Correct Recognition Rate Research Articles

Human recognition using transient auditory evoked potentials: a preliminary study

This study presents a new technique for human recognition using transient auditory evoked potentials (AEPs). AEPs are electrical potentials that are triggered by stimulating ears with auditory stimulus reflecting the neural response from the cochlea to the auditory cortex. These signals feature some advantages over conventional biometric traits as they cannot be easily forged or stolen like fingerprints or faces. Moreover, these signals are cancellable and can be changed by modifying the auditory stimulus. This allows system reuse even if the registered signal was breached. To investigate the biometric potential of this signal, a database of ten subjects was collected where transient AEPs signals were recorded by stimulating the left and the right ears separately. Machine learning techniques were employed to extract unique features for each subject using 1D convolutional neural network. The proposed system was evaluated over single-session and two-session recordings. Moreover, a fusion of left and right ear stimulated AEP signals was adopted for performance improvement. Using single-session and two-session recordings, the proposed system achieved a correct recognition rate over 95% and an equal error rate below 7%. The achieved results show that AEPs carry subject discriminative features allowing the possibility of employing AEP signal as a biometric trait.

Palmprint identification and verification with minimal number of features

In this paper, palmprint verification and identification with minimum number of features is proposed. The wide principal line extractors (WPLEs) on the region of interest (ROI) are applied to generate wide principal line images (WPLIs). The WPLI is segmented into 2 × 2, 4 × 4, 8 × 8 and 16 × 16 and the feature value is extracted directly from each segment. Experiments are conducted by using the extracted features. The results show that the equal error rate (EER), decidability index (DI) and correct recognition rate (CRR) of the proposed approach is better than existing methods for PolyUPalmprint Database.

Determination of Maize Seed Purity Based on Multi-Step Clustering

Abstract. Electrophoresis has been widely used to determine maize seed purity; however, the associated time and complexity hinder its application for maize seeds. Equipment to estimate seed purity was designed to improve the efficiency of identification of circulating maize seeds, and a multi-step clustering method was created for the determination of seed purity. The main components included a host computer, a black box, a seed transmission belt with grooves, a binocular vision system, and an under-controller. First, image information of the crown and the non-embryo side of every maize seed was collected using the binocular vision system while seeds underwent intermittent movement on the transmission belt. Second, multi-area color characteristics, which included red, green, and blue (RGB), hue, saturation, intensity (HSI), and lightness-a-b (Lab) color model parameters of maize seeds were extracted and optimized to generate 25-dimensional purity identification vectors. Finally, a multi-step clustering model was used to determine seed purity. The original center of K-mean clustering was established based on the results of self-organizing map (SOM) clustering; subsequently, maize seed purity parameters were obtained by combining the results of the second and the first clustering analyses. A result was achieved by testing three groups of samples, including 'ZHENGDAN 958' mixed with 'XIANYU 335', 'XIANYU 335' mixed with its male parent, and 'XIANYU 335' mixed with its female parent. The result showed that the correct recognition rate of 'XIANYU 335' mixed with 'ZHENGDAN 958' that had no genetic relationship could reach 100% under the condition of the experimental sample, and the accuracy of identification between 'XIANYU 335' and their respective male and female parents was 96.7% and 88.7%. This recognition rate met with the technical requirements of field inspection and provided a reliable scientific basis for the rapid determination of maize seed purity. Keywords: Identification, Maize seed, Multi-step clustering, Purity, Rapid.

Pollen Image Recognition Based on DGDB-LBP Descriptor

In this paper, we propose DGDB-LBP, a local binary pattern descriptor based on the pixel blocks in the dominant gradient direction. Differing from traditional LBP and its variants, DGDB-LBP encodes by comparing the main gradient magnitude of each block rather than the single pixel value or the average of pixel blocks, in doing so, it reduces the influence of noise on pollen images and eliminates redundant and non-informative features. In order to fully describe the texture features of pollen images and analyze it under multi-scales, we propose a new sampling strategy, which uses three types of operators to extract the radial, angular and multiple texture features under different scales. Considering that the pollen images have some degree of rotation under the microscope, we propose the adaptive encoding direction, which is determined by the texture distribution of local region. Experimental results on the Pollenmonitor dataset show that the average correct recognition rate of our method is superior to other pollen recognition methods in recent years.

