Loading...
Search for:
false-alarms
0.003 seconds
Total 24 records
False alarm reduction by improved filler model and post-processing in speech keyword spotting
, Article IEEE International Workshop on Machine Learning for Signal Processing, 18 September 2011 through 21 September 2011, Beijing ; 2011 ; 9781457716232 (ISBN) ; Sameti, H ; Mohammadi, S. H ; IEEE; IEEE Signal Processing Society ; Sharif University of Technology
2011
Abstract
This paper proposes four methods for improving the performance of keyword spotting (KWS) systems. Keyword models are usually created by concatenating the phoneme HMMs and garbage models consist of all phonemes HMMs. We present the results of investigations involving the use of skips in states of keyword HMMs and we focus on improving the hit ratio; then for false alarm reduction in KWS we model the words that are similar to keywords and we create HMMs for highly frequent words. These models help to improve the performance of the filler model. Two post-processing steps based on phoneme and word probabilities are used on the results of KWS to reduce the false alarms. We evaluate the...
Short-term prediction of medium-and large-size earthquakes based on Markov and extended self-similarity analysis of seismic data
, Article Lecture Notes in Physics ; Volume 705 , 2006 , Pages 281-301 ; 00758450 (ISSN) ; 3540353739 (ISBN); 9783540353737 (ISBN) ; Sahimi, M ; Ghasemi, F ; Kaviani, K ; Allamehzadeh, M ; Peinke, J ; Mokhtari, M ; Vesaghi, M ; Niry, M. D ; Bahraminasab, A ; Tabatabai, S ; Fayazbakhsh, S ; Akbari, M ; Sharif University of Technology
2006
Abstract
We propose a novel method for analyzing precursory seismic data before an earthquake that treats them as a Markov process and distinguishes the background noise from real fluctuations due to an earthquake. A short time (on the order of several hours) before an earthquake the Markov time scale tM increases sharply, hence providing an alarm for an impending earthquake. To distinguish a false alarm from a reliable one, we compute a second quantity, T1, based on the concept of extended self-similarity of the data. T1 also changes strongly before an earthquake occurs. An alarm is accepted if both tM and T1 indicate it simultaneously. Calibrating the method with the data for one region provides a...
CFAR adaptive threshold for ESM receiver with logarithmic amplification
, Article Signal Processing ; Volume 84, Issue 1 , 2004 , Pages 41-53 ; 01651684 (ISSN) ; Nayebi, M. M ; Sharif University of Technology
2004
Abstract
An adaptive threshold with constant false alarm rate (CFAR) property is proposed to be used in a channelized electronic support measures (ESM) system with logarithmic video amplification. For this purpose, two CFAR processors are designed which are in fact modified excision (MEx) and adaptive MEx (AMEx) processors, previously presented by authors, but modified for the logarithmic amplification case. In the case of relatively small variations in the noise power, MEx-LOG/CFAR is proposed. This processor exhibits a good robustness against interfering pulses, which cause the major difficulty in the estimation of noise statistics. In the case of relatively large variations in the noise power,...
Prediction of life-threatening heart arrhythmias using obstructive sleep apnoea characteristics
, Article 27th Iranian Conference on Electrical Engineering, ICEE 2019, 30 April 2019 through 2 May 2019 ; 2019 , Pages 1761-1764 ; 9781728115085 (ISBN) ; Rasoulinezhad, S ; Shamsollahi, M. B ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2019
Abstract
False alarms ratios of up to 86% in Intensive Care Units (ICU) decrease quality of care, impacting both clinical staff and patients through slowing off response time and noise tribulation. We present a novel algorithm to predict heart arrhythmias in ICUs. We focus on five life-threatening arrhythmias: Asystole, Extreme Bradycardia, Extreme Tachycardia, Ventricular Tachycardia, and Ventricular Fibrillation. The algorithm is based on novel features using only 12 seconds of one ECG channel to predict the arrhythmias. Our new feature sets include different SQI and physiological features and the features used in obstructive sleep apnoea detection. We also proposed a new morphological...
Historical Alert Analysis in Host-based Intrusion Detection
, M.Sc. Thesis Sharif University of Technology ; Abolhassani, Hassan (Supervisor)
Abstract
In the last decade, Intrusion Detection Systems has attracted attention due to their importance in network security, but still they've shortcomings. Generating a lot of low level alerts is the main problem. Many of these alerts are actually false positives. One suggested solution is Alert Correlation Analysis. Because of false positives alert correlation techniques are not able to build accurate scenarios, but the accuracy of alerts can be verified with the aid of the information logged in the host systems. In this dissertation after surveying the current alert correlation techniques, a model will be introduced to effectively verify the generated alerts and to apply correlation techniques to...
