Warehouses play a critical role in the distribution of products of many suppliers to many customers. Traditionally, warehouse operations are controlled by centralised control systems. Because of increasing customer de...
详细信息
ISBN:
(纸本)9783642004865
Warehouses play a critical role in the distribution of products of many suppliers to many customers. Traditionally, warehouse operations are controlled by centralised control systems. Because of increasing customer demands. the complexity of such systems becomes too large to respond optimally to all warehouse events. Holonic control systems try to overcome this limitation. This paper presents a framework that supports the development of holonic warehouse control systems. The framework, which is built on top of JADE middleware, allows a holonic control system to be generated from a warehouse layout model and a library of reusable behaviour components. The architecture of the framework and an example of its application to an existing warehouse are presented.
This article presents a bionic model derived from research findings about the perceptual system of the human brain to build next generation intelligent sensor fusion systems. For this purpose, a new information proces...
详细信息
ISBN:
(纸本)9783642032011
This article presents a bionic model derived from research findings about the perceptual system of the human brain to build next generation intelligent sensor fusion systems. For this purpose, a new information processing principle called neuro-symbolic information processing is introduced. According to this method, sensory data are processed by so-called neuro-symbolic networks. The basic processing units of neuro-symbolic networks are neuro-symbols. Correlations between neuro-symbols of a neuro-symbolic network are learned from examples. Perception is based on sensor data and on interaction with cognitive processes like focus of attention, memory, and knowledge.
In this paper a new and robust approach of skin detection is proposed. In the previous proposed system, we introduced a method for skin detection based on RGB vector space. An extended and modified approach based on a...
详细信息
ISBN:
(纸本)9783642032011
In this paper a new and robust approach of skin detection is proposed. In the previous proposed system, we introduced a method for skin detection based on RGB vector space. An extended and modified approach based on a mixed color space is presented. The new approach overcomes the shortcoming of the previous one on detecting complex image's background. This has been achieved by using the HSV parameters to obtain accurate skin detection results. Furthermore an iterative technique is significantly useful for obtaining the more accurate and efficient method. This can be done by changing the vectors in two phases. Skin color has proven to be a useful cue for pre-process of face detection, localization and tracking. Image content filtering, content aware video compression and image color balancing applications can also benefit from automatic detection of skin in images. In order to evaluate our proposed approach we present the results of the experimental study. The results obtained are promising and show that our proposed approach is superior to the existing ones in terms of the number of pixels detected.
This paper summarizes the results obtained from the application of Data Mining techniques in order to detect usual behaviors in the use of computers. For that, based on real security event logs, two different clusteri...
详细信息
ISBN:
(纸本)9783642040900
This paper summarizes the results obtained from the application of Data Mining techniques in order to detect usual behaviors in the use of computers. For that, based on real security event logs, two different clustering strategies have been developed. On the one hand, a clustering process has been carried out taking into account the characteristics that define the events in a quantitative way. On the other hand, an approach based on qualitative aspects has been developed, mainly based on the interruptions among security events. Both approaches have shown to be effective and complementary in order to cluster security audit traits of Windows systems and extract useful behavior patterns.
In this paper, optimal switching signal as well as control input is designed for a general switched linear system using multi-level constrained genetic algorithms (MLCGA). Given any two states in the controllable subs...
详细信息
ISBN:
(纸本)9783540896180
In this paper, optimal switching signal as well as control input is designed for a general switched linear system using multi-level constrained genetic algorithms (MLCGA). Given any two states in the controllable subspace, the proposed approach automatically finds optimal switching signal and control input which steer the system from initial state to final state in a desired feasible time. From optimization perspective, this problem has several linear constraints such as controllability condition and desired dwell time as well as desired final time. Also, the problem is mixed-variable when the switching indices must be integer. The objective function may be nonlinear, multi-modal and non-analytical. Generally the problem must be solved in two levels. At the bottom level, an optimal control input is found for a candidate switching signal and at the top level an optimizer searches for optimal switching signal. To solve this complex problem, we propose Multi-Level Constrained Genetic Algorithms (MLCGA) which can solve this problem efficiently. As it is demonstrated by a simulation example, using the proposed approach an optimal switching signal with desired dwell time as well as optimal control input in the presence of actuator saturation can be efficiently designed.
