We have developed and continue to enhance automated intelligent software that performs the tasks and decision making which now occurs by the personnel manning watch stations in the Combat Direction Center (CDC) and Ta...
详细信息
ISBN:
(纸本)3540325298
We have developed and continue to enhance automated intelligent software that performs the tasks and decision making which now occurs by the personnel manning watch stations in the Combat Direction Center (CDC) and Task Force Combat Center (TFCC), on-board aircraft carriers and other Navy ships. Integrating information from various sources in a combat station is a complex task;disparate sources of information from radars, sonars, and other sensors are obtained by watch station surveillance guards, who must interpret it and relay it up the chain of command. The intelligent Identification Software Module (IISM) alleviates some of the burden placed on battle commanders by automating tasks like management of historical data, disambiguating multiple track targets, assessing threat levels of targets, and rejecting improbable data. We have knowledge engineered current CDC/TFCC experts and designed IISM using C++ and SimBionic, a visual AI development tool. IISM uses multiple soft computing techniques including Baysian inference and fuzzy reasoning. IISM is interfaced to the Advanced Battle Station (ABS) for use on many US Navy sea vessels.
In an object recognition task where an image is represented as a constellation of image patches, often many patches correspond to the cluttered background. If such patches are used for object class recognition, they w...
详细信息
ISBN:
(数字)9783540375982
ISBN:
(纸本)354037597X
In an object recognition task where an image is represented as a constellation of image patches, often many patches correspond to the cluttered background. If such patches are used for object class recognition, they will adversely affect the recognition rate. In this paper, we present a statistical method for selecting the image patches which characterize the target object class and are capable of discriminating between the positive images containing the target objects and the complementary negative images. This statistical method select those images patches from the positive images which, when used individually, have the power of discriminating between the positive and negative images in the evaluation data. Another contribution of this paper is the part-based probabilistic method for object recognition. This Bayesian approach uses a common reference frame instead of reference patch to avoid the possible occlusion problem. We also explore different feature representation using PCA an 2D PCA. The experiment demonstrates our approach has outperformed most of the other known methods on a popular benchmark data set while approaching the best known results.
The 2-dimensional Hilbert scan (HS) is a one-to-one mapping between 2-dimensional (2-D) space and one-dimensional (1-D) space along the 2-D Hilbert curve. Because Hilbert curve can preserve the spatial relationships o...
详细信息
ISBN:
(数字)9783540375982
ISBN:
(纸本)354037597X
The 2-dimensional Hilbert scan (HS) is a one-to-one mapping between 2-dimensional (2-D) space and one-dimensional (1-D) space along the 2-D Hilbert curve. Because Hilbert curve can preserve the spatial relationships of the patterns effectively, 2-D HS has been studied in digital image processing actively, such as compressing image data, pattern recognition, clustering an image, etc. However, the existing HS algorithms have some strict restrictions when they are implemented. For example, the most algorithms use recursive function to generate the Hilbert curve, which makes the algorithms complex and takes time to compute the one-to-one correspondence. And some even request the sides of the scanned rectangle region must be a power of two, that limits the application scope of HS greatly. Thus, in order to improve HS to be proper to real-time processing and general application, we proposed a Pseudo-Hilbert scan (PHS) based on the look-up table method for arbitrarily-sized arrays in this paper. Experimental results for both HS and. PHS indicate that the proposed generalized Hilbert scan algorithm also reserves the good property of HS that the curve preserves point neighborhoods as much as possible, and gives competitive performance in comparison with Raster scan.
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 ...
详细信息
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 act,ion 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 bidden 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.
Network-based intrusion detection systems (IDSs) are designed to monitor potential attacks in network infrastructures. IDSs trigger alerts of potential attacks in network security. These alerts are examined by securit...
详细信息
Network-based intrusion detection systems (IDSs) are designed to monitor potential attacks in network infrastructures. IDSs trigger alerts of potential attacks in network security. These alerts are examined by security analysts to see if they are benign or attacks. However these alerts consist of high volumes of false positives, which are triggered by suspicious but normal, benign connections. These high volumes of false positives make manual analysis of the alerts difficult and inefficient in real-time detection and response. In this paper, we discuss briefly the significance of false positives and their impact on intrusion detection and response. Then we propose a novel approach for an efficient intelligent detection and response through the reduction of false positives. The intelligent strategy consists of technique with multiple zones for isolation and interaction with the hosts from which the packets were sent in real-time. We propose multiple feedback methods to the IDS monitor and database to indicate the status of the alerts. These innovative approaches, using NQC and feedback mechanisms enhance the capability of the IDS to detect threats and benign attacks. This is accomplished by applying adaptive rules to the alert filters and policies of the IDS network sensors
In this paper we argue for UML-based metamodeling and pattern-based graph transformation techniques in computer-based systems development through an illustrative example from the domain of embedded systems. We present...
详细信息
In this paper we argue for UML-based metamodeling and pattern-based graph transformation techniques in computer-based systems development through an illustrative example from the domain of embedded systems. We present a tool that uses advanced graph-rewriting techniques to generate a schedule that satisfies hard real-time constraints for multi-modal systems. The input is a time-triggered system specification (using the Giotto language); the output is an instruction sequence for the E-machine: a virtual machine for hard real-time embedded systems. The resulting model may be refined into a) system implementations (E-code programs) through a trivial synthesis process and b) development-time analysis models expressing the properties of the system implemented over different execution platforms. Furthermore, we identify the next steps to be taken towards generating analysis models using explicit platform models
暂无评论