http://ieeexplore.ieee.org TOC Alert for Publication# 3468 2009 June 19 39 4 C1 693 48 39 4 C2 C2 38 This paper aims to provide reliable indications of driver drowsiness based on the characteristics of driver–vehicle interaction. A test bed was built under a simulated driving environment, and a total of 12 subjects participated in two experiment sessions requiring different levels of sleep (partial sleep-deprivation versus no sleep-deprivation) before the experiment. The performance of the subjects was analyzed in a series of stimulus-response and routine driving tasks, which revealed the performance differences of drivers under different sleep-deprivation levels. The experiments further demonstrated that sleep deprivation had greater effect on rule-based than on skill-based cognitive functions: when drivers were sleep-deprived, their performance of responding to unexpected disturbances degraded, while they were robust enough to continue the routine driving tasks such as lane tracking, vehicle following, and lane changing. In addition, we presented both qualitative and quantitative guidelines for designing drowsy-driver detection systems in a probabilistic framework based on the paradigm of Bayesian networks. Temporal aspects of drowsiness and individual differences of subjects were addressed in the framework. ]]> 39 4 694 705 1278 Understanding and reproducing complex human oculomotor behaviors using computational models is a challenging task. In this paper, two studies are presented, which focus on the development and evaluation of a computational model to show the influences of cyclic top-down and bottom-up processes on eye movements. To explain these processes, reinforcement learning was used to control eye movements. The first study showed that, in a picture-viewing task, different policies obtained from different picture-viewing conditions produced different types of eye movement patterns. In another visual search task, the second study illustrated that feedback information from each saccadic eye movement could be used to update the model's eye movement policy, generating different patterns in the following saccade. These two studies demonstrate the value of an integrated reinforcement learning model in explaining both top-down and bottom-up processes of eye movements within one computational model. ]]> 39 4 706 714 855 Context recognition is an essential aspect of intelligent systems and environments. In most cases, the recognition of a context of interest cannot be achieved in a single step. Between measuring a physical phenomenon and the estimation or recognition of what this phenomenon represents, there are several intermediate stages which require a significant computation. Understanding the resource requirements of these steps is vital to determine the feasibility of context recognition on a given device. In this paper, we propose an adaptive context-recognition architecture that accommodates uncertain knowledge to deal with sensed data. The architecture consists of an adaptation component that monitors the capability and workload of a device and dynamically adapts recognition accuracy and processing time. The architecture is implemented for an audio-based context recognition. A detail account of the tradeoff between recognition time and recognition accuracy is provided. ]]> 39 4 715 725 331 This paper presents a fuzzy relational approach to human emotion recognition from facial expressions and its control. The proposed scheme uses external stimulus to excite specific emotions in human subjects whose facial expressions are analyzed by segmenting and localizing the individual frames into regions of interest. Selected facial features such as eye opening, mouth opening, and the length of eyebrow constriction are extracted from the localized regions, fuzzified, and mapped onto an emotion space by employing Mamdani-type relational models. A scheme for the validation of the system parameters is also presented. This paper also provides a fuzzy scheme for controlling the transition of emotion dynamics toward a desired state. Experimental results and computer simulations indicate that the proposed scheme for emotion recognition and control is simple and robust, with good accuracy. ]]> 39 4 726 743 1256 When viewing multimedia presentations, a user only attends to a relatively small part of the video display at any one point in time. By shifting allocation of bandwidth from peripheral areas to those locations where a user's gaze is more likely to rest, attentive displays can be produced. Attentive displays aim to reduce resource requirements while minimizing negative user perception—understood in this paper as not only a user's ability to assimilate and understand information but also his/her subjective satisfaction with the video content. This paper introduces and discusses a perceptual comparison between two region-of-interest display (RoID) adaptation techniques. A RoID is an attentive display where bandwidth has been preallocated around measured or highly probable areas of user gaze. In this paper, video content was manipulated using two sources of data: empirical measured data (captured using eye-tracking technology) and predictive data (calculated from the physical characteristics of the video data). Results show that display adaptation causes significant variation in users' understanding of specific multimedia content. Interestingly, RoID adaptation and the type of video being presented both affect user perception of video quality. Moreover, the use of frame rates less than 15 frames per second, for any video adaptation technique, caused a significant reduction in user perceived quality, suggesting that although users are aware of video quality reduction, it does impact level of information assimilation and understanding. Results also