Probability Of Recognition Research Articles

SAR Unlabeled Target Recognition Based on Updating CNN With Assistant Decision[-.2pc

Compared with optical images, the number of synthetic aperture radar (SAR) images is limited and growing slowly over time, and most of time the additional SAR images are unlabeled, which restricts the development of target recognition on SAR images. In this letter, the update learning method for SAR unlabeled target recognition based on the convolutional neural network (CNN) with assistant decision is proposed. The seed image set, which contains a small amount of existing labeled SAR images, is used for pretraining a CNN model. The unlabeled samples are fed to both CNN and the assistant classifier, and then, the matrices of the unlabeled samples based on recognition probability will be obtained, respectively. The unlabeled samples with high confidence by decision will be fed to CNN again to fine-tune the CNN model. The proposed method can make full use of the unlabeled samples to update the recognition model and to improve the recognition performance. Experiments on MSTAR data set show that, with the increase of unlabeled samples, the proposed method can improve the recognition performance and outperform the methods of CNN self-update learning and support vector machine update learning with the principal component analysis and the nonnegative matrix factorization. The experiments’ results demonstrate that the proposed method can effectively solve the problems caused by the lack of training samples.

Комбинированные методы спектрального анализа неоднородного потока зерновых смесей

The problem of detecting Fusarium fungi infected grains and identifying the varieties of the components of grain mixtures based on the combined use of various spectral measurement methods in various wavelength ranges is considered. A method for measuring combined reflectance and transmittance spectra of the elements of non-uniform grain flow is described. The results of the spectral measurement are processed using neural network based classification algorithms combined with data dimensionality reduction techniques. The probabilities of incorrect recognition for various numbers of features and combinations of spectral methods are estimated

Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network

In this paper, to solve the problem of the low recognition rate of the existing approaches at low signal-to-noise ratio (SNR), an intra-pulse modulation recognition approach for radar signal is proposed. The approach identifies the modulation of radar signals using the techniques of time-frequency analysis, image processing, and convolutional neural network (CNN). Through Cohen class time-frequency distribution (CTFD), the time-frequency images (TFIs) of received signals are extracted. In order to obtain the high-quality TFIs of received signals, we introduce a new kernel function for the CTFD, which has stronger anti-noise ability than Choi–Williams time-frequency distribution. A series of image processing techniques, including 2-D Wiener filtering, bilinear interpolation, and Otsu method, are applied to remove the background noise of the TFI and obtain a fixed-size binary image that contains only morphological features of the TFI. We design a CNN classifier to identify the processed TFIs. The proposed approach can identify up to 12 kinds of modulation signals, including frequency modulation, phase modulation, and composite modulation. Simulation results show that, for 12 kinds of modulation signals, the proposed approach achieves an overall probability of successful recognition of 96.1% when SNR is −6 dB.

Design of a device for optimal reception of signals against the background of a two-component Markov interference

We synthesized optimal receiver of signals observed against the background of a two-component additive Gaussian Markov interference. The inclusion of such a receiver into an automated locomotive signal system would significantly increase its noise immunity. We obtained mathematical expressions for the transformations that need to be performed over the counts of voltage of the observed mixture of signal and interference. It is shown that in a general case these transformations are nonlinear and require summing the specified counts with weight coefficients whose exact numerical values are rather difficult to calculate without specifying statistical properties and relationships of the interference components. We refined expressions that make it possible to calculate specified coefficients for the case of a Markov Gaussian interference. They proved to be variable magnitudes, expressed through the variance of interferences, their correlation coefficients and magnitudes of voltages of time-adjacent counts of the observed mixture of signal and interference. As a result, the operations, required for optimal reception, of calculating a weighted correlation sum and a weighted energy sum are nonlinear. They are based on the fulfillment of four arithmetic operations and squaring, which is easy in terms of technical implementation. Under condition of statistical independence of counts, the solvers accumulate sums of increments of the input and reference signals, respectively. The quality of signal recognition ensured by the designed optimal receiver was estimated using computer simulation. It is shown that for actual situations the probability of error recognition of informational signals does not exceed 10-2 per one coded parcel. The practical application of results obtained in our study would make it possible to improve safety and rhythmicity in the motion of trains

