Pattern Recognition of Handwritten English Characters

2020 ◽  
pp. 128-144
Keyword(s):  
Pattern Recognition ◽  
Deep Learning ◽  
Problem Solving ◽  
Recognition Accuracy ◽  
Accuracy Rate ◽  
Long Time ◽  
Handwritten Digit ◽  
Online Tests

After success of a total solution to handwriting 99 multiplication by deep learning, this chapter further addresses on the problem with increased complexity. In addition to handwritten digital dataset, the EMNIST database provides multiple balanced or unbalanced datasets. These datasets contain different combinations of handwritten digit and letter images. It is believed that well trained deep CNNs can handle unbalanced datasets, so this chapter chose By_Class of EMNIST database as a dataset to increase the difficulty of problem solving and extend the application of iOS Apps. This chapter discusses classification of handwritten English character, including uppercase and lowercase, data audition due to requirement of further improvement, and online tests on iOS devices. After a long time of training, the developer got the pre-trained CNN model. For 58,405 testing images, the recognition accuracy rate was as high as 97.0%.

Voice Recognition from Spectrograms: A Wavelet Based Approach

Fractals ◽  
1997 ◽  
Vol 05 (supp01) ◽  
pp. 165-172 ◽  
Author(s):  
G. van de Wouwer ◽  
P. Scheunders ◽  
D. van Dyck ◽  
M. de Bodt ◽  
F. Wuyts ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Recognition Accuracy ◽  
Voice Recognition ◽  
Original Signal ◽  
Pattern Recognition Technique ◽  
Time Frequency ◽  
Novel Method ◽  
Recognition Technique

The performance of a pattern recognition technique is usually determined by the ability of extracting useful features from the available data so as to effectively characterize and discriminate between patterns. We describe a novel method for feature extraction from speech signals. For this purpose, we generate spectrograms, which are time-frequency representations of the original signal. We show that, by considering this spectrogram as a textured image, a wavelet transform can be applied to generate useful features for recognizing the speech signal. This method is used for the classification of voice dysphonia. Its performance is compared with another technique taken from the literature. A recognition accuracy of 98% is achieved for the classification between normal an dysphonic voices.

scholarly journals Detection and classification of intracranial haemorrhage on CT images using a novel deep-learning algorithm

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Ji Young Lee ◽  
Jong Soo Kim ◽  
Tae Yoon Kim ◽  
Young Soo Kim
Keyword(s):  
Deep Learning ◽  
Intracranial Haemorrhage ◽  
Diagnostic Performance ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Emergency Situation ◽  
Ct Images ◽  
Accuracy Rate ◽  
Deep Learning Algorithm

AbstractA novel deep-learning algorithm for artificial neural networks (ANNs), completely different from the back-propagation method, was developed in a previous study. The purpose of this study was to assess the feasibility of using the algorithm for the detection of intracranial haemorrhage (ICH) and the classification of its subtypes, without employing the convolutional neural network (CNN). For the detection of ICH with the summation of all the computed tomography (CT) images for each case, the area under the ROC curve (AUC) was 0.859, and the sensitivity and the specificity were 78.0% and 80.0%, respectively. Regarding ICH localisation, CT images were divided into 10 subdivisions based on the intracranial height. With the subdivision of 41–50%, the best diagnostic performance for detecting ICH was obtained with AUC of 0.903, the sensitivity of 82.5%, and the specificity of 84.1%. For the classification of the ICH to subtypes, the accuracy rate for subarachnoid haemorrhage (SAH) was considerably excellent at 91.7%. This study revealed that our approach can greatly reduce the ICH diagnosis time in an actual emergency situation with a fairly good diagnostic performance.

scholarly journals Research on Segmentation and Classification of Heart Sound Signals Based on Deep Learning

2021 ◽  
Vol 11 (2) ◽  
pp. 651
Author(s):  
Yi He ◽  
Wuyou Li ◽  
Wangqi Zhang ◽  
Sheng Zhang ◽  
Xitian Pi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Heart Sound ◽  
Original Data ◽  
Heart Sounds ◽  
Sound Signal ◽  
Accuracy Rate ◽  
Heart Research ◽  
Data Set ◽  
Heart Sound Signal

