Search

This document discusses the societal impact of applying artificial intelligence (AI) to traffic and transportation. Sustainable transport is considered crucial for sustainable cities and communities, and AI has the potential to significantly influence daily life in urban areas. The document highlights the interdisciplinary challenges of understanding and coordinating transportation systems, which involve various players with conflicting goals and constraints. It also presents a selection of innovative solutions related to traffic management, including machine learning, reinforcement learning, and optimization approaches. The document concludes by expressing gratitude to the authors, reviewers, and committee members involved in the creation of the special issue. [Extracted from the article]

In this work we design an information extraction tool text2alm capable of narrative understanding with a focus on action verbs. This tool uses an action language ALM to perform inferences on complex interactions of events described in narratives. The methodology used to implement the text2alm system was originally outlined by Lierler, Inclezan, and Gelfond (In IWCS 2017 – 12th International Conference on Computational Semantics – Short Papers (2017)) via a manual process of converting a narrative to an ALM model. We refine that theoretical methodology and utilize it in design of the text2alm system. This system relies on a conglomeration of resources and techniques from two distinct fields of artificial intelligence, namely, (i) knowledge representation and reasoning and (ii) natural language processing. The effectiveness of system text2alm is measured by its ability to correctly answer questions from the bAbI tasks published by Facebook Research in 2015. This tool matched or exceeded the performance of state-of-the-art machine learning methods in six of the seven tested tasks. We also illustrate that the text2alm approach generalizes to a broader spectrum of narratives. On the path to creating system text2alm, a semantic role labeler text2drs was designed. Its unique feature is the use of the elements of the fine grained linguistic ontology VerbNet as semantic roles/labels in annotating considered text. This paper provides an accurate account on the details behind the text2alm and text2drs systems. [ABSTRACT FROM AUTHOR]

Reports on the holding of an international conference on adaptive or intelligent agents and multi-agent systems, jointly sponsored by the Special Interest Group for Artificial Intelligence and the International Foundation for Multi-Agent Systems. Topics discussed; Highlights of the event; Goals aimed to be achieved for holding the conference.

Encourages the submission of research papers for the Joint German-Austrian Conference on Artificial Intelligence to be held in Vienna, Austria on September 19-21, 2001. Possible topics of the conference; Publication of the conference proceedings; Registration dates for participants.

This document is a summary of a special issue of AI Communications, which features extended versions of papers presented at the French conference on formal tools and methods of Artificial Intelligence (JIAF 2022). The special issue includes five papers that offer a diverse view of the topics discussed at the conference. The papers cover various areas such as logical modeling of board games, uncertainty in argumentation, reasoning about ethics, links between belief merging and voting methods, and the concept of artificial stupidity. The authors express gratitude to the contributors, reviewers, and editorial office for their assistance in preparing the special issue. [Extracted from the article]

The Internet is becoming one of the most significant threats to personal and state information security. Therefore, the identification and counteraction of inappropriate information in global network content become the problem of national importance. The paper presents a new approach to building an intelligent system for identification and counteraction of malicious and inappropriate information on the Internet using artificial intelligence methods, in particular, machine learning and big data processing. The system architecture includes a set of intelligent components for data collection, information objects classification, ensuring the timeliness of analysis, eliminating incompleteness and inconsistency of analysis results, selecting the countermeasures for counteraction, and visualization. The paper presents an experimental evaluation of methods implemented for information object classification in single-threaded and multithreaded modes using various classifiers included in the Scikit-learn and Spark MLlib libraries. [ABSTRACT FROM AUTHOR]

The article calls for papers on state-of-the art research in artificial intelligence in Belgium and the Netherlands to be presented at the 16th Belgian-Dutch Conference on Artificial Intelligence in Groningen, Netherlands on October 21 and 22, 2004.

Encourages the submission of papers for the 21st Annual International Conference of the SGES Specialist Group on Knowledge Based Systems and Applied Artificial Intelligence on December 10-12, 2001. Parallel streams of researches on technical advances in artificial intelligence technology; Instruction to contributors.

