Future Intelligent Systems Research Articles

Multi-Mode Radar Target Detection and Recognition Using Neural Networks

In typical radar systems, the process of recognizing a target requires human involvement. This human element makes radar systems not fully reliable due to unstable performance that varies between operators. This paper describes an intelligent radar system which addresses this problem in a border surveillance environment. The proposed radar system is capable of automatically detecting and then classifying different targets using an artificial neural network trained with the Levenberg-Marquardt algorithm. The training and test sets presented to the neural network are composed by high-resolution Inverse Synthetic Aperture Radar pictures obtained by the radar's detection module. Simulation results show that the intelligent radar system can reliably detect and distinguish the different objectives. Moreover, the radar system can outperform human operators and another radar system that deals with similar objectives. These results indicate that future intelligent systems can potentially replace human radar operators in this critical security setting.

ヒトと共生できる未来の知的システムを目指して～知能システムから人間共生システムへのパラダイムシフト～

ヒトと共生できる未来の知的システムを目指して～知能システムから人間共生システムへのパラダイムシフト～

Exploring user-centered intelligent road lighting design: a road map and future research directions

Traditional road lighting systems are outdated and should be replaced with systems which can sense their environment, i.e., users and their consumer electronics (CE) devices, and react intelligently. Realizing such a system requires an interdisciplinary approach which analyzes the efficient system architecture and communication technology while taking into account the user needs. To understand these necessities, subjective experiments should be conducted in a practical testbed, similar to ours. In this paper, we first present the state-of-the-art solutions in the literature. Then, we describe the system architecture of our testbed deployed on a real street along with the preliminary experiments. Finally, we discuss the open challenges and research directions on designing a future intelligent road lighting system.

On the Roles of Eye Gaze and Head Dynamics in Predicting Driver's Intent to Change Lanes

Driver behavioral cues may present a rich source of information and feedback for future intelligent advanced driver-assistance systems (ADASs). With the design of a simple and robust ADAS in mind, we are interested in determining the most important driver cues for distinguishing driver intent. Eye gaze may provide a more accurate proxy than head movement for determining driver attention, whereas the measurement of head motion is less cumbersome and more reliable in harsh driving conditions. We use a lane-change intent-prediction system (McCall et al., 2007) to determine the relative usefulness of each cue for determining intent. Various combinations of input data are presented to a discriminative classifier, which is trained to output a prediction of probable lane-change maneuver at a particular point in the future. Quantitative results from a naturalistic driving study are presented and show that head motion, when combined with lane position and vehicle dynamics, is a reliable cue for lane-change intent prediction. The addition of eye gaze does not improve performance as much as simpler head dynamics cues. The advantage of head data over eye data is shown to be statistically significant (p < 0.01) 3 s ahead of lane-change situations, indicating that there may be a biological basis for head motion to begin earlier than eye motion during "lane-change"-related gaze shifts.

4.3.1 Research on Creativity Education Incorporating Systems Engineering—An Example with “Intelligent Taiwan”

AbstractUpon the arrival of the era of science and technology and information, pluralism and diversification become important trend of industrial development. Facing the rapid industrial revolution and information explosion, human being's creativity has attracted attention; a lot of studies have been done on creativity, resulting in many theories, which have been applied in various areas in recent years.This research focuses on Taiwan's current technology policy, known as “Intelligent Taiwan”, and discusses the possible future Intelligence systems and issues related to continuous development of humanism. We also propose a Three‐Dimensional systems engineering framework (5‐layer extendable mode), which is adaptable to the future blue print and full of creativity. According to the introduction of the multi‐layer value of human, nature, and esthetics, which is developed as the structure of the proposed Three‐Dimensional framework, we further discuss the different value perspectives, life‐style, and future influence, of systems engineering thinking. In addition, in this paper we also recommend a new thinking of the systems engineering education to link the creativity education. Hence we can expect that the talents trained in the educational way would develop more mew methods, new conceptions, and new theories in the intelligent systems. In this case, our society can become more wholesome, have more excellent engineering creativities, develop continuous new innovations, and finally achieve the intelligent life – Sustainable Humanity and Nature Symbiosis.

