Search

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.robot.2008.10.025 Byline: Ren C. Luo (a), Tung Y. Lin (b), Kuo L. Su (c) Abstract: Intelligent building can provide safety, convenience, efficiency and entertainment for life in the 21st century. The most importance role of the intelligent building is the security system. We develop a multi sensor-based intelligent security robot (ISR) that is widely employed in intelligent buildings. The intelligent security robot can detect abnormal and dangerous situations and notify users. The robot has the shape of cylinder and its diameter, height, and weight are 50 cm, 130 cm and 100 kg respectively. The function of the ISR contains six parts. There is the software development system; avoiding obstacle and motion planning system, image system, sensor system, remote supervise system and other systems. We develop a multi sensor-based sensor system in the ISR. We use multiple multisensor fusion algorithms to get an exact decision in the detection subsystem of the sensor system. There is an adaptive fusion method, a rule based method, and a statistical signal method. We demonstrate the remote supervisory system to control the ISR using a direct control mode and a behavior control mode. We think that the man-machine interface in a security robot system must have mobility and convenience. Therefore, we use a touch screen to display the system state, and design a general user interface (GUI) to service the user and visitors. The user can remotely control the appliance using a cell phone through a GSM modem, too. The appliance module can feedback reaction results to the user through a cell phone. Finally, we implement the fire detection system in the intelligent security robot (Chung-Cheng-I). If a fire occurs, the intelligent security robot can find out the fire source using the fire detection system. In intruder detection, we program the same scenario to detect the intruder using the intelligent security robot. The intelligent security robot transmits the message of the detection result to the user using a GSM modem for a fire event or intruder, and transmits the detection result to a client computer through the internet. Author Affiliation: (a) Intelligent Robotic & Automation Laboratory, Department of Electrical Engineering, National Taiwan University, 1, Sec. 4, Roosevelt Road, Taipei 106, Taiwan, ROC (b) Intelligent Automation Laboratory, Department of Electrical Engineering, National Chung Cheng University, 168 University Road, Ming-Hsiung, Chia-Yi, 621, Taiwan, ROC (c) Department of Electrical Engineering, National Yunlin University of Science & Technology, 123, Sec. 3, University Road, Touliu, Yunlin, 640, Taiwan, ROC

Most existing video-based target detection systems employ state-space models to keep track of an explicit number of individual targets. We introduce a framework for enhancing target detection in video by applying probabilistic models to the soft information in correlation outputs before threshoiding. We show how to efficiently compute arrays of posterior target probabilities for every position in the scene conditioned on all current and past frames of a video sequence. These arrays can then be thresholded in the typical manner to yield more reliable target detections. Because the framework avoids the formation of explicit tracks, it is well suited for handling scenes with unknown numbers of targets at unknown positions. Simulation results on forward-looking infrared (FLIR) video sequences show that our proposed framework can significantly reduce the false-alarm rate of a bank of correlation filters while requiring only a marginal increase in computation.

This paper deals with a new synthetic aperture radar (SAR) Processor based on a subspace detector designed for man-made target (MMT) detection. As MMTs are more accurately decribed by a set of canonical elements than with isotropic points, we develop a new algorithm which aims at using new models, instead of the isotropic point model commonly used in SAR processors. A subspace detector matched to canonical elements is included in the SAR processing. The implementation and the optimization of subspace detector SAR (SDSAR) algorithm is described. Simple examples of MMT detection in simulations and real data with a target hidden in a forest show the power of our approach. The SDSAR algorithm is shown to be the first robust and tractable algorithm relying on realistic scattering assumptions about the target.

Voice over Internet protocol (VoIP) flooding detection system (vFDS) is an online statistical anomaly detection framework for generating alerts based on abnormal variations in a selected hybrid collection of traffic flows. Findings reveal that vFDS is fast and accurate in detecting flooding attacks.

Particle impact noise detection (PIND) is a reliable screening technique specified by MIL-STD-883E. But MIL-STD-883E gives some test conditions which are not always appropriate. The test conditions of PIND are derived here based on dynamics. The upper limit frequency expression is obtained by a transforming equation. How vibration acceleration, vibration frequency, recovery coefficient, particle mass, and cavity height influence the particle's output energy is discussed. Moreover, the applicable range of test conditions of MIL-STD-883E are indicated and the best vibration frequency is derived by analyzing the relationship between the output power of vibrator and the particle's output energy. Some experiments are given.