The increasing demand for mobility in our society poses various challenges to traffic engineering, computer science in general, and artificial intelligence in particular. Increasing the capacity of road networks is not always possible, thus a more efficient use of the available transportation infrastructure is required. Another issue is that many problems in traffic management and control are inherently decentralized and/or require adaptation to the traffic situation. Hence, there is a close relationship to multiagent reinforcement learning. However, using reinforcement learning poses the challenge that the state space is normally large and continuous, thus it is necessary to find appropriate schemes to deal with discretization of the state space. To address these issues, a multiagent system with agents learning independently via a learning algorithm was proposed, which is based on estimating Q-values from k-nearest neighbors. In the present paper, we extend this approach and include transfer of experiences among the agents, especially when an agent does not have a good set of k experiences. We deal with traffic signal control, running experiments on a traffic network in which we vary the traffic situation along time, and compare our approach to two baselines (one involving reinforcement learning and one based on fixed times). Our results show that the extended method pays off when an agent returns to an already experienced traffic situation. [ABSTRACT FROM AUTHOR]

The purpose of the Symposium on Combinatorial Search (SoCS) is to promote the study and understanding of combinatorial search algorithms through the organization of scientific meetings, publications, tutorials, and other public scientific and educational activities. The most prominent among its activities is the annual Symposium on Combinatorial Search that has been organized regularly since 2008 as a result of the success of other scientific meetings, typically workshops co-located with high-level Artificial Intelligence conferences (AAAI and IJCAI). This paper reviews the history of the Symposium making emphasis on the last edition that was held in July 2011 in Barcelona (Spain). [ABSTRACT FROM AUTHOR]

Comments on several papers on environmental sciences and artificial intelligence (AI). Problems to be solved using AI techniques; Information on a paper which deals with knowledge acquisition process.

Neuro-Symbolic Artificial Intelligence – the combination of symbolic methods with methods that are based on artificial neural networks – has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic. [ABSTRACT FROM AUTHOR]

A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks while avoiding catastrophic forgetting. Policy reuse and other multi-policy reinforcement learning techniques can learn multiple tasks but may generate many policies. This paper presents two novel contributions, namely 1) Lifetime Policy Reuse, a model-agnostic policy reuse algorithm that avoids generating many policies by optimising a fixed number of near-optimal policies through a combination of policy optimisation and adaptive policy selection; and 2) the task capacity, a measure for the maximal number of tasks that a policy can accurately solve. Comparing two state-of-the-art base-learners, the results demonstrate the importance of Lifetime Policy Reuse and task capacity based pre-selection on an 18-task partially observable Pacman domain and a Cartpole domain of up to 125 tasks. [ABSTRACT FROM AUTHOR]

This special issue of AI Communications features a selection of extended manuscripts from the 17th Ibero-American Conference on Artificial Intelligence (IBERAMIA) in 2022. The papers cover a range of topics, including a multi-objective optimization framework for Physics-Informed Neural Networks, a temporal embedding method for network data, a genetic algorithm-based hyperparameter optimization for machine learning efficiency, anomaly detection models for wastewater treatment monitoring, and autonomous drone navigation. These papers contribute to our understanding of AI's role in various problem-solving contexts and offer practical insights for the complex world that AI is transforming. [Extracted from the article]

Agent-based modelling (ABM) is a facet of wider Multi-Agent Systems (MAS) research that explores the collective behaviour of individual 'agents', and the implications that their behaviour and interactions have for wider systemic behaviour. The method has been shown to hold considerable value in exploring and understanding human societies, but is still largely confined to use in academia. This is particularly evident in the field of Urban Analytics; one that is characterised by the use of new forms of data in combination with computational approaches to gain insight into urban processes. In Urban Analytics, ABM is gaining popularity as a valuable method for understanding the low-level interactions that ultimately drive cities, but as yet is rarely used by stakeholders (planners, governments, etc.) to address real policy problems. This paper presents the state-of-the-art in the application of ABM at the interface of MAS and Urban Analytics by a group of ABM researchers who are affiliated with the Urban Analytics programme of the Alan Turing Institute in London (UK). It addresses issues around modelling behaviour, the use of new forms of data, the calibration of models under high uncertainty, real-time modelling, the use of AI techniques, large-scale models, and the implications for modelling policy. The discussion also contextualises current research in wider debates around Data Science, Artificial Intelligence, and MAS more broadly. [ABSTRACT FROM AUTHOR]

