Showing papers on "Applications of artificial intelligence published in 2007"

Artificial Intelligence: A Systems Approach

Abstract: This book offers students and AI programmers a new perspective on the study of artificial intelligence concepts. The essential topics and theory of AI are presented, but it also includes practical information on data input & reduction as well as data output (i.e., algorithm usage). Because traditional AI concepts such as pattern recognition, numerical optimization and data mining are now simply types of algorithms, a different approach is needed. This sensor / algorithm / effecter approach grounds the algorithms with an environment, helps students and AI practitioners to better understand them, and subsequently, how to apply them. The book has numerous up to date applications in game programming, intelligent agents, neural networks, artificial immune systems, and more. A CD-ROM with simulations, code, and figures accompanies the book. *Features *Covers not only AI theory, but modern applications e.g., game programming, machine learning, swarming, artificial immune systems, genetic algorithms, pattern recognition, numerical optimization, data mining, and more *Discusses the various computer languages of AI from LISP to JAVA and Python *Includes a CD-ROM with 100MB of simulations, code, and fi gures *Table of Contents 1. Introduction. 2. Search. 3. Games. 4. Logic. 5. Planning. 6. Knowledge Representation. 7. Machine Learning. 8. Probabilistic Reasoning. 9. Stochastic Search. 10. Neural Networks. 11. Intelligent Agents. 12. Hybrid Models. 13. Languages of AI.

Bayesian Network Technologies : Applications and Graphical Models

Abstract: Bayesian networks are now being used in a variety of artificial intelligence applications. These networks are high-level representations of probability distributions over a set of variables that are used for building a model of the problem domain. Bayesian Network Technologies: Applications and Graphical Models provides an excellent and well-balanced collection of areas where Bayesian networks have been successfully applied. This book describes the underlying concepts of Bayesian Networks in an interesting manner with the help of diverse applications, and theories that prove Bayesian networks valid. Bayesian Network Technologies: Applications and Graphical Models provides specific examples of how Bayesian networks are powerful machine learning tools critical in solving real-life problems.

Adaptive localization in a dynamic WiFi environment through multi-view learning

Abstract: Accurately locating users in a wireless environment is an important task for many pervasive computing and AI applications, such as activity recognition. In a WiFi environment, a mobile device can be localized using signals received from various transmitters, such as access points (APs). Most localization approaches build a map between the signal space and the physical location space in a offline phase, and then using the received-signal-strength (RSS) map to estimate the location in an online phase. However, the map can be outdated when the signal-strength values change with time due to environmental dynamics. It is infeasible or expensive to repeat data calibration for reconstructing the RSS map. In such a case, it is important to adapt the model learnt in one time period to another time period without too much recalibration. In this paper, we present a location-estimation approach based on Manifold co-Regularization, which is a machine learning technique for building a mapping function between data. We describe LeManCoR, a system for adapting the mapping function between the signal space and physical location space over different time periods based on Manifold Co-Regularization. We show that LeManCoR can effectively transfer the knowledge between two time periods without requiring too much new calibration effort. We illustrate LeMan-CoR's effectiveness in a real 802.11 WiFi environment.

Scaling games to epic proportions

Abstract: We introduce scalability for computer games as the next frontier for techniques from data management. A very important aspect of computer games is the artificial intelligence (AI) of non-player characters. To create interesting AI in games today, developers or players have to create complex, dynamic behavior for a very small number of characters, but neither the game engines nor the style of AI programming enables intelligent behavior that scales to a very large number of non-player characters. In this paper we make a first step towards truly scalable AI in computer games by modeling game AI as a data management problem. We present a highly expressive scripting language SGL that provides game designers and players with a data-driven AI scheme for customizing behavior for individual non-player characters. We use sophisticated query processing and indexing techniques to efficiently execute large numbers of SGL scripts, thus providing a framework for games with a truly epic number of non-player characters. Experiments show the efficacy of our solutions.

Embedding Computational Intelligence in Pervasive Spaces

Abstract: This paper presents how to embed AI mechanisms in pervasive spaces to produce more intelligent, adaptive, and convenient environments. The paper also concentrated on computational intelligence in particular, fuzzy systems and neural networks because this emerging AI domain covers most of the requirements for this task.

