Highest Average Recognition Rate Research Articles

A comparative study of four types of multi-scale entropies in feature extraction of underwater acoustic signals for potential GNSS positioning applications

The combination of underwater acoustic processing and the Global Navigation Satellite System (GNSS) has achieved remarkable economic benefits in offshore operations. As the key technology of GNNS positioning, feature extraction of underwater acoustic signals is affected by the complex marine environment. To extract more effective information from underwater acoustic signals, we use four types of multi-scale entropies, including multi-scale sample entropy (MSE), multi-scale fuzzy entropy (MFE), multi-scale permutation entropy (MPE), and multi-scale dispersion entropy (MDE), to analyze and distinguish underwater acoustic signals. In this study, two groups of real-word underwater acoustic signal experiments were performed for feature extraction of ship-radiated noises (SRNs) and ambient noises (ANs). The results indicated that the performance of the MFE-based feature extraction method is superior to that of feature extraction methods based on the other three entropies under the same number of features, and the highest average recognition rate (ARR) of the MFE-based feature extraction method for SRNs reaches 100% when the number of features is 3.

Research on Intelligent Evaluation System of Sports Training based on Video Image Acquisition and Scene Semantics

This paper proposes to check the travel target of the dynamic background in the video surveillance with a fixed camera. A travel target detection method based on video picture acquisition and scene semantics for surveillance video was proposed. First, on the basis of combing the concepts and methods of picture recognition, the semantic information of the scene was fused to eliminate the interference factors in the unnecessary detection area. Secondly, a remote sensing picture visual feature representation method containing a semantic recognition method of remote sensing picture scenes and CSIFT features based on PLSA was presented. 10 types of typical remote sensing picture scenes are used for tests, and the visual vocabulary extraction method remains the same. The fixed visual vocabulary was 600, and the potential semantic subjects changes between 8∼50. The test results indicated that the highest average recognition rate was obtained when the latent semantic topics were 20. Inappropriate latent semantic topics will lead to a decline in recognition rates. The effectiveness of this method was fully verified.

Application of Artificial Intelligence Elements and Multimedia Technology in the Optimization and Innovation of Teaching Mode of Animation Sound Production

Nowadays, with the rapid development of multimedia technology and computer information processing, the data of multimedia information presents explosive growth. At present, the method of using artificial recognition of sound materials is inefficient, and an automatic recognition and classification system of sound materials is needed. To improve the accuracy of sound recognition, two algorithm models are established to identify and compare the sound materials, which are the hidden Markov model (HMM) and back propagation neural network (BPNN) model. Firstly, HMM is established, and the sound material is randomly selected as the test sample. The comparison between the expected classification and the actual is tested, and the recognition rate of each classification is got. The final average recognition rate is 61%. The anti-interference characteristics of the training HMM are tested, and the identification rate of the training model is selected in 6 types of signal-to-noise ratio (SNR) environments. The recognition rate of the training model has an obvious downward trend with the decrease of the SNR. Secondly, the BPNN model is built, and 200 BPNN training experiments are conducted. The training model with the highest average recognition rate is selected as the experimental model. The average recognition rate of the final model is higher than 90%. The expression ability and stability of the trained model are simulated after the new sample is introduced, and the anti-interference performance of the model is tested in different environments of SNR. The results of performance test are good, and only the recognition rate of complex types of some sound sources decreased. Finally, the accuracy of the HMM in the experiment is not as high as that obtained by BPNN. Therefore, the training method of BPNN has a greater advantage in both recognition accuracy and recognition efficiency for the studied sound. It provides a reference for automatic recognition of sound materials.

Task-Related Component Analysis Combining Paired Character Decoding for Miniature Asymmetric Visual Evoked Potentials.

Brain-computer interface (BCI) technology based on event-related potentials (ERP) of electroencephalography (EEG) is widely used in daily life and medical treatment. However, the research of identifying the miniature and more informative asymmetric visual evoked potentials (aVEPs), which belongs to ERP, needs further exploration. Herein, a task-related component analysis combining paired character decoding (TRCA-PCD) method, which can enhance reproducibility of aVEPs in multiple trials and strengthen the features of different samples, was designed to realize fast decoding of aVEPs. The BCI performance and the influence of repetition times between the TRCA-PCD method, the discriminative canonical pattern matching (DCPM) method and traditional task-related component analysis (TRCA) method were compared using a 32-class aVEPs dataset recorded from 32 subjects. The highest average recognition accuracy and information transfer rate (ITR) of TRCA-PCD after parameter selection were 70.37 ± 2.49 % (DCPM: 64.91 ± 2.81 %, TRCA: 44.01 ± 3.25 %) with the peak value of 97.92% and 28.90 ± 3.83 bits/min (DCPM: 21.29 ± 3.35 bits/min, TRCA: 11.54 ± 2.81 bits/min) with the peak value of 94.55 bits/min respectively. Statistical analysis indicated that the highest average recognition rate could be obtained when the repetition time was six, and the highest ITR could be obtained when the repetition time was one. Overall, the results verified the effectiveness and superiority of TRCA-PCD in recognition of aVEPs and provided a reference for parameter selection. Therefore, the TRCA-PCD method can promote the further application of aVEPs in the BCI speller field.

