Probability Of Correct Detection Research Articles

Adaptive processing of signals on a background of clutter and noise

Suppression of clutter and noise is one of the most important problems of radio location signals processing. It is shown proposed algorithm of division of processing vector into sub-vectors of non-recursive noise suppression filter allows to increase average by signals Doppler velocities probability of correct detection on 6–28% in compare to known non-adaptive whitening filter. Proposed algorithm does not require the noise correlation matrix inversion in case of modification of power of clutter noise that reduces computational burden 1.8–7 times on its realization in compare to optimal adaptive algorithm.

A Target Guided Subband Filter for Acoustic Event Detection in Noisy Environments Using Wavelet Packets

This paper deals with acoustic event detection (AED), such as screams, gunshots, and explosions, in noisy environments. The main aim is to improve the detection performance under adverse conditions with a very low signal-to-noise ratio (SNR). A novel filtering method combined with an energy detector is presented. The wavelet packet transform (WPT) is first used for time-frequency representation of the acoustic signals. The proposed filter in the wavelet packet domain then uses a priori knowledge of the target event and an estimate of noise features to selectively suppress the background noise. It is in fact a content-aware band-pass filter which can automatically pass the frequency bands that are more significant in the target than in the noise. Theoretical analysis shows that the proposed filtering method is capable of enhancing the target content while suppressing the background noise for signals with a low SNR. A condition to increase the probability of correct detection is also obtained. Experiments have been carried out on a large dataset of acoustic events that are contaminated by different types of environmental noise and white noise with varying SNRs. Results show that the proposed method is more robust and better adapted to noise than ordinary energy detectors, and it can work even with an SNR as low as -15 dB. A practical system for real time processing and multi-target detection is also proposed in this work.

Actuator Fault Diagnosis in a Heat Exchanger based on Classifiers - A Comparative Study

Five different Fault Detection and Isolation (FDI) approaches are compared using the same experimental system: an industrial shell and tube Heat Exchanger (HE). The FDI approaches are classified into two major groups: the Artificial Neural Networks (ANN), the Naive Bayes and the k-Nearest Neighbor (k-NN) classifier are process history-based methods, while the Fuzzy Logic (FL) system and the Fault Decision Tree (FDT) are considered qualitative model-based methods. The Receiver Operating Characteristic curve and the confusion matrix have been used to compare the detection and classification performance when actuators fail. Experimental results show that the k-NN method reached the lowest total error of fault classification (12.4%) using cross-validation while the FDT method obtained several misclassifications (46.2% of error). In the fault detection stage, k-NN presented the best performance assuming a high probability of correct detection (90 %) with the lowest possible probability of false alarms (13 %); however, the ANN method showed the highest probability of correct detection (93 %) but a poor result in the false alarm rate (31%), while the FL method obtained the minimum false alarm rate (9%). Advantages and disadvantages of each FDI approach are highlighted in a particular context for being implemented in a chemical process.

How Business Community Institutions Can Help Fight Corruption

This paper considers the possibility of collective action by the business community to counter corruption in the award of government licenses and contracts. The analogy is with contract enforcement institutions studied by economic historians and contract law scholars. The institution in this context comprises a no-bribery norm, a community system to detect violations, and a multilateral ostracism penalty upon conviction in a community tribunal. The requirements such an institution must meet if it is to be effective are analyzed. It is shown that an institution of sufficient quality -- combining probability of correct detection and severity of punishment -- can eliminate bribery. If the private institution is not sufficiently good, then in conjunction with the state's formal apparatus it reduces the level of bribes demanded, but increases the probability of winning the license or contract through bribery. An improvement in the government's formal anti-corruption mechanism, holding the private institution constant, reduces both the level of bribes and the probability of success through bribery. The two institutions together are shown to achieve substantially better outcomes than either can on its own.

A Sensor Fault Diagnosis Scheme for a DC/DC Converter used in Hybrid Electric Vehicles

With the extensive use of power converters in modern hybrid vehicles, rises the need for efficient methods of condition monitoring and fault diagnosis to ensure the reliability of the automotive electrical power system. This paper addresses detection and isolation of sensor faults in a DC/DC power converter system interfacing the main energy storage unit and the AC drive in a hybrid electric vehicle. A residual-based fault diagnosis scheme that timely detects and localizes sensor faults in the examined system is designed. Residual signals are derived from comparison between estimates generated by a bank of extended Kalman filters and real measurements obtained from a hardware prototype of the power converter. The generalized likelihood ratio test is utilized in a statistical hypothesis testing framework to evaluate the residuals and detect the occurrence of sensor faults. The receiver operating characteristic curve is then employed to optimize the value of the detection threshold and the sliding window width of the statistical test. The proposed algorithm is tested on data obtained from simulated and real measurements with faults injected on the converter sensors. The results obtained promise maximum probability of correct detection and minimum false alarm rate.