Predicted indirectly recognizable HLA epitopes are not associated with clinical outcomes after haploidentical hematopoietic stem cell transplantation

Haploidentical stem cell transplantation (haplo-SCT) provides an alternative method to cure patients with malignant and nonmalignant hematologic diseases who lack a human leukocyte antigen (HLA) matched related or unrelated donor. HLA disparity between donor and patient was the main reason causing lots of clinical immune response. The aim of this study was to investigate whether indirect recognition of mismatched HLA could predict the clinical outcomes in haplo-SCT. The probability of indirect recognition was predicted by the Predicted Indirectly ReCognizable HLA Epitopes (PIRCHE) model. 577 patients with acute leukemia or myelodysplastic syndrome receiving haplo-SCT were enrolled in the study. Patients were divided into 4 quartiles according to PIRCHE-Ⅰ or PIRCHE-Ⅱ. Although the cumulative incidences of chronic graft-versus-host disease (GVHD) were significantly different among the 4 PIRCHE-Ⅰgroups, with 20.4% for group 0–6, 40.5% for group >6–11, 26.1% for group >11–19 and 23.9% for group >19 (P = .007), PIRCHE-Ⅰ was not significantly associated with chronic GVHD in multivariate models (RR, 0.993; 95% CI, 0.858–1.149; P = .926). And no significant associations were observed between PIRCHE-Ⅰ or PIRCHE-Ⅱ and other clinical outcomes. In summary, PIRCHE did not correlate with clinical outcomes and could not predict haplo-SCT outcomes.

ВЛИЯНИЕ ПСИХОФИЗИОЛОГИЧЕСКОГО СОСТОЯНИЯ ПОДПИСАНТА НА РЕЗУЛЬТАТЫ ЕГО ИДЕНТИФИКАЦИИ ПО РУКОПИСНОМУ ОБРАЗУ ЕСТЕСТВЕННЫМ И ИСКУССТВЕННЫМ ИНТЕЛЛЕКТАМИ

At present, while various mechanisms to ensure information security are actively being improved, particular attention is paid to prevent unauthorized access to information resources. The human factor and process of identification still remain the most problematic, as well as user authentication. A progress in the technology of information resources protection from internal security threats paves its way towards biometric systems of hidden identification of computer users and their psychophysiological state. A change in psychophysiological state results in the person's handwriting. The influence of the signer’s state of fatigue and excitation on the results of its identification both by a person and by pattern recognition methods on reproduced signatures are studied. Capabilities of human and artificial intelligence are compared in equal conditions. When the state of the signer changes, the probability of erroneous recognition by artificial intelligence increases by factor 3.3 to 3.7. A person identifies a handwritten image with fewer errors in case when the signer is agitated, and with higher error rate if the signer is tired.

AB045. Studying the probabilities of Down syndrome recognition in Thai children using de-identified computer-aided facial features analysis

AB045. Studying the probabilities of Down syndrome recognition in Thai children using de-identified computer-aided facial features analysis

Optimum selection of detection point and threshold noise ratio of airborne infrared search and track systems.

To improve the recognition probability of airborne infrared search and track systems (IRSTS) in air-to-air operations, the point target recognition probability model is established. And using an operating range model, the detection envelope is calculated for the airborne IRSTS. Combining with different operational backgrounds and specific technical parameters, the simulation results show that: (1)an increase in visual range and target speed, along with a decrease of oblique angle, produces an increase in the recognition probability; (2)the angle of maximum operating range of each detection envelope is the optimum detection point for the airborne IRSTS; and (3)the optimum threshold noise ratio is 8-10. These conclusions provide further scope in improving the operational effectiveness of airborne IRSTS in practical applications.

