Evaluation of six night vision enhancement systems: qualitative and quantitative support for intelligent image processing

OBJECTIVE: An evaluation study was conducted to answer the question of which system properties of night vision enhancement systems (NVESs) provide a benefit for drivers without increasing their workload. BACKGROUND: Different infrared sensor, image processing, and display technologies can be integrated into an NVES to support nighttime driving. Because each of these components has its specific strengths and weaknesses, careful testing is required to determine their best combination. METHOD: Six prototypical systems were assessed in two steps. First, a heuristic evaluation with experts from ergonomics, perception, and traffic psychology was conducted. It produced a broad overview of possible effects of system properties on driving. Based on these results, an experimental field study with 15 experienced drivers was performed. Criteria used to evaluate the development potential of the six prototypes were the usability dimensions of effectiveness, efficiency, and user satisfaction (International Organization for Standardization, 1998). RESULTS: Results showed that the intelligibility of information, the easiness with which obstacles could be located in the environment, and the position of the display presenting the output of the system were of crucial importance for the usability of the NVES and its acceptance. Conclusion: All relevant requirements are met best by NVESs that are positioned at an unobtrusive location and are equipped with functions for the automatic identification of objects and for event-based warnings. APPLICATION: These design recommendations and the presented approach to evaluate the systems can be directly incorporated into the development process of future NVESs.     

Integrated A.I. systems

The broad range of capabilities exhibited by humans and animals is achieved through a large set of heterogeneous, tightly integrated cognitive mechanisms. To move artificial systems closer to such general-purpose intelligence we cannot avoid replicating some subset—quite possibly a substantial portion—of this large set. Progress in this direction requires that systems integration be taken more seriously as a fundamental research problem. In this paper I make the argument that intelligence must be studied holistically. I present key issues that must be addressed in the area of integration and propose solutions for speeding up rate of progress towards more powerful, integrated A.I. systems, including (a) tools for building large, complex architectures, (b) a design methodology for building realtime A.I. systems and (c) methods for facilitating code sharing at the community level.

Lagegeregelte servoantriebe ohne mechanische sensoren

Mechanische Sensoren zur Drehzahl- und Lageerfassung bei elektrischen Antrieben verursachen Kosten, vergrößern das Bauvolumen des Antriebs, bedingen die Datenübertragung zwischen Regler und Sensor und schränken das Einsatzgebiet des Antriebs ein. Daher wurden verschiedene Konzepte zum Ersatz dieser mechanischen Sensoren entwickelt. Sie unterscheiden sich durch den Aufwand, die benötigte Genauigkeit (Pumpenantrieb Servoantrieb) und dem gewünschten Betriebsbereich.In diesem Beitrag wird die Realisierung des sensorlosen Betriebs einer permanenterregten Synchronmaschine durch ein Kalman-Filter beschrieben. Durch Simulation und durch praktische Untersuchungen konnte gezeigt werden, daß die Schätzung von Lage und Drehzahl die Genauigkeitsanforderungen für eine indirekte Lageregelung erfüllt. Eine solche Lageregelung besitzt keinen mechanischen Sensor mehr.     

Microanalytical investigation of sintered SiC

UHV-fracture surfaces of different (B, C)- and (Al, C)-doped pressureless sintered SiC materials are investigated by using high resolution Auger electron spectroscopy (HRAES). The grain boundaries at intergranular fractured regions of (B, C)-doped materials are evidently free of any enrichment of impurity elements or sintering additives. In contrast, the (Al, C)-doped materials reveal the existence of thin Al-containing grain boundary films. Sputtering indicates their thickness to be less than 1 nm. The concentrations of the elements segregated in the grain boundary films are determined.     

Gesture-based control and EMG decomposition

This paper presents two probabilistic developments for the use with electromyograms (EMGs). First described is a neuroelectric interface for virtual device control based on gesture recognition. The second development is a Bayesian method for decomposing EMGs into individual motor unit action potentials (MUAPs). This Bayesian decomposition method allows for distinguishing individual muscle groups with the goal of enhancing gesture recognition. All examples presented rely upon sampling EMG data from a subject's forearm. The gesture-based recognition uses pattern recognition software that has been trained to identify gestures from among a given set of gestures. The pattern recognition software consists of hidden Markov models, which are used to recognize the gestures as they are being performed in real time from moving averages of EMGs. Two experiments were conducted to examine the feasibility of this interface technology. The first replicated a virtual joystick interface, and the second replicated a keyboard. Moving averages of EMGs do not provide an easy distinction between fine muscle groups. To better distinguish between different fine motor skill muscle groups, we present a Bayesian algorithm to separate surface EMGs into representative MUAPs. The algorithm is based on differential variable component analysis, which was originally developed for electroencephalograms. The algorithm uses a simple forward model representing a mixture of MUAPs as seen across multiple channels. The parameters of this model are iteratively optimized for each component. Results are presented on both synthetic and experimental EMG data. The synthetic case has additive white noise and is compared with known components. The experimental EMG data were obtained using a custom linear electrode array designed for this study.     

Fracture and microstructure of open cell aluminum foam

SEM and EDS measurements were used to scrutinize the microstructure of Duocel open cell 6101 aluminum foam in relation to its fracture properties. In-situ SEM tensile tests on the open cell aluminum foam were performed to investigate the different fracture modes of struts and Aramis/Digital Image Correlation software was used to map the strain in individual struts. Observations during tensile tests showed that the microstructure of the struts has a great influence on the fracture behaviour of the foam. In particular AlFeSi-precipitates, which are due to the casting of the 6101 aluminum alloy, and the morphology of the foam alters the fracture mode of the struts in the foam from transgranular to intergranular. Less energy is needed for intergranular fracture of struts and the strain to failure of the foam is decreased due to weak individual struts.     

Hybrid learning concepts based on self-organizing neural networks for adaptive control of walking machines

Online learning of complex control behaviour of autonomous mobile robots like walking machines is one of the current research topics. In this article, a hybrid learning architecture based on reinforcement learning (RL) and self-organizing neural networks for online adaptivity is presented. The hybrid concept integrates different learning methods and task-oriented representations as well as available domain knowledge. The proposed concept is used for RL of control strategies on different control levels on a walking machine.     

A Skeptic's Approach to Combining HOL and Maple

We contrast theorem provers and computer algebra systems, pointing out the advantages and disadvantages of each, and suggest a simple way to achieve a synthesis of some of the best features of both. Our method is based on the systematic separation of search for a solution and checking the solution, using a physical connection between systems. We describe the separation of proof search and checking in some detail, relating it to proof planning and to the complexity class NP, and discuss different ways of exploiting a physical link between systems. Finally, the method is illustrated by some concrete examples of computer algebra results proved formally in the HOL theorem prover with the aid of Maple.     

Development of a Temporal Extension to Query Travel Behavior Time Paths Using an Object-Oriented GIS

An essential requirement to better understand activity-based travel behavior (ABTB) at the disaggregate level is the development of a spatio-temporal model able to support queries related to activities of individuals or groups of individuals. This paper describes the development and implementation of a temporal extension to a geographic information system (GIS) object-oriented model for the modeling of the time path and the retrieval of its event chaining. In this approach, time path is formulated as a totally time ordered set composed by activity events and trip events, themselves organized into time ordered sets. As sets, the time path and its components can be searched using their respective indexes. A series of methods were built that implement temporal predicates as an interface to temporally query the database. A set of positional operator methods were also designed that transform temporal topological queries into retrieval functions based on set ordering indices. Taken together, the temporal predicates and the positional operator methods define a temporal query extension that meets the retrieval needs of an ABTB database.