Implementation of Convolutional Neural Network with Co-design of High-Level Synthesis and Verilog HDL

Emotions are a fundamental part of human behavior and can be stimulated in numerous ways. In real-life, we come across different types of objects such as cake, crab, television, trees, etc., in our routine life, which may excite certain emotions. Likewise, object images that we see and share on different platforms are also capable of expressing or inducing human emotions. Inferring emotion tags from these object images has great significance as it can play a vital role in recommendation systems, image retrieval, human behavior analysis and, advertisement applications. The existing schemes for emotion tag perception are based on the visual features, like color and texture of an image, which are poorly affected by lightning conditions. The main objective of our proposed study is to address this problem by introducing a novel idea of inferring emotion tags from the images based on object-related features. In this aspect, we first created an emotion-tagged dataset from the publicly available object detection dataset (i.e., “Caltech-256”) using subject evaluation from 212 users. Next, we used a convolutional neural network-based model to automatically extract the high-level features from object images for recognizing nine (09) emotion categories, such as amusement, awe, anger, boredom, contentment, disgust, excitement, fear, and sadness. Experimental results on our emotion-tagged dataset endorse the success of our proposed idea in terms of accuracy, precision, recall, specificity, and F1-score. Overall, the proposed scheme achieved an accuracy rate of approximately 85% and 79% using top-level and bottom-level emotion tagging, respectively. We also performed a gender-based analysis for inferring emotion tags and observed that male and female subjects have discernment in emotions perception concerning different object categories.

Download Full-text

Deep Learning-Based Classification of Weld Surface Defects

Applied Sciences ◽

10.3390/app9163312 ◽

2019 ◽

Vol 9 (16) ◽

pp. 3312 ◽

Cited By ~ 4

Author(s):

Zhu ◽

Ge ◽

Liu

Keyword(s):

Neural Network ◽

Deep Learning ◽

Random Forest ◽

Convolutional Neural Network ◽

Surface Defects ◽

Recognition Method ◽

High Level ◽

Intelligent Recognition ◽

Non Destructive

In order to realize the non-destructive intelligent identification of weld surface defects, an intelligent recognition method based on deep learning is proposed, which is mainly formed by convolutional neural network (CNN) and forest random. First, the high-level features are automatically learned through the CNN. Random forest is trained with extracted high-level features to predict the classification results. Secondly, the weld surface defects images are collected and preprocessed by image enhancement and threshold segmentation. A database of weld surface defects is established using pre-processed images. Finally, comparative experiments are performed on the weld surface defects database. The results show that the accuracy of the method combined with CNN and random forest can reach 0.9875, and it also demonstrates the method is effective and practical.

Download Full-text

A High-Density Crowd Counting Method Based on Convolutional Feature Fusion

Applied Sciences ◽

10.3390/app8122367 ◽

2018 ◽

Vol 8 (12) ◽

pp. 2367 ◽

Cited By ~ 5

Author(s):

Hongling Luo ◽

Jun Sang ◽

Weiqun Wu ◽

Hong Xiang ◽

Zhili Xiang ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Large Scale ◽

Feature Fusion ◽

High Density ◽

Counting Problem ◽

Crowd Counting ◽

Low Level ◽

Density Map ◽

High Level

In recent years, the trampling events due to overcrowding have occurred frequently, which leads to the demand for crowd counting under a high-density environment. At present, there are few studies on monitoring crowds in a large-scale crowded environment, while there exists technology drawbacks and a lack of mature systems. Aiming to solve the crowd counting problem with high-density under complex environments, a feature fusion-based deep convolutional neural network method FF-CNN (Feature Fusion of Convolutional Neural Network) was proposed in this paper. The proposed FF-CNN mapped the crowd image to its crowd density map, and then obtained the head count by integration. The geometry adaptive kernels were adopted to generate high-quality density maps which were used as ground truths for network training. The deconvolution technique was used to achieve the fusion of high-level and low-level features to get richer features, and two loss functions, i.e., density map loss and absolute count loss, were used for joint optimization. In order to increase the sample diversity, the original images were cropped with a random cropping method for each iteration. The experimental results of FF-CNN on the ShanghaiTech public dataset showed that the fusion of low-level and high-level features can extract richer features to improve the precision of density map estimation, and further improve the accuracy of crowd counting.

