Deep learning application for box-office evaluation of images

The possibility of application a convolutional neural network to assess the box-office effect of digital images is reviewed. We studied various conditions for sample preparation, optimizer algorithms, the number of pixels in the samples, the size of the training sample, color schemes, compression quality, and other photometric parameters in view of effect on training the neural network. Due to the proposed preliminary data preparation, the optimum of the architecture and hyperparameters of the neural network we achieved a classification accuracy of at least 98%.

Download Full-text

Hyperspectral Image Classification Based on Multi-Scale Residual Network with Attention Mechanism

Remote Sensing ◽

10.3390/rs13030335 ◽

2021 ◽

Vol 13 (3) ◽

pp. 335

Author(s):

Yuhao Qing ◽

Wenyi Liu

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Image Classification ◽

Classification Accuracy ◽

Hyperspectral Image ◽

Principal Component ◽

Hyperspectral Image Classification ◽

Deep Network ◽

Multi Scale

In recent years, image classification on hyperspectral imagery utilizing deep learning algorithms has attained good results. Thus, spurred by that finding and to further improve the deep learning classification accuracy, we propose a multi-scale residual convolutional neural network model fused with an efficient channel attention network (MRA-NET) that is appropriate for hyperspectral image classification. The suggested technique comprises a multi-staged architecture, where initially the spectral information of the hyperspectral image is reduced into a two-dimensional tensor, utilizing a principal component analysis (PCA) scheme. Then, the constructed low-dimensional image is input to our proposed ECA-NET deep network, which exploits the advantages of its core components, i.e., multi-scale residual structure and attention mechanisms. We evaluate the performance of the proposed MRA-NET on three public available hyperspectral datasets and demonstrate that, overall, the classification accuracy of our method is 99.82 %, 99.81%, and 99.37, respectively, which is higher compared to the corresponding accuracy of current networks such as 3D convolutional neural network (CNN), three-dimensional residual convolution structure (RES-3D-CNN), and space–spectrum joint deep network (SSRN).

Download Full-text

Integrating Multitemporal Sentinel-1/2 Data for Coastal Land Cover Classification Using a Multibranch Convolutional Neural Network: A Case of the Yellow River Delta

Remote Sensing ◽

10.3390/rs11091006 ◽

2019 ◽

Vol 11 (9) ◽

pp. 1006 ◽

Cited By ~ 16

Author(s):

Quanlong Feng ◽

Jianyu Yang ◽

Dehai Zhu ◽

Jiantao Liu ◽

Hao Guo ◽

...

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Deep Learning ◽

Land Cover ◽

Convolutional Neural Network ◽

Classification Accuracy ◽

Yellow River ◽

Rapid Development ◽

Land Cover Classification ◽

Coastal Land

Coastal land cover classification is a significant yet challenging task in remote sensing because of the complex and fragmented nature of coastal landscapes. However, availability of multitemporal and multisensor remote sensing data provides opportunities to improve classification accuracy. Meanwhile, rapid development of deep learning has achieved astonishing results in computer vision tasks and has also been a popular topic in the field of remote sensing. Nevertheless, designing an effective and concise deep learning model for coastal land cover classification remains problematic. To tackle this issue, we propose a multibranch convolutional neural network (MBCNN) for the fusion of multitemporal and multisensor Sentinel data to improve coastal land cover classification accuracy. The proposed model leverages a series of deformable convolutional neural networks to extract representative features from a single-source dataset. Extracted features are aggregated through an adaptive feature fusion module to predict final land cover categories. Experimental results indicate that the proposed MBCNN shows good performance, with an overall accuracy of 93.78% and a Kappa coefficient of 0.9297. Inclusion of multitemporal data improves accuracy by an average of 6.85%, while multisensor data contributes to 3.24% of accuracy increase. Additionally, the featured fusion module in this study also increases accuracy by about 2% when compared with the feature-stacking method. Results demonstrate that the proposed method can effectively mine and fuse multitemporal and multisource Sentinel data, which improves coastal land cover classification accuracy.

Download Full-text

Sign Board Recognition Based on Convolutional Neural Network Using Yolo-3

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.9214 ◽

2020 ◽

Vol 17 (8) ◽

pp. 3478-3483

Author(s):

V. Sravan Chowdary ◽

G. Penchala Sai Teja ◽

D. Mounesh ◽

G. Manideep ◽

C. T. Manimegalai

Keyword(s):

Neural Network ◽

Deep Learning ◽

Object Detection ◽

Convolutional Neural Network ◽

Road Accidents ◽

Learning Models ◽

The Neural Network

Road injuries are a big drawback in society for a few time currently. Ignoring sign boards while moving on roads has significantly become a major cause for road accidents. Thus we came up with an approach to face this issue by detecting the sign board and recognition of sign board. At this moment there are several deep learning models for object detection using totally different algorithms like RCNN, faster RCNN, SPP-net, etc. We prefer to use Yolo-3, which improves the speed and precision of object detection. This algorithm will increase the accuracy by utilizing residual units, skip connections and up-sampling. This algorithm uses a framework named Dark-net. This framework is intended specifically to create the neural network for training the Yolo algorithm. To thoroughly detect the sign board, we used this algorithm.

