By Topic

IEEE Expert

Issue 4 • Date Aug. 1996

Filter Results

Displaying Results 1 - 16 of 16
  • Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural information processing in real-world face-recognition applications

    Page(s): 7 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (208 KB)  

    One of the challenges of neural information processing is to achieve, at least partially, a similar performance to humans on systems for automated visual face recognition. Commercial applications of new technology don't care about the underlying architecture or paradigms. The architecture simply needs to work all the time and be easy to use. That was the essence of ZN's product design plan when we began developing our ZN-Face access control system. ZN-Face relies on von der Malsburg's graph matching, which is robust enough to deal with the low quality pictures encountered outside the laboratory when developing automated image acquisition from real world scenes. (In this way, of course, the underlying neural system's robustness is essential, because otherwise we could not have fulfilled the works-all-the-time requirement.) At ZN, we developed the complete hardware and software setup for the biometric access control device. We optimized and adapted the algorithms to the specific verification task-that is, “is the person in question identical to the cardholder?”and tested it in the hardware setup, leading to a 99.5% performance verification rate. As with most face recognizers, ZN-Face requires the cooperation of users, who must orient their heads toward the camera during picture acquisition (±15°). Today's algorithms can only partially solve the challenge of generalizing from, for example, a half profile view to a frontal view View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks for steel manufacturing

    Page(s): 8 - 9
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (260 KB)  

    For several years, the Industrial and Building Systems Group at Siemens has successfully used neural networks for second level process automation in basic industries. Worldwide, Siemens currently has more than 20 neural network applications running in a dozen plants, 24 hours a day. Several aspects of neural networks contribute to their usefulness in the steel industry. First, they speed the development of new applications. In the past, steelmakers had to develop and program special analytical models, a laborious and time consuming process. Neural networks are simple mathematical structures that gather knowledge by learning from examples, which a computer can do automatically. Besides being so much quicker and easier, neural models also often achieve better performance than do analytical models in practical applications. Second, neural networks can handle highly nonlinear problems, making them vastly superior to classical linear approaches. Finally, neural network are able to adapt online. Applying our solutions to real world technical processes at Siemens required that we surmount several challenges, which involved extensive engineering effort. In particular, we needed to improve the control system without discarding existing solutions View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A knowledge-level model of a configurable learning system

    Page(s): 50 - 58
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3304 KB)  

    This proposed learning system model lets engineers experiment more easily with alternative learning-tool configurations when developing knowledge-based applications View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks provide robust character recognition for Newton PDAs

    Page(s): 10 - 11
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (476 KB)  

    While online handwriting recognition is an area of long standing and ongoing research, the recent emergence of portable, pen based computers (personal digital assistants, or PDAs) has focused urgent attention on usable, practical solutions. Pen based PDAs depend wholly on fast and accurate handwriting recognition, because the pen serves as the primary means for inputting data to the devices. To meet this need, we have combined an artificial neural network (ANN) character classifier with context driven search over character segmentation, word segmentation, and word recognition hypotheses to provide robust recognition of hand printed English text in new models of Apple Computer's Newton MessagePad. Earlier attempts at handwriting recognition used strong, limited language models to maximize accuracy. However, this approach failed in real world applications, generating disturbing and seemingly random word substitutions known within Apple as “The Doonesbury Effect”. We have taken an alternative approach, using bottom up classification techniques based on trainable ANNs, in combination with comprehensive but weakly applied language models. By simultaneously providing accurate character level recognition, via the ANN, with dictionaries exhibiting very wide coverage of the language, plus the ability to write entirely outside those dictionaries, we have produced a hand print recognizer that some have called the first usable handwriting recognition system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Task-based specifications through conceptual graphs

    Page(s): 60 - 70
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5172 KB)  

    Conceptual modeling is an important step toward the construction of user requirements. Requirements engineering is knowledge intensive and cannot be dealt with using only a few general principles. Therefore, a conceptual model is domain oriented and should represent the richer semantics of the problem domain. The conceptual model also helps designers communicate among themselves and with users. To capture and represent a conceptual model for the problem domain, we need: mechanisms to structure the knowledge of the problem domain at the conceptual level, which has the underlying principles of abstraction and encapsulation; and formalisms to represent the semantics of the problem domain and to provide a reasoning capability for verification and validation. We propose the task based specification methodology as the mechanism to structure the knowledge captured in conceptual models. TBSM offers four main benefits for constructing conceptual models, which are outlined. We propose conceptual graphs as the formalism to express task based specifications where the task structure of problem solving knowledge drives the specification, the pieces of the specification can be iteratively refined, and verification can be performed for a single layer or between layers. We chose conceptual graphs for their expressive power to represent both declarative and procedural knowledge, and for their assimilation capability-that is, their ability to be combined View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On-board and real-time expert control

    Page(s): 71 - 81
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3572 KB)  

    Development of an on board real time expert system for controlling engineering systems requires tradeoffs between AI and real time approaches. The article presents an alternative that lies between embedding AI in real time and embedding real time in AI. We used this framework to develop an expert system development environment for maintaining and updating information about an evolving system as its state changes because of abnormal events such as faults, or as a consequence of external actions taken upon the system. We've successfully applied it in several engineering domains such as process control, medical monitoring, and onboard diagnosis. The author explains how it was applied to a system that controls automobile manoeuvring View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network model for the automated control of springback in rebars

    Page(s): 45 - 49
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1016 KB)  