Whilst common sense knowledge has been well researched in terms of intelligence and (in particular) artificial intelligence, specific, factual knowledge also plays a critical part in practice. When it comes to testing for intelligence, testing for factual knowledge is, in every-day life, frequently used as a front line tool. This paper presents new results which were the outcome of a series of practical Turing tests held on 23rd June 2012 at Bletchley Park, England. The focus of this paper is on the employment of specific knowledge testing by interrogators. Of interest are prejudiced assumptions made by interrogators as to what they believe should be widely known and subsequently the conclusions drawn if an entity does or does not appear to know a particular fact known to the interrogator. The paper is not at all about the performance of machines or hidden humans but rather the strategies based on assumptions of Turing test interrogators. Full, unedited transcripts from the tests are shown for the reader as working examples. As a result, it might be possible to draw critical conclusions with regard to the nature of human concepts of intelligence, in terms of the role played by specific, factual knowledge in our understanding of intelligence, whether this is exhibited by a human or a machine. This is specifically intended as a position paper, firstly by claiming that practicalising Turing's test is a useful exercise throwing light on how we humans think, and secondly, by taking a potentially controversial stance, because some interrogators adopt a solipsist questioning style of hidden entities with a view that it is a thinking intelligent human if it thinks like them and knows what they know. The paper is aimed at opening discussion with regard to the different aspects considered. [ABSTRACT FROM AUTHOR]

During the centennial year of his birth Alan Turing (1912-1954) has been widely celebrated as having laid the foundations for Computer Science, Automated Decryption, Systems Biology and the Turing Test. In this paper we investigate Turing's motivations and expectations for the development of Machine Intelligence, as expressed in his 1950 article in Mind. We show that many of the trends and developments within AI over the last 50 years were foreseen in this foundational paper. In particular, Turing not only describes the use of Computational Logic but also the necessity for the development of Machine Learning in order to achieve human-level AI within a 50 year time-frame. His description of the Child Machine (a machine which learns like an infant) dominates the closing section of the paper, in which he provides suggestions for how AI might be achieved. Turing discusses three alternative suggestions which can be characterised as: (1) AI by programming, (2) AI by ab initio machine learning and (3) AI using logic, probabilities, learning and background knowledge. He argues that there are inevitable limitations in the first two approaches and recommends the third as the most promising. We compare Turing's three alternatives to developments within AI, and conclude with a discussion of some of the unresolved challenges he posed within the paper. [ABSTRACT FROM AUTHOR]

The application of agent technology to the solution of problems in health care has in recent years become increasingly common. A workshop on this area of research was held as part of the 16th European Conference on Artificial Intelligence (ECAI-2004), in Valencia, August 2004, at which twelve papers were presented. This special issue contains extended versions of a selection of five of the papers presented at the workshop. [ABSTRACT FROM AUTHOR]

Automated Planning deals with reasoning processes where a set of goals must be achieved from an initial state using some actions. Most work on planning have a static view of goals; they are given at start of the planning process and they do not change over planning and/or plan execution. However, in many real world domains, agents need to consider dynamic goal management. In this paper, we propose to increase the performance of planning agents by learning when goals will appear in the near future. The learned predictive models allow agents to perform some kind of anticipatory planning, where the planning process considers not only current goals, but also future predicted goals. We also study under which conditions this anticipatory approach outperforms a standard planning approach. Finally, experiments that support our hypothesis are presented. [ABSTRACT FROM AUTHOR]