Toward an Intelligent Brokerage Platform

In commercial transportation operations, one of the largest wasteful expenditures is the movement of tractor trailers with little or no cargo. Analysis of interfleet data shows many lost opportunities for identifying backhauling loads—cargo that could have been moved by an otherwise empty trailer on its return from a delivery point to its home base. Brokerage systems that facilitate matching of load-sharing and backhaul opportunities currently do not incorporate monitoring of real-time, geo-based information, analysis of historical geo-based information, and user-calibrated preferences from all brokerage participants. Future intelligent brokerage systems will need to provide a full range of services including supply chain visibility and automated identification of potential collaborations based on historical trends. In this paper an algorithm is described for identifying load-sharing and backhaul opportunities based on the detection of patterns in large-scale, event-based telematics network data.

Towards a Wireless Sensor Platform for Energy Efficient Building Operation

Currently, the IT-support for energy performance rating of buildings is insufficient. So-called IT-platforms often “built” of an ad-hoc, inconsistent combination of off-the-shelf building management components, distributed data metering equipment and several monitoring software tools. A promising approach to achieve consistent, holistic performance data management is the implementation of an integrated, modular wireless sensor platform. This paper presents an approach of how wireless sensors can be seamlessly integrated into existing and future intelligent building management systems supporting improved building performance and diagnostics with an emphasis on energy management.

Intelligent Modified Channel and Frequency Offset Estimation Schemes in Future Generation OFDM-Based Packet Communication Systems

The channel estimation and frequency offset estimation scheme for future generation orthogonal frequency division multiplexing (OFDM-) based intelligent packet communication systems are proposed. In the channel estimation scheme, we use additional 8 short training symbols besides 2 long training symbols for intelligently improving estimation performance. In the proposed frequency offset estimation scheme, we allocate intelligently different powers to the short and long training symbols while maintaining average power of overall preamble sequence. The preamble structure considered is based on the preamble specified in standardization group of IEEE802.11a for wireless local area network (WLAN) and IEEE802.11p for intelligent transportation systems (ITSs). From the simulation results, it is shown that the proposed intelligent estimation schemes can achieve better mean squared error (MSE) performance for channel and frequency offset estimation error than the conventional scheme. The proposed schemes can be used in designing for enhancing the performance of OFDM-based future generation intelligent communication network systems.

Innovative lighting systems enhance road safety

In the last twenty years, significant progress has been made in the field of headlight technology. Today’s systems are making driving at night much safer. Future intelligent lighting systems, which make use of computer-aided image processing sensors, will bring further safety benefits. Automotive supplier Valeo is currently developing such lighting systems.

Analysis of the ageing impact on the strength of the adhesive sealed joints of conveyor belts

The article is devoted to the presentation and analysis of laboratory test results and of industrial measurements, for conveyor-belt bonded joint strength from the point of view of the impact of aging on their durability and reliability. The purpose of this extensive research was to obtain the strength parameters of conveyor-belt bonded joints during different periods of use, as well as to compare the laboratory tests results with long-term measurements carried out under working conditions. The laboratory tests included a typical new joint as well as a joint used previously at the LW “Bogdanka” S.A. mine. Analogous joints were monitored under a real dynamic load with the use of a measurement device intended to form an element of a future intelligent diagnostic and control system.

Driver tracking and posture detection using low-resolution infrared sensing

Intelligent sensors are playing an ever-increasing role in automotive safety. This paper describes the development of a low-resolution infrared (IR) imaging system for continuous tracking and identification of driver postures and movements. The resolution of the imager is unusually low at 16 − 16 pixels. An image processing technique has been developed using neural networks operating on a segmented thermographic image to categorize driver postures. The system is able reliably to identify 18 different driver positions, and results have been verified experimentally with 20 subjects driving in a car simulator. IR imaging offers several advantages over visual sensors; it will operate in any lighting conditions and is less intrusive in terms of the privacy of the occupants. Hardware costs for the low-resolution sensor are an order of magnitude lower than those of conventional IR imaging systems. The system has been shown to have the potential to play a significant role in future intelligent safety systems.