50 years of artificial intelligence: essays dedicated to the 50th anniversary of artificial intelligence

Abstract: Historical and Philosphical Issues.- AI in the 21st Century - With Historical Reflections.- The Physical Symbol System Hypothesis: Status and Prospects.- Fifty Years of AI: From Symbols to Embodiment - and Back.- 2006: Celebrating 75 Years of AI - History and Outlook: The Next 25 Years.- Evolutionary Humanoid Robotics: Past, Present and Future.- Philosophical Foundations of AI.- On the Role of AI in the Ongoing Paradigm Shift within the Cognitive Sciences.- Information Theory and Quantification.- On the Information Theoretic Implications of Embodiment - Principles and Methods.- Development Via Information Self-structuring of Sensorimotor Experience and Interaction.- How Information and Embodiment Shape Intelligent Information Processing.- Preliminary Considerations for a Quantitative Theory of Networked Embodied Intelligence.- A Quantitative Investigation into Distribution of Memory and Learning in Multi Agent Systems with Implicit Communications.- Morphology and Dynamics.- AI in Locomotion: Challenges and Perspectives of Underactuated Robots.- On the Task Distribution Between Control and Mechanical Systems.- Bacteria Integrated Swimming Microrobots.- Adaptive Multi-modal Sensors.- Neurorobotics.- What Can AI Get from Neuroscience?.- Dynamical Systems in the Sensorimotor Loop: On the Interrelation Between Internal and External Mechanisms of Evolved Robot Behavior.- Adaptive Behavior Control with Self-regulating Neurons.- Brain Area V6A: A Cognitive Model for an Embodied Artificial Intelligence.- The Man-Machine Interaction: The Influence of Artificial Intelligence on Rehabilitation Robotics.- Machine Intelligence, Cognition, and Natural Language Processing.- Tests of Machine Intelligence.- A Hierarchical Concept Oriented Representation for Spatial Cognition in Mobile Robots.- Anticipation and Future-Oriented Capabilities in Natural and Artificial Cognition.- Computer-Supported Human-Human Multilingual Communication.- Human-Like Intelligence: Motivation, Emotions, and Consciousness.- A Paradigm Shift in Artificial Intelligence: Why Social Intelligence Matters in the Design and Development of Robots with Human-Like Intelligence.- Intrinsically Motivated Machines.- Curious and Creative Machines.- Applying Data Fusion in a Rational Decision Making with Emotional Regulation.- How to Build Consciousness into a Robot: The Sensorimotor Approach.- Robot Platforms.- A Human-Like Robot Torso ZAR5 with Fluidic Muscles: Toward a Common Platform for Embodied AI.- The iCub Cognitive Humanoid Robot: An Open-System Research Platform for Enactive Cognition.- Intelligent Mobile Manipulators in Industrial Applications:Experiences and Challenges.- Art and AI.- The Dynamic Darwinian Diorama: A Landlocked Archipelago Enhances Epistemology.

Buffer allocation and performance modeling in asynchronous assembly system operations: An artificial neural network metamodeling approach

Abstract: This article investigates metamodeling opportunities in buffer allocation and performance modeling in asynchronous assembly systems (AAS). Practical challenges to properly design these complex systems are emphasized. A critical review of various approaches in modeling and evaluation of assembly systems reported in the recently published literature, with a special emphasis on the buffer allocation problems, is given. Various applications of artificial intelligence techniques on manufacturing systems problems, particularly those related to artificial neural networks, are also reviewed. Advantages and the drawbacks of the metamodeling approach are discussed. In this context, a metamodeling application on AAS buffer design/performance modeling problems in an attempt to extend the application domain of metamodeling approach to manufacturing/assembly systems is presented. An artificial neural network (ANN) metamodel is developed for a simulation model of an AAS. The ANN and regression metamodels for each AAS are compared with respect to their deviations from the simulation results. The analysis shows that the ANN metamodels can successfully be used to model of AASs. Consequently, one concludes that practising engineers involved in assembly system design can potentially benefit from the advantages of the metamodeling approach.

Game AI is Dead. Long Live Game AI

Abstract: This paper discusses how the recent advances in game AI technology can help benefit industry and the academia. Some of these advances include large-scale automated art and content generation, automated storytelling, goal-driven virtual actors, and the ability to adapt to the player's preferences and mental state

Artificial Intelligence for Space Applications

Abstract: The ambitious short-term and long-term goals set down by the various national space agencies call for radical advances in several of the main space engineering areas, the design of intelligent space agents certainly being one of them. In recent years, this has led to an increasing interest in artificial intelligence by the entire aerospace community. However, in the current state of the art, several open issues and showstoppers can be identified. In this chapter, we review applications of artificial intelligence in the field of space engineering and space technology and identify open research questions and challenges. In particular, the following topics are identified and discussed: distributed artificial intelligence, enhanced situation self-awareness, and decision support for spacecraft system design.

