research-article | 31-August-2021
packaging, provides comprehensive analysis of product production data, and establishes a production record system that focuses on the production process. In the intelligent manufacturing mode, the operator uses the code scanning gun to enter the relevant data of the product. It greatly improves the efficiency of production data collection and facilitates the improvement of product production efficiency. Deep learning has taken off in recent years, making major breakthroughs not only in medical research
Wenjing Wang,
Li Zhao
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 3, 59–65
Article | 14-October-2020
object detection algorithm based on deep learning uses CPMC, Selective Search, MCG, RPN and other methods to generate candidate regions instead of window sliding strategy. These methods usually use various details of the image, such as image contrast, edge parts and color to extract higher-quality candidate regions, while reducing the number of candidate regions and time complexity.
This type of object detection method is generally divided into two types: one-stage detection algorithm and two-stage
Wei Zhang,
Hongge Yao,
Yuxing Tan
International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 3, 65–72
research-article | 25-October-2021
-assisted diagnostics of prostate core needle biopsies (CNBs) by developing an algorithm that takes input as hematoxylin and eosin (H&E) stained slides outputs the result with 0.997 AUC. Deep learning was also used for detecting cancer in animals (Aubreville et al., 2020), agricultural greenhouse detection (Li et al., 2020), analyzing traffic load distribution on a bridge (Ge et al., 2020), airplane detection (Chen et al., 2018), hand gesture recognition (Kharate et al., 2016), automatic vehicle
Rohan Ibn Azad,
Subhas Mukhopadhyay,
Mohsen Asadnia
International Journal on Smart Sensing and Intelligent Systems, Volume 14 , ISSUE 1, 1–16
research-article | 31-August-2021
-spline model uses multiple control points to fit the lane lines, also based on parallel perspective technology, and the algorithm is highly accurate but has poor real-time performance; moreover, the method divides the lane lines into multiple areas for separate detection, especially in the presence of false lane lines or lane wear, and the accuracy of the algorithm is not guaranteed, and the lane line jump is serious.
B.
Deep learning methods
Research on lane detection based on deep learning neural
Jiaqi Shi,
Li Zhao
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 3, 1–8
Article | 13-July-2020
technology and method that can automatically inpainting damaged digital images, so digital image inpainting technology is born.
I.
INTRODUCTION
Image inpainting is one of the most popular areas of deep learning. Its basic principle is to give an image of a damaged or corroded area, and try to use the intact information of the known area of the damaged image to inpainting the damaged area of the image[1-2]. Digital image inpainting methods can be divided into two major categories: traditional image
Zhao Li,
Zhao Ruixia
International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 2, 23–30
Article | 30-November-2018
neural network based on the deep learning framework PyTorch and achieved an accuracy of 92.32% on the SVHN dataset at a time of 6 hours and 17 minutes.
II.
RELATED WORK
A.
Network structure
The network used in this experiment is modified by LeNet-5 as shown in Figure 1. LeNet-5 appeared to solve the problem of recognition of handwritten characters. The data set used in the training process is the MNIST. The samples in the data set are single-channel grayscale images, and the street view dataset is
Haoqi Yang,
Hongge Yao
International Journal of Advanced Network, Monitoring and Controls, Volume 4 , ISSUE 3, 47–52
Article | 30-November-2020
I.
