scispace - formally typeset
Search or ask a question

Showing papers on "Applications of artificial intelligence published in 2003"


Book ChapterDOI
04 May 2003
TL;DR: This work introduces captcha, an automated test that humans can pass, but current computer programs can't pass; any program that has high success over a captcha can be used to solve an unsolved Artificial Intelligence (AI) problem; and provides several novel constructions of captchas, which imply a win-win situation.
Abstract: We introduce captcha, an automated test that humans can pass, but current computer programs can't pass: any program that has high success over a captcha can be used to solve an unsolved Artificial Intelligence (AI) problem. We provide several novel constructions of captchas. Since captchas have many applications in practical security, our approach introduces a new class of hard problems that can be exploited for security purposes. Much like research in cryptography has had a positive impact on algorithms for factoring and discrete log, we hope that the use of hard AI problems for security purposes allows us to advance the field of Artificial Intelligence. We introduce two families of AI problems that can be used to construct captchas and we show that solutions to such problems can be used for steganographic communication. captchas based on these AI problem families, then, imply a win-win situation: either the problems remain unsolved and there is a way to differentiate humans from computers, or the problems are solved and there is a way to communicate covertly on some channels.

1,525 citations


Book
09 Dec 2003
TL;DR: If you're a game programmer (AI/logic, front-end, user interface, tools, graphics, etc.) this comprehensive resource will help you take your skills and knowledge to the next level.
Abstract: From the Publisher: Learn how AI experts create intelligent game objects and characters with this firstvolume in the AI Game Programming Wisdom series. This unique collection of articles gives programmers and developers access to the insights and wisdom of over thirty AI pros. Each article delves deep into key AI game programming issues and provides insightful new ideas and techniques that can be easily integrated into your own games. Everything from general AI architectures, rule based systems, level-of-detail AI, scripting language issues, to expert systems, fuzzy logic, neural networks, and genetic algorithms are thoroughly covered. If you're a game programmer (AI/logic, front-end, user interface, tools, graphics, etc.) this comprehensive resource will help you take your skills and knowledge to the next level. KEY FEATURES - Contains new AI techniques and solutions written by over thirty industry experts - Provides comprehensive coverage of all aspects of AI programming - Includes ready-to-use ideas and code - Provides skill enhancement for beginning/ intermediate programmers, and insightful new ideas for the pros - Companion CD includes all code for easy implementation Author Biography: Steve Rabin is a 10-year video game industry veteran working at Nintendo of America. He's written AI for three published games and was a contributor to both Game Programming Gems 1 and 2. He was also the AI section editor for Game Programming Gems 2. He's spoken on AI at the Game Developers Conference and holds a degree in Computer Engineering from the University of Washington, where he specialized in robotics.

343 citations


Journal ArticleDOI
TL;DR: It is revealed that although still regarded as a novel methodology, AI technologies are shown to have matured to the point of offering real practical benefits in many of their applications.

267 citations


Journal ArticleDOI
TL;DR: The most important steps of this process of application of pattern recognition techniques, expert systems, artificial neural networks, fuzzy systems and nowadays hybrid artificial intelligence techniques in manufacturing are outlined and some new results are introduced with special emphasis on hybrid AI and multistrategy machine learning approaches.

179 citations


Journal ArticleDOI
TL;DR: In this paper, the authors presented a thorough introduction in Artificial Neural Networks (ANNs) and their contribution to modern Urologic Oncology, and pointed out the differences of Artificial Intelligence to traditional statistic models in terms of serving patients and clinicians, in a different way than current statistical analysis.

121 citations


Proceedings ArticleDOI
07 Oct 2003
TL;DR: A review of developments in applications of artificial intelligence techniques for induction machine stator fault diagnostics, including fault diagnosis of electric motor drive systems using AI techniques has been considered.
Abstract: The on-line fault diagnostics technology for induction machines is fast emerging for the detection of incipient faults as to avoid the unexpected failure. Approximately 30-40 % faults of induction machines are stator faults. This paper presents a review of developments in applications of artificial intelligence techniques for induction machine stator fault diagnostics. Now a days artificial intelligence (AI) techniques are being preferred over traditional protective relays for fault diagnostics of induction machines. The application of expert system, fuzzy logic system, artificial neural networks, genetic algorithm have been considered for fault diagnostics. These systems and techniques can be integrated into each other with more traditional techniques. A brief description of various AI techniques highlighting the merits and demerits of each other have been discussed. Fault diagnosis of electric motor drive systems using AI techniques has been considered. The futuristic trends are also indicated.