Role of steering wheel feedback on driver performance: driving simulator and modeling analysis

When driving in curves, how do drivers use the force appearing on the steering wheel? As it carries information related to lateral acceleration, this force could be necessary for drivers to tune their internal model of vehicle dynamics; alternatively, being opposed to the drivers' efforts, it could just help them stabilize the steering wheel position. To assess these two hypotheses, we designed an experiment on a motion-based driving simulator. The steering characteristics of the vehicle were modified in the course of driving, unknown to drivers. Results obtained with standard drivers showed a surprisingly wide range of adaptation, except for exaggerated modifications of the steering force feedback. A two-level driver model, combining a preview of vehicle dynamics and a neuromuscular steering control, reproduces these experimental results qualitatively and indicates that adaptation occurs at the haptic level rather than in the internal model of vehicle dynamics. This effect is related to other theories on the manual control of dynamics systems, wherein force feedback characteristics are abstracted at the position control level. This research also illustrates the use of driving simulation for the study of driver behavior and future intelligent steering assistance systems.

A TAXONOMY OF STRATEGIES FOR MULTIMODAL PERSUASIVE MESSAGE GENERATION

Future intelligent systems will have contextual goals to pursue. As opposed to more traditional scenarios of human computer interaction, intelligent persuasive systems may also aim to induce the user or, in general, the audience, to perform some actions in the real world. Some scenarios of application are dynamic advertisement, preventive medicine, social action, and edutainment. As a step in this direction, a prototype called Promoter was developed for the production of persuasive messages. In modeling persuasion, the cognitive state of the participants (beliefs, desires, and intentions) is taken into account, as well as their social relations, their emotions, and the context of interaction. In this article, a taxonomy of persuasive strategies and the meta-reasoning model that works on this taxonomy is described. The taxonomy is built by taking into consideration studies coming both from social psychology and philosophy, and from the area of natural argumentation. The taxonomy is not domain specific and it helps to bridge persuasion strategies and rhetorical relations, a fundamental element in text planning. The use of this taxonomy also permits reasoning on the basis of emotion expression in accordance with persuasion strategies for multimodal message generation.

Semiotic Dynamics for Embodied Agents

Artificial intelligence explores the many different aspects of intelligence like a meandering stream carving out rivers, lakes, and deltas in an endless magnificent landscape. Each time new vistas on intelligence open up, we build new technologies to explore them and find new types of applications. In this article, the author briefly illustrate the current study of semiotic dynamics, the resulting technologies, and the field's impact on current and future intelligent systems applications

Computational Cybernetics

This issue contains selected papers from the International IEEE Conference on Computational Cybernetics that took place in August 2003 in Hungary at the site of lake Balaton. Computational Cybernetics is the synergetic integration of Cybernetics and Computational Intelligence techniques. Cybernetics was defined by Wiener as "the science of control and communication, in the animal and the machine". The word "cybernetics" itself stems from the Greek "kybernetes" that means pilot or governor. Thus, the science of computational Cybernetics is especially concerned with the comparative study of automatic control systems. Furthermore, Computational Cybernetics covers not only mechanical, but biological (living), social and economical systems and for this uses computational intelligence based results of communication theory, signal processing, information technology, control theory, the theory of adaptive systems, the theory of complex systems (game theory, operational research), and computer science. We have selected 14 papers from the conference covering the fields of system design and modeling, neural networks, and fuzzy control, which resemble the great variety of computational cybernetics. While it is sometimes difficult to integrate over these differing fields, we expect the evolution of future intelligent systems at the service of mankind by the synergetic integration of these different areas. It is our hope that the papers in this issue will inspire and help our readers in the development of advanced intelligent systems.