Statistical estimation of the probability of the correct substance detection in FTIR spectroscopy

In the present paper a problem of substance identification in FTIR (Fourier transform infrared) spectroscopy is considered. The spectral library hitlist search is chosen as the main tactic. In the paper the Pearson correlation coefficient as a similarity criterion between two spectra is suggested. A situation when one of the measured spectra has an additive narrowband white noise component with a Gaussian distribution is considered. In that case the probability density of the correlation coefficient is found. A concept of the probability of correct detection is proposed and a theoretical expression is found. In addition, we consider a boundary correlation coefficient search algorithm, which allows one to find a boundary value providing the required correct detection. Computational experiments have shown the applicability of the method.

Secondary Network Connectivity of <italic>Ad Hoc</italic> Cognitive Radio Networks

This letter investigates the connectivity of large-scale ad hoc cognitive radio networks (CRNs). Considering correct detection and false alarm probabilities ( P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</sub> and P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</sub> , we derive in closed-form the thinned density of active secondary users (SUs) in a secondary network. We show the active-probability and detectable radius of primary users (PUs) have a significant impact on the density of active SUs. Moreover, we find that increasing P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</sub> of SUs considerably decreases the node density of active SUs. The connectivity of the secondary network is further analysed with the continuum percolation theory. Given the critical density of the secondary network without the impact of PUs, the critical density of the secondary network coexisting with PUs is estimated analytically. Simulations confirm our analysis.

Evaluation of ISCCP cloud amount with MODIS observations

The goal of the International Satellite Cloud Climatology Project (ISCCP) is to provide global cloud amount statistics for atmospheric radiation flux modeling, which is a key element of climate change studies. However, ISCCP estimates rely on two spectral channels only, while the most advanced satellite sensors offer over 20 spectral bands, and thus a higher probability of correct cloud detection. We validated the accuracy of ISCCP mean monthly cloud amount statistics using the state-of-the-art, 36-spectral channel Moderate-resolution Imaging Spectroradiometer (MODIS) instrument aboard the Terra and Aqua satellites. Based on the MODIS Level 2 Cloud Mask we developed a dedicated Level 3 product for Central Europe (2004–2009). For the first time, MODIS swath data were projected onto an ISCCP equal-area grid, which guaranteed an exact geometrical agreement between both climatologies. Results showed that there was a close correlation between ISCCP and MODIS data (ρ=0.872, α=0.99), especially at warmer part of the year (ρ≥0.940, α>0.99). However, ISCCP estimations were found to be unreliable in wintertime when surface was covered with snow. The presence of snow resulted in a significant underestimate of cloud amount by 0.45 for individual ISCCP grid boxes. Our results suggest that MODIS cloud climatology is more reliable when estimates of mean monthly cloud amount are required.

Dust aerosol index (DAI) algorithm for MODIS

AbstractA dust aerosol index (DAI) algorithm based on measurements in deep blue (412 nm), blue (440 nm), and shortwave IR (2130 nm) wavelengths using Moderate Resolution Imaging Spectroradiometer (MODIS) observations has been developed. Contrary to some dust detection algorithms that use measurements at thermal IR bands, this algorithm takes advantage of the spectral dependence of Rayleigh scattering, surface reflectance, and dust absorption to detect airborne dust. The DAI images generated by this algorithm agree qualitatively with the location and extent of dust observed in MODIS true color images. Quantitatively, the dust index generated for hundreds of dust outbreaks observed between 2006 and 2013 were compared to Cloud Aerosol Lidar with Orthogonal Polarization (CALIOP) Vertical Feature Mask (VFM) product and the detections are found to be accurate at 70% over land and 82% over ocean. The Probability of Correct Detection (POCD) is 80% over land and 76% over ocean. The dust detections with DAI‐based dust identification algorithm were also compared to 5 years of Aerosol Robotic Network (AERONET) observations for 13 stations with a wide range of geographical coverage. The average detection accuracy is ~70%, whereas the POCD is ~67%. The performance of DAI‐based dust detection against AERONET is slightly weaker than that against CALIOP VFM because of the limited number of matchups for some stations. For stations close to source region or coastal and island stations, the accuracy and POCD can be as high as ~85% and ~89%, respectively.

Adaptive likelihood ratio approaches for the detection of space–time disease clusters

A methodology based on adaptive likelihood ratios (ALRs) for the detection of emerging disease clusters is presented. The martingale structure of the regular likelihood ratio is preserved by the ALR. The upper limit for the false alarm rate of the proposed method depends only on the quantity of evaluated cluster candidates. Thus Monte Carlo simulations are not required to validate the procedures’ statistical significance, allowing the construction of a fast computational algorithm to detect clusters. The number of evaluated clusters is also significantly reduced, through the use of an adaptive approach to prune many unpromising clusters. This further increases the computational speed. Performance is evaluated through simulations to measure the average detection delay and the probability of correct cluster detection. We present applications for thyroid cancer in New Mexico and hanseniasis in children in the Brazilian Amazon.