97 citations


Proceedings Article
01 Jan 2003
TL;DR: It is argued that AIbased art and entertainment constitutes a new interdisciplinary agenda linking games studies, design practice, and technical research, and is called expressive AI.
Abstract: In recent years, as dramatic increases in graphic sophistication began yielding diminishing returns, the technical focus in game design has been turning towards Artificial Intelligence (AI). While game AI might be considered a “purely technical” phenomenon not of interest to game designers and theorists, this paper argues that AIbased art and entertainment constitutes a new interdisciplinary agenda linking games studies, design practice, and technical research. I call this new interdisciplinary agenda expressive AI.

57 citations


Journal ArticleDOI
TL;DR: It seems likely that applications like distributed blackboards will continue apace in specialist domains, and progress toward the popular idea of AI manifested in human-like robots as the authors progress in simulating vision, language, common sense, and adaptability behaviors.
Abstract: Artificial intelligence is not just hype, as many working applications use AI techniques. However, we have yet to develop a system that spans the full spectrum of intelligent behavior. For example, building a system that an make sensible decisions about unfamiliar situations in everyday, nonspecialist domains remains difficult. Nevertheless, it seems likely that applications like distributed blackboards will continue apace in specialist domains. This quiet revolution can make a significant contribution to our lives. Meanwhile, we can also expect progress toward the popular idea of AI manifested in human-like robots as we progress in simulating vision, language, common sense, and adaptability behaviors.

28 citations


Journal ArticleDOI
TL;DR: The aim of this research is to use artificial neural networks as the brain of grinding machine controller to achieve the desired workpiece surface roughness under grinding wheel surface topography variations.
Abstract: In recent years, artificial intelligence played an important role in machine tool automation. Artificial neural networks, as one of the artificial intelligence algorithms, has superiority in representing the relation between the inputs and outputs of the multi‐variable system. Hence, it can be applied to sophisticated operations such as grinding operation. The aim of this research is to use artificial neural networks as the brain of grinding machine controller. The target of this controller was to achieve the desired workpiece surface roughness under grinding wheel surface topography variations. The core of the system consists of two multi‐layers feed forward artificial neural networks based on back error propagation learning algorithm. The first one was used for process design to achieve the desired surface roughness. It extracts suitable process variables such as grinding wheel speed and feed rate. The second one monitors the cutting operation using sensors' readings. It extracts the different controlli...

25 citations


Journal ArticleDOI
01 Jun 2003
TL;DR: The aim of this paper is to review some recent applications of artificial intelligence in finding better solutions to various problems in different areas of the colour and textile industry and to describe the applications rather briefly.
Abstract: The use of computers in the colour and textile industry dates back to 1960s 111. A significant number of papers have been published over the years describing the application of computer control in various fields of textiles (21, including fibre production [3,4], yarn formation 151, fabric formation [6-8], and dyeing processes and machinery [9-211. Although the term ’artificial intelligence’ was coined in 1956 1221, it was during the last decade of the 20th century that textile researchers actively investigated its application in various fields. Some earlier developments in artificial intelligence have been reported for the textiles industry [23], textile finishing 124,251 and the colour industry [26]. One of the earlier applications of artificial intelligence in textile coloration was robotics, which was explored in the quest for automation and control. However, more recently, artificial neural networks (ANN) 127,281, fuzzy logic and some expert or knowledge-based systems have attracted the attention of researchers in different sectors of the colour and textile industry. The aim of this paper is to review some recent applications of artificial intelligence in finding better solutions to various problems in different areas of the colour and textile industry. The intention is to describe the applications rather briefly and to give a more thorough account of specific technologies that are being used or have a huge potential for use in the foreseeable future.

19 citations


Journal ArticleDOI
TL;DR: This paper investigates the impact of momentum bias on forecasting financial markets through knowledge discovery techniques using implicit knowledge representation (NNs) and case based reasoning (CBR).
Abstract: To an increasing extent since the late 1980s, software learning methods including neural networks (NN) and case based reasoning (CBR) have been used for prediction in financial markets and other areas. In the past, the prediction of foreign exchange rates has focused on isolated techniques, as exemplified by the use of time series models including regression models or smoothing methods to identify cycles and trends. At best, however, the use of isolated methods can only represent fragmented models of the causative agents, which underlie business cycles. Experience with artificial intelligence applications since the early 1980s points toward a multistrategy approach to discovery and prediction. This paper investigates the impact of momentum bias on forecasting financial markets through knowledge discovery techniques. Different modes of bias are used as input into learning systems using implicit knowledge representation (NNs) and CBR. The concepts are examined in the context of predicting movements in the Japanese yen .

