A Double-Branch Surface Detection System for Armatures in Vibration Motors with Miniature Volume Based on ResNet-101 and FPN

In this paper, a complete system based on computer vision and deep learning is proposed for surface inspection of the armatures in a vibration motor with miniature volume. A device for imaging and positioning was designed in order to obtain the images of the surface of the armatures. The images obtained by the device were divided into a training set and a test set. With continuous experimental exploration and improvement, the most efficient deep-network model was designed. The results show that the model leads to high accuracy on both the training set and the test set. In addition, we proposed a training method to make the network designed by us perform better. To guarantee the quality of the motor, a double-branch discrimination mechanism was also proposed. In order to verify the reliability of the system, experimental verification was conducted on the production line, and a satisfactory discrimination performance was reached. The results indicate that the proposed detection system for the armatures based on computer vision and deep learning is stable and reliable for armature production lines.

Download Full-text

Weakly supervised deep learning for determining the prognostic value of 18F-FDG PET/CT in extranodal natural killer/T cell lymphoma, nasal type

European Journal of Nuclear Medicine and Molecular Imaging ◽

10.1007/s00259-021-05232-3 ◽

2021 ◽

Author(s):

Rui Guo ◽

Xiaobin Hu ◽

Haoming Song ◽

Pengpeng Xu ◽

Haoping Xu ◽

...

Keyword(s):

Deep Learning ◽

Fdg Pet ◽

Cell Lymphoma ◽

Training Set ◽

Test Set ◽

Natural Killer T Cell ◽

Pet Ct ◽

Weakly Supervised ◽

Fdg Pet Ct ◽

Killer T Cell

Abstract Purpose To develop a weakly supervised deep learning (WSDL) method that could utilize incomplete/missing survival data to predict the prognosis of extranodal natural killer/T cell lymphoma, nasal type (ENKTL) based on pretreatment 18F-FDG PET/CT results. Methods One hundred and sixty-seven patients with ENKTL who underwent pretreatment 18F-FDG PET/CT were retrospectively collected. Eighty-four patients were followed up for at least 2 years (training set = 64, test set = 20). A WSDL method was developed to enable the integration of the remaining 83 patients with incomplete/missing follow-up information in the training set. To test generalization, these data were derived from three types of scanners. Prediction similarity index (PSI) was derived from deep learning features of images. Its discriminative ability was calculated and compared with that of a conventional deep learning (CDL) method. Univariate and multivariate analyses helped explore the significance of PSI and clinical features. Results PSI achieved area under the curve scores of 0.9858 and 0.9946 (training set) and 0.8750 and 0.7344 (test set) in the prediction of progression-free survival (PFS) with the WSDL and CDL methods, respectively. PSI threshold of 1.0 could significantly differentiate the prognosis. In the test set, WSDL and CDL achieved prediction sensitivity, specificity, and accuracy of 87.50% and 62.50%, 83.33% and 83.33%, and 85.00% and 75.00%, respectively. Multivariate analysis confirmed PSI to be an independent significant predictor of PFS in both the methods. Conclusion The WSDL-based framework was more effective for extracting 18F-FDG PET/CT features and predicting the prognosis of ENKTL than the CDL method.

Download Full-text

A new strategy for curriculum learning using model distillation

Global Journal of Computer Sciences Theory and Research ◽

10.18844/gjcs.v10i2.5810 ◽

2020 ◽

Vol 10 (2) ◽

pp. 57-65

Author(s):

Kaan Karakose ◽

Metin Bilgin

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Artificial Neural Networks ◽

Deep Learning ◽

Deep Neural Networks ◽

Mixed Data ◽

Training Set ◽

Complex Samples ◽

New Strategy ◽

Sample Sorting

In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. Humans and animals learn much better when gradually presented in a meaningful order showing more concepts and complex samples rather than randomly presenting the information. The use of such training strategies in the context of artificial neural networks is called curriculum learning. In this study, a strategy was developed for curriculum learning. Using the CIFAR-10 and CIFAR-100 training sets, the last few layers of the pre-trained on ImageNet Xception model were trained to keep the training set knowledge in the model’s weight. Finally, a much smaller model was trained with the sample sorting methods presented using these difficulty levels. The findings obtained in this study show that the accuracy value generated when trained by the method we provided with the accuracy value trained with randomly mixed data was more than 1% for each epoch. Keywords: Curriculum learning, model distillation, deep learning, academia, neural networks.