The heart sound signal is one of the signals that reflect the health of the heart. Research on the heart sound signal contributes to the early diagnosis and prevention of cardiovascular diseases. As a commonly used deep learning network, convolutional neural network (CNN) has been widely used in images. In this paper, the method of analyzing heart sound through using CNN has been studied. Firstly, the original data set was preprocessed, and then the heart sounds were segmented on U-net, based on the deep CNN. Finally, the classification of heart sounds was completed through CNN. The data from 2016 PhysioNet/CinC Challenge was utilized for algorithm validation, and the following results were obtained. When the heart sound segmented, the overall accuracy rate was 0.991, the accuracy of the first heart sound was 0.991, the accuracy of the systolic period was 0.996, the accuracy of the second heart sound was 0.996, and the accuracy of the diastolic period was 0.997, and the average accuracy rate was 0.995; While in classification, the accuracy was 0.964, the sensitivity was 0.781, and the specificity was 0.873. These results show that deep learning based on CNN shows good performance in the segmentation and classification of the heart sound signal.

scholarly journals PARTICLE SWARM OPTIMIZATION (PSO) FOR TRAINING OPTIMIZATION ON CONVOLUTIONAL NEURAL NETWORK (CNN)

2016 ◽  
Vol 9 (1) ◽  
pp. 52 ◽  
Author(s):  
Arie Rachmad Syulistyo ◽  
Dwi Marhaendro Jati Purnomo ◽  
Muhammad Febrian Rachmadi ◽  
Adi Wibowo
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Deep Learning ◽  
Recognition Accuracy ◽  
Particle Swarm ◽  
Learning Method ◽  
Training Process ◽  
Swarm Optimization ◽  
Handwritten Digit ◽  
Better Than

Neural network attracts plenty of researchers lately. Substantial number of renowned universities have developed neural network for various both academically and industrially applications. Neural network shows considerable performance on various purposes. Nevertheless, for complex applications, neural network’s accuracy significantly deteriorates. To tackle the aforementioned drawback, lot of researches had been undertaken on the improvement of the standard neural network. One of the most promising modifications on standard neural network for complex applications is deep learning method. In this paper, we proposed the utilization of Particle Swarm Optimization (PSO) in Convolutional Neural Networks (CNNs), which is one of the basic methods in deep learning. The use of PSO on the training process aims to optimize the results of the solution vectors on CNN in order to improve the recognition accuracy. The data used in this research is handwritten digit from MNIST. The experiments exhibited that the accuracy can be attained in 4 epoch is 95.08%. This result was better than the conventional CNN and DBN.  The execution time was also almost similar to the conventional CNN. Therefore, the proposed method was a promising method.  

Classification of Ecological Data by Deep Learning

2020 ◽  
Vol 34 (13) ◽  
pp. 2052010
Author(s):  
Shaobo Liu ◽  
Frank Y. Shih ◽  
Gareth Russell ◽  
Kimberly Russell ◽  
Hai Phan
Keyword(s):  
Deep Learning ◽  
Computational Models ◽  
Data Augmentation ◽  
Small Data ◽  
Learning Models ◽  
Ecological Data ◽  
Accuracy Rate ◽  
Learning Techniques ◽  
Residual Block

Ecologists have been studying different computational models in the classification of ecological species. In this paper, we intend to take advantages of variant deep-learning models, including LeNet, AlexNet, VGG models, residual neural network, and inception models, to classify ecological datasets, such as bee wing and butterfly. Since the datasets contain relatively small data samples and unbalanced samples in each class, we apply data augmentation and transfer learning techniques. Furthermore, newly designed inception residual and inception modules are developed to enhance feature extraction and increase classification rates. As comparing against currently available deep-learning models, experimental results show that the proposed inception residual block can avoid the vanishing gradient problem and achieve a high accuracy rate of 92%.

scholarly journals Defect Classification of Green Plums Based on Deep Learning

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6993
Author(s):  
Haiyan Zhou ◽  
Zilong Zhuang ◽  
Ying Liu ◽  
Yang Liu ◽  
Xiao Zhang
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Surface Defects ◽  
Recognition Accuracy ◽  
Economic Value ◽  
Recognition Rate ◽  
Cost Effective ◽  
Test Time ◽  
Training Set