Intra-pulse modulation recognition using short-time ramanujan Fourier transform spectrogram

Intra-pulse modulation recognition under negative signal-to-noise ratio (SNR) environment is a research challenge. This article presents a robust algorithm for the recognition of 5 types of radar signals with large variation range in the signal parameters in low SNR using the combination of the Short-time Ramanujan Fourier transform (ST-RFT) and pseudo-Zernike moments invariant features. The ST-RFT provides the time-frequency distribution features for 5 modulations. The pseudo-Zernike moments provide invariance properties that are able to recognize different modulation schemes on different parameter variation conditions from the ST-RFT spectrograms. Simulation results demonstrate that the proposed algorithm achieves the probability of successful recognition (PSR) of over 90% when SNR is above -5 dB with large variation range in the signal parameters: carrier frequency (CF) for all considered signals, hop size (HS) for frequency shift keying (FSK) signals, and the time-bandwidth product for Linear Frequency Modulation (LFM) signals.

Redes heterogéneas de neuronas que reconocen firmas neuronales

Resultados experimentales muestran que células de diferentes sistemas neuronales vivos pueden identificar de forma inequívoca sus señales de salida mediante firmas neuronales específicas. El significado funcional de estas firmas aún no está claro, la existencia de mecanismos celulares para identificar el origen de señales individuales y contextualizar la llegada de un mensaje, puede ser una poderosa estrategia de procesamiento de información para el sistema nervioso. Recientemente construimos diferentes modelos para estudiar la capacidad de una red neuronal para codificar y procesar información basada en la emisión y reconocimiento de firmas específicas, en donde las neuronas son capaces de reconocer y emitir la misma firma, con la misma probabilidad. En este artículo, analizamos las características que pueden influir en la capacidad de procesamiento cuando variamos la probabilidad de reconocimiento que tiene cada neurona para distintas firmas en redes heterogéneas. Las simulaciones muestran el incremento de las propiedades dinámicas de la red.

A modified version of Helmholtz machine by using a Restricted Boltzmann Machine to model the generative probability of the top layer

The Helmholtz machine is an unsupervised deep neural network with different bottom-up recognition weights and top-down generative weights, which attempts to build probability density models of sensory inputs. The recognition weights are used to determine the recognition probability of each unit from bottom layer to top layer and the generative weights are used to determine the generative probability of each unit from top layer to bottom layer. The model parameters can be gained by minimizing the sum of the Kullback–Leibler divergence between generative and recognition distributions of all units. In this paper, we proposed a modified Helmholtz machine by adding an additional hidden layer on the top layer of the Helmholtz machine, which is used to model the generative probability of the top layer. The additional added hidden layer provides ‘complementary prior’ to the original top layer and can eliminate the ‘explaining away effects’ to make the Helmholtz machine fitting sensory inputs much better. The experimental results of new algorithm on various data sets show that the modified Helmholtz machine learns better generative models.

Assistant Models for MITL Target Recognition Based on INS and Imaging FOV

Man-in-the-loop (MITL) target recognition system can recognise the target by man operation in the long-distance, and it is a new target reconition system presented for solving Auto Target Recognition (ATR) system’s drawbacks of very low recognition probability in condition of complex background. But MITL relays on template matching of ATR, and the real-time template is not checked by matching criterions. At present, the problem of the lower target recognition probability, poor precision and poor reliability are not solved. To solve the problem, research using Inertial Navigation System (INS) and optical imaging sensor's Field Of View(FOV) to assist MITL. Design a correct model assistansed by INS and FOV of imaging, and simulations are done to check the model and the rusult show that the model can provid target direction angle for aircraft, and the angel precision is fine.

Memory effects of sleep, emotional valence, arousal and novelty in children.