highlight that user level of enjoyment is significantly affected by the type of video yet is not as affected by the quality or type of video adaptation—an interesting implication in the field of entertainment. ]]> 39 4 744 753 706 Rapid prototyping methods are in need of autonomous decision making and analysis during the product development stages so that the “time-to-market” can be reduced faster than traditional product development methodologies. Therefore, new methods of prototyping are inevitably essential. This paper proposes an approach to utilize the benefits of virtual prototyping (VP) and physical prototyping (PP) methodologies by integrating them into knowledge-based systems (KBSs) by providing seamless connection. This approach is termed autonomous integrated prototyping. The main contribution of this paper is the development of an intelligent system architecture to facilitate and guide the product development autonomously and simultaneously in both VP and PP environments. The seamless connection between VP and PP, along with KBSs, enables the exploration of new behaviors of developing systems and analyzing different behaviors. The architecture is applicable to embedded real-time systems (ERTSs), sensor applications, robotics, and ubiquitous applications where system interaction with the external environment is necessary. ]]> 39 4 754 769 1712 This paper proposes a model for invariant resource sharing problems in dioid algebra. A strong motivation for investigating the issue is the absence of a general systematic technique which can be used to tackle these problems. $(min, +)$ constraints have been developed to handle resource sharing in Discrete-Event Dynamic Systems. In particular, the part that can be modeled by a Timed Event Graph induce $(min, +)$-linear equations which are constrained by the resource availability. The proposed algebraic model has been proved to describe the actual behavior of the systems dealt with. This paper will show two examples of systems that are modeled and controlled by means of this approach. ]]> 39 4 770 781 999 As sensors become more complex and prevalent, they present their own issues of cost effectiveness and timeliness. It becomes increasingly important to select sensor sets that provide the most information at the least cost and in the most timely and efficient manner. Two typical sensor selection problems appear in a wide range of applications. The first type involves selecting a sensor set that provides the maximum information gain within a budget limit. The other type involves selecting a sensor set that optimizes the tradeoff between information gain and cost. Unfortunately, both require extensive computations due to the exponential search space of sensor subsets. This paper proposes efficient sensor selection algorithms for solving both of these sensor selection problems. The relationships between the sensors and the hypotheses that the sensors aim to assess are modeled with Bayesian networks, and the information gain (benefit) of the sensors with respect to the hypotheses is evaluated by mutual information. We first prove that mutual information is a submodular function in a relaxed condition, which provides theoretical support for the proposed algorithms. For the budget-limit case, we introduce a greedy algorithm that has a constant factor of $(1 - 1/e)$ guarantee to the optimal performance. A partitioning procedure is proposed to improve the computational efficiency of the algorithms by efficiently computing mutual information as well as reducing the search space. For the optimal-tradeoff case, a submodular–supermodular procedure is exploited in the proposed algorithm to choose the sensor set that achieves the optimal tradeoff between the benefit and cost in a polynomial-time complexity. ]]> 39 4 782 794 582 This paper proposes a robot-deployment algorithm that overcomes unpredicted obstacles and employs full-coverage deployment with a minimal number of sensor nodes. Without the location information, node placement and spiral movement policies are proposed for the robot to deploy sensors efficiently to achieve power conservation and full coverage, while an obstacle surrounding movement policy is proposed to reduce the impacts of an obstacle upon deployment. Simulation results reveal that the proposed robot-deployment algorithm outperforms most existing robot-deployment mechanisms in power conservation and obstacle resistance and therefore achieves a better deployment performance. ]]> 39 4 795 806 1519 Data objects have to be replicated in large-scale distributed systems for reasons of fault tolerance, availability, and performance. Furthermore, computations may have to be scheduled on these objects, when these objects are part of a grid computation. Although replication mechanism for unstructured peer-to-peer (P2P) systems can place replicas on capable nodes, they may not be able to provide deterministic guarantees on searching. Replication mechanisms in structured P2P systems provide deterministic guarantees on searching but do not address node capability in replica placement. We propose Virat, a node-capability-aware P2P middleware for managing replicas in large-scale distributed systems. Virat uses a unique two-layered architecture that builds a structured overlay over an unstructured P2P layer, combining the advantages of both structured and unstructured P2P systems. Detailed performance comparison is made with a replication mechanism realized over OpenDHT, a state-of-the-art structured P2P system. We show that the 99th percentile response time for Virat does not exceed 600 ms, whereas for OpenDHT, it goes beyond 2000 ms in our test bed, created specifically for the aforementioned comparison. ]]> 39 4 807 818 815 Despite the suggestions of friction-free information availability, considerable