Application of the fruit fly optimization algorithm to an optimized neural network model in radar target recognition

With the development of computer technology, there are more and more algorithms and models for data processing and analysis, which brings a new direction to radar target recognition. This study mainly analyzed the recognition of high resolution range profile (HRRP) in radar target recognition and applied the generalized regression neural network (GRNN) model for HRRP recognition. In order to improve the performance of HRRP, the fruit fly optimization algorithm (FOA) algorithm was improved to optimize the parameters of the GRNN model. Simulation experiments were carried out on three types of aircraft. The improved FOA-GRNN (IFOA-GRNN) model was compared with the radial basis function (RBF) and GRNN models. The results showed that the IFOA-GRNN model had a better convergence accuracy, the highest average recognition rate (96.4 %), the shortest average calculation time (275 s), and a good recognition rate under noise interference. The experimental results show that the IFOA-GRNN model has a good performance in radar target recognition and can be further promoted and applied in practice.

Selection of Multi-Level Deep Features via Spearman Rank Correlation for Synthetic Aperture Radar Target Recognition Using Decision Fusion

Convolutional neural networks (CNN) now become one of the most popular methods in synthetic aperture radar (SAR) target recognition. To fully exploit the deep features learned by CNN, this paper considers all the feature maps from different convolution layers. At each layer, the Spearman rank correlation is employed to evaluate the similarities between the feature maps and original SAR image. A certain proportion of feature maps with high similarities are selected and jointly represented based on the joint sparse representation (JSR) model. For the reconstruction error vectors from different layers, they are combined based on linear weighting using a random weight matrix. The fused reconstruction errors are analyzed to form a decision value for target recognition. The feature selection chooses the robust features and JSR considers the inner correlations between the feature maps from the same layer. In addition, the linear weighting using the random weight matrix could statistically reveal the correlations between the test sample and a certain training class. Therefore, the overall effectiveness and robustness of the proposed method can be enhanced. By performing experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset, the proposed method could achieve a very high average recognition rate of 99.32% for ten classes of ground targets under the standard operating condition (SOC). Furthermore, under the extended operating conditions (EOCs) like configuration differences, depression angle differences, noise corruption, and partial occlusion, the proposed could also achieve superior robustness over some state-of-the-art SAR target recognition methods.

Bearing Operating State Evaluation Based on Improved HMM

With the development of industry, the fault diagnosis requirements for rolling bearings are getting higher and higher. This paper aims to develop low-complexity solutions for bearing fault diagnosis. In this paper, we use wavelet decomposition to obtain gesture Monitoring Index Vector (MIVs), after this, an improved Hidden Markov Model (HMM) algorithm was proposed for bearing fault diagnosis, in which we apply the Genetic Algorithm (GA) to avoid the convergence to local optimum, thus improving the recognition performance. The experimental results on 11 groups of test datasets demonstrate that the proposed algorithm (GAHMM) can achieve a higher average recognition rate of 93%, 87%, 87%, 93%, 93%, 97%, 100%, 97%, 97%, 100%, 97%.

Research on gait recognition algorithm based on multiinformation perception

With the collected multi-information, through the information preprocessing, feature vector extraction, analysis and fusion, the recognition model based on BP neural network, genetic algorithm optimization BP neural network, the extreme learning machine and support vector machine are established. We have accurately identified five gait modes: flat walking, upstairs, downstairs, uphill, and downhill. The highest average recognition rate is 96.5%, and the recognition time is 0.156 s. By analyzing the advantages and disadvantages of the four recognition models, the optimal gait recognition algorithm can be obtained.

