Average Recognition Rate Research Articles

Research on Robot-Based Gesture Interactive Decoration Design

Recently, automata have become a research hott spot in various countries for a wide range of applications in areas such as security, entertainment, and industry. We designed a mobile robot which is based on gesture control with the focus on gesture interaction control which includes: gesture definition, hand gesture acquisition, hand gesture decoration, hand gesture pre-processing and hand pointer recognition in this paper.This paper uses a combination of qualitative analysis and quantitative research to study the mapping characteristics of gesture interactive decoration and its internal connection with user interaction behaviors by using a combination of theoretical analysis and situational experiments, which not only helps to understand the human-computer interaction decoration Complexity, it has important positive significance in theoretical discussion, research methods and experimental methods. The experiments show that the average recognition rate of the five gestures obtained in this paper reaches 92.5%. The robot can accurately recognize gestures and make corresponding actions

Experimental realization of visible gas sensing technology based on spatial heterodyne spectroscopy

Based on the characteristics of optical absorption gas sensing technology (OA-GST) and spatial heterodyne spectroscopy (SHS), a novel type of visual gas sensing technology (V-GST) can present the invisible gas information in the form of two-dimensional visual fingerprint, which has attracted people's attention. In this paper, we have realized the NO2 detection of V-GST in the laboratory environment for the first time. Experimental results show that: V-GST not only has different interferogram response to different spectra, but also has good response to different concentrations of NO2, which lays a foundation for the application of this technology in gas sensing. And the average classification recognition rate of the system for different band NO2 response data is over 80%, which verifies the effectiveness of the V-GST in gas detection.

Intelligent identification of two-phase flow patterns in a long pipeline-riser system

Accurate and rapid identification of multiphase flow patterns in long-distance pipelines is an important means for flow assurance. In this paper, an experiment of air-water two-phase flow has been carried out on a pipeline-S-shaped riser system with a length of 1687 m. Based on the amplitude of riser differential pressure, the working conditions are categorised into three typical flow patterns, severe slugging flow, oscillatory flow, and stable flow. Only two difference pressure signals that are most practical near the offshore platforms are used. The data of liquid phase accumulation of severe slugging is adopted as samples, and the signal features are extracted by wavelet multiresolution analysis. The parameters of six common classifiers are optimized, and the effects of different classifiers with the optimal hyperparameters on flow pattern recognition are compared and analyzed. For neural networks, decision trees, support vector machines and k-Nearest Neighbors classifier with the optimal hyperparameters, the recognition rate of severe slugging is higher than 95.8% and the average recognition rate of the three flow patterns is higher than 94.2% when the sample duration is only 6.2 s. On the premise of achieving the highest recognition rate, the number of features is substantially reduced to 15.6% of the original number by principal component analysis.

Correlation Analysis between Cultural Differences and Normal Music Perception Based on Embedded Voice Multisensor

In order to effectively improve the sense of difference brought by the extracorporeal machine to users and minimize the related derived problems, the implementation based on embedded multisensor has become a major breakthrough in the research of cochlear implant. To explore the impact of different cultural differences on timbre perception, effectively evaluate the correlation between cultural differences and music perception teaching based on embedded multisensor normal hearing, evaluate the discrimination ability of embedded multisensor normal hearing to music timbre, and analyse the correlation between cultural differences and timbre perception, it provides a basis for the evaluation of music perception of normal hearing people with embedded multisensor and the design and development of evaluation tool. In this paper, adults with normal hearing in different cultures matched with music experience are selected to test their recognition ability of different musical instruments and the number of musical instruments by using music evaluation software, and the recognition accuracy of the two tests is recorded. The results show that the accuracy of musical instrument recognition in the mother tongue group is 15% higher than that in the foreign language group, and the average recognition rates of oboe, trumpet, and xylophone in the foreign language group are lower than those in the mother tongue group, the recognition rate of oboe and trumpet in wind instruments was low in both groups, and the recognition rate of oboe and trumpet in foreign language group was high.