A generalized likelihood ratio test (GLRT) is derived for adaptive detection of range and Doppler-distributed targets. The clutter is modeled as a spherically invariant random process (SIRP) and its texture component is range dependent (heterogeneous clutter). We suppose here that the speckle component covariance matrix is known or estimated thanks to a secondary data set. Thus, unknown parameters to be estimated are local texture values, the complex amplitudes and Doppler frequencies of all scattering centers. To do so, we use superresolution methods. The proposed detector assumes a priori knowledge on the spatial distribution of the target and has the precious property of having a constant false alarm rate (CFAR) with the assumption of a known speckle covariance matrix or by the use of frequency agility.

The joint successive interference cancellation technique (JSIC) is capable of jointly detecting consecutive users in an ordered set. Results suggest that the proposed JSIC is capable of achieving higher performance with an increase in complexity.

This paper describes the development of adaptive importance sampling (IS) techniques for estimating false alarm probabilities of detectors that use space-time adaptive processing (STAP) algorithms. Fast simulation using IS methods has been notably successful in the study of conventional constant false alarm rate (CFAR) radar detectors, and in several other applications. The principal objectives here are to examine the viability of using these methods for STAP detectors, develop them into powerful analysis and design algorithms and, in the long term, use them for synthesizing novel detection structures. The adaptive matched filter (AMF) detector has been analyzed successfully using fast simulation. Of two biasing methods considered, one is implemented and shown to yield good results. The important problem of detector threshold determination is also addressed, with matching outcome. As an illustration of the power of these methods, two variants of the square-law AMF detector that are thought to be robust under heterogeneous clutter conditions have also been successfully investigated. These are the envelope-law and geometric-mean STAP detectors. Their CFAR property is established and performance evaluated. It turns out the variants have detection performances better than those of the AMF detector for training data contaminated by interferers. In summary, the work reported here paves the way for development of advanced estimation techniques that can facilitate design of powerful and robust detection algorithms.

A network of sensors polled by a mobile agent, the SENMA paradigm is used for detection purposes, with both the remote nodes and the mobile agent implementing Wald's sequential tests. At optimality, the decentralized system overcomes a single supernode by orders of magnitude in terms of decision time, while only 30% of the sensors encountered by the mobile agent spend energy to reveal themselves.

This paper presents a new application of modern numerical algorithms, such as neural and probabilistic networks, for monitoring pressure system installations. Theoretical background as well as custom implementation of the algorithms is presented, and a complete system for monitoring high-pressure, fluid-filled (HPFF) cables is described. Index Terms--Dielectric fluid leak detection, neural networks, pipe type cables, probabilistic networks.

Cough is a common symptom of many respiratory diseases. The evaluation of its intensity and frequency of occurrence could provide valuable clinical information in the assessment of patients with chronic cough. In this paper we propose the use of hidden Markov models (HMMs) to automatically detect cough sounds from continuous ambulatory recordings. The recording system consists of a digital sound recorder and a microphone attached to the patient's chest. The recognition algorithm follows a keyword-spotting approach, with cough sounds representing the keywords. It was trained on 821 min selected from 10 ambulatory recordings, including 2473 manually labeled cough events, and tested on a database of nine recordings from separate patients with a total recording time of 3060 min and comprising 2155 cough events. The average detection rate was 82 % at a false alarm rate of seven events/h, when considering only events above an energy threshold relative to each recording's average energy. These results suggest that HMMs can be applied to the detection of cough sounds from ambulatory patients. A postprocessing stage to perform a more detailed analysis on the detected events is under development, and could allow the rejection of some of the incorrectly detected events. Index Terms--Automatic detection, cough counts, cough monitor, hidden Markov models.

Abstract: This study presents a robust audio retrieval method and discusses its control strategy. In the method, the retrieval target is divided into short segments, each segment is searched respectively [...]

