scholarly journals Review on Deep Learning and Neural Network Implementation for Emotions Recognition

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
Renas Rajab Asaad
Keyword(s):  
Neural Network ◽  
Intelligent System ◽  
Electronic Devices ◽  
Network Architectures ◽  
Digital Information ◽  
Final Model ◽  
Social And Emotional ◽  
Video Application ◽  
Emotional Relationships ◽  
Classification Tasks

     Recently, we humans integrate into the world of our smart phones and our portable electronic devices to the point that that world can numb us in one way or another and separate us from the real world, so that we and the generations that come after us are fully adapted to dealing with huge amounts of digital information, so they are ready to be absorbed faster And ready to deal with it more efficiently than previous generations, but during this process of rapid adaptation and adapting to the digital age gradually begins to lose one thing, this thing is what the machine has not given it yet and it is human emotions. A key step in the humanization of robotics is the ability to classify the emotion of the human operator. In this paper we present the design of an artificially intelligent system capable of emotion recognition trough facial expressions. Three Promising neural network architectures are customized, trained. and subjected to various classification tasks, after which the best performing network is further optimized. The applicability of the final model is portrayed in a live video application that can instantaneously return the emotion of the user. Technology experts have found that we can create empathy through technology as well, which will consequently lead to what is known as “emotional intelligence.” Instead of seeking about digital communication that is losing us to real communication, experts have found that we can employ technology in favor of that type of communication to restore Soul for social and emotional relationships that technology has lost its advantages for many years.

Color Space Transformation using Neural Networks

2019 ◽  
Vol 2019 (1) ◽  
pp. 153-158
Author(s):  
Lindsay MacDonald
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Color Space ◽  
Reflectance Spectra ◽  
Network Architectures ◽  
Color Spaces ◽  
Natural Materials ◽  
Space Transformation ◽  
Color Space Transformation

We investigated how well a multilayer neural network could implement the mapping between two trichromatic color spaces, specifically from camera R,G,B to tristimulus X,Y,Z. For training the network, a set of 800,000 synthetic reflectance spectra was generated. For testing the network, a set of 8,714 real reflectance spectra was collated from instrumental measurements on textiles, paints and natural materials. Various network architectures were tested, with both linear and sigmoidal activations. Results show that over 85% of all test samples had color errors of less than 1.0 ΔE2000 units, much more accurate than could be achieved by regression.

Research on visual recognition intelligent system of city brand image based on fuzzy theory and regional culture

2021 ◽  
pp. 1-9
Author(s):  
Lin Han ◽  
Lu Han
Keyword(s):  
Neural Network ◽  
Visual Recognition ◽  
Intelligent System ◽  
Brand Image ◽  
Fuzzy Theory ◽  
Recognition System ◽  
Market Competitiveness ◽  
Visual Identity ◽  
Fuzzy Neural ◽  
Intelligent Recognition

With the rapid development of China’s market economy, brand image is becoming more and more important for an enterprise to enhance its market competitiveness and occupy a favorable market share. However, the brand image of many established companies gradually loses with the development of society and the improvement of people’s aesthetic pursuit. This has forced it to change its corporate brand image and regain the favor of the market. Based on this, this article combines the related knowledge and concepts of fuzzy theory, from the perspective of visual identity design, explores the development of corporate brand image visual identity intelligent system, and aims to design a set of visual identity system that is different from competitors in order to shape the enterprise. Distinctive brand image and improve its market competitiveness. This article first collected a large amount of information through the literature investigation method, and made a systematic and comprehensive introduction to fuzzy theory, visual recognition technology and related theoretical concepts of brand image, which laid a sufficient theoretical foundation for the later discussion of the application of fuzzy theory in the design of brand image visual recognition intelligent system; then the fuzzy theory algorithm is described in detail, a fuzzy neural network is proposed and applied to the design of the brand image visual recognition intelligent system, and the design experiment of the intelligent recognition system is carried out; finally, through the use of the specific case of KFC brand logo, the designed intelligent recognition system was tested, and it was found that the visual recognition intelligent system had an overall accuracy rate of 96.08% for the KFC brand logo. Among them, the accuracy rate of color recognition was the highest, 96.62%; comparing the changes in the output value of the training sample and the test sample, the output convergence effect of the color network is the best; through the comparison test of the BP neural network, the recognition effect of the fuzzy neural network is better.