The purpose of the Symposium on Combinatorial Search (SoCS) is to promote the study and understanding of combinatorial search algorithms through the organization of scientific meetings, publications, tutorials, and other public scientific and educational activities. The most prominent among its activities is the Annual Symposium on Combinatorial Search that has been organized annually since 2008. This short paper introduces the most relevant accomplishments of the Fifth Annual Symposium (SoCS 2012), that was held in July 2012 in Niagara Falls, Canada. [ABSTRACT FROM AUTHOR]

Essay writing is widely used for student performance assessment. This paper presents a hybrid automatic essay scoring system (AES) for Arabic essays. The system attempts at saving the time teachers spend on reading and scoring Arabic essays. It utilizes latent semantic analysis (LSA) and three linguistic features (i.e., word stemming, number of words and number of spelling mistakes). This paper also describes an algorithm to determine the optimal reduced dimensionality used in LSA. To evaluate the performance of this system, an Arabic dataset was developed based on essays collected from college students. The experimental results show the effectiveness of using LSA for scoring Arabic essays, especially when combined with other linguistic features. The system shows that 96.72% of the test data are correctly scored and the correlation between automatic and manual scores is 0.78, which is close to the interhuman correlation of 0.7. [ABSTRACT FROM AUTHOR]

Focuses on the solicitation of papers dealing with vehicle-centered intelligent systems by the IEEE Intelligent Transportation System Council. Conference on basic research and applications for intelligent vehicles; Topics of the symposium; Format of the report.

We survey all known results in the area of quasigroup and loop theory to have been obtained with the assistance of automated theorem provers. We provide both informal and formal descriptions of selected problems, and compare the performance of selected state-of-the art first order theorem provers on them. Our analysis yields some surprising results, e.g., the theorem prover most often used by loop theorists does not necessarily yield the best performance. [ABSTRACT FROM AUTHOR]

In studies concerned with sustainability the underlying models are, in most cases, not strictly numerical since they depend on many conditions that can be regarded as qualitative. In this paper, a model to evaluate citizens' satisfaction learnt from data collected from a survey is presented. The model, which involves the use of RBF neural networks, will provide local councillors with useful information, enabling them to evaluate trends and improve strategies focused on enhancing sustainability. In this paper a contribution describing a practical experience with a model-based system applied to a study commissioned by the town council of Vilanova i la Geltrú (Catalonia, Spain) is presented. [ABSTRACT FROM AUTHOR]

The paper presents an approach for the on-line monitoring and diagnosis of multi-robot systems where services are provided by a team of robots and the environment is only partially observable via a net of fixed sensors. This kind of systems exhibits complex dynamics where weakly predictable interactions among robots may occur. To face this problem, a model-based approach is adopted: in particular, the paper discusses how to build a system model by aggregating a convenient set of basic system components, which are modeled via communicating automata. Since the dynamics of a multi-robot system depend on the actions performed by the robots (and actions change over time), the global system model is partitioned into a number of submodels, each one describing the dynamics of a single action. The paper introduces the architecture of the Supervisor which has to track the actions progress and to infer an explanation when an action is completed with delay or fails. The Supervisor includes two main modules: the On-line Monitoring Module (OMM) tracks the status of the system by exploiting the (partial) observations provided by sensors and robots. When the monitor detects failures in the actions execution, the Diagnostic Interpretation Module (DIM) is triggered for explaining the failure in terms of faults in the robots and/or troublesome interactions among them. The RoboCare domain has been selected as a test bed of the approach. The paper discusses experimental results collected in such a domain with particular focus on the competence and the efficiency of both the OMM and the DIM. [ABSTRACT FROM AUTHOR]

Presents highlights of the Starting Artificial Intelligence Researchers Symposium (STAIRS) 2002 held in Lyon, France in July 2002. Features of the symposium; Goal of STAIRS; Topics covered by research papers presented at the symposium.

