scholarly journals Progressive Deep Learning Framework for Recognizing 3D Orientations and Object Class Based on Point Cloud Representation

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6108
Author(s):  
Sukhan Lee ◽  
Yongjun Yang
Keyword(s):  
Deep Learning ◽  
High Efficiency ◽  
Object Classification ◽  
High Accuracy ◽  
Fine Tuning ◽  
Object Class ◽  
Global Features ◽  
Axis Orientation ◽  
Learning Framework ◽  
Object Classes

Deep learning approaches to estimating full 3D orientations of objects, in addition to object classes, are limited in their accuracies, due to the difficulty in learning the continuous nature of three-axis orientation variations by regression or classification with sufficient generalization. This paper presents a novel progressive deep learning framework, herein referred to as 3D POCO Net, that offers high accuracy in estimating orientations about three rotational axes yet with efficiency in network complexity. The proposed 3D POCO Net is configured, using four PointNet-based networks for independently representing the object class and three individual axes of rotations. The four independent networks are linked by in-between association subnetworks that are trained to progressively map the global features learned by individual networks one after another for fine-tuning the independent networks. In 3D POCO Net, high accuracy is achieved by combining a high precision classification based on a large number of orientation classes with a regression based on a weighted sum of classification outputs, while high efficiency is maintained by a progressive framework by which a large number of orientation classes are grouped into independent networks linked by association subnetworks. We implemented 3D POCO Net for full three-axis orientation variations and trained it with about 146 million orientation variations augmented from the ModelNet10 dataset. The testing results show that we can achieve an orientation regression error of about 2.5° with about 90% accuracy in object classification for general three-axis orientation estimation and object classification. Furthermore, we demonstrate that a pre-trained 3D POCO Net can serve as an orientation representation platform based on which orientations as well as object classes of partial point clouds from occluded objects are learned in the form of transfer learning.

scholarly journals Multisignal VGG19 Network with Transposed Convolution for Rotating Machinery Fault Diagnosis Based on Deep Transfer Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Jianye Zhou ◽  
Xinyu Yang ◽  
Lin Zhang ◽  
Siyu Shao ◽  
Gangying Bian
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
High Efficiency ◽  
Image Resolution ◽  
Fine Tuning ◽  
Test Accuracy ◽  
Multiple Sensors ◽  
Learning Framework ◽  
Training Samples ◽  
Model Training

To realize high-precision and high-efficiency machine fault diagnosis, a novel deep learning framework that combines transfer learning and transposed convolution is proposed. Compared with existing methods, this method has faster training speed, fewer training samples per time, and higher accuracy. First, the raw data collected by multiple sensors are combined into a graph and normalized to facilitate model training. Next, the transposed convolution is utilized to expand the image resolution, and then the images are treated as the input of the transfer learning model for training and fine-tuning. The proposed method adopts 512 time series to conduct experiments on two main mechanical datasets of bearings and gears in the variable-speed gearbox, which verifies the effectiveness and versatility of the method. We have obtained advanced results on both datasets of the gearbox dataset. The dataset shows that the test accuracy is 99.99%, achieving a significant improvement from 98.07% to 99.99%.

scholarly journals Deep Learning-based Trichoscopic Image Analysis and Quantitative Model for Predicting Basic and Specific Classification in Male Androgenic Alopecia

2021 ◽  
Author(s):  
Meng Gao ◽  
Yue Wang ◽  
Haipeng Xu ◽  
Congcong Xu ◽  
Xianhong Yang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Image Analysis ◽  
Deep Learning ◽  
Quantitative Model ◽  
High Accuracy ◽  
Diameter Distribution ◽  
Androgenic Alopecia ◽  
Hair Density ◽  
Learning Framework ◽  
Quantitative Indicators

Since the results of basic and specific classification in male androgenic alopecia are subjective, and trichoscopic data, such as hair density and diameter distribution, are potential quantitative indicators, the aim of this study was to develop a deep learning framework for automatic trichoscopic image analysis and a quantitative model for predicting basic and specific classification in male androgenic alopecia. A total of 2,910 trichoscopic images were collected and a deep learning framework was created on convolutional neural networks. Based on the trichoscopic data provided by the framework, correlations with basic and specific classification were analysed and a quantitative model was developed for predicting basic and specific classification using multiple ordinal logistic regression. The aim of this study was to develop a deep learning framework that can accurately analyse hair density and diameter distribution on trichoscopic images, and a quantitative model for predicting basic and specific classification in male androgenic alopecia with high accuracy.

A multimodal deep learning framework for predicting drug–drug interaction events

2020 ◽  
Vol 36 (15) ◽  
pp. 4316-4322 ◽  
Author(s):  
Yifan Deng ◽  
Xinran Xu ◽  
Yang Qiu ◽  
Jingbo Xia ◽  
Wen Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Adverse Reactions ◽  
High Efficiency ◽  
Pharmaceutical Research ◽  
Supplementary Information ◽  
Drug Usage ◽  
Learning Framework ◽  
Event Prediction ◽  
Precision Recall Curve ◽  
Drugbank Database