Feature Extraction of Ship Radiation Signals Based on Wavelet Packet Decomposition and Energy Entropy

The analysis of ship radiation signals to identify ships is an important research content of underwater acoustic signal processing. The traditional fast Fourier transform (FFT) is not suitable for analyzing non-stationary, non-Gaussian, and nonlinear signal processing. In order to realize the feature extraction and accurate classification of ship radiation signals with higher accuracy, a feature extraction method of ship radiation signals based on wavelet packet decomposition and energy entropy is proposed in this paper. According to wavelet packet decomposition, the ship radiation signal is decomposed into different frequency bands, and its energy entropy feature is extracted. As for comparisons, the center frequency and permutation entropy are also used as features to be extracted, then the k-nearest neighbor is applied to classify and recognize the extracted results. Based on the comparisons of wavelet packet decomposition, the center frequency, permutation entropy, and the k-nearest neighbor are used for classification and recognition. The experimental results present that, when comparing with center frequency and permutation entropy, the method based on energy entropy has the best availability, with the highest average recognition rate for four types of ship radiation signals, up to 98%.

An image recognition method for speed limit plate based on deep learning algorithm

In order to overcome the problems of large number of sample data collected from speed limit image and unclear image feature hierarchy, a recognition method for speed limit plate image based on deep learning algorithm is proposed. This method combines deep learning with SVM to build a multi-level classification model, and uses deep learning method to re-represent the original data through unsupervised learning. The image features of speed limit plate are extracted in depth, and the image is preprocessed by colour component compensation, image denoising and threshold segmentation. The similarity between the image features extracted layer by layer and the standard features is calculated, and the final recognition result of speed limit plate image is obtained through feature matching. The experimental results show that the average recognition rate is increased by 6.6%, which can effectively provide data reference for vehicle speed control in the actual driving process.

4D Facial Expression Recognition Using Geometric Landmark-based Axes-angle Feature Extraction

The primary goal of this paper is to describe a proposed framework for identifying human face expressions. A methodology has been proposed and developed to identify facial emotions using an axes-angular feature extracted from facial landmarks for 4D dynamic facial expression video data. The 4D facial expression recognition (FER) problem is modeled as an unbalanced problem using the full video sequence. The proposed dataset includes landmarks that are positioned to be fiducial features: around the brows, eyes, nose, cheeks, and lips. Following the initial facial landmark preprocessing, feature extraction is carried out. Input feature vectors from gamma axes and magnitudes in three-dimensional Euclidean space are constructed. This paper develops a new feature vector by concatenating the angle and magnitude features and compares them to a model created independently using angle features. In all three models, several filter-based feature selection techniques are used to estimate feature importance. The framework employs a multi-class support vector machine (SVM) on MATLAB, and the true positive rate (TPR) and average recognition rates (ARR) are used as performance metrics. In terms of average classification accuracy, the final results are compared to conventional state-of-the-art approaches. The results revealed a highly informative combined feature, demonstrating the efficiency of the proposed landmark-based strategy to classify facial expressions.

Recognition Method of Dim and Small Targets in SAR Images based on Machine Vision

Aiming at the problems of long recognition time and low recognition accuracy of traditional SAR image dim target recognition methods, a method of SAR image dim target recognition based on machine vision was proposed. SAR images are collected and preprocessed by machine vision, and the image information is processed by PCA dimension reduction considering the linear characteristics of the data to extract image features. Then, the SAR image target feature key frame frequency band is divided by the segmentation results, and the recognition model is established based on the image trajectory tracking and target analysis. The proposed algorithm is applied and analyzed. The simulation results show that the proposed algorithm has good recognition rate, average recognition rate and false detection rate are 99% and 0.9%, and can effectively ensure the data processing performance.

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.

