Improvement Of Pattern Recognition Rate Using Hybrid Learning-reverse Learning Processes Of Neural Network

English letters cannot be recognized by the Hopfield Neural Network if it contains noise over 50%. This paper proposes a new method to improve recognition rate of the Hopfield Neural Network. To advance it, we add the Gaussian distribution feature to the Hopfield Neural Network. The Gaussian filter was added to eliminate noise and improve Hopfield Neural Network’s recognition rate. We use English letters from ‘A’ to ‘Z’ as training data. The noises from 0% to 100% were generated randomly for testing data. Initially, we use the Gaussian filter to eliminate noise and then to recognize test pattern by Hopfield Neural Network. The results are we found that if letters contain noise between 50% and 53% will become reverse phenomenon or unable recognition [6]. In this paper, we propose to uses multiple filters to improve recognition rate when letters contain noise between 50% and 53%.

Download Full-text

Application of ART-2 Neural Network and Invariant Moment in Image Pattern Recognition

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.433-440.4014 ◽

2012 ◽

Vol 433-440 ◽

pp. 4014-4019 ◽

Cited By ~ 22

Author(s):

Lei Hao ◽

Yue Hua Gao ◽

Rui Jun Jia

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Feature Extraction ◽

Recognition Rate ◽

Experimental Results ◽

Invariant Moment ◽

Recognition Model ◽

Image Pattern

This paper mainly uses image pre-processing and feature extraction to calculate the invariant moment of image, and ultimately realizes the image pattern recognition based on ART-2 neural network. Experimental results show that ART-2 neural network has high recognition rate. It also solves the contradiction between network's plasticity and stability, when new recognition model appears.

Download Full-text

Rough Set Neural Network Feature Extraction and Pattern Recognition of Shaft Orbits Based on the Zernike Moment

Shock and Vibration ◽

10.1155/2021/6680640 ◽

2021 ◽

Vol 2021 ◽

pp. 1-11

Author(s):

Xinfeng Ge ◽

Jing Zhang ◽

Ye Zhou ◽

Jianguo Cai ◽

Hui Zhang ◽

...

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Feature Extraction ◽

Fault Diagnosis ◽

Hybrid Model ◽

Rough Set ◽

Recognition Rate ◽

Zernike Moment ◽

Calculation Error ◽

Time Step

In the shaft axis monitoring of hydrogenerating unit condition monitoring and fault diagnosis, the shaft orbit is intuitive and comprehensively reflects the unit operation state, and different shaft orbits correspond to different fault types, which can accurately indicate a system vibration fault. Shaft orbit identification has important significance for vibration fault diagnosis. In getting the feature extraction and pattern recognition of a shaft orbit, the Zernike moment is better than the Hu moment; it has the advantages of a small calculation error and a high recognition rate. A rough set neural network (RS-BP hybrid model) of shaft orbit recognition is established, which uses just 13 moment eigenvalues reserved by the rough set feature selection algorithm as input variables; it has the same calculation error and recognition rate and reduces the calculation time step. The simulation of the recognition of shaft orbits shows that the hybrid model has achieved good results in the identification of shaft orbits.

Download Full-text

Real-Time Surface EMG Pattern Recognition for Hand Gestures Based on an Artificial Neural Network

Sensors ◽

10.3390/s19143170 ◽

2019 ◽

Vol 19 (14) ◽

pp. 3170 ◽

Cited By ~ 17

Author(s):

Zhang ◽

Yang ◽

Qian ◽

Zhang

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Artificial Neural Network ◽

Real Time ◽

Recognition Rate ◽

Recognition System ◽

Test Method ◽

Training Dataset ◽

Artificial Neural ◽

Semg Signals

In recent years, surface electromyography (sEMG) signals have been increasingly used in pattern recognition and rehabilitation. In this paper, a real-time hand gesture recognition model using sEMG is proposed. We use an armband to acquire sEMG signals and apply a sliding window approach to segment the data in extracting features. A feedforward artificial neural network (ANN) is founded and trained by the training dataset. A test method is used in which the gesture will be recognized when recognized label times reach the threshold of activation times by the ANN classifier. In the experiment, we collected real sEMG data from twelve subjects and used a set of five gestures from each subject to evaluate our model, with an average recognition rate of 98.7% and an average response time of 227.76 ms, which is only one-third of the gesture time. Therefore, the pattern recognition system might be able to recognize a gesture before the gesture is completed.

Download Full-text

Recognition of Brahmi Words by Using Deep Convolutional Neural Network

10.20944/preprints202005.0455.v1 ◽

2020 ◽

Author(s):

Neha Gautam ◽

Soo See Chai ◽

Jais Jose

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Convolutional Neural Network ◽

Recognition Rate ◽

Image Database ◽

Deep Convolutional Neural Network ◽

Significant Progress ◽

Practical Operation ◽

Series Of Experiments ◽

Made In

Significant progress has made in pattern recognition technology. However, one obstacle that has not yet overcome is the recognition of words in the Brahmi script, specifically the identification of characters, compound characters, and word. This study proposes the use of the deep convolutional neural network with dropout to recognize the Brahmi words. This study also proposed a DCNN for Brahmi word recognition and a series of experiments are performed on standard Brahmi dataset. The practical operation of this method was systematically tested on accessible Brahmi image database, achieving 92.47% recognition rate by CNN with dropout respectively which is among the best while comparing with the ones reported in the literature for the same task.