Iris recognition: using a statistical model of shape and spatial relation for effective segmentation

This paper presents a new segmentation method based both on active shape model (ASM) and spatial distance model to segment iris structures. The extracted iris is normalised by Daugman's rubber sheet model. Then the features are extracted by the 1D log Gabor filter, afterwards the hamming distance is used to compare the binary codes stored previously. The evaluation experiments are performed on a set of 300 right iris images from 41 persons of CASIA-IrisV4 database. We obtain a correct recognition rate of 100%. The experimental results have shown that the performance of the proposed approach is encouraging.

Classification and Identification of Pesticide Residues in Cucumber Based on Near Infrared Spectroscopy

To explore the feasibility of Near Infrared spectroscopy (NIR) for rapid and nondestructive qualitative identification of pesticide residues in vegetables, this paper presents a qualitative classification and discrimination method based on Support Vector Machine (SVM) with Gaussian Radial Basis Function (RBF). The cucumber with three kinds of pesticide residue levels (no pesticide, standard pesticide residue, severe excess) was used as the research object. The total reflectance NIR spectra of two groups of cucumber were collected after spraying 24 hours and 48 hours of pesticide respectively. First, Principal Component Analysis (PCA) was applied to dimensionality reduction of spectral data. Then normalize the spectrum. Next, the SVM training model based on RBF was established, and then SVM prediction was carried out. The correct recognition rate of the training set was 100%, and the correct prediction rate of the test set was 94.4444% and 95.5556%, respectively. Experiments show that this method is accurate and fast for qualitative classification and identification of pesticide residues in cucumbers with different concentrations, and provides a new idea for rapid non-destructive detection of vegetable pesticide residues.

A Study of the Multisensor Estimation Method Based on Fusion Technology for Subsurface Defect Depth

In consideration of difficulty in directly using the multisensor detecting feature information for the defect identification, an improved multisensor recognition algorithm based on data-fusion technology for subsurface defect depth evaluation is proposed. At first, two common nondestructive testing technologies such as ultrasonic testing (UT) and eddy current testing (ECT) are introduced; then, a fusion method based on the error distribution characteristics of two kinds of detection methods is improved through the hyperbolic discriminant function to evaluate the subsurface defect depth. The experimental result shows that the improved algorithm is superior to the existing algorithm, so it can achieve better synthesis results and improve the correct recognition rate.

Research on Modulation Recognition Algorithm of Submarine Modulation Signal

By studying the characteristics of four modulation signals of CW, OOK, FSK and MSK, the pattern recognition method based on characteristic parameter extraction is used to identify, and three characteristic parameters of four modulation signals are extracted. The classification flow chart based on decision tree classifier is designed and simulated with MATLAB. The results show that the method can recognize the submarine signal effectively. When the signal to noise ratio is 10dB, the correct recognition rate of the signal is above 92.1%, especially, the MSK signal can be identified by 100%.

A weighted sparse neighbor representation based on Gaussian kernel function to face recognition

Currently, sparse representation was widely used in face recognition. However, traditional sparse representation method cannot effectively consider the effect of different weight of training samples When reconstruct the test samples. In this paper, a weighted sparse neighbor representation based on Gaussian kernel function model is presented to resolve above problems. Firstly, K nearest training samples is selected for constructing a new training dictionary according to the Euclidean distances between the test samples and training samples. Then, a weight is given to each sparse coefficient of new training sample. Above sparse coefficient is solved by norm L1 minimization method. Finally, recognition task is performed by the minimum reconstruction error of sparse coefficient. Experimental results illustrate that, the proposed algorithm achieves 96.64% correct recognition rate, which is significantly higher than the various existing comparison methods.