Concrete Damage Identification based on Acoustic Emission and Wavelet Neural Network

In order to improve the accuracy of damage source identification in concrete based on acoustic emission testing (AE) and neural networks, and locating and repairing the damage in a practical roller compacted concrete (RCC) dam, a multilevel AE processing platform based on wavelet energy spectrum analysis, principal component analysis (PCA), and a neural network is proposed. Two data sets of 15 basic AE parameters and 23 AE parameters added on the basis of the 15 basic AE parameters were selected as the input vectors of a basic parameter neural network and a wavelet neural network, respectively. Taking the measured tensile data of an RCC prism sample as an example, the results show that compared with the basic parameter neural network, the wavelet neural network achieves a higher accuracy and faster damage source identification, with an average recognition rate of 8.2% and training speed of about 33%.

Research on Fast Identification and Location of Contour Features of Electric Vehicle Charging Port in Complex Scenes

The maturity of automatic driving and parking technologies is gradually driving electric vehicle charging toward automation. The primary condition of automatic charging that has a high significance is the identification of electric vehicle charging ports. This research proposes an automatic system for the identification and positioning of charging ports of electric vehicles. The system is mainly divided into rough and precise positioning. The former is based on the Hough circle and the Hough line, and locates the position information of the charging port. The latter uses the Canny operator to obtain the contour information of the original and gradient images respectively. All the contours of the two images are fitted into ellipses by the quadratic curve standardization (QCS) method, and irrelevant ellipses are screened out. Finally, the perspective-n-point (PNP) algorithm is used to locate the pose information of the charging port. The aubo-i10 6-DOF articulated robot is used to test the recognition and insertion accuracies in different environments. The results show that the average recognition rate of rough positioning is 97.9%, the average displacement error of precise positioning in X, Y and Z directions are 0.60, 0.83 and 1.23 mm, respectively, and the average angle errors in RX, RY and RZ directions are 1.19, 0.97 and 0.50 degrees, respectively. The average success rate is 94.8%. These results demonstrate that the proposed system meets the basic plug-in requirements of electric vehicle charging ports.

Analysis of the Correlation between Football Education Environment and Students' Psychology Health Based on Gauss Characteristics.

Campus football has become a core content of school physical education. Through football education, we can cultivate students' sound personality and promote students' all-round physical and mental development. At the same time, through psychological skills training methods, we can enrich the educational methods of football skills and provide theoretical reference for promoting educational reform. On the basis of Gaussian features, this paper combines the mixed Gaussian feature model to further describe the relationship between football education and students' psychology. At the same time, Apriori association rule algorithm in data mining is introduced, and Apriori algorithm is improved in parallel with Hadoop data processing platform. Several parallel association rule algorithms are emphatically studied and analyzed to strengthen the analysis of the relationship between football education and students' psychology. The results show that the average recognition rate of the correlation between football education and students' psychology based on Gaussian features is 17.91% higher than that of ordinary results, which obviously improves the correlation recognition result and has a good descriptive ability. Therefore, it has become an important issue for today's physical education workers to analyze the correlation between football education and students' psychology in order to cultivate students' sports and mental health.

A Study of Artificial Neural Network Technology Applied to Image Recognition for Underwater Images

In this study, the researchers developed holographic image software for the Polaris, a nongovernmental Taiwanese oceanographic research vessel. It is a survey vessel that was codeveloped through an industry–academia collaboration between National Kaohsiung University of Science and Technology and Dragon Prince Hydro-Survey Enterprise Co. With a weight of 260 tons, length of 36.98 m, and width of 6.80 m, the vessel can travel at a speed of 11 knots. It has undergone underwater rescue and exploration operations and is therefore fairly experienced in such operations. When performing underwater exploration missions, survey vessels are often faced with interferences caused by factors such as current velocity; water temperature, refraction, and spectral conditions; climate; ocean current; presence of algae; and light reflection from schools of fish. Therefore, instantaneous image analysis is imperative for marine exploration. In accordance with the instantaneous recognition needs of the Polaris, the researchers developed artificial-neural-network-based recognition software for rapidly recognizing the category of a detected underwater object. Recognition of shapes in low-resolution underwater images was improved using a neural network resulting in an average recognition rate of 95%. Analysis of variance also indicated that the neural network yielded a significantly higher recognition rate than did manual recognition.