The green plum is rich in amino acids, lipids, inorganic salts, vitamins, and trace elements. It has high nutritional value and medicinal value and is very popular among Chinese people. However, green plums are susceptible to collisions and pests during growth, picking, storage, and transportation, causing surface defects, affecting the quality of green plums and their products and reducing their economic value. In China, defect detection and grading of green plum products are still performed manually. Traditional manual classification has low accuracy and high cost, which is far from meeting the production needs of green plum products. In order to improve the economic value of green plums and their products and improve the automation and intelligence level of the product production process, this study adopted deep learning methods based on a convolutional neural network and cost-effective computer vision technology to achieve efficient classification of green plum defects. First, a camera and LEDs were used to collect 1240 green plum images of RGB, and the green plum experimental classification standard was formulated and divided into five categories, namely, rot, spot, scar, crack, and normal. Images were randomly divided into a training set and test set, and the number of images of the training set was expanded. Then, the stochastic weight averaging (SWA) optimizer and w-softmax loss function were used to improve the VGG network, which was trained and tested to generate a green plum defect detection network model. The average recognition accuracy of green plum defects was 93.8%, the test time for each picture was 84.69 ms, the recognition rate of decay defect was 99.25%, and the recognition rate of normal green plum was 95.65%. The results were compared with the source VGG network, resnet18 network, and green lemon network. The results show that for the classification of green plum defects, the recognition accuracy of the green plum defect detection network increased by 9.8% and 16.6%, and the test speed is increased by 1.87 and 6.21 ms, respectively, which has certain advantages.

scholarly journals Klasifikasi Tekstur Kematangan Buah Jeruk Manis Berdasarkan Tingkat Kecerahan Warna dengan Metode Deep Learning Convolutional Neural Network

2021 ◽  
Vol 6 (2) ◽  
pp. 259
Author(s):  
Budi Yanto ◽  
Luth Fimawahib ◽  
Asep Supriyanto ◽  
B.Herawan Hayadi ◽  
Rinanda Rizki Pratama
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Sweet Orange ◽  
Citrus Fruit ◽  
Accuracy Rate ◽  
Long Time ◽  
Orange Fruit ◽  
Manual Methods ◽  
Computerized System

Sweet orange is very much consumed by humans because oranges are rich in vitamin C, sweet oranges can be consumed directly to drink. The classification carried out to determine proper (good) and unfit (rotten) oranges still uses manual methods, This classification has several weaknesses, namely the existence of human visual limitations, is influenced by the psychological condition of the observations and takes a long time. One of the classification methods for sweet orange fruit with a computerized system the Convolutional Neural Network (CNN) is algorithm deep learning to the development of the Multilayer Perceptron (MLP) with 100 datasets of sweet orange images, the classification accuracy rate was 97.5184%. the classification was carried out, the result was 67.8221%. Testing of 10 citrus fruit images divided into 5 good citrus images and 5 rotten citrus images at 96% for training 92% for testing which were considered to have been able to classify the appropriateness of sweet orange fruit very well. The graph of the results of the accuracy testing is 0.92 or 92%. This result is quite good, for the RGB histogram display the orange image is good

scholarly journals Classification of Adulterated Particle Images in Coconut Oil Using Deep Learning Approaches

2022 ◽  
Vol 12 (2) ◽  
pp. 656
Author(s):  
Attapon Palananda ◽  
Warangkhana Kimpan
Keyword(s):  
Deep Learning ◽  
Coconut Oil ◽  
Learning Approaches ◽  
Accuracy Rate ◽  
Fine Filter ◽  
Testing Accuracy ◽  
Particle Images ◽  
Processing Techniques ◽  
Oil Filtration

In the production of coconut oil for consumption, cleanliness and safety are the first priorities for meeting the standard in Thailand. The presence of color, sediment, or impurities is an important element that affects consumers’ or buyers’ decision to buy coconut oil. Coconut oil contains impurities that are revealed during the process of compressing the coconut pulp to extract the oil. Therefore, the oil must be filtered by centrifugation and passed through a fine filter. When the oil filtration process is finished, staff inspect the turbidity of coconut oil by examining the color with the naked eye and should detect only the color of the coconut oil. However, this method cannot detect small impurities, suspended particles that take time to settle and become sediment. Studies have shown that the turbidity of coconut oil can be measured by passing light through the oil and applying image processing techniques. This method makes it possible to detect impurities using a microscopic camera that photographs the coconut oil. This study proposes a method for detecting impurities that cause the turbidity in coconut oil using a deep learning approach called a convolutional neural network (CNN) to solve the problem of impurity identification and image analysis. In the experiments, this paper used two coconut oil impurity datasets, PiCO_V1 and PiCO_V2, containing 1000 and 6861 images, respectively. A total of 10 CNN architectures were tested on these two datasets to determine the accuracy of the best architecture. The experimental results indicated that the MobileNetV2 architecture had the best performance, with the highest training accuracy rate, 94.05%, and testing accuracy rate, 80.20%.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

Sign in / Sign up

Export Citation Format

Share Document