Iris double recognition based on modified evolutionary neural network

Aiming at multicategory iris recognition under illumination and noise interference, this paper proposes a method of iris double recognition based on a modified evolutionary neural network. An equalization histogram and Laplace of Gaussian operator are used to process the iris to suppress illumination and noise interference and Haar wavelet to convert the iris feature to binary feature encoding. Calculate the Hamming distance for the test iris and template iris , and compare with classification threshold, determine the type of iris. If the iris cannot be identified as a different type, there needs to be a secondary recognition. The connection weights in back-propagation (BP) neural network use modified evolutionary neural network to adaptively train. The modified neural network is composed of particle swarm optimization with mutation operator and BP neural network. According to different iris libraries in different circumstances of experimental results, under illumination and noise interference, the correct recognition rate of this algorithm is higher, the ROC curve is closer to the coordinate axis, the training and recognition time is shorter, and the stability and the robustness are better.

Encrypted network behaviors identification based on dynamic time warping and k-nearest neighbor

In order to solve the problem of encrypted traffic identification, the identification method based on dynamic time warping (DTW) and k-nearest neighbor (KNN) for the encrypted network behaviors was proposed. The method took the encrypted Twitter traffic as an example of research, and a large number of encrypted Twitter network behaviors were deeply analyzed, and then the features representing the encrypted network behaviors were extracted, and the specific encrypted network behavior module database based on DTW and KNN were established, and the DTW between the collection data set and the module database were calculated, and then were normalized, and then the encrypted network behaviors were classified by comparing with the preset empirical threshold, and the distance information were also considered by DTW algorithm, at the same time, the influence of TCP retransmission and duplicate ACK packets can be effectively eliminated by the dynamic time warping algorithm. In order to overcome the noise interference of the similar data traffic except the distance information, the similar filtered data packets were classified as the true behavior or the false behavior by KNN algorithm, and then the encrypted network behaviors were identified automatically and in real time, compared with the only correlation coefficient method or only DTW method, the online correct recognition rate by DTW and KNN has been greatly increased and reached to about 93%, and the missed detection rate is almost same with the traditional methods, the experiments and actual project applications showed that the proposed method was effective.

Classification of weld defects based on the analytical hierarchy process and Dempster–Shafer evidence theory

Weld quality management is currently one of the most concerning issues in the manufacturing industry. In this paper, a novel method is proposed for weld defect classification based on the analytical hierarchy process (AHP) and Dempster–Shafer (DS) evidence theory. First, to overcome the problem of traditional DS methods, which weigh every feature equally in classification, a method is proposed based on AHP to calculate the weight of features (WF) of a weld defect, which can then be utilized in classification. Then, an improved method based on DS evidence theory is presented to improve the accuracy of classification, which includes calculation of the standard value of features based on frequency histograms analysis and an improved Dempster’s rule for combination based on WF. A case study on the classification of steam turbine weld defects is provided to illustrate and evaluate the proposed techniques. The results show that the proposed method increases the correct recognition rate of classification with limited samples, making DS evidence theory applicable to weld defect classification.

Knowledge and attitude of mothers regarding infant hearing loss in Changsha, Hunan province, China

Objective: The objective of this study was to explore the knowledge and attitude among mothers of newborns regarding infant hearing loss (HL) in Changsha, Hunan province, China. Design: A questionnaire including 18 items was given to mothers. Study sample: A total of 115 mothers participated in the study. Results: Seven risk factors for hearing loss were identified correctly by above 60% of respondents and the top three were prolonged noise (88.7%), high fever (82.6%) and ear discharge (82.6%). Poor knowledge was demonstrated on risk factors jaundice (20.0%), measles (22.6%), convulsion (33.0%) and traditional Chinese medicine (39.1%). Maternal knowledge scores in identification and intervention (2.68 ± 0.31) was slightly higher than the score in risk factors (2.47 ± 0.34). Ninety-nine per cent of the mothers expressed the willingness to test baby’s hearing soon after birth and concern about hearing. Conclusions: Mothers were concerned about baby’s hearing and the attitude was positive. However, the correct recognition rate towards some risk factors for HL was low. Action needs to be taken to raise awareness about ear and hearing care, prevent HL caused by preventable causes and prompt early identification, early diagnosis and intervention of HL.