Artificial intelligence applications in the telecommunications industry

Abstract: Artificial intelligence (AI) has been applied to the telecommunications industry for more than a decade. The purpose of this paper is to examine the application of AI in the telecommunications industry sector. Our research finds that AI's first main application in telecommunications is in the network management area. Expert systems and machine learning are the two AI techniques that have been widely used in telecommunications, while machine learning and distributed artificial intelligence are the two AI techniques which are most promising for the future. The research also finds that different AI techniques have their unique applications in the telecommunications industry.

Artificial Intelligence Applications in Transportation

Abstract: This paper addresses artificial intelligence (AI) applications in transportation Areas examined include AI methods, a brief history of AI, why AI is appropriate for transportation problems, and AI application areas This paper serves as an introduction to this circular which focuses on the following five paradigms: knowledge-based systems, neural networks, fuzzy sets, genetic algorithms, and agent-based models

Fifty years of AI: from symbols to embodiment - and back

Abstract: There are many stories to tell about the first fifty years of AI. One story is about AI as one of the big forces of innovation in information technology. It is now forgotten that initially computers were just viewed as calculating machines. AI has moved that boundary, by projecting visions on what might be possible, and by building technologies to realise them. Another story is about the applications of AI. Knowledge systems were still a rarity in the late seventies but are now everywhere, delivered through the web. Knowledge systems routinely deal with financial and legal problem solving, diagnosis and maintenance of power plants and transportation networks, symbolic mathematics, scheduling, etc. The innovative aspects of search engines like Google are almost entirely based on the information extraction, data mining, semantic networks and machine learning techniques pioneered in AI. Popular games like SimCity are straightforward applications of multi-agent systems. Sophisticated language processing capacities are now routinely embedded in text processing systems like Microsoft's Word. Tens of millions of people use AI technology every day, often without knowing it or without wondering how these information systems can do all these things. In this essay I will focus however on another story: AI as a contributor to the scientific study of mind.

Automated Natural Deduction for Propositional Linear-Time Temporal Logic

Abstract: We present a proof searching technique for the natural deduction calculus for the prepositional linear-time temporal logic and prove its correctness. This opens the prospect to apply our technique as an automated reasoning tool in a number of emerging computer science applications and in a deliberative decision making framework across various AI applications.

2006: celebrating 75 years of AI - history and outlook: the next 25 years

Abstract: When Kurt Godel layed the foundations of theoretical computer science in 1931, he also introduced essential concepts of the theory of Artificial Intelligence (AI). Although much of subsequent AI research has focused on heuristics, which still play a major role in many practical AI applications, in the new millennium AI theory has finally become a full-fledged formal science, with important optimality results for embodied agents living in unknown environments, obtained through a combination of theory a la Godel and probability theory. Here we look back at important milestones of AI history, mention essential recent results, and speculate about what we may expect from the next 25 years, emphasizing the significance of the ongoing dramatic hardware speedups, and discussing Godel-inspired, self-referential, self-improving universal problem solvers.

Real Robots Don't Drive Straight

Abstract: Over last fifteen years, robot technology has become popularinclassroomsacrossourwholeeducationalsystem. BothengineeringandAIeducatorshavedeveloped ways to integrate robots into their teaching. Engineering educators are primarily concerned with engineering science (e.g., feedback control) and process (e.g., design skills). AI educators have different goals—namely, AI educators want students to learn AI concepts. Both agree that students are enthusiastic about working with robots, and in both cases, the pedagogical challenge is to develop robotics technology and provide classroom assignments that highlight key ideas in the respective field. Mobile robots are particularly intriguing because of their dual nature as both deterministic machines and unpredictable entities. This paper explores challenges for both engineering and AI educators as robot toolkits evolve.