Deep neural network-based detection and segmentation of intracranial aneurysms on 3D rotational DSA

2021 ◽  
pp. 159101992110009
Author(s):  
Xinke Liu ◽  
Junqiang Feng ◽  
Zhenzhou Wu ◽  
Zhonghao Neo ◽  
Chengcheng Zhu ◽  
...  
Keyword(s):  
Neural Network ◽  
Intracranial Aneurysms ◽  
Training Dataset ◽  
Maximum Diameter ◽  
Free Response ◽  
Final Model ◽  
Test Dataset ◽  
Segmentation Accuracy ◽  
Froc Analysis ◽  
Aneurysm Detection

Objective Accurate diagnosis and measurement of intracranial aneurysms are challenging. This study aimed to develop a 3D convolutional neural network (CNN) model to detect and segment intracranial aneurysms (IA) on 3D rotational DSA (3D-RA) images. Methods 3D-RA images were collected and annotated by 5 neuroradiologists. The annotated images were then divided into three datasets: training, validation, and test. A 3D Dense-UNet-like CNN (3D-Dense-UNet) segmentation algorithm was constructed and trained using the training dataset. Diagnostic performance to detect aneurysms and segmentation accuracy was assessed for the final model on the test dataset using the free-response receiver operating characteristic (FROC). Finally, the CNN-inferred maximum diameter was compared against expert measurements by Pearson’s correlation and Bland-Altman limits of agreement (LOA). Results A total of 451 patients with 3D-RA images were split into n = 347/41/63 training/validation/test datasets, respectively. For aneurysm detection, observed FROC analysis showed that the model managed to attain a sensitivity of 0.710 at 0.159 false positives (FP)/case, and 0.986 at 1.49 FP/case. The proposed method had good agreement with reference manual aneurysmal maximum diameter measurements (8.3 ± 4.3 mm vs. 7.8 ± 4.8 mm), with a correlation coefficient r = 0.77, small bias of 0.24 mm, and LOA of -6.2 to 5.71 mm. 37.0% and 77% of diameter measurements were within ±1 mm and ±2.5 mm of expert measurements. Conclusions A 3D-Dense-UNet model can detect and segment aneurysms with relatively high accuracy using 3D-RA images. The automatically measured maximum diameter has potential clinical application value.

scholarly journals Single-cell conventional pap smear image classification using pre-trained deep neural network architectures

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Mohammed Aliy Mohammed ◽  
Fetulhak Abdurahman ◽  
Yodit Abebe Ayalew
Keyword(s):  
Neural Network ◽  
Cervical Cancer ◽  
Computer Vision ◽  
Single Cell ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Pap Smear ◽  
Experimental Result ◽  
Network Architectures ◽  
Average Accuracy

Abstract Background Automating cytology-based cervical cancer screening could alleviate the shortage of skilled pathologists in developing countries. Up until now, computer vision experts have attempted numerous semi and fully automated approaches to address the need. Yet, these days, leveraging the astonishing accuracy and reproducibility of deep neural networks has become common among computer vision experts. In this regard, the purpose of this study is to classify single-cell Pap smear (cytology) images using pre-trained deep convolutional neural network (DCNN) image classifiers. We have fine-tuned the top ten pre-trained DCNN image classifiers and evaluated them using five class single-cell Pap smear images from SIPaKMeD dataset. The pre-trained DCNN image classifiers were selected from Keras Applications based on their top 1% accuracy. Results Our experimental result demonstrated that from the selected top-ten pre-trained DCNN image classifiers DenseNet169 outperformed with an average accuracy, precision, recall, and F1-score of 0.990, 0.974, 0.974, and 0.974, respectively. Moreover, it dashed the benchmark accuracy proposed by the creators of the dataset with 3.70%. Conclusions Even though the size of DenseNet169 is small compared to the experimented pre-trained DCNN image classifiers, yet, it is not suitable for mobile or edge devices. Further experimentation with mobile or small-size DCNN image classifiers is required to extend the applicability of the models in real-world demands. In addition, since all experiments used the SIPaKMeD dataset, additional experiments will be needed using new datasets to enhance the generalizability of the models.

Sign in / Sign up

Export Citation Format

Share Document