Adaptive enhancement and binarization techniques for degraded plate images

Vehicle License Plate Recognition (VLPR) is one of the most important aspects of applying computer techniques in Intelligent Transport Systems (ITS). They face difficulties like shadows effects, non-uniform illumination intensity, and dirty plates. To tackle these problems, this paper proposes a new VLPR system by producing a contrast enhancement method, a background removal method, and a binarization method. After binarization, an OCR method using artificial neural network (ANN) reads the plate characters. The performance of the proposed system is tested on 4 k Iranian vehicle license plate images. The proposed method causes the correct recognition rate of 91.2%. The results obtained in comparison to those of well-known methods show that the proposed system is robust for moving cars in outside environment and under different illumination conditions.

Postsurgical Disfigurement Influences Disgust Recognition: A Case-Control Study

Little is known about how emotion recognition may be modified in individuals prone to elicit disgust. We sought to determine if subjects with total laryngectomy would present a modified recognition of facial expressions of disgust. A total of 29 patients presenting with a history of advanced-stage laryngeal cancer were recruited, 17 being surgically treated (total laryngectomy) and 12 treated with chemoradiation therapy only. Based on a validated set of images of facial expressions of fear, disgust, surprise, happiness, sadness and anger displayed by 6 actors, we presented participants with expressions of each emotion at 5 levels of increasing intensity and measured their ability to recognize these emotions. Participants with (vs without) laryngectomy showed a higher threshold for the recognition of disgust (3.2. vs 2.7 images needed before emotion recognition, p = 0.03) and a lower success rate of correct recognition (75.5% vs 88.9%, p = 0.03). Subjects presenting with an aesthetic impairment of the head and neck showed poorer performance in disgust recognition when compared with those without disfigurement. These findings might relate either to some perceptual adaptation, habituation phenomenon, or to some higher-level processes related to emotion regulation strategies.

Recognition and drinking behaviour analysis of individual pigs based on machine vision

Abstract Water consumption by individual pigs can be an interesting indicator of their health. A method using machine vision is proposed to (a) recognise the presence of an individual pig within the drinking zone and (b) analyse the vision images to determine if the pig is drinking. First, isolation of an individual pig within the drinking zone is extracted from the topview of the set of video sequences for group-housed pigs. Next, the distance between the individual pig and the drink nipple is calculated and used to determine whether the individual pig is in contact with the drink nipple. If yes, the colour moments, area, perimeter and other features of the pig are extracted. Then the features are normalised. The individual pig is recognised by computing the Euclidean distance between the pig and the standard sample. The contact time between an individual pig and the drink nipple is used to determine whether the pig is drinking. The pigsty contains 7 pigs and is monitored in real-time, and 140 video clips containing images of the individual pigs while drinking are captured. The correct (drinking) recognition rate for individual pigs is 90.7%. Our method differs from traditional methods in that it avoids any disturbance to the pigs, and it can be used for the recognition of individual pigs within a stress-free environment. Our results can provide a reference point and direction for exploration of other behaviours of topview group-housed pigs.