Download Full-text

A neural network based algorithm for the scheduling problem in high-level synthesis

Proceedings EURO-DAC '92: European Design Automation Conference ◽

10.1109/eurdac.1992.246221 ◽

2003 ◽

Cited By ~ 4

Author(s):

M. Nourani ◽

C. Papachristou ◽

Y. Takefuji

Keyword(s):

Neural Network ◽

High Level Synthesis ◽

Scheduling Problem ◽

High Level

Download Full-text

Detection and Classification of White Blood Cells through Deep Learning Techniques

International Journal of Online and Biomedical Engineering (iJOE) ◽

10.3991/ijoe.v16i15.15481 ◽

2020 ◽

Vol 16 (15) ◽

pp. 94

Author(s):

Samir Abou El-Seoud ◽

Muaad Hammuda Siala ◽

Gerard McKee

Keyword(s):

Neural Network ◽

Blood Cell ◽

Convolutional Neural Network ◽

White Blood Cell ◽

Blood Cells ◽

Human Life ◽

White Blood Cells ◽

Learning Techniques ◽

Normal White Blood Cell ◽

High Level

Leukemia is one of the deadliest diseases in human life, it is a type of cancer that hits blood cells. The task of diagnosing Leukemia is time consuming and tedious for doctors; it is also challenging to determine the level and type of Leukemia. The diagnoses of Leukemia are achieved through identifying the changes on the White blood Cells (WBC). WBCs are divided into five types: Neutrophils, Eosinophils, Basophils, Monocytes, and Lymphocytes. In this paper, the authors propose a Convolutional Neural Network to detect and classify normal white blood cells. The program will learn about the shape and type of normal WBC by performing the following two tasks. The first task is identifying high level features of a normal white blood cell. The second task is classifying the normal white blood cell according to its type. Using a Convolutional Neural Network CNN, the system will be able to detect normal WBCs by comparing them with the high-level features of normal WBC. This process of identifying and classifying WBC can be vital for doctors and medical staff to make a decision. The proposed network achieves an accuracy up to 96.78% with a dataset including 10,000 blood cell images.

Download Full-text

A Multibranch of Convolutional Neural Network Models for Electroencephalogram-Based Motor Imagery Classification

Biosensors ◽

10.3390/bios12010022 ◽

2022 ◽

Vol 12 (1) ◽

pp. 22

Author(s):

Ghadir Ali Altuwaijri ◽

Ghulam Muhammad

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Motor Imagery ◽

Classification Accuracy ◽

Network Models ◽

Classification Methods ◽

Neural Network Models ◽

High Gamma ◽

Public Datasets ◽

High Level

Automatic high-level feature extraction has become a possibility with the advancement of deep learning, and it has been used to optimize efficiency. Recently, classification methods for convolutional neural network (CNN)-based electroencephalography (EEG) motor imagery have been proposed, and have achieved reasonably high classification accuracy. These approaches, however, use the CNN single convolution scale, whereas the best convolution scale varies from subject to subject. This limits the precision of classification. This paper proposes multibranch CNN models to address this issue by effectively extracting the spatial and temporal features from raw EEG data, where the branches correspond to different filter kernel sizes. The proposed method’s promising performance is demonstrated by experimental results on two public datasets, the BCI Competition IV 2a dataset and the High Gamma Dataset (HGD). The results of the technique show a 9.61% improvement in the classification accuracy of multibranch EEGNet (MBEEGNet) from the fixed one-branch EEGNet model, and 2.95% from the variable EEGNet model. In addition, the multibranch ShallowConvNet (MBShallowConvNet) improved the accuracy of a single-scale network by 6.84%. The proposed models outperformed other state-of-the-art EEG motor imagery classification methods.

Download Full-text

Incorporating Context-Relevant Knowledge into Convolutional Neural Networks for Short Text Classification

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.330110067 ◽

2019 ◽

Vol 33 ◽

pp. 10067-10068 ◽

Cited By ~ 2

Author(s):

Jingyun Xu ◽

Yi Cai

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Text Classification ◽

Classification Methods ◽

Short Text ◽

Proposed Model ◽

High Level ◽

Context Features

Some text classification methods don’t work well on short texts due to the data sparsity. What’s more, they don’t fully exploit context-relevant knowledge. In order to tackle these problems, we propose a neural network to incorporate context-relevant knowledge into a convolutional neural network for short text classification. Our model consists of two modules. The first module utilizes two layers to extract concept and context features respectively and then employs an attention layer to extract those context-relevant concepts. The second module utilizes a convolutional neural network to extract high-level features from the word and the contextrelevant concept features. The experimental results on three datasets show that our proposed model outperforms the stateof-the-art models.

Download Full-text