Download Full-text

Local Deep Descriptor for Remote Sensing Image Feature Matching

Remote Sensing ◽

10.3390/rs11040430 ◽

2019 ◽

Vol 11 (4) ◽

pp. 430 ◽

Cited By ~ 4

Author(s):

Yunyun Dong ◽

Weili Jiao ◽

Tengfei Long ◽

Lanfa Liu ◽

Guojin He ◽

...

Keyword(s):

Remote Sensing ◽

Computer Vision ◽

Deep Learning ◽

Feature Matching ◽

Remote Sensing Image ◽

Image Feature ◽

Training Dataset ◽

Feature Descriptor ◽

Remote Sensing Images

Feature matching via local descriptors is one of the most fundamental problems in many computer vision tasks, as well as in the remote sensing image processing community. For example, in terms of remote sensing image registration based on the feature, feature matching is a vital process to determine the quality of transform model. While in the process of feature matching, the quality of feature descriptor determines the matching result directly. At present, the most commonly used descriptor is hand-crafted by the designer’s expertise or intuition. However, it is hard to cover all the different cases, especially for remote sensing images with nonlinear grayscale deformation. Recently, deep learning shows explosive growth and improves the performance of tasks in various fields, especially in the computer vision community. Here, we created remote sensing image training patch samples, named Invar-Dataset in a novel and automatic way, then trained a deep learning convolutional neural network, named DescNet to generate a robust feature descriptor for feature matching. A special experiment was carried out to illustrate that our created training dataset was more helpful to train a network to generate a good feature descriptor. A qualitative experiment was then performed to show that feature descriptor vector learned by the DescNet could be used to register remote sensing images with large gray scale difference successfully. A quantitative experiment was then carried out to illustrate that the feature vector generated by the DescNet could acquire more matched points than those generated by hand-crafted feature Scale Invariant Feature Transform (SIFT) descriptor and other networks. On average, the matched points acquired by DescNet was almost twice those acquired by other methods. Finally, we analyzed the advantages of our created training dataset Invar-Dataset and DescNet and gave the possible development of training deep descriptor network.

Download Full-text

Content Estimation of Foreign Fibers in Cotton Based on Deep Learning

Electronics ◽

10.3390/electronics9111795 ◽

2020 ◽

Vol 9 (11) ◽

pp. 1795

Author(s):

Wei Wei ◽

Chen Zhang ◽

Dexiang Deng

Keyword(s):

Deep Learning ◽

Evaluation Method ◽

Test Results ◽

Production Lines ◽

Prototype Test ◽

Textile Product ◽

Time Segmentation ◽

Image Segmentation Algorithm ◽

Actual Size

Cotton foreign fibers directly affect the quality of a textile product; the less foreign fibers in raw cotton, the higher the quality grade of the textile product. Based on the foreign fiber clean machine, this paper proposed an evaluation method of foreign fiber content using deep learning. First of all, a large number of images of foreign fibers were collected from different production lines and annotated to obtain the mask image dataset of foreign fibers. Secondly, by comparing the image segmentation algorithm based on deep learning, tests showed that U-Net has a better performance on different segment metrics evaluations, and U-Net is improved to realize the real-time segmentation of foreign fiber images. The actual size of the foreign fiber could be calculated through the combination of the segment result and the mechanical parameters of the machine. Finally, the test results showed that the relative error between the estimated size and the actual size was less than 4%. After the prototype test, the algorithm was deployed on the actual production line and, by comparing the algorithm data in a random time with the actual foreign fiber statistical data, the overall error was less than 2%. The test showed that the new evaluation method can fully reflect the content of foreign fiber in raw cotton.