    Automating the process of cold-bending steel reinforcing bars for concrete structures can save time, prevent serious injuries, and increase productivity. Neural network models can play a key role in the adaptive control of this process View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying AI to structural safety monitoring and evaluation

    Page(s): 24 - 34
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2116 KB)  

    Four decision-support systems: Mistral, Damsafe, Kaleidos, and Igor provide powerful AI-based tools for evaluating structural data. The paper considers how safety managers, engineers, and authorities are using the systems to handle safety problems in structures View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent control at the OSU Control Research Lab

    Page(s): 82 - 83
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (572 KB)  

    The field of intelligent control has witnessed remarkable growth recently. Two main trends fuel this surge: our increasing understanding of how biological systems operate and astounding advances in computer technology. Together, these advances encourage the development of the field of intelligent control by providing alternative strategies for designing and implementing controllers for dynamical systems. As remarkable as this growth has been, development of the resulting intelligent controllers still fits within the conventional engineering methodology for the construction of control systems. Thus, effective intelligent control research requires a team of investigators, well grounded in the theory and application of conventional control methods. The Control Research Laboratory at Ohio State's Department of Electrical Engineering is one such group. The article includes some of the major players at the CRL and gives an overview of the work going on there View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural networks for computer virus recognition

    Page(s): 5 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (240 KB)  

    We have developed a neural network for generic detection of a particular class of computer viruses-the so called boot sector viruses that infect the boot sector of a floppy disk or a hard drive. This is an important and relatively tractable subproblem of generic virus detection. Only about 5% of all known viruses are boot sector viruses, yet they account for nearly 90% of all virus incidents. We have successfully deployed our neural network as a commercial product, distributing it to millions of PC users worldwide as part of the IBM AntiVirus software package. We faced several challenges in taking our neural network from a research idea to a commercial product. These included designing an appropriate input representation scheme; dealing with the scarcity of available training data; finding an appropriate trade off point between false positives and false negatives to conform to user expectations; and making the software conform to strict constraints on memory and speed of computation needed to run on PCs. The article discusses our methods for handling these challenges View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural-network speech processing for toys and consumer electronics

    Page(s): 4 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (176 KB)  

    The ongoing challenge in speech research is the recognition of continuous, unconstrained speech. In comparison, isolated word recognition with small vocabularies is easy. Many research efforts and commercial ventures aim at the high end problem. Sensory Inc. has successfully focused on the low end, producing a family of inexpensive speech recognition ICs for markets such as interactive toys, consumer electronics, electronic learning aids, telecommunication devices, security systems, and household appliances. These markets are extremely cost conscious and demand solutions in the under five dollar price range. Previous low cost solutions relied on coarse properties of the speech signal, such as the amplitude envelope or zero crossing rates, and typically yielded poor recognition performance. Digital signal processor based approaches can achieve adequate performance but are beyond the low cost market's reach. Sensory uses a neural network based approach that provides robust performance at a low cost. Sensory's general purpose RSC-164 controller performs four speech recognition functions View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Al models for business process reengineering

    Page(s): 16 - 23
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (852 KB)  

    Most models fail to capture the rationale behind processes, making business reengineering less effective. The authors describe their I* framework, which views organizations as collections of actors with strategic interests, and interdependencies involving goals, tasks, and resources. The authors discuss the ConGolog framework, which supports reasoning about the dynamics of processes under incomplete knowledge View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • AI tools for business-process modeling

    Page(s): 13 - 15
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (596 KB)  

    For more than a decade, artificial intelligence techniques have served as critical building blocks for cutting edge business applications. Knowledge based systems (KBS) in particular have helped numerous Fortune 1000 companies solve pressing business problems-everything from scheduling their manufacturing operations to managing their investment portfolios. AI has helped many companies improve productivity and reduce costs to meet the demands of today's competitive global economy. Today, business management itself is undergoing fundamental change. For the past several years, business process reengineering (BPR) has become the watchword. This move to rethink and redesign the way a company works aims at further boosting productivity and cutting costs. No wonder then that business managers worldwide are turning to explicit KBS techniques, long proven to achieve the very goals of BPR, to model change. The first wave of AI based tools and applications for business process modeling (BPM) is just hitting the shore. Organizations such as IBM, EDS, the US Army, and Swiss Bank are among the first to adopt AI for BPM. Some are using traditional KBS tools such as ART*Enterprise and ProKappa, while others are turning to ReThink, the first AI tool designed specifically for BPM View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Support for integrated value-based maintenance planning

    Page(s): 35 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2784 KB)  

    The paper considers how IRTMM intelligent real-time maintenance management system helps process-plant engineers and owners perform value-based plant maintenance. With IRTMM, they can inspect subsystems, identify component operating parameters, and review and make notes regarding component performance or operational and maintenance history View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time for the Web to grow up?

    Page(s): 84 - 86
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (356 KB)  

    New technologies often pass through similar stages in development. First, the creators of the technology, driven by a vision to improve the world, push the technology forward. Once the technology reaches a critical threshold, society adopts it and pulls it in unexpected directions. The Web is no exception. Until recently, the Web was used primarily for fun by a small segment of society made up of folks who were comfortable with computers and networks and who thrived in the unmanaged, free spirit of the Internet. Now, as forces unite to integrate the Web into society, it's time for the Web to grow up. The strongest of these integrating forces, technological progress, is discussed. The author reviews various technological issues and describes some of the other forces fueling the Web's explosive growth View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

This Periodical ceased production in 1997. The current retitled publication is IEEE Intelligent Systems.

Full Aims & Scope