In recent years the field of Automated Planning has significantly advanced and several powerful domain-independent planners have been developed. However, none of these systems clearly outperforms all the others in every known benchmark domain. This observation motivated the idea of configuring and exploiting a portfolio of planners to perform better than any individual planner: some recent planning systems based on this idea achieved significantly good results in experimental analysis and International Planning Competitions. Such results let us suppose that future challenges of the Automated Planning community will converge on designing different approaches for combining existing planning algorithms. This paper reviews existing techniques and provides an exhaustive guide to portfolio-based planning. In addition, the paper outlines open issues of existing approaches and highlights possible future evolution of these techniques. [ABSTRACT FROM AUTHOR]

AI systems typically make decisions and find patterns in data based on the computation of aggregate and specifically sum functions, expressed as queries, on data's attributes. This computation can become costly or even inefficient when these queries concern the whole or big parts of the data and especially when we are dealing with big data. New types of intelligent analytics require also the explanation of why something happened. In this paper we present a randomised algorithm that constructs a small summary of the data, called Aggregate Lineage, which can approximate well and explain all sums with large values in time that depends only on its size. The size of Aggregate Lineage is practically independent on the size of the original data. Our algorithm does not assume any knowledge on the set of sum queries to be approximated. [ABSTRACT FROM AUTHOR]

Agreement, cooperation and trust would be straightforward if deception did not ever occur in communicative interactions. Humans have deceived one another since the species began. Do machines deceive one another or indeed humans? If they do, how may we detect this? To detect machine deception, arguably requires a model of how machines may deceive, and how such deception may be identified. Theory of Mind (ToM) provides the opportunity to create intelligent machines that are able to model the minds of other agents. The future implications of a machine that has the capability to understand other minds (human or artificial) and that also has the reasons and intentions to deceive others are dark from an ethical perspective. Being able to understand the dishonest and unethical behaviour of such machines is crucial to current research in AI. In this paper, we present a high-level approach for modelling machine deception using ToM under factors of uncertainty and we propose an implementation of this model in an Agent-Oriented Programming Language (AOPL). We show that the Multi-Agent Systems (MAS) paradigm can be used to integrate concepts from two major theories of deception, namely Information Manipulation Theory 2 (IMT2) and Interpersonal Deception Theory (IDT), and how to apply these concepts in order to build a model of computational deception that takes into account ToM. To show how agents use ToM in order to deceive, we define an epistemic agent mechanism using BDI-like architectures to analyse deceptive interactions between deceivers and their potential targets and we also explain the steps in which the model can be implemented in an AOPL. To the best of our knowledge, this work is one of the first attempts in AI that (i) uses ToM along with components of IMT2 and IDT in order to analyse deceptive interactions and (ii) implements such a model. [ABSTRACT FROM AUTHOR]

Time is pervasive of the human way of approaching reality, so that it has been widely studied in many research areas, including AI and relational Temporal Databases (TDB). While temporally imprecise information has been widely studied by the AI community, only few approaches have faced temporal indeterminacy (in particular, "don't know exactly when" indeterminacy) in TDBs. Indeed, as we will show in this paper, the treatment of time in general, and of temporal indeterminacy in particular, involves the introduction of implicit forms of data representation in TDBs. As a consequence, we propose a new AI-style methodology to cope with temporal indeterminacy in TDBs. Specifically, we show that typical AI notions and techniques, such as making explicit the semantics of the representation formalism, and adopting symbolic manipulation techniques based on such a semantics, can be fruitfully exploited in the development of a "principled" treatment of indeterminate time in relational databases. [ABSTRACT FROM AUTHOR]

The rapidly increasing deployment of AI raises societal issues about its safety, reliability, robustness, fairness and moral integrity. This paper reports on a declaration intended as a code of conduct for AI researchers and application developers. It came out of a workshop held in Barcelona in 2017 and was discussed further in various follow up meetings, workshops, and AI schools. The present publication is a matter of historical record and a way to publicize the declaration so that more AI researchers and developers can get to know it and that policy makers and industry leaders can use it as input for governance. It also discusses the rationale behind the declaration in order to stimulate further debates. [ABSTRACT FROM AUTHOR]

The paper tells the story of the beginnings of Artificial Intelligence (AI) as a scientific venture from a European perspective. The story is embedded into three main steps of history. In view of a sustainable future of our globe it is deemed necessary to vigorously advance the initiated third step. Assuming AI's due role in this process would mean a change in its long-term goal: enhancing rather than simulating human intelligence. [ABSTRACT FROM AUTHOR]