Recognition Method for Face Local Features Based on Fuzzy Algorithm and Intelligent Data Analysis

Traditional recognition methods for face local features have a low recognition rate, so the recognition method for face local features based on the fuzzy algorithm and intelligent data analysis was designed. Firstly, the wavelet denoising method was used to reduce the noise of face images, and adaptive template matching was performed on the obtained images. Then, the face information was encoded, and the face features were identified to locate the face features. On this basis, the principal components of the face were analyzed to obtain the global features of the face. Finally, through the candidate set of facial local feature recognition, the extraction of face local features, and the fusion of face local features, the recognition of local face features were realized. The experimental results show that the average recognition rate of this method is 88.84% in a noise environment and 97.3% in noise‐free environment. It can accurately recognize the face local features, can meet the needs of recognition of the face local features, and has certain practical application significance.

Concrete Damage Identification based on Acoustic Emission and Wavelet Neural Network

In order to improve the accuracy of damage source identification in concrete based on acoustic emission testing (AE) and neural networks, and locating and repairing the damage in a practical roller compacted concrete (RCC) dam, a multilevel AE processing platform based on wavelet energy spectrum analysis, principal component analysis (PCA), and a neural network is proposed. Two data sets of 15 basic AE parameters and 23 AE parameters added on the basis of the 15 basic AE parameters were selected as the input vectors of a basic parameter neural network and a wavelet neural network, respectively. Taking the measured tensile data of an RCC prism sample as an example, the results show that compared with the basic parameter neural network, the wavelet neural network achieves a higher accuracy and faster damage source identification, with an average recognition rate of 8.2% and training speed of about 33%.

Rapid and nondestructive determination of sorghum purity combined with deep forest and near-infrared hyperspectral imaging

This study combined hyperspectral imaging (HSI) and deep forest (DF) to develop a reliable model for conducting a rapid and nondestructive determination of sorghum purity. Isolated forest (IF) algorithm and principal component analysis (PCA) were used to remove the abnormal data of sorghum grains. Competitive adaptive reweighted sampling (CARS) algorithm and successive projections algorithm (SPA) were combined and used to extract the characteristic wavelengths. Gray-level co-occurrence matrix (GLCM) was used to extract the textural features. DF models were established based on the different types of data. Specifically, the DF models established using the characteristic spectra produced the best recognition results: the average correct recognition rate (CRR) of the models was greater than 91%. In addition, the average CRR of validation set Ⅰ was 88.89%. These results show that a combination of HSI and DF could be used for the rapid and nondestructive determination of sorghum purity.

The Detection of Impurity Content in Machine-Picked Seed Cotton Based on Image Processing and Improved YOLO V4

The detection of cotton impurity rates can reflect the cleaning effect of cotton impurity removal equipment, which plays a vital role in improving cotton quality and economic benefits. Therefore, several studies are being carried out to improve detection accuracy. Image processing technology is increasingly used in cotton impurity detection, in which deep learning technology based on convolution neural networks has shown excellent results in image classification, segmentation, target detection, etc. However, most of these applications focus on detecting foreign fibers in lint, which is of little significance to the parameter adjustment of cotton impurity removal equipment. For this reason, our goal was to develop an impurity detection system for seed cotton. In image segmentation, we propose a multi-channel fusion segmentation algorithm to segment the machine-picked seed cotton image. We collected 1017 images of machine-picked seed cotton as a dataset to train the detection model and tested and recognized 100 groups of samples, with an average recognition rate of 94.1%. Finally, the image segmented by the multi-channel fusion algorithm is input into the improved YOLOv4 network model for classification and recognition, and the established V–W model calculates the content of all kinds of impurities. The experimental results show that the impurity content in machine-picked cotton can be obtained effectively, and the detection accuracy of the impurity rate can increase by 5.6%.