Journal ArticleDOI
TL;DR: From his work with natural language and robot behavior, to his new focus on building robot communities and studying robot interactions, Luc Steel has continually sought to redefine the AI field.
Abstract: From his work with natural language and robot behavior, which became especially visible with Sony's Aibo, to his new focus on building robot communities and studying robot interactions, Luc Steel has continually sought to redefine the AI field. He shares his opinions on AI and how the field is evolving.

Journal ArticleDOI
TL;DR: In the parallel sessions at ACAT2002 different artificial intelligence applications in high energy and nuclear physics were presented as discussed by the authors, and a summary of these presentations can be found in the relevant section of these proceedings.
Abstract: In the parallel sessions at ACAT2002 different artificial intelligence applications in high energy and nuclear physics were presented. I will briefly summarize these presentations. Further details can be found in the relevant section of these proceedings.

Journal ArticleDOI
Anne Jenkins1
01 Sep 2003-Futures

Book ChapterDOI
23 Jun 2003
TL;DR: The aim is to develop a methodology for analog circuit diagnosis based on improving the well-known fault dictionary techniques by means of new cases addition or adaptation towards a Case Based Reasoning system.
Abstract: There have been some Artificial Intelligence applications developed for electronic circuits diagnosis, but much remains to be done in this field, above all in the analog domain. The purpose of this paper is not to give a general solution, but to contribute with a new methodology. Our aim is to develop a methodology for analog circuit diagnosis based on improving the well-known fault dictionary techniques by means of new cases addition or adaptation towards a Case Based Reasoning system. As an example, a fault dictionary method have been studied in detail. It has been used as starting point for case base construction to be applied to a real electronic circuit. The faults considered are parametric, permanent, independent and simple.

Journal ArticleDOI
TL;DR: Trends in computer science show that various aspects of artificial intelligence (AI) are emerging, and other trends show that these advances are being applied to create intelligent information systems.
Abstract: Trends in computer science show that various aspects of artificial intelligence (AI) are emerging, and other trends show that these advances are being applied to create intelligent information systems. Although the field of AI has not been very successful in the past, these trends suggest that it may finally arrive in the next few years.

Book ChapterDOI
01 Jan 2003
TL;DR: This chapter explains about the automated visual inspection (AVI), artificial intelligence, and growing amount of research has been aimed at incorporating artificial intelligence techniques into AVI systems to increase their capability.
Abstract: This chapter explains about the automated visual inspection (AVI) and artificial intelligence. AVI operates by employing a camera to acquire an image of the object being inspected and then utilizing appropriate image processing hardware and software routines to find and classify areas of interest in the image. Generally, AVI involves five different processing stages, such as the image acquisition, the image enhancement, segmentation, feature extraction, and classification. One of the problems with the widespread acceptance of automated inspection systems is that companies who have installed them are unwilling to release the details of their system or the cost savings because they want to maintain a competitive advantage over their rivals. The three main applications of the AVI are mark identification, dimension checking, and presence verification. Artificial intelligence (AI) involves the development of computer programs that mimic some form of natural intelligence. Some of the most common AI techniques with industrial applications are expert systems, fuzzy logic, inductive learning, neural networks, genetic algorithms, simulated annealing, and Tabu search. No computer system has so far been developed, which can interpret all images. Rather, many machine vision systems have been built that deal with one specific object in a restricted environment. Over recent years, a growing amount of research has been aimed at incorporating artificial intelligence techniques into AVI systems to increase their capability.

Journal ArticleDOI
TL;DR: So what does an artificial intelligence do with itself after it has become self-aware?
Abstract: So what does an artificial intelligence do with itself after it has become self-aware? Suppose that we do succeed in creating an AI. Or suppose that an AI emerges spontaneously out of data networks' growing complexity. What then-from the point of view of the AI? Science fiction provides some interesting thought experiments on the subject of AI motivation.

Book ChapterDOI
01 Jan 2003
TL;DR: The utility of the distinguishing features of the support vector method for two important tasks in stochastic mechanics: the learning from random samples in a Monte Carlo simulation context and the possibility of defining a reliability index that characterizes arbitrary safe domains.
Abstract: Publisher Summary This chapter focuses on the relevance of support vector machines for stochastic mechanics. The last years have witnessed a growing research on applications of artificial intelligence algorithms in several fields of computational mechanics. Most applications concern genetic algorithms, fuzzy set reasoning, and neural networks. Few applications have been reported on the kernel methods, which is a family of artificial learning algorithms that are distinguished by their use of kernels. Kernel methods and support vector machines have emerged as a potent artificial intelligence alternative to neural networks for complicated tasks, especially those concerning image analysis. This chapter presents a paper that examines learning algorithm with respect to their utility in solving stochastic mechanics problems. It describes the main features of support vector machines and their differences in neural networks. It discusses the utility of the distinguishing features of the support vector method for two important tasks in stochastic mechanics: the learning from random samples in a Monte Carlo simulation context and the possibility of defining a reliability index that characterizes arbitrary safe domains.