Download Full-text

Convolutional neural network for image classification based on transfer learning technique

10.32920/ryerson.14663658 ◽

2021 ◽

Author(s):

Ghassan Mohammed Halawani

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Network ◽

Image Classification ◽

Transfer Learning ◽

Learning Networks ◽

The Neural Network ◽

Learning Technique ◽

Common Architecture

The main purpose of this project is to modify a convolutional neural network for image classification, based on a deep-learning framework. A transfer learning technique is used by the MATLAB interface to Alex-Net to train and modify the parameters in the last two fully connected layers of Alex-Net with a new dataset to perform classifications of thousands of images. First, the general common architecture of most neural networks and their benefits are presented. The mathematical models and the role of each part in the neural network are explained in detail. Second, different neural networks are studied in terms of architecture, application, and the working method to highlight the strengths and weaknesses of each of neural network. The final part conducts a detailed study on one of the most powerful deep-learning networks in image classification – i.e. the convolutional neural network – and how it can be modified to suit different classification tasks by using transfer learning technique in MATLAB.

Download Full-text

Four-Dimension Deep Learning Method for Flower Quality Grading with Depth Information

Electronics ◽

10.3390/electronics10192353 ◽

2021 ◽

Vol 10 (19) ◽

pp. 2353

Author(s):

Xinyan Sun ◽

Zhenye Li ◽

Tingting Zhu ◽

Chao Ni

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Classification Accuracy ◽

Network Models ◽

Depth Image ◽

Depth Information ◽

Neural Network Models ◽

Flower Bud ◽

Flower Quality

Grading the quality of fresh cut flowers is an important practice in the flower industry. Based on the flower maturing status, a classification method based on deep learning and depth information was proposed for the grading of flower quality. Firstly, the RGB image and the depth image of a flower bud were collected and transformed into fused RGBD information. Then, the RGBD information of a flower was set as inputs of a convolutional neural network to determine the flower bud maturing status. Four convolutional neural network models (VGG16, ResNet18, MobileNetV2, and InceptionV3) were adjusted for a four-dimensional (4D) RGBD input to classify flowers, and their classification performances were compared with and without depth information. The experimental results show that the classification accuracy was improved with depth information, and the improved InceptionV3 network with RGBD achieved the highest classification accuracy (up to 98%), which means that the depth information can effectively reflect the characteristics of the flower bud and is helpful for the classification of the maturing status. These results have a certain significance for the intelligent classification and sorting of fresh flowers.

Download Full-text

Multisource Hyperspectral and LiDAR Data Fusion for Urban Land-Use Mapping based on a Modified Two-Branch Convolutional Neural Network

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi8010028 ◽

2019 ◽

Vol 8 (1) ◽

pp. 28 ◽

Cited By ~ 12

Author(s):

Quanlong Feng ◽

Dehai Zhu ◽

Jianyu Yang ◽

Baoguo Li

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Land Use ◽

Deep Learning ◽

Convolutional Neural Network ◽

Classification Accuracy ◽

Urban Land ◽

Urban Land Use ◽

Lidar Data ◽

Adaptive Fusion

Accurate urban land-use mapping is a challenging task in the remote-sensing field. With the availability of diverse remote sensors, synthetic use and integration of multisource data provides an opportunity for improving urban land-use classification accuracy. Neural networks for Deep Learning have achieved very promising results in computer-vision tasks, such as image classification and object detection. However, the problem of designing an effective deep-learning model for the fusion of multisource remote-sensing data still remains. To tackle this issue, this paper proposes a modified two-branch convolutional neural network for the adaptive fusion of hyperspectral imagery (HSI) and Light Detection and Ranging (LiDAR) data. Specifically, the proposed model consists of a HSI branch and a LiDAR branch, sharing the same network structure to reduce the time cost of network design. A residual block is utilized in each branch to extract hierarchical, parallel, and multiscale features. An adaptive-feature fusion module is proposed to integrate HSI and LiDAR features in a more reasonable and natural way (based on "Squeeze-and-Excitation Networks"). Experiments indicate that the proposed two-branch network shows good performance, with an overall accuracy of almost 92%. Compared with single-source data, the introduction of multisource data improves accuracy by at least 8%. The adaptive fusion model can also increase classification accuracy by more than 3% when compared with the feature-stacking method (simple concatenation). The results demonstrate that the proposed network can effectively extract and fuse features for a better urban land-use mapping accuracy.