RETRACTED ARTICLE: A novel system for automatic detection of K-complexes in sleep EEG

Sleep staging process is applied to diagnose sleep-related disorders by sleep experts through analyzing sleep signals such as electroencephalogram (EEG), electrooculogram and electromyogram of subjects and determining the stages in 30-s-length time parts of sleep named as epochs. Subjects enter several stages during the sleep, and N-REM2 is one of them which has also the highest duration among the other stages. Approximately half of the sleep consists of N-REM2. One of the important parameters in determining N-REM2 stage is K-complex (Kc). In this study, some time and frequency analysis methods were used to determine the locations of Kcs, automatically. These are singular value decomposition (SVD), variational mode decomposition and discrete wavelet transform. The performance of them in detecting Kcs was compared. Furthermore, systems with combinations of these methods were presented with logic AND operations. The EEG recordings of seven subjects were obtained from the Sleep Research Laboratory of Necmettin Erbakan University. A database with total 359 Kcs in 320 epochs was prepared from the recordings. According to the results, the highest average recognition rate was found as 92.29% for the SVD method. Thanks to this study, the sleep experts can find out whether there were Kcs in related epochs and also know their locations in these epochs, automatically. Also, it will help automatic sleep stage classification systems.

Vocal-based emotion recognition using random forests and decision tree

This paper proposes a new vocal-based emotion recognition method using random forests, where pairs of the features on the whole speech signal, namely, pitch, intensity, the first four formants, the first four formants bandwidths, mean autocorrelation, mean noise-to-harmonics ratio and standard deviation, are used in order to recognize the emotional state of a speaker. The proposed technique adopts random forests to represent the speech signals, along with the decision-trees approach, in order to classify them into different categories. The emotions are broadly categorised into the six groups, which are happiness, fear, sadness, neutral, surprise, and disgust. The Surrey Audio-Visual Expressed Emotion database is used. According to the experimental results using leave-one-out cross-validation, by means of combining the most significant prosodic features, the proposed method has an average recognition rate of $$66.28\%$$66.28%, and at the highest level, the recognition rate of $$78\%$$78% has been obtained, which belongs to the happiness voice signals. The proposed method has $$13.78\%$$13.78% higher average recognition rate and $$28.1\%$$28.1% higher best recognition rate compared to the linear discriminant analysis as well as $$6.58\%$$6.58% higher average recognition rate than the deep neural networks results, both of which have been implemented on the same database.

Recognizing Surgically Altered Face Images and 3D Facial Expression Recognition

Altering Facial appearances using surgical procedures are common now days. But it raised challenges for face recognition algorithms. Plastic surgery introduces non linear variations. Because of these variations it is difficult to be modeled by the existing face recognition system. Here presents a multi objective evolutionary granular algorithm. It operates on several granules extracted from a face images at multiple level of granularity. This granular information is unified in an evolutionary manner using multi objective genetic approach. Then identify the facial expression from the face images. For that 3D facial shapes are considering here. A novel automatic feature selection method is proposed based on maximizing the average relative entropy of marginalized class-conditional feature distributions and apply it to a complete pool of candidate features composed of normalized Euclidian distances between 83 facial feature points in the 3D space. A regularized multi-class AdaBoost classification algorithm is used here to get the highest average recognition rate.

Assessing the performance of Random Partitioning and K-Fold Cross Validation methods of evaluation of a Face Recognition System

Face recognition has been an active research area in the pattern recognition and computer vision domains due to its many potential applications in surveillance, credit cards, passport and security. However, the problem of correct method of partitioning the face data into train and test set has always been a challenge to the development of a robust face recognition system. The performance of the System was tested on locally acquired face database when the face database was randomly partitioned and when k-fold Cross Validation partition was used. The face database was captured under the condition of significant variations of rotation, illumination and facial expression. Quantitative evaluation experimental results showed that Random Sampling technique has a higher average recognition rate (96.7%) than Cross Validation partition method (95.3%). However, recognition time in Cross Validation is faster (0.36 secs) than that of Random Sampling (0.38 secs).

Trajectory‐based view‐invariant hand gesture recognition by fusing shape and orientation

Traditional studies in vision-based hand gesture recognition remain rooted in view-dependent representations, and hence users are forced to be fronto-parallel to the camera. To solve this problem, view-invariant gesture recognition aims to make the recognition result independent of viewpoint changes. However, in current works the view-invariance is achieved at the price of mixing different gesture patterns that have similar trajectory curve shape but different semantic meanings. For example, the gesture ‘push’ can be mistaken as ‘drag’ from another viewpoint. To address this shortcoming, in this study, the authors use a shape descriptor to extract the view-invariant features of a three-dimensional (3D) trajectory. As the shape features are invariant to omnidirectional viewpoint changes, the orientation features are then added into weight different rotation angles so that similar trajectory shapes are better separated. The proposed method was conducted on two different databases, including a popular Australian Sign Language database and a challenging Kinect Hand Trajectory database. Experimental results show that the proposed algorithm achieves a higher average recognition rate than the state-of-the-art approaches, and can better distinguish confusing gestures while meeting the view-invariant condition.