price dispersions for the same product are not uncommon across online retailers in the business-to-consumer (B2C) segment. Online customers do not necessarily always buy from the site with the lowest price, suggesting that other forces are at work. This paper presents and empirically examines a model that proposes that website value in terms of (perceived) website quality as well as awareness of the site and consumer differences (on price sensitivity) are key variables in explaining online consumer behavior in their choice of website despite the existence of price dispersions. Two hundred ninety-three students participated in a series of controlled laboratory experiments making use of two different types of products in terms of complexity and expensiveness (Canon digital camera Powershot S400 and digital versatile disc full-screen edition of Star Wars: Episodes I and II) that required them to interact with three different real-world websites offering each of these two branded products and make their decision on which of the three websites they will chose to buy the product from. The prices varied across the websites, as did the quality of the sites on various dimensions and site awareness of the participants. Conditional logit models of discrete choice for each of the two product types indicate differential influences of website quality dimensions and price sensitivity. A number of interesting implications emerge, and pointers to further extensions of the research theme are discussed. ]]> 39 4 819 839 691 This paper presents a sensory-updated degradation-based predictive maintenance policy (herein referred to as the SUDM policy). The proposed maintenance policy utilizes contemporary degradation models that combine component-specific real-time degradation signals, acquired during operation, with degradation and reliability characteristics of the component's population to predict and update the residual life distribution (RLD). By capturing the latest degradation state of the component being monitored, the updating process provides a more accurate of the remaining life. With the aid of a stopping rule, maintenance routines are scheduled based on the most recently updated RLD. The performance of the proposed maintenance policy is evaluated using a simulation model of a simple manufacturing cell. Frequency of unexpected failures and overall maintenance costs are computed and compared with two other benchmark maintenance policies: a reliability-based and a conventional degradation-based maintenance policy (without any sensor-based updating). ]]> 39 4 840 849 620 Given the advance of Internet technologies, we can now easily extract hundreds or thousands of news stories of any ongoing incidents from newswires such as CNN.com, but the volume of information is too large for us to capture the blueprint. Information retrieval techniques such as Topic Detection and Tracking are able to organize news stories as events, in a flat hierarchical structure, within a topic. However, they are incapable of presenting the complex evolution relationships between the events. We are interested to learn not only what the major events are but also how they develop within the topic. It is beneficial to identify the seminal events, the intermediary and ending events, and the evolution of these events. In this paper, we propose to utilize the event timestamp, event content similarity, temporal proximity, and document distributional proximity to model the event evolution relationships between events in an incident. An event evolution graph is constructed to present the underlying structure of events for efficient browsing and extracting of information. Case study and experiments are presented to illustrate and show the performance of our proposed technique. It is found that our proposed technique outperforms the baseline technique and other comparable techniques in previous work. ]]> 39 4 850 863 938 In this paper, we propose a new interactive method for multiobjective programming (MOP) called the PROJECT method. Interactive methods in MOP are techniques that can help the decision maker (DM) to generate the most preferred solution from a set of efficient solutions. An interactive method should be capable of capturing the preferences of the DM in a pragmatic and comprehensive way. In certain decision situations, it may be easier and more reliable for DMs to follow an interactive process for providing local tradeoffs than other kinds of preferential information like aspiration levels, objective function classification, etc. The proposed PROJECT method belongs to the class of interactive local tradeoff methods. It is based on the projection of utility function gradients onto the tangent hyperplane of an efficient set and on a new local search procedure that inherits the advantages of the reference-point method to search for the best compromise solution within a local region. Most of the interactive methods based on local tradeoffs assume convexity conditions in a MOP problem, which is too restrictive in many real-life applications. The use of a reference-point procedure makes it possible to generate any efficient solutions, even the nonsupported solutions or efficient solutions located in the nonconvex part of the efficient frontier of a nonconvex MOP problem. The convergence of the proposed method is investigated. A nonlinear example is examined using the new method, as well as a case study on efficiency analysis with value judgements. The proposed PROJECT method is coded in Microsoft Visual C++ and incorporated into the software PROMOIN (Interactive MOP). ]]> 39 4 864 879 822 The goal of raising customer loyalty in electronic commerce requires an emphasis on one-to-one marketing and personalized services. To this end, it is essential to understand individual customer preferences