Download Full-text

A Simple Method to Train the AI Diagnosis Model of Pulmonary Nodules

Computational and Mathematical Methods in Medicine ◽

10.1155/2020/2812874 ◽

2020 ◽

Vol 2020 ◽

pp. 1-6

Author(s):

Zhehao He ◽

Wang Lv ◽

Jian Hu

Keyword(s):

Deep Learning ◽

Data Augmentation ◽

Pulmonary Nodules ◽

Learning System ◽

Pathological Diagnosis ◽

Classification Model ◽

Lung Nodules ◽

Training Set ◽

Simple Method ◽

Test Set

Background. The differential diagnosis of subcentimetre lung nodules with a diameter of less than 1 cm has always been one of the problems of imaging doctors and thoracic surgeons. We plan to create a deep learning model for the diagnosis of pulmonary nodules in a simple method. Methods. Image data and pathological diagnosis of patients come from the First Affiliated Hospital of Zhejiang University School of Medicine from October 1, 2016, to October 1, 2019. After data preprocessing and data augmentation, the training set is used to train the model. The test set is used to evaluate the trained model. At the same time, the clinician will also diagnose the test set. Results. A total of 2,295 images of 496 lung nodules and their corresponding pathological diagnosis were selected as a training set and test set. After data augmentation, the number of training set images reached 12,510 images, including 6,648 malignant nodular images and 5,862 benign nodular images. The area under the P-R curve of the trained model is 0.836 in the classification of malignant and benign nodules. The area under the ROC curve of the trained model is 0.896 (95% CI: 78.96%~100.18%), which is higher than that of three doctors. However, the P value is not less than 0.05. Conclusion. With the help of an automatic machine learning system, clinicians can create a deep learning pulmonary nodule pathology classification model without the help of deep learning experts. The diagnostic efficiency of this model is not inferior to that of the clinician.

Download Full-text

Development of a Nomogram Based on Preoperative Bi-Parametric MRI and Blood Indices for the Differentiation Between Cystic-Solid Pituitary Adenoma and Craniopharyngioma

Frontiers in Oncology ◽

10.3389/fonc.2021.709321 ◽

2021 ◽

Vol 11 ◽

Author(s):

Zhen Zhao ◽

Dongdong Xiao ◽

Chuansheng Nie ◽

Hao Zhang ◽

Xiaobing Jiang ◽

...

Keyword(s):

Logistic Regression ◽

Discrimination Performance ◽

Clinical Effectiveness ◽

Preoperative Imaging ◽

Classification Models ◽

Training Set ◽

Test Set ◽

Clinical Model ◽

Blood Indices ◽

Radiomics Signature

BackgroundGiven the similarities in clinical manifestations of cystic-solid pituitary adenomas (CS-PAs) and craniopharyngiomas (CPs), this study aims to establish and validate a nomogram based on preoperative imaging features and blood indices to differentiate between CS-PAs and CPs.MethodsA departmental database was searched to identify patients who had undergone tumor resection between January 2012 and December 2020, and those diagnosed with CS-PAs or CPs by histopathology were included. Preoperative magnetic resonance imaging (MRI) features as well as blood indices were retrieved and analyzed. Radiological features were extracted from the tumor on contrast-enhanced T1 (CE-T1) weighted and T2 weighted sequences. The two independent samples t-test and principal component analysis (PCA) were used for feature selection, data dimension reduction, and radiomics signature building. Next, the radiomics signature was put in five classification models for exploring the best classifier with superior identification performance. Multivariate logistic regression analysis was then used to establish a radiomic-clinical model containing radiomics and hematological features, and the model was presented as a nomogram. The performance of the radiomics-clinical model was assessed by calibration curve, clinical effectiveness as well as internal validation.ResultsA total of 272 patients were included in this study: 201 with CS-PAs and 71 with CPs. These patients were randomized into training set (n=182) and test set (n=90). The radiomics signature, which consisted of 18 features after dimensionality reduction, showed superior discrimination performance in 5 different classification models. The area under the curve (AUC) values of the training set and the test set obtained by the radiomics signature are 0.92 and 0.88 in the logistic regression model, 0.90 and 0.85 in the Ridge classifier, 0.88 and 0.82 in the stochastic gradient descent (SGD) classifier, 0.78 and 0.85 in the linear support vector classification (Linear SVC), 0.93 and 0.86 in the multilayers perceptron (MLP) classifier, respectively. The predictive factors of the nomogram included radiomic signature, age, WBC count, and FIB. The nomogram showed good discrimination performance (with an AUC of 0.93 in the training set and 0.90 in the test set) and good calibration. Moreover, decision curve analysis (DCA) demonstrated satisfactory clinical effectiveness of the proposed radiomic-clinical nomogram.ConclusionsA personalized nomogram containing radiomics signature and blood indices was proposed in this study. This nomogram is simple yet effective in differentiating between CS-PAs and CPs and thus can be used in routine clinical practice.