Performance characterization of the PET-CT tomograph at the PET-cyclotron-radiochemistry site of Messina University

The paper presents a face recognition system based on 3D features with the aim of verifying the identity of subjects accessing a controlled Ambient Intelligence Environment and customizing all the services accordingly. The proposed approach relies on stereoscopic face acquisition and 3D mesh reconstruction avoiding non automated and expensive 3D scanners, unsuitable for real time applications in general. A bidimensional feature descriptor is extracted from each 3D mesh. It consists in a color image transferring face's 3D features in a 2D space. An automatic weighting mask of each authorized person improves the robustness of recognition in presence of diverse facial expressions and beard. The experiments conducted show high average recognition rate and a measurable effectiveness of both flesh mask and expression weighting mask.

EEG based patient emotion monitoring using relative wavelet energy feature and Back Propagation Neural Network.

In EEG-based emotion recognition, feature extraction is as important as the classification algorithm. A good choice of features results in higher recognition rate. However, there is no standard method for feature extraction in EEG-based emotion recognition, especially for real time monitoring, where speed of computation is crucial. In this work, we assess the use of relative wavelet energy as features and Back Propagation Neural Network (BPNN) as classifier for emotion recognition. This method was implemented in simulated real time emotion recognition by using a publicly accessible database. The results showed that relative wavelet energy and BPNN achieved an average recognition rate of 92.03%. The highest average recognition rate was achieved when the time window was 30s.

Computer Intelligent Nursing Care of Critically III Patients Based on Improved Patient Facial Expression Recognition Method

In order to extract the expression features of critically ill patients, and realize the computer intelligent nursing, an improved facial expression recognition method is proposed based on the of active appearance model, the support vector machine (SVM) for facial expression recognition is taken in research, and the face recognition model structure active appearance model is designed, and the attribute reduction algorithm of rough set affine transformation theory is introduced, and the invalid and redundant feature points are removed. The critically ill patient expressions are classified and recognized based on the support vector machine (SVM). The face image attitudes are adjusted, and the self-adaptive performance of facial expression recognition for the critical patient attitudes is improved. New method overcomes the effect of patient attitude to the recognition rate to a certain extent. The highest average recognition rate can be increased about 7%. The intelligent monitoring and nursing care of critically ill patients are realized with the computer vision effect. The nursing quality is enhanced, and it ensures the timely treatment of rescue.

Upgrading FPGA Implementation of Isolated Word Recognition System for a Real-Time Operation

The article reports on the upgrading of the FPGA based isolated word recognition system for real-time tasks. All recognition system components (except some feature calculation steps) were implemented using VHDL. Some high precision calculations were implemented on soft core processor. The employed Dynamic time warping algorithm was speeded-up 2.8 times by restricting the calculated error matrix size. This enabled us to reduce the average word recognition time to 12.81 ms. Linear predictive coding, linear predictive coding cepstral and linear frequency cepstral coefficients feature analyses were investigated for 100 Lithuanian word recognition. In speaker dependent experiments linear predictive coding cepstral analysis gave the highest average recognition rate of 95 % and the highest robustness to white noise in speech. 15 dB noise level lowered average recognition rate to 86.2 %. DOI: http://dx.doi.org/10.5755/j01.eee.19.10.5907

Hand Gesture Recognition using Improved Hidden Markov Models

In this paper, an improved method of hand detecting and hand gesture recognition is proposed, it can be applied in different illumination condition and complex background. We use Adaptive Skin Threshold (AST) to detect the areas of hand. Then the result of hand detection is used to hand recognition through the improved HMM algorithm. At last, we design a simple program using the result of hand recognition for recognizing "stone, scissors, cloth" these three kinds of hand gesture. Experimental results had proved that the hand and gesture can be detected and recognized with high average recognition rate (92.41%) and better than some other methods such as syntactical analysis, neural based approach by using our approach.

A Codebook Design Method for Robust VQ-Based Face Recognition Algorithm

In this paper, we present a theoretical codebook design method for VQ-based fast face recognition algorithm to im-prove recognition accuracy. Based on the systematic analysis and classification of code patterns, firstly we theoretically create a systematically organized codebook. Combined with another codebook created by Kohonen’s Self-Organizing Maps (SOM) method, an optimized codebook consisted of 2×2 codevectors for facial images is generated. Experimental results show face recognition using such a codebook is more efficient than the codebook consisted of 4×4 codevector used in conventional algorithm. The highest average recognition rate of 98.6% is obtained for 40 persons’ 400 images of publicly available face database of AT&T Laboratories Cambridge containing variations in lighting, posing, and expressions. A table look-up (TLU) method is also proposed for the speed up of the recognition processing. By applying this method in the quantization step, the total recognition processing time achieves only 28 msec, enabling real-time face recognition.