Machine Learning has been at the core of Artificial Intelligence since its inception. Many promises have been held, if one is to consider that Google is a living demonstration of AI. This paper presents a historical perspective on Machine Learning, describing how the emphasis was gradually shifted from logical to statistical induction, from induction to optimization, from the search of hypotheses to the search of representations. The paper concludes with a discussion about the new frontier of Machine Learning. [ABSTRACT FROM AUTHOR]

Despite a very strong synergy between Robotics and AI at their early beginning, the two fields progressed widely apart in the following decades. However, we are witnessing a revival of interest in the fertile domain of embodied machine intelligence. This is due in particular to the dissemination of more mature techniques from both areas, to more accessible robot platforms with advanced sensory motor capabilities, and to a better understanding of the scientific challenges of the AI-Robotics intersection.The ambition of this paper is to contribute to this revival. It proposes an overview of problems and approaches to autonomous deliberate action in robotics. The paper advocates for a broad understanding of deliberation functions. It presents a synthetic perspective on planning, acting, perceiving, monitoring, goal reasoning and their integrative architectures, which is illustrated through several contributions that addressed deliberation from the AI-Robotics point of view. [ABSTRACT FROM AUTHOR]

This article presents information on papers presented in a symposium on the foundations and applications of spatio-temporal reasoning. It was said that significant progress has been made in the area of spatial and temporal reasoning. The progress is made primarily in inventing new domains of space and time and in studying complexity issues in reasoning over them. The interest in the area of spatial and temporal reasoning is still growing, especially within the artificial intelligence community. Dealing with time and space is not restricted to artificial intelligence. Geographic information systems, tracking systems, mobile networks, distributed systems, cooperating autonomous agents, distributed databases, planning, robot motion, and other complex systems challenge the capabilities of existing knowledge representation methods and reasoning techniques. Tony Cohn of the University of Leeds started the symposium with an invited tutorial on qualitative spatio-temporal calculi that gave all the participants the necessary background for discussions. Jayant Sharma gave an application-oriented perspective in his invited talk on spatio-temporal reasoning for location-based services. In his invited tutorial on relation algebras, Ivo Düntsch presented the theoretical perspective. The last invited presentation was by Thomas Barkowsky who gave an overview of the SFB/TR8, a huge German research project on Spatial Cognition, which shows that major grant agencies are realizing the importance of the field and are willing to invest large amounts of money for research in spatiotemporal reasoning.

This paper describes WORD2HTN, a new approach for learning hierarchical tasks and goals from plan traces in planning domains. Our approach combines semantic text analysis techniques and subgoal learning in order to produce Hierarchical Task Networks (HTNs). Unlike existing HTN learning algorithms, our system uses semantics and similarities of the atoms and actions in the plan traces. WORD2HTN first learns vector representations that represent the semantics and similarities of the atoms occurring in the plan traces. Then the system uses those representations to group atoms occurring in the traces into clusters. Clusters are grouped together into larger clusters based on their similarity. These groupings define a hierarchy of atom clusters. These atom clusters help to define task and goal hierarchies, which can then be transformed into HTN methods and used by an HTN planner for automated planning. We describe our algorithm and present our experimental evaluation. [ABSTRACT FROM AUTHOR]

In the context of deliberative reasoning, autonomous systems should be able to explicitly reason about goals. Most research in automated planning assume that goals are initially given and fixed and planners generate plans to achieve them. However, in some real-world scenarios where planners work in an on-line continual planning setting, additional goals may arrive over time. When information about future goal arrivals is known, it can be exploited to direct the system towards those goals even though they have not arrived yet. Recent work presented an approach that exhibited such anticipatory behavior based on hindsight optimization on a domain-dependent setup. In this paper, we tackle this problem from the point of view of domain-independent planning. The available per-step time in on-line continual problems can be very short and domain-independent planners can scale poorly in such short time. In fact, a domain-independent reimplementation of the hindsight optimization scheme may not even be applicable. We propose several alternative approaches that consider future goals in a domain-independent planning process. Experimental results in several benchmark domains suggest that these approaches exhibit a more efficient and effective behavior than a reactive approach in which goals are pursued after their arrival. [ABSTRACT FROM AUTHOR]