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.compeleceng.2005.07.004 Byline: OAuz Kucur (a), Guillermo E. Atkin (b) Keywords: Wavelets; Multi-rate/multi-media communication; Code division multiple access (CDMA); Multi-user detection Abstract: Recently, we have proposed a new multi-rate/multi-media system called wavelet based scale-code division multiple access (W/S-CDMA) that depends on the code, time and scale orthogonality introduced by pseudo-noise (PN) sequences, and wavelets. Wavelets are used as an orthogonal set of symbols for signaling, and their orthogonality is exploited over scale and time. In this system, the channel is divided into different scales, and each scale into time slots. In addition, the PN sequences are used in each scale to accommodate multiple users. In other words, each user encodes its successive information symbols with time-shifted replicas of the same basic wavelet in a specific scale and spreads its scaled and translated wavelets with its PN sequence. The finer the scale used, more symbols are transmitted. In this paper, we analyze the performance of Haar wavelet based S-CDMA (HW/S-CDMA) over a synchronous additive white Gaussian noise (AWGN) channel using a decorrelating multi-user detector. Results reveal that HW/S-CDMA holds promise since the users of HW/S-CDMA can achieve variable and higher data rates than those of direct sequence (DS)-CDMA for a similar bit error rate performance when real-valued PN sequences are used. However, HW/S-CDMA achieves better performance than DS-CDMA when complex-valued PN sequences are used. In addition, for all rates the same performance is achieved in HW/S-CDMA and the multi-user detector has no processing delay for different rates and has the same features as the standard decorrelating detector. Because of the reuse capability introduced by the scales, HW/S-CDMA is also capable of employing many available PN sequences from the optimal PN sequence families with limited number of sequences such as Kasami, Bent, etc. Author Affiliation: (a) Department of Electronics Engineering, Gebze Institute of Technology, P.K. 141, 41400 Gebze-Kocaeli, Turkey (b) Department of Electrical and Computer Engineering, Illinois Institute of Technology, 3301 S. Dearborn St., Chicago, IL 60616, USA Article History: Received 4 November 2004; Revised 1 June 2005; Accepted 25 July 2005

In this second part we deal with the problem of detecting subspace random signals against correlated non-Gaussian clutter modeled by the compound-Gaussian distribution. In the first part of the paper, we derived the optimum Neyman-Pearson (NP) detector, the generalized likelihood ratio test (GLRT), and a constant false-alarm rate (CFAR) detector; we also provided some interesting interpretations of them. In this second part, these detectors are tested against both simulated data and measured high resolution sea clutter data to investigate the dependence of their performance on the various clutter and signal parameters. Numerical examples concern a space-time adaptive processing (STAP) scenario and a ground-based surveillance radar system scenario.

Condition-based maintenance (CBM) of industrial equipment is generally recognized as being the most cost-effective means for improving equipment availability. However, prerequisite to successful implementation of CBM is a reliable detector of failing components. One such detector, termed the effective negative-sequence impedance, had previously been identified as an indicator of induction motor stator winding degradation. However, a limitation of this detector is that it may not change in a predicable manner for extremely low levels of deterioration. Presented in this paper is an experimental investigation of a technique for online detection of induction motor stator winding degradation that addresses this difficulty. It begins with a brief description of the detectors, followed by a detailed description of the experimental setup, the experiments conducted, and results. Index Terms--Conditioning monitoring, induction motors, stator winding fault.

A detector based on a model with signal components comprising radiant thermal energy from the small target or the intense, highly structure background, is proposed. The resulting statistics were useful in enhancement of the target and in suppression of the cluttered background. Stochastic approximation techniques were used to estimate system parameters.

General zero-crossing-based discontinuity detectors in two dimensions, which include Marr-Hildreth, residual difference of Gaussians and other detectors, are studied and mathematically justified. An optimal detector which maximizes the signal-to-noise ratio (SNR) and the localization error is parameterized by the size of the support. Post-processing has yet to be fully exploited for discontinuity detection.

Byline: Tak-Chung Fu, Chung-Leung Lui Most of the existing commercial Network Intrusion Detection System (NIDS) products are signature-based but not adaptive. In this paper, an adaptive NIDS using data mining technology is developed. Data mining approaches are used to accurately capture the actual behaviour of network traffic, and the portfolio mined is useful for differentiating 'normal' and 'attack' traffics. On the other hand, most of the current researches use only one engine for detection of various attacks; the proposed system, which is constructed by a number of agents, is totally different in both training and detecting processes. Each of the agents has its own strength in capturing a kind of network behaviour and hence the system has strength in detecting different types of attack. In addition, its ability in detecting new types of attack and its higher tolerance to fluctuations were shown. The experimental results showed that the frequent patterns mined from the audit data could be used as reliable agents, which outperformed the traditional signature-based NIDS.

The impact of microsensors on different areas are explained in detail. The role of sensors include connecting people, environment to computers and controls.

Exponential mixture probability density functions (pdfs) are shown to be useful models of radar sea clutter. The variability of certain parameters leads to estimation error and degredation in the performance of detection algorithms derived from this model. Robust implementations are introduced by assuming that parameters are known within certain intervals and selecting values to prevent an excessive number of false alarms. An empirical study demonstrates an average 6-9 dB gain in comparison with a constant false-alarm rate (CFAR) processor.