Correct recognition and continuum belief of mental disorders in a nursing student population

BackgroundThe current study aimed to explore the correct recognition of mental disorders across dementia, alcohol abuse, obsessive compulsive disorder (OCD), schizophrenia and depression, along with its correlates in a nursing student population. The belief in a continuum of symptoms from mental health to mental illness and its relationship with the non-identification of mental illness was also explored.MethodsFive hundred students from four nursing institutions in Singapore participated in this cross-sectional online study. Respondents were randomly assigned to a vignette describing one of the five mental disorders before being asked to identify what the person in the vignette is suffering from. Continuum belief was assessed by rating their agreeableness with the following statement: “Sometimes we all behave like X. It is just a question of how severe or obvious this condition is”.ResultsOCD had the highest correct recognition rate (86%), followed by depression (85%), dementia (77%), alcohol abuse (58%) and schizophrenia (46%). For continuum belief, the percentage of respondents who endorsed symptom continuity were 70% for depression, 61% for OCD, 58% for alcohol abuse, 56% for dementia and 46% for schizophrenia. Of concern, we found stronger continuum belief to be associated with the non-identification of mental illness after controlling for covariates.ConclusionsThere is a need to improve mental health literacy among nursing students. Almost a quarter of the respondents identified excessive alcohol drinking as depression, even though there was no indication of any mood symptom in the vignette on alcohol abuse. Further education and training in schizophrenia may need to be conducted. Healthcare trainees should also be made aware on the possible influence of belief in symptom continuity on one’s tendency to under-attribute mental health symptoms as a mental illness.

Blind equalization and automatic modulation classification based on subspace for subcarrier MPSK optical communications

Equalization can compensate channel distortion caused by channel multipath effects, and effectively improve convergent of modulation constellation diagram in optical wireless system. In this paper, the subspace blind equalization algorithm is used to preprocess M-ary phase shift keying (MPSK) subcarrier modulation signal in receiver. Mountain clustering is adopted to get the clustering centers of MPSK modulation constellation diagram, and the modulation order is automatically identified through the k-nearest neighbor (KNN) classifier. The experiment has been done under four different weather conditions. Experimental results show that the convergent of constellation diagram is improved effectively after using the subspace blind equalization algorithm, which means that the accuracy of modulation recognition is increased. The correct recognition rate of 16PSK can be up to 85% in any kind of weather condition which is mentioned in paper. Meanwhile, the correct recognition rate is the highest in cloudy and the lowest in heavy rain condition.

Synergetic damage recognition approach for messenger wire in icing environment using piezoceramic transducers

In recent years, high-speed electric railway has become a major means of transport. Messenger wire is the main bearing part of electrified railway catenary, and once the damage occurs, it will easily cause a serious accident. In the harsh areas of climate, the messenger wire is covered with ice for a long time. To identify damages of electrical messenger wire in the icing environment, a synergetic damage recognition approach was put forward. On the basis of the synergetic principle, a dynamic decision-making mechanism was established. And the feature extraction and evaluation method for active acoustic emission signal was studied. Subsequently, a reconstruction method of damage status vector by using training sample fusion algorithm was introduced. Experiments were conducted in icing environment. Firstly, the impact of messenger wire galloping on identification performance was studied and found such influence can be ignored. In experiment of damage type recognition, the experimental results show that the proposed approach can identify different types of damages well. And compared with the cluster learning algorithm, the correct rate of recognition increased by 5% when training samples fusion method was adopted. This proposed approach demonstrates a strong anti-noise-interference ability, and it can provide a theoretical basis for the separation of stress wave modals in subsequent messenger wire structural damage monitoring imaging.

A cooperative modulation recognition: New paradigm for power line networks in smart grid

Power Line communication (PLC) is an attractive approach to provide information transfer services for future smart grids. However, since various modulations are adopted, it is a great challenge to add new nodes to collect the data from the devices or sensors in in-home PLC networks. In this paper, we propose an approach to automatically access to the PLC network by identifying the modulation of signals. To improve the correct recognition rate on identification of modulations, we propose a multiple input and multiple output (MIMO) based cooperative modulation identification scheme. After receiving the recognition results from accessing nodes, the central server makes the comprehensive and accurate recognition decision on the modulation of the PLC network. Furthermore, the fourth-order cumulants for multiple users are adopted as the feature for this modulation classifier. With the feature, we propose an improved modulation classification algorithm based on the maximum likelihood. Simulations show that a high detection rate and low false positive rate can be achieved as we employ the cooperative modulation identifying scheme and the improved recognition algorithm.