In this paper we describe holonic multi agent architecture of iForestFire (Intelligent Forest Fire Monitoring System) through phases and activities of the holonic software engineering process. iForestFire is a web-based information system used in all aspects of forest fire management. Its central part is an artificial perception system, observer network, whose aim is early detection of forest fires. Although the agents that the system consists of are inseparably connected, they can be clustered in several independent systems that can be used separately. Independent holons are built from agents that are part of the observer network, as well as other agents with auxiliary functionalities. [ABSTRACT FROM AUTHOR]

With model-based diagnosis, diagnoses for occurring faults can be directly computed from a given system model and actual observations about system behavior. Model-based diagnosis has been successfully accommodated to several purposes, including the diagnosis of space probes and configuration knowledge bases. Recent research includes extensions for distributed systems, motivated by the ever-growing system complexity and inherently distributed domains like service-oriented architectures. Previous work in this context lacks however a detailed analysis and classification approach that considers essential underlying issues like diagnosis architecture, utilized models, and abstract requirements that might stem from the application domain. In this paper, we will show an analysis of distributed system diagnosis and a characterization in the three dimensions mentioned. [ABSTRACT FROM AUTHOR]

In this paper we introduce the notion of 'Social Web of Intelligent Things' (SWIT hereafter) as a an evolution of both the 'Web of Things' and 'Smart Objects' paradigms. In a SWIT, things become entities capable of an intelligent and social behavior. On the one hand, things maintain and socialize knowledge and can interact and communicate with people; on the other, 'social' networks of people and things arise as a result of this interaction. SWIT is an evolution of social media that goes beyond the desktop paradigm and is a way of bridging the gap between real-life and virtual experiences. Interactions between people and things happen naturally in real life, augmenting and enhancing people's experiences. We claim that SWITs are a challenging area of research and application for Artificial Intelligence in the context of the Future Internet. The paper provides a characterization of SWITs, discussing the ingredients that are needed to create a SWIT; it introduces a framework for building SWITs and briefly presents an instance we developed and tested with users. In the paper we claim that many areas of Artificial Intelligence can contribute to the is framework, which in turn can stimulate research in these areas and on their integration. [ABSTRACT FROM AUTHOR]

For planning to come of age, plans must be judged by a measure of quality, such as the total cost of actions. This paper describes an optimal-cost planner which guarantees global optimality whenever the planning problem has a solution. We code the extraction of an optimal plan, from a planning graph with a fixed number k of levels, as a weighted constraint satisfaction problem (WCSP). The specific structure of the resulting WCSP means that a state-of-the-art exhaustive solver was able to find an optimal plan in planning graphs containing several thousand nodes. Thorough experimental investigations demonstrated that using the planning graph in optimal planning is a practical possibility for problems of moderate size, although not competitive, in terms of computation time, with optimal state-space-search planners. Our general conclusion is, therefore, that planning-graph-based optimal planning is not the most efficient method for cost-optimal planning. Nonetheless, the notions of indispensable (sets of) actions and too-costly actions introduced in this paper have various potential applications in optimal planning. These actions can be detected very rapidly by analysis of the relaxed planning graph. [ABSTRACT FROM AUTHOR]

Building adaptive constraint solvers is a major challenge in constraint programming. An important line of research towards this goal is concerned with ways to dynamically adapt the propagation method applied on the constraints of the problem during search. In this paper we present a heuristic approach to this problem based on the monitoring of propagation events like value deletions and domain wipeouts. We develop a number of heuristics that allow the constraint solver to dynamically switch between a weaker and cheap local consistency and a stronger, but more expensive one, when certain conditions are met. The success of this approach is based on the observation that propagation events for individual constraints in structured problems mostly occur in clusters of nearby revisions. Hence, parts of the search space where certain constraints are highly active can be identified and exploited paving the way for the informed use of constraint propagation techniques. In this paper we first give some experimental results displaying the clustering of propagation events in structured binary CSPs. Then we present simple heuristics that exploit this clustering to efficiently switch between different local consistencies on individual constraints during search. Finally, we make an experimental study on various binary CSPs demonstrating the effectiveness of the proposed heuristics. [ABSTRACT FROM AUTHOR]