Download Full-text

MASK DETECTION SYSTEM FOR COVID-19 SCENARIO USING COMPUTER VISION

International Journal of Engineering Applied Sciences and Technology ◽

10.33564/ijeast.2021.v05i12.015 ◽

2021 ◽

Vol 5 (12) ◽

Author(s):

Dr. Prakash Prasad ◽

Mukul Shende ◽

Mayur Karemore ◽

Lucky Khobragade ◽

Amit Dravyakar ◽

...

Keyword(s):

Computer Vision ◽

Deep Learning ◽

Detection System ◽

Face Mask ◽

World Health ◽

Public Places ◽

Learning Module ◽

Different Types ◽

Health Organization ◽

The Impact

The new pandemic of (Coronavirus Disease-2019) COVID-19 continues to spread worldwide. Every potential sector is experiencing a decline in growth. (World Health Organization) WHO suggests that Wearing Face Mask can reduce the impact of COVID-19. So, This Paper Proposed a system that controls the growth of COVID-19 by finding individuals who don't wear masks in populated areas like malls, markets where all public places are under surveillance with closed-circuit television cameras (CCTV). When a person without a mask is found, the corresponding authority is informed by the CCTV network. And it can calculate the number of people that do not wear the mask and emit an audible signal to inform the authority. A deep learning module is trained on a dataset composed of images of people wearing different types of masks and people without masks collected from various sources. It also contains some confusing images that help the model to achieve greater precision than other models. This model will use the dataset to build a COVID-19 face mask detector with computer vision using Computer Vision. This approach allowed extracting even the details from the pixels

Download Full-text

Deep Learning-based Sentiment Analysis and Topic Modeling on Tourism During Covid-19 Pandemic

Frontiers in Computer Science ◽

10.3389/fcomp.2021.775368 ◽

2021 ◽

Vol 3 ◽

Author(s):

Ram Krishn Mishra ◽

Siddhaling Urolagin ◽

J. Angel Arul Jothi ◽

Ashwin Sanjay Neogi ◽

Nishad Nawaz

Keyword(s):

Social Media ◽

Deep Learning ◽

Topic Modeling ◽

Tourism Industry ◽

Classification Model ◽

Training Set ◽

Test Set ◽

Multiple Parameters ◽

Social Media Platforms ◽

Flow Of Information

The Covid-19 pandemic has disrupted the world economy and significantly influenced the tourism industry. Millions of people have shared their emotions, views, facts, and circumstances on numerous social media platforms, which has resulted in a massive flow of information. The high-density social media data has drawn many researchers to extract valuable information and understand the user’s emotions during the pandemic time. The research looks at the data collected from the micro-blogging site Twitter for the tourism sector, emphasizing sub-domains hospitality and healthcare. The sentiment of approximately 20,000 tweets have been calculated using Valence Aware Dictionary for Sentiment Reasoning (VADER) model. Furthermore, topic modeling was used to reveal certain hidden themes and determine the narrative and direction of the topics related to tourism healthcare, and hospitality. Topic modeling also helped us to identify inter-cluster similar terms and analyzing the flow of information from a group of a similar opinion. Finally, a cutting-edge deep learning classification model was used with different epoch sizes of the dataset to anticipate and classify the people’s feelings. The deep learning model has been tested with multiple parameters such as training set accuracy, test set accuracy, validation loss, validation accuracy, etc., and resulted in more than a 90% in training set accuracy tourism hospitality and healthcare reported 80.9 and 78.7% respectively on test set accuracy.

