A Convolutional Neural Network to Perform Object Detection and Identification in Visual Large-Scale Data

Big Data ◽  
2020 ◽  
Author(s):  
Riadh Ayachi ◽  
Yahia Said ◽  
Mohamed Atri
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Large Scale Data ◽  
Detection And Identification ◽  
Scale Data

scholarly journals High-Performance Machine Learning for Large-Scale Data Classification considering Class Imbalance

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Yang Liu ◽  
Xiang Li ◽  
Xianbang Chen ◽  
Xi Wang ◽  
Huaqiang Li
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
High Performance ◽  
Large Scale ◽  
Class Imbalance ◽  
Data Classification ◽  
Training Dataset ◽  
Large Scale Data ◽  
Input Layer ◽  
Scale Data

Currently, data classification is one of the most important ways to analysis data. However, along with the development of data collection, transmission, and storage technologies, the scale of the data has been sharply increased. Additionally, due to multiple classes and imbalanced data distribution in the dataset, the class imbalance issue is also gradually highlighted. The traditional machine learning algorithms lack of abilities for handling the aforementioned issues so that the classification efficiency and precision may be significantly impacted. Therefore, this paper presents an improved artificial neural network in enabling the high-performance classification for the imbalanced large volume data. Firstly, the Borderline-SMOTE (synthetic minority oversampling technique) algorithm is employed to balance the training dataset, which potentially aims at improving the training of the back propagation neural network (BPNN), and then, zero-mean, batch-normalization, and rectified linear unit (ReLU) are further employed to optimize the input layer and hidden layers of BPNN. At last, the ensemble learning-based parallelization of the improved BPNN is implemented using the Hadoop framework. Positive conclusions can be summarized according to the experimental results. Benefitting from Borderline-SMOTE, the imbalanced training dataset can be balanced, which improves the training performance and the classification accuracy. The improvements for the input layer and hidden layer also enhance the training performances in terms of convergence. The parallelization and the ensemble learning techniques enable BPNN to implement the high-performance large-scale data classification. The experimental results show the effectiveness of the presented classification algorithm.

scholarly journals Earlier stage for straggler detection and handling using combined CPU test and LATE methodology

2020 ◽  
Vol 10 (5) ◽  
pp. 4910
Author(s):  
Anwar H. Katrawi ◽  
Rosni Abdullah ◽  
Mohammed Anbar ◽  
Ammar Kamal Abasi
Keyword(s):  
Power Consumption ◽  
Execution Time ◽  
Large Scale ◽  
Poor Performance ◽  
Mapreduce Framework ◽  
Computing Systems ◽  
Large Scale Data ◽  
Detection And Identification ◽  
Scale Data

Using MapReduce in Hadoop helps in lowering the execution time and power consumption for large scale data. However, there can be a delay in job processing in circumstances where tasks are assigned to bad or congested machines called "straggler tasks"; which increases the time, power consumptions and therefore increasing the costs and leading to a poor performance of computing systems. This research proposes a hybrid MapReduce framework referred to as the combinatory late-machine (CLM) framework. Implementation of this framework will facilitate early and timely detection and identification of stragglers thereby facilitating prompt appropriate and effective actions.

Hybrid Deep Neural Network-Based Cross-Modal Image and Text Retrieval Method for Large-Scale Data

2020 ◽  
pp. 2150018
Author(s):  
Baohua Qiang ◽  
Ruidong Chen ◽  
Yuan Xie ◽  
Mingliang Zhou ◽  
Riwei Pan ◽  
...  
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Deep Neural Network ◽  
Text Retrieval ◽  
Retrieval Method ◽  
Multimodal Data ◽  
Hierarchical Learning ◽  
Fine Grained ◽  
Large Scale Data ◽  
Scale Data

In this paper, we propose the hybrid deep neural network-based cross-modal image and text retrieval method to explore complex cross-modal correlation by considering multi-layer learning. First, we propose intra-modal and inter-modal representations to achieve a complementary single-modal representation that preserves the correlation between the modalities. Second, we build an association between different modalities through hierarchical learning to further mine the fine-grained latent semantic association among multimodal data. The experimental results show that our algorithm substantially enhances retrieval performance and consistently outperforms four comparison methods.

scholarly journals Class-Specific Anchor Based and Context-Guided Multi-Class Object Detection in High Resolution Remote Sensing Imagery with a Convolutional Neural Network

2019 ◽  
Vol 11 (3) ◽  
pp. 272 ◽  
Author(s):  
Nan Mo ◽  
Li Yan ◽  
Ruixi Zhu ◽  
Hong Xie
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Shape Change ◽  
Context Information ◽  
False Detection ◽  
Multi Scale

In this paper, the problem of multi-scale geospatial object detection in High Resolution Remote Sensing Images (HRRSI) is tackled. The different flight heights, shooting angles and sizes of geographic objects in the HRRSI lead to large scale variance in geographic objects. The inappropriate anchor size to propose the objects and the indiscriminative ability of features for describing the objects are the main causes of missing detection and false detection in multi-scale geographic object detection. To address these challenges, we propose a class-specific anchor based and context-guided multi-class object detection method with a convolutional neural network (CNN), which can be divided into two parts: a class-specific anchor based region proposal network (RPN) and a discriminative feature with a context information classification network. A class-specific anchor block providing better initial values for RPN is proposed to generate the anchor of the most suitable scale for each category in order to increase the recall ratio. Meanwhile, we proposed to incorporate the context information into the original convolutional feature to improve the discriminative ability of the features and increase classification accuracy. Considering the quality of samples for classification, the soft filter is proposed to select effective boxes to improve the diversity of the samples for the classifier and avoid missing or false detection to some extent. We also introduced the focal loss in order to improve the classifier in classifying the hard samples. The proposed method is tested on a benchmark dataset of ten classes to prove the superiority. The proposed method outperforms some state-of-the-art methods with a mean average precision (mAP) of 90.4% and better detects the multi-scale objects, especially when objects show a minor shape change.

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Sign in / Sign up

Export Citation Format

Share Document