AI in the 21st century - with historical reflections

Abstract: The discipline of Artificial Intelligence (AI) was born in the summer of 1956 at Dartmouth College in Hanover, New Hampshire. Half of a century has passed, and AI has turned into an important field whose influence on our daily lives can hardly be overestimated. The original view of intelligence as a computer program - a set of algorithms to process symbols - has led to many useful applications now found in internet search engines, voice recognition software, cars, home appliances, and consumer electronics, but it has not yet contributed significantly to our understanding of natural forms of intelligence. Since the 1980s, AI has expanded into a broader study of the interaction between the body, brain, and environment, and how intelligence emerges from such interaction. This advent of embodiment has provided an entirely new way of thinking that goes well beyond artificial intelligence proper, to include the study of intelligent action in agents other than organisms or robots. For example, it supplies powerful metaphors for viewing corporations, groups of agents, and networked embedded devices as intelligent and adaptive systems acting in highly uncertain and unpredictable environments. In addition to giving us a novel outlook on information technology in general, this broader view of AI also offers unexpected perspectives into how to think about ourselves and the world around us. In this chapter, we briefly review the turbulent history of AI research, point to some of its current trends, and to challenges that the AI of the 21st century will have to face.

On construction of a GeometryNet

Abstract: GeometryNet can be considered as a lexical database for geometric entities and concepts. The idea is borrowed from WordNet, a popular knowledge repository often used for natural language processing tasks in AI applications. The basic objective behind the construction of a GeometryNet is to analyze and understand the geometric problems and draw relevant geometric figures automatically. Initial emphasis is put on machine understanding of problem statements that involve geometric constructions. School level geometry problems practiced by students of age group 13-16 are targeted. This paper explains different aspects of a GeometryNet, issues behind its construction, and its possible use for machine understanding of geometric problem statements.

Machine Translation for Manufacturing: A Case Study at Ford Motor Company

Abstract: Machine translation (MT) was one of the first applications of artificial intelligence technology that was deployed to solve real-world problems. Since the early 1960s, researchers have been building and utilizing computer systems that can translate from one language to another without requiring extensive human intervention. In the late 1990s, Ford Vehicle Operations began working with Systran Software Inc. to adapt and customize its machine-translation technology in order to translate Ford's vehicle assembly build instructions from English to German, Spanish, Dutch, and Portuguese. The use of machine translation was made necessary by the vast amount of dynamic information that needed to be translated in a timely fashion. The assembly build instructions at Ford contain text written in a controlled language as well as unstructured remarks and comments. The MT system has already translated more than 7 million instructions into these languages and is an integral part of the overall manufacturing process-planning system used to support Ford's assembly plants in Europe, Mexico and South America. In this paper, we focus on how AI techniques, such as knowledge representation and natural language processing can improve the accuracy of machine translation in a dynamic environment such as auto manufacturing.

LEONARDO - The computational intelligence (CI) model selection wizard

Abstract: The need for tools to aid the selection of the CI models that lie at the heart of many AI systems has never been greater, due to the mainstreaming of data mining and other AI applications. LEONARDO -our contribution to this process- is a recommender system that selects and ranks applicable CI models for a given problem based on the peculiarities of the domain as determined by the user's preferences and dataset characteristics. Leonardo's recommendations are based on two knowledge bases. One contains the description of 65 CI models and provides the Meta knowledge for pruning the space of all CI models to only those applicable to the current task. The second KB contains the performance results of over 200 datasets on the applicable CI models. LEONARDO's ranking is achieved by using the performance information of the k entries, from this KB, nearest in similarity to the new domain dataset.

CompoNet: Programmatically Embedding Neural Networks into AI Applications as Software Components

Abstract: The provision of embedding neural networks into software applications can enable variety of artificial intelligence systems for individual users as well as organizations. Previously, software implementation of neural networks remained limited to only simulations or application specific solutions. Tightly coupled solutions end up in monolithic systems and non reusable programming efforts. We adapt component based software engineering approach to effortlessly integrate neural network models into AI systems in an application independent way. As proof of concept, this paper presents componentization of three famous neural network models i) multi layer perceptron ii) learning vector quantization and iii) adaptive resonance theory family of networks.

Game AI in Delta3D

Abstract: Delta3D is a GNU-licensed open source game engine with an orientation towards supporting "serious games" such as those with defense and homeland security applications. AI is an important issue for serious games, since there is more pressure to "get the AI right", as opposed to providing an entertaining user experience. We describe several of our near-and longer-term AI projects oriented towards making it easier to build AI-enhanced applications in Delta3D.

