopenia (11%), neutropenia (8%), diarrhea (3%) and fatigue (3%) being the most frequent complications of CTC grade III or higher. Eighteen patients received 6 or more cycles of everolimus treatment. The objective response rate was 20% (95% CI: 8-37%) with 2 CR, 5 PR, 17 SD, and 11 PD. At a median follow-up of 6 months, TTP was 5.45 months (95% CI: 2.8-8.2 months) for the entire population and 10.6 months for the 18 patients receiving 6 or more cycles of treatment. Conclusion: This study demonstrates that single agent everolimus 10 mg once daily orally is well tolerated. The null hypothesis of inactivity could be rejected indicating a moderate anti-lymphoma activity in relapsed/refractory MCL. Further studies of either everolimus in combination with chemotherapy or as single agent for maintenance treatment are warranted in MCL.