for products. In this paper, we present a method for identifying customer preferences and recommending the most appropriate product. The identification and recommendation of such products are all based on the use of customer's real-time web usage behavior, including activities such as viewing, basket placement, and purchasing of products. Therefore, in this approach, we do not force a customer to explicitly express his or her preference information for particular products but rather capture his or her preferences from data that result from such activities. Information on the web usage behavior for the products determines the ordinal relationships among the products, which express that certain product is preferred to other products across the multiple aspects. The ordinal relationships among the products and the multiple aspects of products lead to the consideration of a multiple-criteria decision-making approach. Thus, the problem eventually results in the identification of weights attached to the multiple criteria in the multidimensional preference space constructed by the ordinal relationships among the products. The derived weights are then used for the prioritization of products that are not included in the navigation behavior due to factors such as time pressure, cognitive burden, and the like. ]]> 39 4 880 889 386 A multiple-swarm multiobjective particle swarm optimization (PSO) algorithm, named dynamic multiple swarms in multiobjective PSO, is proposed in which the number of swarms is adaptively adjusted throughout the search process via the proposed dynamic swarm strategy. The strategy allocates an appropriate number of swarms as required to support convergence and diversity criteria among the swarms. Additional novel designs include a PSO updating mechanism to better manage the communication within a swarm and among swarms and an objective space compression and expansion strategy to progressively exploit the objective space during the search process. Comparative study shows that the performance of the proposed algorithm is competitive in comparison to the selected algorithms on standard benchmark problems. In particular, when dealing with test problems with multiple local Pareto fronts, the proposed algorithm is much less computationally demanding. Sensitivity analysis indicates that the proposed algorithm is insensitive to most of the user-specified design parameters. ]]> 39 4 890 911 2027 As a structural object of Petri nets, siphons play a key role in the development of deadlock prevention policies for resource allocation systems. Elementary siphons are a novel concept in net theory. Based on graph theory, this paper proposes an effective algorithm with polynomial complexity to find a set of elementary siphons for a linear system of simple sequential processes with resources ($hbox{LS}^{3} hbox{PR}$), a subclass of Petri nets, which can model many flexible manufacturing systems. The algorithm is established through the use of a resource directed graph and complementary sets of strict minimal siphons (SMS) of the net. The upper bound of the number of SMS in such a net is identified. A running example is used to demonstrate the proposed method. ]]> 39 4 912 923 362 The main purpose of workflow management systems is to support the definition, execution, and control of workflow processes. With or without time constraints, workflow management systems should satisfy certain correctness properties. The most important and widely used is the soundness property . In this paper, we focus on the soundness property for two classes of Petri-net-based workflow management systems with time constraints, $S$- and $A$-timed workflow nets (WNs), and we show that this property is undecidable for them. The proof technique, based on the undecidability of the halting problem for deterministic counter machines, shows first that the reachability, coverability, boundedness, and quasi-liveness problems are undecidable for these two classes of timed WNs, and then, as a consequence, the undecidability of the soundness problem is derived. ]]> 39 4 924 932 207 Reactive ion etching (RIE) is a process in the fabrication of semiconductor devices. The ability to predict the influence of the process parameters of RIE is crucial in terms of machine performance as they may have a serious impact on product quality as well as on the probability of machine failure. To address this issue, this correspondence paper presents a novel performance tradeoff function for evaluating the overall suitability of adopting the predicted control parameters suggested by domain experts, taking into full consideration their impact on the performance of the machine involved. An experiment using the RIE machine is provided to validate the practicability of the proposed approach. ]]> 39 4 933 938 499 Motivated by the study of a class of networked control systems, this correspondence paper is concerned with the design problem of stabilization controllers for linear systems with stochastic input delays. Different from the common assumptions on time delays, it is assumed here that the probability distribution of the delay taking values in some intervals is known a priori. By making full use of the information concerning the probability distribution of the delays, criteria for the stochastic stability and stabilization controller design are derived. Traditionally, in the case that the variation range of the time delay is available, the maximum allowable bound of time delays can be calculated to ensure the stability of the time-delay system. It is shown, via numerical examples, that such a maximum allowable bound could be made larger in the case that the probability distribution of the time delay is known. ]]> 39 4 939 945 179 39 4 946 946 152 39 4 947 947 149 39 4 948 948 128 39 4 C3 C3 29 39 4 C4 C4 35