Robust Wiener filter-based time gating method for detection of shallowly buried objects
, Article IET Signal Processing ; 2021 ; 17519675 (ISSN) ; Behnia, F ; Shokouhmand, A ; Shaker, G ; Sharif University of Technology
Institution of Engineering and Technology
2021
Abstract
A robust method for ultra-wideband (UWB) imaging of buried shallow objects based on time gating, Wiener filtering, as well as constant false alarm rate (CFAR) is proposed. Moreover, it is demonstrated that Wiener filtering can be used as a clutter removal tool in UWB signal applications. Basically, the problem with time gating method is that the length of the timing window for unknown targets cannot be determined accurately in advance. In fact, it is a blind methodology and some targets can be missed due to a lack of pre-knowledge about their depth. Imprecise window length selection leads to missing some parts of the target signals along with the clutter, which in turn increases the missed...
A new technique in passive coherent radar signal processing
, Article EURAD 2005 - 2nd European Radar Conference, Paris, 6 October 2005 through 7 October 2005 ; Volume 2005 , 2005 , Pages 149-151 ; 2960055136 (ISBN); 9782960055139 (ISBN) ; Sedghi, V ; Nayebi, M. M ; Sharif University of Technology
IEEE Computer Society
2005
Abstract
In this paper, we focus on adaptive and wavelet based systems in radar signal processing, and a new algorithm to Doppler compensation is developed. The new wavelet-based method for ambiguity surface smoothing that applies the three dimensions dual tree wavelet transform and adapt constant false alarm rate, is proposed. The model captures the dependence between a wavelet coefficient and its parent. Simulation results show that new approach is better than older algorithms. We have simulated this new method for bistatic FM-based passive coherent receiver
Multi-antenna assisted spectrum sensing in spatially correlated noise environments
, Article Signal Processing ; Volume 108 , December , 2015 , Pages 69-76 ; 01651684 (ISSN) ; Malek Mohammadi, M ; Babaie Zadeh, M ; Skoglund, M ; Sharif University of Technology
Elsevier
2015
Abstract
A significant challenge in spectrum sensing is to lessen the signal to noise ratio needed to detect the presence of primary users while the noise level may also be unknown. To meet this challenge, multi-antenna based techniques possess a greater efficiency compared to other algorithms. In a typical compact multi-antenna system, due to small interelement spacing, mutual coupling between thermal noises of adjacent receivers is significant. In this paper, unlike most of the spectrum sensing algorithms which assume spatially uncorrelated noise, the noises on the adjacent antennas can have arbitrary correlations. Also, in contrast to some other algorithms, no prior assumption is made on the...
Quantization effect of the parameter space on the performance of Hough detector
, Article 4th Microwave and Radar Week MRW-2010 - 11th International Radar Symposium, IRS 2010 - Conference Proceedings, 16 June 2010 through 18 June 2010 ; June , 2010 , Pages 457-460 ; 9789955690184 (ISBN) ; Moqiseh, A ; Nayebi, M. M ; Sharif University of Technology
2010
Abstract
Hough transform is proposed in literature as an effective technique for target detection in search radars. However, this detector has a disadvantage when the received SNR of radar is low. Although the distribution of noise power in the data space is often uniform and all processing cells of this space approximately receive the same power of noise, after transforming these cells to the Hough parameter space, this distribution will not remain uniform. In other words, noise power in some regions of the parameter space is greater than the others. Therefore, false alarm increases in these regions. Selecting a greater threshold to reduce the number of false detections will result a lower...
A new spectrum sensing method using output analysis of the PFD
, Article IEEE Transactions on Circuits and Systems II: Express Briefs ; Volume 60, Issue 6 , 2013 , Pages 366-370 ; 15497747 (ISSN) ; Fotowat Ahmady, A ; Forooraghi, K ; Atlasbaf, Z ; Sharif University of Technology
2013
Abstract
In this brief, a new blind spectrum sensing method is proposed based on frequency comparison using a phase frequency detector (PFD). The PFD output patterns are utilized in a way to sense the spectrum with no knowledge of incoming signals, noise, or channel parameters. The detection and false alarm error probabilities are analytically calculated for additive white Gaussian noise and sine-wave input and are simulated for different inputs. It is shown that the required detection and false alarm probabilities can be achieved by changing the system parameters. The results show that the proposed method has lower complexity and outperforms the previous single-antenna blind method over flat fading...
