scholarly journals Noise and Memristance Variation Tolerance of Single Crossbar Architectures for Neuromorphic Image Recognition

Micromachines ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 690
Author(s):  
Minh Le ◽  
Thi Kim Hang Pham ◽  
Son Ngoc Truong
Keyword(s):  
Pattern Recognition ◽  
Image Recognition ◽  
Gaussian Noise ◽  
Signal To Noise Ratio ◽  
Recognition Rate ◽  
Aluminum Film ◽  
Successful Implementation ◽  
Crossbar Architecture ◽  
Variation Tolerance ◽  
Memristor Crossbar

We performed a comparative study on the Gaussian noise and memristance variation tolerance of three crossbar architectures, namely the complementary crossbar architecture, the twin crossbar architecture, and the single crossbar architecture, for neuromorphic image recognition and conducted an experiment to determine the performance of the single crossbar architecture for simple pattern recognition. Ten grayscale images with the size of 32×32 pixels were used for testing and comparing the recognition rates of the three architectures. The recognition rates of the three memristor crossbar architectures were compared to each other when the noise level of images was varied from -10 to 4 dB and the percentage of memristance variation was varied from 0% to 40%. The simulation results showed that the single crossbar architecture had the best Gaussian noise input and memristance variation tolerance in terms of recognition rate. At the signal-to-noise ratio of –10 dB, the single crossbar architecture produced a recognition rate of 91%, which was 2% and 87% higher than those of the twin crossbar architecture and the complementary crossbar architecture, respectively. When the memristance variation percentage reached 40%, the single crossbar architecture had a recognition rate as high as 67.8%, which was 1.8% and 9.8% higher than the recognition rates of the twin crossbar architecture and the complementary crossbar architecture, respectively. Finally, we carried out an experiment to determine the performance of the single crossbar architecture with a fabricated 3 × 3 memristor crossbar based on carbon fiber and aluminum film. The experiment proved successful implementation of pattern recognition with the single crossbar architecture.

scholarly journals The Design and Realization of Cherry Tomato Harvesting Robot Based on IOT

2016 ◽  
Vol 12 (12) ◽  
pp. 23 ◽  
Author(s):  
Biqing Li ◽  
Yongfa Ling ◽  
Hongyan Zhang ◽  
Shiyong Zheng
Keyword(s):  
Image Recognition ◽  
Recognition Rate ◽  
Control Technology ◽  
Original Image ◽  
Cherry Tomato ◽  
Modular Control ◽  
Breakage Rate ◽  
Harvesting Efficiency ◽  
Technology Processes ◽  
Harvesting Robot

To improve the efficiency of harvesting cherry tomato and reduce its breakage rate, we design a harvesting robot base on image recognition and modular control. After image acquisition with IOT technology, the binary processing and expansion and corrosion processing of original image can effectively increase the fruit recognition rate. In addition, the use of fuzzy control technology processes the response error of manipulator. We test the performance of cherry tomato harvesting robot through harvesting experiment. The experimental results show that the harvesting efficiency significantly improves and the degree of crushing cherry tomato greatly reduces after using the cherry tomato harvesting robot.

Research on Modulation Recognition Algorithm of Digital Communication Signal Based on Wavelet Denoising

2014 ◽  
Vol 608-609 ◽  
pp. 459-467 ◽  
Author(s):  
Xiao Yu Gu
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Decision Theory ◽  
Recognition Rate ◽  
Recognition Algorithm ◽  
Modulation Recognition ◽  
The Core ◽  
Feature Parameters ◽  
Communication Signal ◽  
Modulation Signal

The paper researches a recognition algorithm of modulation signal and modulation modes. The modulation modes to be recognized include 2ASK, 2FSK, 2PSK, 4ASK, 4FSK and 4PSK modulation. There are two methods recognizing modulation modes of digital signal, method based on decision theory and pattern-recognition method based on feature extraction. The method based on decision theory is not suitable for recognition with multiple modulation modes. The core of pattern recognition based on feature extraction is selection of feature parameters. So the paper uses the feature parameters with simple calculation, easy to be implemented and high recognition rate as the core. The extraction of feature parameters is based on instant feature of modulation signal after Hilbert transformation.

Improving Pattern Recognition Rate by Gaussian Hopfield Neural Network

2011 ◽  
Vol 189-193 ◽  
pp. 2042-2045 ◽  
Author(s):  
Shang Jen Chuang ◽  
Chiung Hsing Chen ◽  
Chien Chih Kao ◽  
Fang Tsung Liu
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Gaussian Distribution ◽  
Test Pattern ◽  
Recognition Rate ◽  
Hopfield Neural Network ◽  
Training Data ◽  
New Method ◽  
Gaussian Filter ◽  
Testing Data

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%.

scholarly journals Smooth Signal Activity Detection in White Gaussian Noise: Application to P300 Detection

2021 ◽  
Author(s):  
Ali Mobaien ◽  
Reza Boostani ◽  
Negar Kheirandish
Keyword(s):  
Gaussian Noise ◽  
Signal To Noise Ratio ◽  
Hypothesis Test ◽  
White Gaussian Noise ◽  
Least Square ◽  
Unknown Parameters ◽  
Detection Scheme ◽  
Ml Estimation ◽  
Unknown Variance ◽  
Synthetic Datasets