01 Jan 2003
TL;DR: This thesis presents the results from an experiment aiming at testing strategy game AI, where test persons played against traditional strategy gameAI, a genetic algorithm AI, and other humans to see if they experienced any differences in the behaviour of the opponents.
Abstract: If a computer game company wants to stay competitive they must offer something extra. For many years, this extra has often been synonymous with better graphics. Lately, and thanks to the Internet, the focus has shifted in favour of more multi-player support. This also means that the requirements of one-player games increases. Our proposal, to meet these new requirements, is that future game AI is made more human-like. One way to achieve this is believed to be the use of learning AI techniques, such as genetic algorithms and neural networks. In this thesis we will present the results from an experiment aiming at testing strategy game AI. Test persons played against traditional strategy game AI, a genetic algorithm AI, and other humans to see if they experienced any differences in the behaviour of the opponents.

Proceedings ArticleDOI
04 Sep 2003
TL;DR: An AI application whereby a designer or developer sketches an entity's AI using a graphical “drag and drop” interface to quickly articulate behavior using a UML-like representation of state charts is created.
Abstract: Simulation developers often realize an entity's AI by writing a program that exhibits the intended behavior. These behaviors are often the product of design documents written by designers. These individuals, while possessing a vast knowledge of the subject matter, might not have any programming knowledge whatsoever. To address this disconnect between design and subsequent development, we have created an AI application whereby a designer or developer sketches an entity's AI using a graphical “drag and drop” interface to quickly articulate behavior using a UML-like representation of state charts. Aside from the design-level benefits, the application also features a runtime engine that takes the application's data as input along with a simulation or game interface, and makes the AI operational. We discuss our experience in creating such an application for both designer and developer.

Proceedings Article
01 Jan 2003
TL;DR: In this article, the authors focus on lessons learned with respect to human-robot interface usability and robotic control architecture dynamic configuration and portability during the 2003 Robot Rescue Competition held in Acapulco as part of American Association for Artificial Intelligence (AAAI) Fifteenth Innovative Applications of Artificial Intelligence Conference.
Abstract: In order to realize the broad use of robotic systems in hazardous environments, shortcomings in robot interfaces, control system configurability, and overall usability must be addressed. A concerted effort was made to build a foundation of well-engineered communication, perception and autonomous behavior that is robust to changing, unstructured environments and which can be reused across different robot geometries and sensors. During the 2003Robot Rescue competition held in Acapulco as part of American Association for Artificial Intelligence (AAAI) Fifteenth Innovative Applications of Artificial Intelligence Conference, the INEEL demonstrated a high level of success in the areas of human-robot interaction, dynamic sensor configuration, and code portability. This paper will focus on lessons learned with respect to human-robot interface usability and robotic control architecture dynamic configuration and portability.

Journal Article
TL;DR: The four components (problem-solving or expertise module, student model, tutoring module and the user interface) of an ITS will be described and the nine elements (objectives, content, learning activities, evaluation procedures, materials or resources, teaching strategies and space) of a curriculum design will be explained.
Abstract: An ITS (Intelligent Tutoring System) is a teaching-learning medium that uses artificial intelligence (AI) technology for instruction. Roberts and Park (1983) defines AI as the attempt to get computers to perform tasks that if performed by a human-being, intelligence would be required to perform the task. The design of an ITS comprises two distinct features - a sophisticated computer programming feature which has to be programmed by a computer scientist and a comprehensive curriculum design feature which has to be developed by a curriculum specialist. Unfortunately, most of the existing ITS’s were designed by AI researchers alone without much involvement of curriculum designers, education psychologists and/or subject specialists. These AI researchers were not primarily concerned about instructional issues and their main concerns were to test their research curiosities in the AI field with minimum involvement of other people. This paper will analyze both features of an ITS; first, the four components (problem-solving or expertise module, student model, tutoring module and the user interface) of an ITS will be described and then the nine elements (objectives, content, learning activities, evaluation procedures, materials or resources, teaching strategies, time, grouping and space) of a curriculum design will be explained. The paper will end with a discussion of the problems that can arise if both curriculum development and computer programming features of the design of an ITS are not taken into consideration.