KNNDIST: A non-parametric distance measure for speaker segmentation
, Article 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 ; Volume 3 , 2012 , Pages 2279-2282 ; 9781622767595 (ISBN) ; Sameti, H ; Langarani, M. S. E ; Tavanaei, A ; Sharif University of Technology
2012
Abstract
A novel distance measure for distance-based speaker segmentation is proposed. This distance measure is nonparametric, in contrast to common distance measures used in speaker segmentation systems, which often assume a Gaussian distribution when measuring the distance between two audio segments. This distance measure is essentially a k-nearest-neighbor distance measure. Non-vowel segment removal in preprocessing stage is also proposed. Speaker segmentation performance is tested on artificially created conversations from the TIMIT database and two AMI conversations. For short window lengths, Missed Detection Rated is decreased significantly. For moderate window lengths, a decrease in both...
Image steganalysis based on SVD and noise estimation: Improve sensitivity to spatial LSB embedding families
, Article IEEE Region 10 Annual International Conference, Proceedings/TENCON, 21 November 2011 through 24 November 2011, Bali ; 2011 , Pages 1266-1270 ; 9781457702556 (ISBN) ; Farhat, F ; Ghaemmaghami, S ; Sharif University of Technology
2011
Abstract
We propose a novel image steganalysis method, based on singular value decomposition and noise estimation, for the spatial domain LSB embedding families. We first define a content independence parameter, DS, that is calculated for each LSB embedding rate. Next, we estimate the DS curve and use noise estimation to improve the curve approximation accuracy. It is shown that the proposed approach gives an estimate of the LSB embedding rate, as well as information about the existence of the embedded message (if any). The proposed method can effectively be applied to a wide range of the image LSB steganography families in spatial domain. To evaluate the proposed scheme, we applied the method to a...
Acoustical gas-leak detection in the presence of multiple reflections, dispersion, and uncorrelated noise using optimized residual complexity
, Article Journal of the Acoustical Society of America ; Volume 140, Issue 3 , 2016 , Pages 1817-1827 ; 00014966 (ISSN) ; Amjadi, A ; Bahrampour, A. R ; Ravanbod, H ; Tofighi, S ; Sharif University of Technology
Acoustical Society of America
2016
Abstract
Precise acoustical leak detection calls for robust time-delay estimates, which minimize the probability of false alarms in the face of dispersive propagation, multiple reflections, and uncorrelated background noise. Providing evidence that higher order modes and multi-reflected signals behave like sets of correlated noise, this work uses a regression model to optimize residual complexity in the presence of both correlated and uncorrelated noise. This optimized residual complexity (ORC) is highly robust since it takes into account both the level and complexity of noise. The lower complexity of the dispersive modes and multiple reflections, compared to the complexity of the plane mode, points...
Critical object recognition in millimeter-wave images with robustness to rotation and scale
, Article Journal of the Optical Society of America A: Optics and Image Science, and Vision ; Volume 34, Issue 6 , 2017 , Pages 846-855 ; 10847529 (ISSN) ; Ghojogh, B ; Faezi, S ; Shabany, M ; Sharif University of Technology
OSA - The Optical Society
2017
Abstract
Locating critical objects is crucial in various security applications and industries. For example, in security applications, such as in airports, these objects might be hidden or covered under shields or secret sheaths. Millimeter-wave images can be utilized to discover and recognize the critical objects out of the hidden cases without any health risk due to their non-ionizing features. However, millimeter-wave images usually have waves in and around the detected objects, making object recognition difficult. Thus, regular image processing and classification methods cannot be used for these images and additional pre-processings and classification methods should be introduced. This paper...
Non-coherent radar CFAR detection based on goodness-of-fit tests
, Article IET Radar, Sonar and Navigation ; Volume 1, Issue 2 , 2007 , Pages 98-105 ; 17518784 (ISSN) ; Gini, F ; Nayebi, M. M ; Greco, M ; Sharif University of Technology
2007
Abstract
This paper considers the problem of constant false alarm rate (CFAR) detection of radar targets using multiple observations. In the Gaussian clutter scenario, the structure of the optimum (uniformly most powerful) CFAR detector is rather simple, but when the clutter is heavy-tailed, that is non-Gaussian distributed, the derivation of the optimal detector becomes infeasible. For this latter relevant case, a new CFAR algorithm is porposed based on goodness-of-fit (GoF) tests. The performance of the proposed detector is numerically investigated through Monte Carlo simulations assuming heavy-tailed Weibull and Lognormal distributed clutter. Numerical results shown that, in heavy-tailed clutter...