This paper presents a new method for user identification based on hand images. Because in user identification the processing time is an important issue, we use only the hand boundary as a hand representation. Using th...
详细信息
ISBN:
(纸本)9783642032011
This paper presents a new method for user identification based on hand images. Because in user identification the processing time is an important issue, we use only the hand boundary as a hand representation. Using this representation, an alignment technique is used to make the index of corresponding features of different hands get the same index in the feature vector. To improve the classification performance a new ensemble-based method is proposed. This method uses feature transformation to create the needed diversity between base classifiers. In other words, first different sets of features are created by transforming the original features into new spaces where the samples are well separated, and then each base classifier is trained on one of these newly created features sets. The proposed method for constructing an ensemble of classifiers is a general method which may be used in any classification problem. The results of experiments performed to assess the presented method and compare its performance with other alternative classification methods are encouraging.
Multi-agent systems and mobile agents are enabling the deployment of applications in multi-domain environments. In these scenarios, different domains interact toward the same goal through resource sharing. As a result...
详细信息
ISBN:
(纸本)9783642004865
Multi-agent systems and mobile agents are enabling the deployment of applications in multi-domain environments. In these scenarios, different domains interact toward the same goal through resource sharing. As a result, there is the need to control the actions that an agent can perform in a foreign domain, with the only information of where it comes from and which roles does it hold in its own domain. However, this information will not be directly understandable as domains may not share the same role definitions. MedlGS is a multi-agent middleware for the medical data sharing between hospitals which take part of a multi-domain environment. In this paper, a distributed access control for MedlGS is presented. Based on attribute conversion, this authorization scheme proposes a solution with a minimum impact in the local access control systems of the hospitals.
Independent Component Analysis (ICA) is a method for separating the components as independent as possible, out of mixture of a number of mixed signals. There exist a number of statistical techniques based on informati...
详细信息
ISBN:
(纸本)9783540896180
Independent Component Analysis (ICA) is a method for separating the components as independent as possible, out of mixture of a number of mixed signals. There exist a number of statistical techniques based on information theoretic concepts and algebraic approaches for performing ICA. Neural algorithms derived from these approaches are used for extracting the independent components. Besides its application in signal processing such as speech signal separation, it has also successfully been used for face recognition. Analysis of face database has shown that the face images do possess negative and positive kurtosis values. This indicates that face images are of sub-Gaussian and super-Gaussian nature. This paper proposes a technique that deals with such type of face database. In this work, based on the assumption of the nonlinearity for sub-Gaussian sources, the nonlinearity for the super-Gaussian sources has been derived. A symmetric probability density function around the Gaussian distribution has been used for representing the sub and super-Gaussian sources. The proposed method has been successfully used for face recognition. Experimental results with the ORL face database have been presented. The results show the superiority of the proposed algorithm.
The development and management of end-user computing capability is needed to efficiently do the given tasks in an organizational computing environment. This study presents a 16-item tool that can effectively evaluate ...
详细信息
ISBN:
(纸本)9783642032011
The development and management of end-user computing capability is needed to efficiently do the given tasks in an organizational computing environment. This study presents a 16-item tool that can effectively evaluate end-user computing capability with an evaluation system, procedure and method. The utilization and application of the developed tool is confirmed by applying it to a case study and presenting its results.
This article presents a sensor data fusion method that can be used for map building. This takes into account the uncertainty inherent in sensor measurements. To this end, fuzzy logic operators are used to fuse the sen...
详细信息
ISBN:
(纸本)9783540896180
This article presents a sensor data fusion method that can be used for map building. This takes into account the uncertainty inherent in sensor measurements. To this end, fuzzy logic operators are used to fuse the sensory information and to update the fuzzy logic maps. The sensory information is obtained from a sonar array and a stereo vision system. Features are extracted using the Scale Invariant Feature Transform (SIFT) algorithm. The approach is illustrated using actual measurements from a laboratory robot.
暂无评论