Download Full-text

IDENTIFIKASI POLA IRIS MENGGUNAKAN METODE BACKPROPAGATION

Manutech : Jurnal Teknologi Manufaktur ◽

10.33504/manutech.v8i02.21 ◽

2019 ◽

Vol 8 (02) ◽

pp. 43-48

Author(s):

Yoan Elviralita ◽

Asrul Hidayat

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Unknown Parameter ◽

Recognition Rate ◽

Backpropagation Neural Network ◽

Excellent Performance ◽

Controlling System

In recent years, there has been a lot of research related to pattern recognition is conducted to identify various forms of patterns and controlling system. Utilizing backpropagation neural network in pattern identifying is very useful to solve problems with unknown parameter and difficult to determined. And then the data of the pattern are trained and tested. The results obtained from the recognition rate indicates a backpropagation neural network, provide excellent performance, which is an average of 98%. This neural network is expected to be developed by other researchers for the advancement of knowledge in all fields.

Download Full-text

Comparison between BP and RBF Neural Network Pattern Recognition Process Applied in the Droplet Analyzer

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.543-547.2333 ◽

2014 ◽

Vol 543-547 ◽

pp. 2333-2336

Author(s):

Qing Song ◽

Gao Jie Meng ◽

Lu Yang ◽

Dan Qing Du ◽

Xue Fei Mao

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Liquid Droplet ◽

Rbf Neural Network ◽

Recognition Rate ◽

Uncertain System ◽

Training Data ◽

Waveform Analysis ◽

Bp Network ◽

Rbf Network

Among various pattern recognition methods used for liquid identification, the method based on neural network has the advantages of robustness and fault tolerance, which can study and adapt to the uncertain system. The waveform analysis is exploited for feature extraction of the liquid droplet fingerprint (LDF) in this paper, and the liquid identification is carried out by means of BP and RBF neural network. The experimental results proved that the recognition rate is excellent in both of these two methods. In condition that the training data is limited, RBF network is better than BP network in recognition speed and rate.

Download Full-text

Pattern Recognition of the Steel Rod Based on Artificial Neural Network and SVM

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.301-303.329 ◽

2011 ◽

Vol 301-303 ◽

pp. 329-333

Author(s):

Hong Chun Sun

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Artificial Neural Network ◽

Large Scale ◽

Recognition Rate ◽

Support Vector ◽

Artificial Neural ◽

Defects Identification ◽

The Time Domain ◽

Frequency Band Energy

The steel rod is an important part for project fields , and it is large-scale to be used. it is apt to crack, corrosion and so on in the poor working conditions. In order to recognize correctly the type of defects, a method was presented to extract frequency band energy feature by using wavelet package decomposition. In the meantime, to extract the peak-peak value in the time-domain and make the mixed feature vector. With the way of pattern recognition, the best recognition way was got by comparing the BP artificial neural network(ANN), PNN(probability neural network) artificial neural network and "one-versus-one" support vector machine(SVM).The result showed that the recognition rate of SVM was more suitable for defects’ identification in steel rod.

Download Full-text

Analysis of Back Propagation Neural Network Method for Heart Disease Recognition

International Journal of Organizational and Collective Intelligence ◽

10.4018/ijoci.2019040104 ◽

2019 ◽

Vol 9 (2) ◽

pp. 45-54

Author(s):

Amit K. Gupta ◽

Ajay Agarwal ◽

Ruchi Rani Garg

Keyword(s):

Neural Network ◽

Pattern Recognition ◽

Wavelet Transform ◽

Bp Neural Network ◽

Heart Diseases ◽

Recognition Rate ◽

P Wave ◽

Experimental Result ◽

Qrs Complex ◽

T Wave

ECG is the recording of the electrical activity of the heart, and has become one of the most important tools in the diagnosis of heart diseases. ECG signal is shaped by P wave, QRS complex, and T wave. In the normal ECG beat, the main parameters including shape, duration, R-R interval and relationship between P wave, QRS complex, and T wave components are inspected. Any change in these parameters indicates an illness of the heart. This article introduces an electrocardiogram (ECG) pattern recognition method based on wavelet transform and standard BP neural network classifier. Experiment analyzes wavelet transform of ECG to extract the maximum wavelet coefficients of multi-scale firstly. This article then inputs them into BP to classify for different kinds of ECGs. The experimental result shows that the standard BP neural network classifier's overall pattern recognition rate is well.

Download Full-text