Contour-Based Corner Detection and Classification by Using Mean Projection Transform

Image corner detection is a fundamental task in computer vision. Many applications require reliable detectors to accurately detect corner points, commonly achieved by using image contour information. The curvature definition is sensitive to local variation and edge aliasing, and available smoothing methods are not sufficient to address these problems properly. Hence, we propose Mean Projection Transform (MPT) as a corner classifier and parabolic fit approximation to form a robust detector. The first step is to extract corner candidates using MPT based on the integral properties of the local contours in both the horizontal and vertical directions. Then, an approximation of the parabolic fit is calculated to localize the candidate corner points. The proposed method presents fewer false-positive (FP) and false-negative (FN) points compared with recent standard corner detection techniques, especially in comparison with curvature scale space (CSS) methods. Moreover, a new evaluation metric, called accuracy of repeatability (AR), is introduced. AR combines repeatability and the localization error (Le) for finding the probability of correct detection in the target image. The output results exhibit better repeatability, localization, and AR for the detected points compared with the criteria in original and transformed images.

Comparing Edge Detection Methods Based on Stochastic Entropies and Distances for PolSAR Imagery

Polarimetric synthetic aperture radar (PolSAR) has achieved a prominent position as a remote imaging method. However, PolSAR images are contaminated by speckle noise due to the coherent illumination employed during the data acquisition. This noise provides a granular aspect to the image, making its processing and analysis (such as in edge detection) hard tasks. This paper discusses seven methods for edge detection in multilook PolSAR images. In all methods, the basic idea consists in detecting transition points in the finest possible strip of data which spans two regions. The edge is contoured using the transitions points and a B-spline curve. Four stochastic distances, two differences of entropies, and the maximum likelihood criterion were used under the scaled complex Wishart distribution; the first six stem from the h-φ class of measures. The performance of the discussed detection methods was quantified and analyzed by the computational time and probability of correct edge detection, with respect to the number of looks, the backscatter matrix as a whole, the SPAN, the covariance an the spatial resolution. The detection procedures were applied to three real PolSAR images. Results provide evidence that the methods based on the Bhattacharyya distance and the difference of Shannon entropies outperform the other techniques.

DETECTION OF WEAK SIGNALS IN HIGH-DIMENSIONAL COMPLEX-VALUED DATA

This paper considers the problem of detecting a few signals in high-dimensional complex-valued Gaussian data satisfying Johnstone's [On the distribution of the largest eigenvalue in principal components analysis, Ann. Statist.29 (2001) 295–327] spiked covariance model. We focus on the difficult case where signals are weak in the sense that the sizes of the corresponding covariance spikes are below the phase transition threshold studied in Baik et al. [Phase transition of the largest eigenvalue for non-null complex sample covariance matrices, Ann. Probab.33 (2005) 1643–1697]. In contrast to the majority of previous studies, we base the signal detection on the information contained in all the eigenvalues of the sample covariance matrix, as opposed to a few of the largest ones. This allows us to detect weak signals with non-trivial asymptotic probability when the dimensionality of the data and the number of observations go to infinity proportionally. We derive a simple analytical expression for the maximal possible asymptotic probability of correct detection holding the asymptotic probability of false detection fixed. To accomplish this derivation, we establish a novel representation for the hypergeometric function [Formula: see text] of two p × p matrix arguments, one of which has a deficient rank r &lt; p, as a repeated contour integral of the hypergeometric function [Formula: see text] of two r × r matrix arguments.

MINIMIZATION OF THE NUMBER OF INFORMING SIGNS WHEN CONSTRUCTING THE CLASSIFIER OF VEGETABLE OBJECTS

In the article a possibility is considered as to decrease information features at discrimination of vegetable objects. The multiple discriminant Fisher analysis with step-by-step inclusion of variables was used as an algorithm of discrimination. The information features were selected on the basis of the subjectively individual approach. The features were selected from frequency areas in which there existed the greatest difference by a reflection coefficient value between spectral reflection coefficients for each kind of plants. The special-purpose literature on these themes was also taken into account. For the analysis of the discrimination efficiency by the classifier of plants (for a different amount of features) a probability of plant proper discrimination was used. A minimum admissible level of the correct detection probability for each kind was set as 90 %. For investigation there were used the real reflection coefficients of plants – maize, bristlegrass and ambrosia that were measured in field conditions.