An Embedded System for Artificial Intelligence Applications

Abstract: Conventional approaches in the implementation of logic programming applications on embedded systems are solely of software nature. As a consequence, a compiler is needed that transforms the initial declarative logic program to its equivalent procedural one, to be programmed to the microprocessor. This approach increases the complexity of the final implementation and reduces the overall system’s performance. On the contrary, presenting hardware implementations which are only capable of supporting logic programs prevents their use in applications where logic programs need to be intertwined with traditional procedural ones, for a specific application. We exploit HW/SW codesign methods to present a microprocessor, capable of supporting hybrid applications using both programming approaches. We take advantage of the close relationship between attribute grammar (AG) evaluation and knowledge engineering methods to present a programmable hardware parser that performs logic derivations and combine it with an extension of a conventional RISC microprocessor that performs the unification process to report the success or failure of those derivations. The extended RISC microprocessor is still capable of executing conventional procedural programs, thus hybrid applications can be implemented. The presented implementation is programmable, supports the execution of hybrid applications, increases the performance of logic derivations (experimental analysis yields an approximate 1000% increase in performance) and reduces the complexity of the final implemented code. The proposed hardware design is supported by a proposed extended C-language called C-AG. Keywords— Attribute Grammars, Logic Programming, RISC microprocessor.

Artificial intelligence as an aide in management of security technology

Abstract: Historically, artificial intelligence (AI) research draws inspiration from human cognition, seeking to produce similarly intelligent behavior in artificial systems. Repetitive learning is the most important part of artificial intelligence. The South African electronic security industry is very data intensive, able to produce 1000 000 events per day and more than 1000 GB of video and voice data per day at a site. Many research and development groups in the security industry are looking extensively at AI to assist human operators to isolate important information from the avalanche of data. The selling potential systems resides in new AI based products and systems that can provide human-like sensibilities and reasoning. This paper gives an overview of existing and potential applications of AI in the security industry in South Africa. The paper highlights the value-adding potential of AI as a management tool to security systems.

A Hypothetical Case Study: Creating AI Assistants in the Law Library

Abstract: SUMMARY This article explores the burgeoning world of artificial intelligence (AI) and its applications to law libraries. An AI system is best described as a technology made to mimic intelligence derived from the combinations of various processes that the computer can perform simultaneously and automatically. A library's input in designing and programming an AI system is a critical component of the system's success. AI systems have the potential to supplement and expand the public services offered by libraries. Using current technology a library may create a basic AI system but more sophisticated systems have yet to emerge.

Game Smarts

Abstract: Artificial intelligence has been a part of videogames since their early days. For game developers, Al has come to mean the broad range of techniques used to generate the behavior of these opponents, battlefield units, team mates, NPCs, or anything else that acts in the game with simulated intelligence. A few of these techniques, such as finite state machines and the heuristic A* search algorithm, have proven themselves in many games over the years. Following the A* search algorithm's path, game developers are starting to explore techniques from several AI research subfields, including automated planning and machine learning. Machine learning has the potential to let AI characters improve with experience and adapt to individual players. The two machine learning techniques most commonly discussed in the games context are inductive and reinforcement learning

Map-Adaptive Artificial Intelligence for Video Games.

Abstract: This paper proposes an approach to automatically adapt game AI to the environment of the game (i.e., the socalled map). In the approach, a particular map is first analysed for specific features. Subsequently, an automatically established decision tree is applied to adapt the game AI according to the features of the map. Experiments that test our approach are performed in the RTS game Spring. From our results we may conclude that the approach can be used to automatically establish effective strategies dependent on the map of a game.

Parallel between definition of chess playing program and

Abstract: In this report we will explain some earlier papers (1, 2) which are about definition of Artificial Intelligence and about perfect AI. The definition of AI is intuitive in (1) and formal in (2). The perfect AI is a program that satisfies the definition for AI but which is absolutely useless because of the combinatory explosion. Most people do not understand these papers because they never saw AI and that is why for them the notion of AI is too abstract. In this report we will make parallel between definition of chess playing program and definition of AI. Of course, the definition of chess playing program is useless because people already know what this is. Anyway, we will give you this definition because its construction follows closely the construction of the definition of AI. Also the results are almost the same with the only difference that we can optimise the perfect chess playing program in order to obtain a real chess playing program, but for the moment we cannot optimise the perfect AI in order to obtain a real AI. In this report we will not speak about AI. The only matter which we will observe will be about chess playing programs. If you understand the construction and the results about chess playing programs then you can read the papers (1, 2) and to see similar results about AI.