Handwriting-Assistant

Pen-based handwriting has become one of the major human-computer interaction methods. Traditional approaches either require writing on the specific supporting device like the touch screen, or limit the way of using the pen to pure rotation or translation. In this paper, we propose Handwriting-Assistant, to capture the free handwriting of ordinary pens on regular planes with mm-level accuracy. By attaching the inertial measurement unit (IMU) to the pen tail, we can infer the handwriting on the notebook, blackboard or other planes. Particularly, we build a generalized writing model to correlate the rotation and translation of IMU with the tip displacement comprehensively, thereby we can infer the tip trace accurately. Further, to display the effective handwriting during the continuous writing process, we leverage the principal component analysis (PCA) based method to detect the candidate writing plane, and then exploit the distance variation of each segment relative to the plane to distinguish on-plane strokes. Moreover, our solution can apply to other rigid bodies, enabling smart devices embedded with IMUs to act as handwriting tools. Experiment results show that our approach can capture the handwriting with high accuracy, e.g., the average tracking error is 1.84mm for letters with the size of about 2cmx1cm, and the average character recognition rate of recovered single letters achieves 98.2% accuracy of the ground-truth recorded by touch screen.

Motor Imagination of Lower Limb Movements at Different Frequencies.

Motor imagination (MI) is the mental process of only imagining an action without an actual movement. Research on MI has made significant progress in feature information detection and machine learning decoding algorithms, but there are still problems, such as a low overall recognition rate and large differences in individual execution effects, which make the development of MI run into a bottleneck. Aiming at solving this bottleneck problem, the current study optimized the quality of the MI original signal by “enhancing the difficulty of imagination tasks,” conducted the qualitative and quantitative analyses of EEG rhythm characteristics, and used quantitative indicators, such as ERD mean value and recognition rate. Research on the comparative analysis of the lower limb MI of different tasks, namely, high-frequency motor imagination (HFMI) and low-frequency motor imagination (LFMI), was conducted. The results validate the following: the average ERD of HFMI (−1.827) is less than that of LFMI (−1.3487) in the alpha band, so did (−3.4756 < −2.2891) in the beta band. In the alpha and beta characteristic frequency bands, the average ERD of HFMI is smaller than that of LFMI, and the ERD values of the two are significantly different (p=0.0074 < 0.01; r = 0.945). The ERD intensity STD values of HFMI are less than those of LFMI. which suggests that the ERD intensity individual difference among the subjects is smaller in the HFMI mode than in the LFMI mode. The average recognition rate of HFMI is higher than that of LFMI (87.84% > 76.46%), and the recognition rate of the two modes is significantly different (p=0.0034 < 0.01; r = 0.429). In summary, this research optimizes the quality of MI brain signal sources by enhancing the difficulty of imagination tasks, achieving the purpose of improving the overall recognition rate of the lower limb MI of the participants and reducing the differences of individual execution effects and signal quality among the subjects.

Stack LSTM-Based User Identification Using Smart Shoes with Accelerometer Data.

In this study, we propose a long short-term memory (LSTM)-based user identification method using accelerometer data from smart shoes. In general, for the user identification with human walking data, we require a pre-processing stage in order to divide human walking data into individual steps. Next, user identification can be made with divided step data. In these approaches, when there exist partial data that cannot complete a single step, it is difficult to apply those data to the classification. Considering these facts, in this study, we present a stack LSTM-based user identification method for smart-shoes data. Rather than using a complicated analysis method, we designed an LSTM network for user identification with accelerometer data of smart shoes. In order to learn partial data, the LSTM network was trained using walking data with random sizes and random locations. Then, the identification can be made without any additional analysis such as step division. In the experiments, user walking data with 10 m were used. The experimental results show that the average recognition rate was about 93.41%, 97.19%, and 98.26% by using walking data of 2.6, 3.9, and 5.2 s, respectively. With the experimental results, we show that the proposed method can classify users effectively.