<div>Abstract—In this research, we have proposed a new scheme to detect and extract the activity of an unknown smooth template in presence of white Gaussian noise with unknown variance. In this regard, the problem is considered a binary hypothesis test, and it is solved employing the generalized likelihood ratio (GLR) method. GLR test uses the maximum likelihood (ML) estimation of unknown parameters under each hypothesis. The ML estimation of the desired signal yields an optimization problem with smoothness constraint which is in the form of a conventional least square error estimation problem and can be solved optimally. The proposed detection scheme is studied for P300 elicitation from the background electroencephalography signal. In addition, to assume the P300 smoothness, two prior knowledge are considered in terms of positivity and approximate occurrence time of P300. The performance of the method is assessed on both real and synthetic datasets in different noise levels and compared to a conventional signal detection scheme without considering smoothness priors, as well as state-of-theart linear and quadratic discriminant analysis. The results are illustrated in terms of detection probability, false alarm rate, and accuracy. The proposed method outperforms the counterparts in low signal-to-noise ratio situations.</div>

scholarly journals Minimum Array Elements for Resolution of Several Direction of Arrival Estimation Methods in Various Noise-Level Environments

2018 ◽  
Vol 2 ◽  
pp. 87-94
Author(s):  
Ismail El Ouargui ◽  
Said Safi ◽  
Miloud Frikel
Keyword(s):  
Gaussian Noise ◽  
Noise Level ◽  
Signal To Noise Ratio ◽  
Additive White Gaussian Noise ◽  
Direction Of Arrival ◽  
Estimation Algorithm ◽  
Doa Estimation ◽  
Estimation Methods ◽  
Minimum Number ◽  
Informative Signals

The resolution of a Direction of Arrival (DOA) estimation algorithm is determined based on its capability to resolve two closely spaced signals. In this paper, authors present and discuss the minimum number of array elements needed for the resolution of nearby sources in several DOA estimation methods. In the real world, the informative signals are corrupted by Additive White Gaussian Noise (AWGN). Thus, a higher signal-to-noise ratio (SNR) offers a better resolution. Therefore, we show the performance of each method by applying the algorithms in different noise level environments.

scholarly journals Research on Speaker Recognition of DRNN in Different Noise Environment

2020 ◽  
Author(s):  
chaofeng lan ◽  
yuanyuan Zhang ◽  
hongyun Zhao
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Recurrent Neural Network ◽  
Speaker Recognition ◽  
Signal To Noise Ratio ◽  
Recognition Rate ◽  
Noisy Environment ◽  
Signal To Noise ◽  
Noise Ratio ◽  
Improved Model

Abstract This paper draws on the training method of Recurrent Neural Network (RNN), By increasing the number of hidden layers of RNN and changing the layer activation function from traditional Sigmoid to Leaky ReLU on the input layer, the first group and the last set of data are zero-padded to enhance the effective utilization of data such that the improved reduction model of Denoise Recurrent Neural Network (DRNN) with high calculation speed and good convergence is constructed to solve the problem of low speaker recognition rate in noisy environment. According to this model, the random semantic speech signal with a sampling rate of 16 kHz and a duration of 5 seconds in the speech library is studied. The experimental settings of the signal-to-noise ratios are − 10dB, -5dB, 0dB, 5dB, 10dB, 15dB, 20dB, 25dB. In the noisy environment, the improved model is used to denoise the Mel Frequency Cepstral Coefficients (MFCC) and the Gammatone Frequency Cepstral Coefficents (GFCC), impact of the traditional model and the improved model on the speech recognition rate is analyzed. The research shows that the improved model can effectively eliminate the noise of the feature parameters and improve the speech recognition rate. When the signal-to-noise ratio is low, the speaker recognition rate can be more obvious. Furthermore, when the signal-to-noise ratio is 0dB, the speaker recognition rate of people is increased by 40%, which can be 85% improved compared with the traditional speech model. On the other hand, with the increase in the signal-to-noise ratio, the recognition rate is gradually increased. When the signal-to-noise ratio is 15dB, the recognition rate of speakers is 93%.

A New Location Method of ROI for Contactless Palm Vein Recognition

2013 ◽  
Vol 760-762 ◽  
pp. 1398-1401
Author(s):  
Wei Wu ◽  
Wei Qi Yuan ◽  
Hui Song
Keyword(s):  
Pattern Recognition ◽  
Recognition Rate ◽  
New Method ◽  
Vein Pattern ◽  
Location Method ◽  
Vein Recognition ◽  
Palm Vein ◽  
New Location

Palm vein pattern recognition is one of the newest biometric techniques researched today.At present, literatures selecte the center of the palm as the ROI of palm vein recognition. However the vein image in this area is not clear in some peoples palm. In this paper, we proposed a new location method of ROI which takes thenar area as the ROI. In the experiment part, it compares the recognition rate between the new and the traditional ROI in self-established contactless palm vein database. The result shows that this new method has got the recognition rate of 98.9258% and has increased recognition rate 2.0911% compared with the traditional one.

Sequential Memristor Crossbar for Neuromorphic Pattern Recognition

2016 ◽  
Vol 15 (6) ◽  
pp. 922-930 ◽  
Author(s):  
Son Ngoc Truong ◽  
Khoa Van Pham ◽  
Wonsun Yang ◽  
Kyeong-Sik Min
Keyword(s):  
Pattern Recognition ◽  
Memristor Crossbar
Sign in / Sign up

Export Citation Format

Share Document