Presents a series of articles on artificial intelligence research activities being carried out in China. Method for rule extraction from ensembles of neural networks; Approach to multilevel data summarization by employing the rule-plus-exception model in cognitive science; Development of a technique by employing a stepwise greedy algorithm for certain data sets with medium size.

In this paper, we first discuss how to define lines of demarcation between model-based systems and other disciplines that also use models. A brief overview of the main techniques and model types used in model-based reasoning then provide background information to introduce the articles selected for this special issue. [ABSTRACT FROM AUTHOR]

Intelligent adaptation is a key issue for the design of flexible support systems for mobile users. In this paper we present UbiquiTO, a tourist guide which integrates different forms of adaptation: (i) to the device used (web access via Laptop, PDA, smartphone), (ii) to the user and her features and preferences (personalized interaction), (iii) to the context of interaction, and in particular to the user location, besides some other features such as the time of the day. UbiquiTO adapts the content of the service being provided (recommendation and amount/type of information/features associated with each recommendation) and the presentation (interface). In order to achieve better performance it keeps track of the user behavior, updating and refining the user model during the interaction. In the paper we introduce the architecture of the system and the choices we made as regards user, device and context modeling and adaptation strategies. We also present the results of a preliminary evaluation of the system behavior. [ABSTRACT FROM AUTHOR]

In the setting of possibility theory, a tool named “fuzzy pattern matching” (FPM) has been proposed in the eighties, and then successfully used in flexible querying of fuzzy databases and in classification. Given a pattern representing a request expressed in terms of fuzzy sets, and a database containing imprecise or fuzzy attribute values, the FPM returns two matching degrees. Namely, for each item in the base, the possibility and the certainty that it matches the requirements of the pattern are computed. In multiple‐source information systems, attribute values are often assessed in linguistic terms belonging to different vocabularies. The request itself, which may include preferences, may be expressed using terms of another vocabulary. The paper proposes a counterpart of FPM, called “Qualitative Pattern Matching” (QPM), for estimating levels of matching between a request and data expressed with words; words can be related together through a qualitative thesaurus or ontology, where approximate synonymy and specialization relations are encoded. Given a request, QPM rank‐orders the items which possibly, or which certainly match the requirements, according to the preferences of the user. The proposed approach is based on a qualitative assessment of matching degrees which does not necessarily require the use of numerical scales. Its merits for dealing with information querying in face of heterogeneous sources of information are advocated. Application to the handling of textual data in information retrieval is also outlined. [ABSTRACT FROM AUTHOR]

Feature selection is a process of determining the most relevant features of a given problem in order to improve the generalization and the performance of a relevant classification or regression algorithm. This paper focuses on the exploitation of a genetic algorithm following a wrapping iterative approach used to extract an optimal feature subset of a large database containing pollutant concentration measurements. The feature subset is fed to a machine learning algorithm in order to predict the daily maximum concentration of two air pollutants. The encoding problem of the complexity of representation of the features in the genomes is tackled. Results of the experimentation on a specific dataset of an air quality forecasting problem are presented, as well as some proposed alterations on the standard genetic algorithm that guided the process to a mature convergence and gave good solutions for this problem. A modified version of the initial algorithm is presented as well, implemented for the purpose of being compared on an equal basis with other feature selection methods. Two such methods of the filtering type, CFS and ReliefF, are being compared with. The comparative results suggest that the wrapping type technique described in this paper is significantly better in the specific problem at hand, but this conclusion is limited to the machine learning algorithm that the technique uses at its core in the feature selection phase. [ABSTRACT FROM AUTHOR]