PPCNN: Object Detection using Fine-grained Feature Extraction and Localization

Haque, Foysal; Kang, Dae-Seong

doi:10.14801/jkiit.2021.19.2.29

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use two main methods to select the hyperparameters. One is based on the training experience of models in the same field [36,37]. The other one is based on the experiments in Section 3.…”

Section: Resultsmentioning

confidence: 99%

Automatic detection of three cell types in a microscope image based on deep learning

Zhang

Zhou

et al. 2022

Journal of Biophotonics

View full text Add to dashboard Cite

With the continuous integration of deep learning and the technique of molecular biology, target detection models must accurately detect the position of each cell in the image and classify it correctly. We present a model for the multi‐scale feature fusion of the existing human cell image dataset based on Gaussian mixedly clustering. First, a novel feature extraction network for extracting preliminary features at picture multi scales was presented, which was based on a residual neural network with Instance Normalization and a Mish activation function. Second, the presented model adopts the idea of feature fusion and introduced a new type of feature fusion network to integrate feature graphs on different scales. Furthermore, a Gaussian hybrid clustering algorithm was proposed to cluster the hyperparameters. Based on the experimental results, the average accuracy of the proposed model in the human cell image dataset exceeds 0.96, which improves by 11.9% compared with the existing target detection methods in the same field. Experiments show that the proposed model had been adapted to datasets with uneven sample distribution, providing new ideas for research on medical images.

show abstract

“…We use two main methods to select the hyperparameters. One is based on the training experience of models in the same field [36,37]. The other one is based on the experiments in Section 3.…”

Section: Resultsmentioning

confidence: 99%

Automatic detection of three cell types in a microscope image based on deep learning

Zhang

Zhou

et al. 2022

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…The packet capture process requires the system to have sufficient processing power and storage resources to process and store a large number of network data packets. Therefore, it is considered to use NIC drivers for data collection [6][7][8]. The principle of packet capture in the real-time monitoring system of power grid communication network is mainly divided into three steps:…”

Section: Data Acquisition and Processingmentioning

confidence: 99%

Feature Extraction and Attack Correlation Detection in Power Communication Networks Based on Convolutional Neural Networks

Wang,

Zhang,

et al. 2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

To solve the problem of low feature recognition in existing feature extraction methods in power communication networks, a CNN model is adopted for network data feature extraction and attack correlation detection. Firstly, a basic framework for data preprocessing and further system analysis is proposed for the communication protocol and link basic structure of intelligent substations, as well as general network communication flow collection and analysis methods. Then, detailed design will be performed for different functional modules, including data collection, traffic extraction, and SVM based classification and recognition. Then, convolutional neural networks are used to classify the associated and non associated traffic feature maps, in order to determine whether they are related. Finally, an experiment is conducted with a real power communication network. The results show that the data feature extraction method proposed in the article can achieve reliability prediction from actual operating data of the power communication network, greatly improving feature identification and reducing storage and calculation costs while maintaining accuracy.

show abstract

PPCNN: Object Detection using Fine-grained Feature Extraction and Localization

Cited by 2 publications

References 17 publications

Automatic detection of three cell types in a microscope image based on deep learning

Automatic detection of three cell types in a microscope image based on deep learning

Feature Extraction and Attack Correlation Detection in Power Communication Networks Based on Convolutional Neural Networks

Contact Info

Product

Resources

About