Download Full-text

Diagnostic Classification of Cystoscopic Images Using Deep Convolutional Neural Networks

JCO Clinical Cancer Informatics ◽

10.1200/cci.17.00126 ◽

2018 ◽

pp. 1-8 ◽

Cited By ~ 9

Author(s):

Okyaz Eminaga ◽

Nurettin Eminaga ◽

Axel Semjonow ◽

Bernhard Breil

Keyword(s):

Deep Learning ◽

Harmonic Series ◽

Diagnostic Classification ◽

Training Set ◽

Deep Convolutional Neural Networks ◽

Data Set ◽

Test Set ◽

Filter Size ◽

Validation Set

Purpose The recognition of cystoscopic findings remains challenging for young colleagues and depends on the examiner’s skills. Computer-aided diagnosis tools using feature extraction and deep learning show promise as instruments to perform diagnostic classification. Materials and Methods Our study considered 479 patient cases that represented 44 urologic findings. Image color was linearly normalized and was equalized by applying contrast-limited adaptive histogram equalization. Because these findings can be viewed via cystoscopy from every possible angle and side, we ultimately generated images rotated in 10-degree grades and flipped them vertically or horizontally, which resulted in 18,681 images. After image preprocessing, we developed deep convolutional neural network (CNN) models (ResNet50, VGG-19, VGG-16, InceptionV3, and Xception) and evaluated these models using F1 scores. Furthermore, we proposed two CNN concepts: 90%-previous-layer filter size and harmonic-series filter size. A training set (60%), a validation set (10%), and a test set (30%) were randomly generated from the study data set. All models were trained on the training set, validated on the validation set, and evaluated on the test set. Results The Xception-based model achieved the highest F1 score (99.52%), followed by models that were based on ResNet50 (99.48%) and the harmonic-series concept (99.45%). All images with cancer lesions were correctly determined by these models. When the focus was on the images misclassified by the model with the best performance, 7.86% of images that showed bladder stones with indwelling catheter and 1.43% of images that showed bladder diverticulum were falsely classified. Conclusion The results of this study show the potential of deep learning for the diagnostic classification of cystoscopic images. Future work will focus on integration of artificial intelligence–aided cystoscopy into clinical routines and possibly expansion to other clinical endoscopy applications.

Download Full-text

A Training Method for Low Rank Convolutional Neural Networks Based on Alternating Tensor Compose-Decompose Method

Applied Sciences ◽

10.3390/app11020643 ◽

2021 ◽

Vol 11 (2) ◽

pp. 643

Author(s):

Sukho Lee ◽

Hyein Kim ◽

Byeongseon Jeong ◽

Jungho Yoon

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Learning Model ◽

Low Rank ◽

Training Method ◽

Training Stage ◽

Fixed Structure ◽

Deep Learning Model

Over the past decade, deep learning-based computer vision methods have been shown to surpass previous state-of-the-art computer vision techniques in various fields, and have made great progress in various computer vision problems, including object detection, object segmentation, face recognition, etc. Nowadays, major IT companies are adding new deep-learning-based computer technologies to edge devices such as smartphones. However, since the computational cost of deep learning-based models is still high for edge devices, research is being actively carried out to compress deep learning-based models while not sacrificing high performance. Recently, many lightweight architectures have been proposed for deep learning-based models which are based on low-rank approximation. In this paper, we propose an alternating tensor compose-decompose (ATCD) method for the training of low-rank convolutional neural networks. The proposed training method can better train a compressed low-rank deep learning model than the conventional fixed-structure based training method, so that a compressed deep learning model with higher performance can be obtained in the end of the training. As a representative and exemplary model to which the proposed training method can be applied, we propose a rank-1 convolutional neural network (CNN) which has a structure alternatively containing 3-D rank-1 filters and 1-D filters in the training stage and a 1-D structure in the testing stage. After being trained, the 3-D rank-1 filters can be permanently decomposed into 1-D filters to achieve a fast inference in the test time. The reason that the 1-D filters are not being trained directly in 1-D form in the training stage is that the training of the 3-D rank-1 filters is easier due to the better gradient flow, which makes the training possible even in the case when the fixed structured network with fixed consecutive 1-D filters cannot be trained at all. We also show that the same training method can be applied to the well-known MobileNet architecture so that better parameters can be obtained than with the conventional fixed-structure training method. Furthermore, we show that the 1-D filters in a ResNet like structure can also be trained with the proposed method, which shows the fact that the proposed method can be applied to various structures of networks.

Download Full-text