Abstract Motivation Drug–drug interactions (DDIs) are one of the major concerns in pharmaceutical research. Many machine learning based methods have been proposed for the DDI prediction, but most of them predict whether two drugs interact or not. The studies revealed that DDIs could cause different subsequent events, and predicting DDI-associated events is more useful for investigating the mechanism hidden behind the combined drug usage or adverse reactions. Results In this article, we collect DDIs from DrugBank database, and extract 65 categories of DDI events by dependency analysis and events trimming. We propose a multimodal deep learning framework named DDIMDL that combines diverse drug features with deep learning to build a model for predicting DDI-associated events. DDIMDL first constructs deep neural network (DNN)-based sub-models, respectively, using four types of drug features: chemical substructures, targets, enzymes and pathways, and then adopts a joint DNN framework to combine the sub-models to learn cross-modality representations of drug–drug pairs and predict DDI events. In computational experiments, DDIMDL produces high-accuracy performances and has high efficiency. Moreover, DDIMDL outperforms state-of-the-art DDI event prediction methods and baseline methods. Among all the features of drugs, the chemical substructures seem to be the most informative. With the combination of substructures, targets and enzymes, DDIMDL achieves an accuracy of 0.8852 and an area under the precision–recall curve of 0.9208. Availability and implementation The source code and data are available at https://github.com/YifanDengWHU/DDIMDL. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals An Integrated Deep Learning Framework of Tomato Leaf Disease Detection

2019 ◽  
Vol 8 (11S) ◽  
pp. 46-50
Keyword(s):  
Deep Learning ◽  
Plant Disease ◽  
Raw Materials ◽  
Human Life ◽  
High Accuracy ◽  
Tomato Leaf ◽  
Plant Diseases ◽  
Ensemble Model ◽  
Agriculture Sector ◽  
Learning Framework

Plants are a very important part of human life. They have variety of use as food, medication, raw materials and maintaining a balanced ecosystem. Plant disease is a deterioration of normal state of plant that interrupts and modifies its functionality. Pathogens are the main cause of such diseases. For agricultural purposes, a variety of methods have been proposed to detect plant diseases in the recent technological era. However, detecting plant diseases with high accuracy is still a challenge in computer vision. In this study, we propose an integrated deep learning framework where a pre-trained VGG-19 model is used for feature extraction and stacking ensemble model is used to detect and classify leaf diseases from images so as to reduce production and economic loses in agriculture sector. A dataset consisting of two classes (Infected and Healthy) and a total of 3242 images was used to test the system. Our proposed work has been compared with other contemporary algorithms (kNN, SVM, RF and Tree) and have outperformed by obtaining an accuracy of 98.6%

scholarly journals Unsupervised law article mining based on deep pre-trained language representation models with application to the Italian civil code

2021 ◽  
Author(s):  
Andrea Tagarelli ◽  
Andrea Simeri
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Civil Code ◽  
Fine Tuning ◽  
Learning Approaches ◽  
Retrieval Task ◽  
Learning Framework ◽  
Text Classifiers ◽  
The Law ◽  
Prediction Problems

AbstractModeling law search and retrieval as prediction problems has recently emerged as a predominant approach in law intelligence. Focusing on the law article retrieval task, we present a deep learning framework named LamBERTa, which is designed for civil-law codes, and specifically trained on the Italian civil code. To our knowledge, this is the first study proposing an advanced approach to law article prediction for the Italian legal system based on a BERT (Bidirectional Encoder Representations from Transformers) learning framework, which has recently attracted increased attention among deep learning approaches, showing outstanding effectiveness in several natural language processing and learning tasks. We define LamBERTa models by fine-tuning an Italian pre-trained BERT on the Italian civil code or its portions, for law article retrieval as a classification task. One key aspect of our LamBERTa framework is that we conceived it to address an extreme classification scenario, which is characterized by a high number of classes, the few-shot learning problem, and the lack of test query benchmarks for Italian legal prediction tasks. To solve such issues, we define different methods for the unsupervised labeling of the law articles, which can in principle be applied to any law article code system. We provide insights into the explainability and interpretability of our LamBERTa models, and we present an extensive experimental analysis over query sets of different type, for single-label as well as multi-label evaluation tasks. Empirical evidence has shown the effectiveness of LamBERTa, and also its superiority against widely used deep-learning text classifiers and a few-shot learner conceived for an attribute-aware prediction task.

A Deep Learning Framework for Prediction of Retinal Disorders

2020 ◽  
Author(s):  
Raniyaharini R ◽  
Madhumitha K ◽  
Mishaa S ◽  
Virajaravi R
Keyword(s):  
Deep Learning ◽  
Learning Framework ◽  
Retinal Disorders

COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image (Preprint)

2020 ◽  
Author(s):  
Jinseok Lee
Keyword(s):  
Deep Learning ◽  
Diagnostic Performance ◽  
Ct Images ◽  
Chest Ct ◽  
University Hospital ◽  
Detection Accuracy ◽  
Ct Image ◽  
Test Dataset ◽  
Learning Framework ◽  
Testing Dataset

BACKGROUND The coronavirus disease (COVID-19) has explosively spread worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) can be used as a relevant screening tool owing to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely busy fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE We aimed to quickly develop an AI technique to diagnose COVID-19 pneumonia and differentiate it from non-COVID pneumonia and non-pneumonia diseases on CT. METHODS A simple 2D deep learning framework, named fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning, using one of the four state-of-art pre-trained deep learning models (VGG16, ResNet50, InceptionV3, or Xception) as a backbone. For training and testing of FCONet, we collected 3,993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and non-pneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training and a testing set at a ratio of 8:2. For the test dataset, the diagnostic performance to diagnose COVID-19 pneumonia was compared among the four pre-trained FCONet models. In addition, we tested the FCONet models on an additional external testing dataset extracted from the embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS Of the four pre-trained models of FCONet, the ResNet50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100%, and accuracy 99.87%) and outperformed the other three pre-trained models in testing dataset. In additional external test dataset using low-quality CT images, the detection accuracy of the ResNet50 model was the highest (96.97%), followed by Xception, InceptionV3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS The FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing dataset, the ResNet50-based FCONet might be the best model, as it outperformed other FCONet models based on VGG16, Xception, and InceptionV3.

Sign in / Sign up

Export Citation Format

Share Document