Download Full-text

Implementasi Speech Recognition Pada Aplikasi E-Prescribing Menggunakan Algoritme Convolutional Neural Network

JURNAL MEDIA INFORMATIKA BUDIDARMA ◽

10.30865/mib.v5i2.2841 ◽

2021 ◽

Vol 5 (2) ◽

pp. 460

Author(s):

Nur Azis ◽

Herwanto Herwanto ◽

Fathurrahman Ramadhani

Keyword(s):

Neural Network ◽

Deep Learning ◽

Speech Recognition ◽

Convolutional Neural Network ◽

Open Source ◽

Basic Method ◽

Neural Network Method ◽

The Neural Network ◽

Network Method

The process of manually prescribing drugs by doctors can cause several problems, including doctors not knowing what drugs are available and it takes time to find out what drugs are available in the pharmacy. Speech recognition is now widely used in various ways, which can help facilitate work. The application of speech recognition can be done in the e-prescribing application with the neural network method using the Convolutional Neural Network (CNN) algorithm, which is the basic method of deep learning. This study aims to facilitate physicians in filling out drug data in e-prescribing applications using speech recognition. The data used in this study were obtained from the open source dataset provided by Google and collected independent datasets. From the results of experiments that have been carried out, the accuracy achieved with 40 epochs and 40 direct impressions with different words is 90%. Where words are successfully recognized 36 words out of 40 words

Download Full-text

Improving the Cognitive Agent Intelligence by Deep Knowledge Classification

International Journal of Computational Intelligence and Applications ◽

10.1142/s1469026819500056 ◽

2019 ◽

Vol 18 (01) ◽

pp. 1950005 ◽

Cited By ~ 3

Author(s):

Amine Chemchem ◽

François Alin ◽

Michael Krajecki

Keyword(s):

Neural Network ◽

Deep Learning ◽

Comparative Study ◽

Convolutional Neural Network ◽

Classification Accuracy ◽

Rule Base ◽

Learning Method ◽

Cognitive Agent ◽

Agent Intelligence ◽

Knowledge Classification

In this paper, a new idea is developed for improving the agent intelligence. In fact with the presented convolutional neural network (CNN) approach for knowledge classification, the agent will be able to manage its knowledge. This new concept allows the agent to select only the actionable rule class, instead of trying to infer its whole rule base exhaustively. In addition, through this research, we developed a comparative study between the proposed CNN approach and the classical classification approaches. As foreseeable the deep learning method outperforms the others in term of classification accuracy.

Download Full-text

Way of application of convolutional neural networks for personality recognition and user emotions by keyboard handwriting

Legal, regulatory and metrological support of information security system in Ukraine ◽

10.20535/2074-9481.2(38).2019.232654 ◽

2021 ◽

pp. 9-17

Author(s):

Yurii Kulakov ◽

Liudmyla Tereikovska ◽

Ihor Tereikovskyi

Keyword(s):

Neural Network ◽

Face Recognition ◽

Convolutional Neural Network ◽

Structural Parameters ◽

Computer Experiments ◽

Training Sample ◽

Input Field ◽

The Neural Network ◽

Important Direction ◽

Personality Recognition

An important direction of increasing the security and expanding the functionality of modern information systems is the introduction of face recognition tools and user emotions by their keyboard handwriting. The expediency of improving the indicated recognition means by introducing modern neural network solutions into them is shown. A way has been developed for using a convolutional neural network for recognizing a user's face and emotions from keyboard handwriting, the features of which are the procedure for adapting the structural parameters of a convolutional neural network of the VGG type to the expected conditions of use and a procedure for determining the input field, which provides the representation of the parameters of colored channels. After adapting the structural parameters, the VGG network was implemented using the MATLAB R2018b application package, which made it possible to carry out computer experiments aimed at verifying the proposed method. As a result of the conducted computer experiments, it was determined that the use of the proposed method of applying a convolutional neural network makes it possible to achieve a user face recognition accuracy of about 82% with 50 learning epochs. The need for further research in the direction of the formation of a training sample is shown, which will ensure high-quality training of the neural network model.

Download Full-text

Text classification using convolutional neural network

Information Technology and Nanotechnology ◽

10.18287/1613-0073-2019-2416-219-226 ◽

2019 ◽

pp. 219-226

Author(s):

L E Sapozhnikova ◽

O A Gordeeva

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Text Classification ◽

Classification Accuracy ◽

Convolutional Network ◽

The Neural Network ◽

Internet Information ◽

And Control ◽

Classification Quality ◽

Control Samples

In this article, the method of text classification using a convolutional neural network is presented. The problem of text classification is formulated, the architecture and the parameters of a convolutional neural network for solving the problem are described, the steps of the solution and the results of classification are given. The convolutional network which was used was trained to classify the texts of the news messages of Internet information portals. The semantic preprocessing of the text and the translation of words into attribute vectors are generated using the open word2vec model. The analysis of the dependence of the classification quality on the parameters of the neural network is presented. The using of the network allowed obtaining a classification accuracy of about 84%. In the estimation of the accuracy of the classification, the texts were checked to belong to the group of semantically similar classes. This approach allowed analyzing news messages in cases where the text themes and the number of classification classes in the training and control samples do not equal.

Download Full-text