Effectiveness of memory consolidation is determined by multiple factors, including sleep after learning, emotional valence, arousal and novelty. Few studies investigated how the effect of sleep compares with (and interacts with) these other factors, of which virtually none are in children. The present study did so by repeated assessment of declarative memory in 386 children (45% boys) aged 9-11years through an online word-pair task. Children were randomly assigned to either a morning or evening learning session of 30 unrelated word-pairs with positive, neutral or negative valenced cues and neutral targets. After immediately assessing baseline recognition, delayed recognition was recorded either 12 or 24h later, resulting in four different assessment schedules. One week later, the procedure was repeated with exactly the same word-pairs to evaluate whether effects differed for relearning versus original novel learning. Mixed-effect logistic regression models were used to evaluate how the probability of correct recognition was affected by sleep, valence, arousal, novelty and their interactions. Both immediate and delayed recognition were worse for pairs with negatively valenced or less arousing cue words. Relearning improved immediate and delayed word-pair recognition. In contrast to these effects, sleep did not affect recognition, nor did sleep moderate the effects of arousal, valence and novelty. The findings suggest a robust inclination of children to specifically forget the pairing of words to negatively valenced cue words. In agreement with a recent meta-analysis, children seem to depend less on sleep for the consolidation of information than has been reported for adults, irrespective of the emotional valence, arousal and novelty of word-pairs.

An improved CS-LSSVM algorithm-based fault pattern recognition of ship power equipments.

A ship power equipments’ fault monitoring signal usually provides few samples and the data’s feature is non-linear in practical situation. This paper adopts the method of the least squares support vector machine (LSSVM) to deal with the problem of fault pattern identification in the case of small sample data. Meanwhile, in order to avoid involving a local extremum and poor convergence precision which are induced by optimizing the kernel function parameter and penalty factor of LSSVM, an improved Cuckoo Search (CS) algorithm is proposed for the purpose of parameter optimization. Based on the dynamic adaptive strategy, the newly proposed algorithm improves the recognition probability and the searching step length, which can effectively solve the problems of slow searching speed and low calculation accuracy of the CS algorithm. A benchmark example demonstrates that the CS-LSSVM algorithm can accurately and effectively identify the fault pattern types of ship power equipments.

Semi-fragile Image Authentication based on CFD and 3-bit Quantization

There is a great adventure of watermarking usage in the context of conventional authentication since it does not require additional storage space for supplementary metadata. However, JPEG compression, being a conventional method to compress images, leads to exact authentication breaking. We discuss a semi-fragile watermarking system for digital images tolerant to JPEG/JPEG2000 compression. Recently we have published a selective authentication method based on Zernike moments. But unfortunately it has large computational complexity and not sufficiently good detection of small image modifications. In the current paper it is proposed (in contrast to Zernike moments approach) the usage of image finite differences and 3-bit quantization as the main technique. In order to embed watermark (WM) into the image, some areas of the Haar wavelet transform coefficients are used. Simulation results show a good resistance of this method to JPEG compression with CR≤30% (Compression Ratio), high probability of small image modification recognition, image quality assessments PSNR≥40 dB (Peak signal-to-noise ratio) and SSIM≥0.98 (Structural Similarity Index Measure) after embedding and lower computation complexity of WM embedding and extraction. All these properties qualify this approach as effective.

The New Algorithm for Speech Control in the Cockpit

Speech technologies are being developed intensively in the recent years, especially the automatic speech recognition as an additional input method in human interface and technical devices. Most of the known algorithms for speech control have small probability of correct recognition. Widespread methods, like Markov models and neural networks, which require large processing power, allow recognizing the words with a probability of no more than 85–92 %. Such accuracy is not enough to use the voice control on board of a modern aircraft. The article is devoted to a problem of improving the automatic speech recognition’s accuracy. A version of word recognition algorithm based on the classical approach is suggested, it includes the comparison with the patterns. In this work to improve the recognition’s accuracy a new method of calculating a similarity measurement between the recognizable word and the pattern, which based on z-Fisher transformation, is described. This article also contains an algorithm’s modification that takes into account the fixed ratios with the patterns of other words and uses the words adjustment to the pattern with dynamic programming elements. The usage of fixed relations between words provides additional information, which positively affects the recognition. The experimental results of the developed algorithm’s approbation on a large amount of speech data are presented.