Proceedings ArticleDOI
10 Dec 2003
TL;DR: The concept and use of artificial intelligence techniques for solving problems in electrical power systems in the final year of an undergraduate programme in Electrical and Electronic Engineering are described.
Abstract: This paper describes the concept and use of artificial intelligence techniques for solving problems in electrical power systems in the final year of an undergraduate programme in Electrical and Electronic Engineering. Nowadays, the analysis and design of power systems involve numerical computer modeling and simulations. Besides the classical techniques, which are conventionally used for analyzing power systems, artificial intelligence techniques have come up as a logical solution to the large-scale, non-linear nature inherent in such systems as can be observed in power systems literature. The integration of these new techniques for power system analysis enables better understanding of the subject with hands-on practice on personal computers through simulations. Existing programmes in power systems in most universities can easily be extended to include a module in AI applications in power systems.

01 Jan 2003
TL;DR: In this paper a genetic algorithm approach was used in order to obtain two major desired eects to increase the disjunction level in knowledge representation and the processing speed.
Abstract: The complex analyses required by artificial intelligence applications need both a flexible structure for information representation and a quick and ecient method for information categorization. The latter has a great impact on the former because it can increase or not the knowledge database dimension. This situation can sometimes lead to undesired complexity. In this paper a genetic algorithm approach was used in order to obtain two major desired eects. The first one is to increase the disjunction level in knowledge representation and the second is to increase the processing speed. Comparisons were made between our solutions and the weighting results of ReliefF algorithm.

Patent
14 Apr 2003
TL;DR: In this article, a flexible method of representing things that is suitable for artificial intelligence applications is proposed based on creating instances of the form named ''thing'' in programmable systems Similar to things, each instance can have various types of relationships with any number of other instances.
Abstract: This invention provides a flexible method of representing things that is suitable for artificial intelligence applications The method is based on creating instances of the form named _THING The instance can be created in programmable systems Similar to things, each instance can have various types of relationships with any number of other instances

Proceedings ArticleDOI
02 Nov 2003
TL;DR: The artificial intelligence applications in the design of VRTOS-MAD are analyzed as three aspects: kinematics models managing based on knowledge, VE manager designing based on environment semantics constraint; multilevel operation monitoring based on simply plan recognition.
Abstract: It is necessary to inspect periodically in maintenance of the STE (special type equipment). However, it requires a lot of workforces with a high degree of technical skill in assembling and disassembling various sorts of STE in hazardous environment. Since physical simulation prototypes are too sparse and extremely costly to be a training substitute, we have to study the development of the STE VROTS (virtual reality operation training simulator) named VROTS-MAD which can be used easily by novice users. The focus of this paper is the artificial intelligence applications in the design of VRTOS-MAD. The artificial intelligence applications are analyzed as three aspects: kinematics models managing based on knowledge, VE manager designing based on environment semantics constraint; multilevel operation monitoring based on simply plan recognition.


Journal Article
TL;DR: A comprehensive survey of the history, architecture of and the techniques used in ITS, based on the latest progress in this field and the experience in developing intelligent language training systems, with emphasis on the applications of AI in ITS.
Abstract: An ITS (i.e. Intelligent Tutoring System) is a representative combination of AI and education. In this paper, we give a comprehensive survey of the history, architecture of and the techniques used in ITS, based on the latest progress in this field and our experience in developing intelligent language training systems; our emphasis lies on the applications of AI in ITS. Meanwhile, we look into some critical problems in today's ITS. At the end of the paper, we point out some directions we should follow in future work.

Journal Article
01 Jan 2003-Rays
TL;DR: The evolution of logic thought in relation to the predominant recent advances in technology is analyzed and it is extremely relevant how the computer has completely transformed medicine and the medical role, especially in the field of radiology.
Abstract: The evolution of logic thought in relation to the predominant recent advances in technology is analyzed. In fact, the computer was the prime mover of this major change. At present the use of sophisticated software has allowed to attain increasingly accurate levels of simulation of human reasoning. The computer has determined profound transformations in many sectors of work, study and research. Among these, it is extremely relevant how the computer has completely transformed medicine and the medical role, especially in the field of radiology. Expert systems are the most interesting and futuristic applications of artificial intelligence. These systems are able to reproduce on a computer the behavior of an expert human being. Some of the recent innovations introduced in the field of breast, thoracic and mainly neural pathology are illustrated.