Configurable RF receiver architectures

In the heterogeneous world of communication and radar systems, a steadily increasing number of technical approaches for different applications are observed. A new application on the horizon is the transmission of very high data rate streams (> 500 Mb/s) during a short time interval between moving clients. Such applications may be applicable to future intelligent traffic control systems based on R.D. Kuhne (2002) and will require the support of different standards for communication and radio location services. The high data rates require high bandwidths, which become available at millimeter wave frequencies. From an engineering point of view, we may not be unsatisfied with a growing number of tasks, however, economic aspects are forcing us to search for unified solutions that do not require reengineering for every new or modified application. Therefore, the goal is to shift functionality from hardware to software. For example, channel selection and demodulation can be implemented as software codes and are no longer hardware realizations. These software-defined radios (SDRs), which compute classical receiver functions, can be reconfigurable. Therefore, the need for hardware solutions that can handle several standards and related software implementations arises. It is the purpose of this article to compare two very promising solutions (sampling and six-port) with respect to their suitability in the millimeter-wave range and to discuss some related research aspects.

Evaluating Real Time Ability and Failure Propagation in Distributed Systems

In future many intelligent systems are integrated into complex distributed systems. The individual subsystems operate autonomously. They are however dependent on the interaction with other subsystems. The aim is to develop a design process for such systems in which several objectives are regarded. A first objective is to ensure real time ability. A second one is to consider fault propagation. This is of growing importance as electronics are penetrating into even safety-relevant areas such as in automotive “driveby-wire” applications. This paper shows the most relevant modelling of functions in realtime systems by describing them in combined Max-Min-Plus-Algebra. The gained model can be used both for timing analysis and for Failure Propagation Analysis (FPA).

A neurofuzzy approach to future intelligent driver support systems

This paper reviews a variety of advanced signal processing algorithms that have been developed at the University of Southampton as part of the Prometheus (PROgraMme for European Traffic flow with Highest Efficiency and Unprecedented Safety) research programme to achieve an intelligent driver warning system (IDWS). The IDWS includes: visual detection of both generic obstacles and other vehicles, together with their tracking and identification, estimates of time to collision and behavioural modelling of drivers for a variety of scenarios. These application areas are used to show the applicability of neurofuzzy techniques to the wide range of problems required to support an IDWS, and for future fully autonomous vehicles.

Traffic Dynamics: Method for Estimating Freeway Travel Times in Real Time from Flow Measurements

This paper presents a method for estimating freeway travel times in real time directly from flow measurements, which is desirable for present and future Intelligent Vehicle-Highway Systems (IVHS) applications. An inductive modeling approach adapted here is based on stochastic queuing theory and the principle of conservation of vehicles. The analytical expression for link travel times satisfies traffic dynamics where the new form of the conservation of vehicles has been derived under generalized traffic conditions. A computer program has been developed to implement the algorithm. Analysis results show that the estimates have good agreement with empirical data measured at 30-s intervals. This methodology has potential applicable to automatic traffic control and automatic incident detection.

Vehicle Motion Control Using Genetic Algorithm. 1st Report. Urgent Obstacle Avoidance Steering.

The reduction of traffic accidents has become an increasingly important issue during recent years with the advance of the automobile society. Thorough investigation of the behavior of drivers, especially in the case of suddenly encountering an obstacle during driving has been regarded as a key in coping with this issue. Assuming an obstacle avoidance, taking full consideration of the nonlinearity of tires, we study the behavior of the driver under the critical condition by way of genetic algorithm (GA). Computer simulations are carried out, which indicate that the GA is a very successful means of determining the driver's behavior under the defined emergent situation. With its powerful ability to search for optimal solutions to certain problems, GA is expected to be a very useful method in studying human factors to gain knowledge for the development of future intelligent traffic system.