INTRODUCTION
Identity identification is a basic problem in social life [1], which is not only closely related to the interests of individuals, but also affected national security and social stability. This paper studies the periocular recognition technology based on deep learning, which is to use the image of the eye area to identify the identity of people. Due to the high precision, high ease of use and high security of the eye circumference [2], it is easy to obtain eye images, analyze
Bo Liu,
Songze Lei,
Yonggang Li,
Aokui Shan,
Baihua Dong
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 1, 11–17
Article | 01-December-2016
Hyperspectral data has rich spectrum information, strong correlation between bands and high data redundancy. Feature band extraction of hyperspectral data is a prerequisite and an important basis for the subsequent study of classification and target recognition. Deep belief network is a kind of deep learning model, the paper proposed a deep belief network to realize the characteristics band extraction of hyperspectral data, and use the advantages of unsupervised and supervised learning of deep
Jiang Xinhua,
Xue Heru,
Zhang Lina,
Zhou Yanqing
International Journal on Smart Sensing and Intelligent Systems, Volume 9 , ISSUE 4, 1991–2009
Article | 30-November-2018
In recent years, with the rapid development of artificial intelligence, machine learning methods represented by statistical machine learning and deep learning are one of the main research directions [1]. Among them, the model of deep learning can be divided into discriminant model and generative model. Because of the invention of Logistic Regression, Support Vector Machine, Conditional Random Field and other algorithms, the discriminant model has developed rapidly. However, the development of
Jie Chen,
Li Zhao
International Journal of Advanced Network, Monitoring and Controls, Volume 4 , ISSUE 2, 93–98
Article | 13-July-2020
I.
INTRODUCTION
Since the concept of deep learning was proposed by Hinton et al[1]. In 2006, during more than a decade of development, machine learning is closer to the original goal of “artificial intelligence”. Deep learning is a hierarchical machine learning approach that involves multiple levels of nonlinear transformations that learn the inherent laws and representation levels of sample data, and the feature information obtained in the process of learning can help the machine achieve
Gao Zhiyu,
Liu Bailin,
Gu Hongxian,
Mu Jing
International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 2, 31–38
Article | 30-November-2020
prior, which can save the memory of potential image edge information and iterative support detection algorithm, which can strengthen the correct preservation of the space constraint kernel. parameter.In the study of unblind deblurring, Sun et al. [10] is a method based on deep learning to estimate uneven motion blur. First, CNN is used to predict the probability of different motion kernels for each image patch, and then image rotation is used. The technology expands the candidate motion kernel set
Xu Hexin,
Zhao Li,
Jiao Yan
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 1, 57–67
Article | 01-March-2015
Alexander A S Gunawan,
Wisnu Jatmiko
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 1, 429–463
Article | 21-April-2019
Chris Bradbeer,
Marian Mahat,
Terry Byers,
Ben Cleveland,
Thomas Kvan,
Wesley Imms
Journal of Educational Leadership, Policy and Practice, Volume 32 , ISSUE 1, 22–38
Article | 07-May-2018
In order to expand the application range of the intelligent traffic management system, and to solve the problem that the license plate positioning accuracy is low in the changing of the scene. On the basis of the analysis of previous methods advantages and disadvantages, applying deep learning model orientation method is proposed. The image expressed as graph of graph theory. Based on the principle of minimum spanning tree preliminary separate target objects in image of vehicle. Combined with
Yaxin Zhao,
Li Zhao,
Ya Li
International Journal of Advanced Network, Monitoring and Controls, Volume 3 , ISSUE 1, 62–68
research-article | 06-November-2020
discussed. The model and training data set are fully available via GitHub and can be freely used as well as further improved upon and trained for other purposes.
Materials and methods
Developing and training the CNN model
A deep learning architecture based on CNN called Mask R-CNN (He et al., 2017) was chosen to address the problem of counting two classes of objects, namely GFP and non-GFP (focal) animals. The chosen architecture was previously implemented in Python and is published under an MIT
Joanna K. Palka,
Krzysztof Fiok,
Weronika Antoł,
Zofia M. Prokop
Journal of Nematology, Volume 52 , 1–15
research-article | 31-August-2021
gradually applied to the field of car assisted driving [1]. It can provide vehicles with the perception information of the surrounding environment and automatically detect road obstacles to improve the road. The purpose of driving safety.
In recent years, scholars at home and abroad have gradually applied deep learning technology to obstacle object detection [2]. Prabhakar [3] and others have developed a set of deep learning systems on assisted driving for the detection and classification of road
Xiao Zuo,
Jun Yu,
Tong Xian,
Yuzhe Hu,
Zhiyi Hu
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 3, 18–25