Enhancement of the noise immunity of a voice-activated robotics control system based on phonetic word decoding method

The problem of protection of a voice-activated robotics control system against the acoustic noise similar to the speaker voice is investigated. A new algorithm for voice signal processing using the phonetic word decoding method and the (R+1) information element is proposed. The results of the experimental study of this algorithm are reported. It is shown that the developed algorithm reduces the false alarm ratio by and an order of magnitude or even more and retains high probability of correct voice recognition.

Intelligent information technology building systems diagnostics using nuclear moments Volterra

The paper presents the intelligent information technology to increase the efficiency of diagnosing the state of nonlinear dynamical objects of different physical nature with the use of mathematical models in the form of Volterra kernels. Research results on the test object monitoring show that moments of nuclei Volterra 2nd order characterized by the highest stability of the quality of diagnosis (probability of correct recognition) errors in measuring the response of objects of control compared to the data of their classification on the basis of samples of nuclei with a given increment. Figs.: 5. Tabl.: 2. Refs.: 13 titles.Keywords: intelligent information technology; systems diagnostics; Volterra kernels; mathematical models in the form of Volterra kernels; quality of diagnosis.

SANIST: optimization of a technology for compound identification based on the European Union directive with applications in forensic, pharmaceutical and food analyses.

Electrospray Ionization and collision induced dissociation tandem mass spectrometry are usually employed to obtain compound identification through a mass spectra match. Different algorithms have been developed for this purpose (for example the nist match algorithm). These approaches compare the tandem mass spectra of the unknown analyte with the tandem mass spectra spectra of known compounds inserted in a database. The compounds are usually identified on the basis of spectral match value associated with a probability of recognition. However, this approach is not usually applied to multiple reaction monitoring transition spectra achieved by means of triple quadrupole apparatus, mainly due to the lack of a transition spectra database. The Surface Activated Chemical Ionization-Electrospray-NIST Bayesian model database search (SANIST) platform has been recently developed for new potential metabolite biomarker discovery, to confirm their identity and to use them for clinical and diagnostic applications. Here, we present an improved version of the SANIST platform that extends its application to forensic, pharmaceutical, and food analysis studies, where the compound identification rules are strict. The European Union (EU) has set directives for compound identification (EU directive 2002/657/EC). We have applied the SANIST method to identification of 11-nor-9-carboxytetrahydro-cannabinol in urine samples (an example of a forensic application), circulating levels of the immunosuppressive drug tacrolimus in blood (an example of a pharmaceutical application) and glyphosate in fruit juice (an example of a food analysis application) that meet the EU directive requirements. Copyright © 2016 John Wiley & Sons, Ltd.

Research on Low Probability of Intercept Radar Signal Recognition Using Deep Belief Network and Bispectra Diagonal Slice

A novel recognition algorithm for Low Probability of Intercept (LPI) radar signal based on deep learning of radar signals Bispectra Diagonal Slice (BDS) is proposed in this paper. Firstly, a Deep Belief Network (DBN) model is established on stacked Restricted Boltzmann Machines (RBM), then the model is used for layer-by-layer unsupervised greedy learning of radar signals BDS. Secondly, a Back Propagation (BP) algorithm is applied to fine tune parameters of DBN model with a supervised way according to learning error. Finally, the BDS-DBN model is constructed to classify and recognize unknown LPI signals. The theoretical analysis and the simulation results show that, the average recognition accuracy of the proposed algorithm for Frequency Modulation Continuous Wave (FMCW), Frank, Costas and FSK/PSK signals can reach 93.4% or ever higher while the SNR is better than 8 dB, which is better than that of Principal Component Analysis-Support Vector Machine (PCA-SVM) algorithm and Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA) algorithm.