Detection of a band-limited signal using an orthonormal, fully-decimated filter-bank
, Article Scientia Iranica ; Volume 14, Issue 6 , 2007 , Pages 555-565 ; 10263098 (ISSN) ; Tadaion, A. A ; Nayebi, M. M ; Aref, M. R ; Sharif University of Technology
Sharif University of Technology
2007
Abstract
In this paper, two methods are proposed for the detection of a band-limited signal in unknown variance white Gaussian noise. The complex amplitude and the frequency of the signal and the noise variance are assumed as unknown parameters. Using wavelet concepts, an orthonormal, fully-decimated filter-bank is employed to decompose the signal into its subband components. It is shown that, in this process, the noise is also decomposed into orthonormal zero-mean components. In the output, if a band-limited target signal is present, the respective single subband component (or two components in marginal cases) containing the target signal presents a non-zero mean. The presence of a non-zero mean...
Fast and high-resolution PCL radar detection in noisy environment
, Article 2nd Microwave and Radar Week in Poland - International Radar Symposium, IRS 2006, Krakow, 24 May 2006 through 26 May 2006 ; 2006 ; 8372076219 (ISBN); 9788372076212 (ISBN) ; Emadi, M ; Mousavi, M. R ; Jafargholi, A ; Nayebi, M. M ; Sharif University of Technology
2006
Abstract
Multiple target detection in conventional PCL (Passive Coherent Location) radar systems by means of Ambiguity Function Processing and without any powerful algorithm is impossible. Presented Gradual Clean Algorithm (GCA) is a new and simple method, which could provide the perfect detection in noisy environment and heavy clutter condition up to SNR=-15 dB and SCR=-100 dB (clutter is assumed as a distributed target with large RCS). Determining the number of real targets and keeping the false alarm probability approximately constant are the presented algorithm capabilities
A hybrid method of artificial neural networks and simulated annealing in monitoring auto-correlated multi-attribute processes
, Article International Journal of Advanced Manufacturing Technology ; Volume 56, Issue 5-8 , 2011 , Pages 777-788 ; 02683768 (ISSN) ; Akbari Nasaji, S ; Sharif University of Technology
Abstract
The quality characteristics of both manufacturing and service industries include not only the variables but the attributes as well. While a substantial research have been performed on auto-correlated variables, little attempt has been fulfilled for auto-correlated attributes. Ignoring the imbedded autocorrelation structure in constructing control charts cause not only the in-control run length to decrease, but also the false alarms to increase. To overcome these shortcomings, in this research, an autoregressive vector first models the autocorrelation structure of the process data. Then, a modified Elman neural network is developed to generate simulated data using the ARTA algorithm. Next, a...
Artificial neural network in applying multi attribute control chart for AR processes
, Article 2010 The 2nd International Conference on Computer and Automation Engineering, ICCAE 2010, 26 February 2010 through 28 February 2010, Singapore ; Volume 5 , 2010 , Pages 216-220 ; 9781424455850 (ISBN) ; Akbari Nasaji, S ; Sharif University of Technology
2010
Abstract
Quality characteristics are subject of both manufacturing and service industries, which include not only the variables but the attributes as well. In Quality Control area substantial research has been done for Auto-correlated variables; however, no attempt was done for Auto-correlated attributes. Ignoring the autocorrelation structure in constructing control charts cause the in-control run length to decrease, and the false alarms to increase as such. In this article we develop a new methodology based upon the modified Elman neural network capabilities to overcome this problem. Moreover, instead of back propagation, simulated annealing is suggested as an alternative training technique that is...
AdaBoost-based face detection in color images with low false alarm
, Article ICCMS 2010 - 2010 International Conference on Computer Modeling and Simulation, 22 January 2010 through 24 January 2010, Sanya ; Volume 2 , 2010 , Pages 107-111 ; 9780769539416 (ISBN) ; Kasaei, S ; Sharif University of Technology
2010
Abstract
In this paper, we have proposed a new face detection method which combines the AdaBoost algorithm with skin color information and support vector machine (SVM). First, a cascade classifier based on AdaBoost is used to detect faces in images. Due to noise and illumination changes some nonfaces might be detected too, therefore we have used a skin color model in the YCbCr color space to remove some of the detected nonfaces. Finally, we have utilized SVM to detect faces more accurately. Experimental results show that the performance of the proposed method is higher than the basic AdaBoost in the sense of detecting fewer nonfaces