A Game-Theoretic Approach for Energy-Efficient Contention-Based Synchronization in OFDMA Systems

The purpose of this paper is to provide a novel energy-efficient perspective to the problem of contention-based synchronization in orthogonal frequency-division multiple-access communication systems. This is achieved by modeling the terminals and their corresponding receivers at the base station as economic and rational agents that engage in a noncooperative game. In the proposed game, each one trades off its available resources (transmit power and detection strategy) so as to selfishly maximize its own revenue (in terms of probability of correct detection) while saving as much energy as possible and satisfying quality-of-service requirements given in terms of probability of false alarm and timing estimation accuracy. The existence and uniqueness of the equilibrium of the game are studied. In particular, a necessary and sufficient condition on the system parameters is given for the equilibrium to exist. An iterative and distributed algorithm based on best-response dynamics (at the transmit side) and a practical parameter estimation (at the receive side) are proposed to achieve the equilibrium point. Numerical results are used to highlight the effectiveness of the proposed solution and to make comparisons with existing alternatives in terms of power consumption, synchronization time, and estimation accuracy.

On statistical properties of the detection range of a moving target

The detection range of a moving target at which an approaching target is first detected by a radar according to some criterion is analyzed. Because of the effect of random factors (noise, fluctuations of the target’s echo signal, etc.), the detection range of a moving target is a random quantity. The probability density function of the detection range is calculated. It is shown that the most probable value of the detection range of a moving target may differ substantially from the traditional maximum detection range with specified probabilities of correct detection and false alarms. It is found that the detection range of a moving target depends substantially of the target velocity and its statistical spread is rather large as compared to the mean value of this range.

Multitask Spectrum Sensing in Cognitive Radio Networks via Spatiotemporal Data Mining

Recently, compressive sensing (CS) and spectrum sensing have been two hot topics in the signal processing and cognitive radio network (CRN) fields, respectively. Due to the sampling rate limitation of the analog-to-digital converter in spectrum-sensing circuits, some works have proposed integrating these two techniques to achieve low-overhead spectrum sensing in CRNs. These works aim to minimize spectrum reconstruction errors based on linear regression methods, and <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$\ell_{1}$</tex></formula> -norm is typically used to make a tradeoff between spectrum sparseness and reconstruction accuracy. However, since the interference range of primary users is limited, multiple clusters in the CRN may not share a common sparse spectrum, and thus, the <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">$\ell_{1}$</tex></formula> -norm may not be appropriate to handle all clusters in CS inversion. Hence, we propose a novel multitask spectrum-sensing method based on spatiotemporal data mining methods. In each cluster, we assume that the spectrum sensing is executed in a synchronized way. The cluster head (CH) manages the operations, and a common sparseness hyperparameter is used to make a consensus decision. Among multiple clusters, synchronized CS sampling is not required in our scheme; instead, the Dirichlet process prior is employed to make an automatic grouping of the spectrum-sensing results among different clusters with a common sparseness hyperparameter shared inside each group. To exploit the time-domain relevance among consecutive CS observations, a hidden Markov model is employed to describe the relationship between the hidden subcarrier states and the consecutive CS observations, and the Viterbi algorithm is used to make an accurate spectrum decision for each secondary user. Simulation results show that our proposed algorithm can successfully exploit the spatiotemporal relationship to achieve higher spectrum-sensing performance in terms of normalized mean square error, probability of correct detection, and probability of false alarm, compared with a few other related works.

Discrimination between geometrically uniform quantum states with inconclusive results

We consider the problem of discrimination between a set of quantum states with the maximum probability of correct detection for a fixed rate of inconclusive results. We show that this type of measurement can be decomposed into two steps. The first step is the discrimination of whether the measurement result is inconclusive. The second step, which is performed in the case in which a conclusive result was obtained, is minimum error discrimination of output states of the first step. Using this result, we derive a closed-form analytical expression for an optimal measurement for both a geometrically uniform pure-state set and a set of binary doubly symmetric mixed states for any probability of an inconclusive result.

Minimum-error discrimination among three pure linearly independent symmetric qutrit states

Using a sufficient condition for POM which gives an optimal measurement to discriminate among given states, we obtain an optimum measurement maximizing the probability of correct detection of three equally-likely, symmetric, linearly-independent qutrit states. The maximum probability with which such states can be discriminated is also derived.

Ellipticity angle of electromagnetic signals and its use for non-energetic detection optimal by the Neumann-Pearson criterion

621.396.969.11 An interval method of radar signal detection and selection based on non-energetic polarization parameter – the ellipticity angle – is suggested. The examined method is optimal by the Neumann–Pearson criterion. The probability of correct detection for a preset probability of false alarm is calculated for different signal/noise ratios. Recommendations for optimization of the given method are provided.