Digital Library[ Search Result ]
Knowledge Graph Embedding for Link Prediction using Node-Link Interaction-based Graph Attention Networks
http://doi.org/10.5626/JOK.2022.49.7.555
Knowledge graphs are structures that express knowledge in the real world in the form of nodes and links-based triple form. These knowledge graphs are incomplete and many embedding techniques have been studied to effectively represent nodes and links in low-dimensional vector spaces to find other missing relationships. Recently, many neural network-based knowledge graph link prediction methods have been studied. However existing models consider nodes and links independently when determining the importance of a triple to a node which makes it difficult to reflect the interaction between nodes and links. In this paper, we propose an embedding method that will be used to analyze the importance of triple units by simultaneously considering nodes and links using composition operators, and at the same time prove that the model outperforms other methods in knowledge graph link prediction.
Alpha-Integration Pooling for Convolutional Neural Networks
http://doi.org/10.5626/JOK.2021.48.7.774
Convolutional neural networks (CNNs) have achieved remarkable performance in many applications, especially in image recognition tasks. As a crucial component of CNNs, sub-sampling plays an important role for efficient training or invariance property, and max-pooling and arithmetic average-pooling are commonly used sub-sampling methods. In addition to the two pooling methods, however, there are many other pooling types, such as geometric average, harmonic average, among others. Since it is not easy for algorithms to find the best pooling method, usually the pooling types are predefined, which might not be optimal for different tasks. As other parameters in deep learning, however, the type of pooling can be driven by data for a given task. In this paper, we propose α-integration pooling (αI-pooling), which has a trainable parameter α to find the type of pooling. αI-pooling is a general pooling method including max-pooling and arithmetic average-pooling as a special case, depending on the parameter α. Experiments show that αI-pooling outperforms other pooling methods, in image recognition tasks. Also, it turns out that each layer has a different optimal pooling type.
Ensemble Modeling with Convolutional Neural Networks for Application in Visual Object Tracking
Minji Kim, Ilchae Jung, Bohyung Han
http://doi.org/10.5626/JOK.2021.48.2.211
In the area of computer vision, visual object tracking aims to estimate the status of a target object from an input video stream, which can be broadly applicable to industries such as surveillance and the military. Recently, deep learning-based tracking algorithms have gone through significant improvements by using tracking-by-detection or template-based approach. However, these approaches are still suffering from inherent limitations caused by each strategy. In this paper, we propose a novel method to model ensemble trackers by fusing the two strategies, tracking-by-detection and template-based approach. We report significantly enhanced performance on widely adopted visual object tracking benchmarks, OTB100, UAV123, and LaSOT.
Breast Cancer Subtype Classification Using Multi-omics Data Integration Based on Neural Network
Joungmin Choi, Jiyoung Lee, Jieun Kim, Jihyun Kim, Heejoon Chae
http://doi.org/10.5626/JOK.2020.47.9.835
Breast cancer is one of the highly heterogeneous diseases comprising multiple biological factors, causing multiple subtypes. Early diagnosis and accurate subtype prediction of breast cancer play a critical role in the prognosis of cancer and are crucial to providing appropriate treatment for each patient with different subtypes. To identify significant patterns from enormous volumes of genetic and epigenetic data, machine learning-based methods have been adopted to the breast cancer subtype classification. Recently, multi-omics data integration has attracted much attention as a promising approach in recognizing complex molecular mechanisms and providing a comprehensive view of patients. However, because of the characteristics of high dimensionality, multi-omics based approaches are limited in prediction accuracy. In this paper, we propose a neural network-based breast cancer subtype classification model using multi-omics data integration. The gene expression, DNA methylation, and miRNA omics dataset were integrated after preprocessing and the classification model was trained based on the neural network using the dataset. Our performance evaluation results showed that the proposed model outperforms all other methods, providing the highest classification accuracy of 90.45%. We expect this model to be useful in predicting the subtypes of breast cancer and improving patients’ prognosis.
A New Light-Weight and Efficient Convolutional Neural Network Using Fast Discrete Cosine Transform
http://doi.org/10.5626/JOK.2020.47.3.276
Recently proposed light-weight neural networks maintain high accuracy in some degree with a small amount of weight parameters and low computation cost. Nevertheless, existing convolutional neural networks commonly have a lot of weight parameters from the Pointwise Convolution (1x1 convolution), which also induces a high computational cost. In this paper, we propose a new Pointwise Convolution operation with one dimensional Fast Discrete Cosine Transform (FDCT), resulting in dramatically reducing the number of learnable weight parameters and speeding up the process of computation. We propose light-weight convolutional neural networks in two specific aspects: 1) Application of DCT on the block structure and 2) Application of DCT on the hierarchy level in the CNN models. Experimental results show that our proposed method achieved the similar classification accuracy compared to the MobileNet v1 model, reducing 79.1% of the number of learnable weight parameters and 48.3% of the number of FLOPs while achieving 0.8% increase in top-1 accuracy.
Automatic Convolution Neural Network Model Compression Framework for Resource-Constrained Embedded Systems
Jonghun Jeong, Dasom Lee, Hyeonseok Jung, Hoeseok Yang
http://doi.org/10.5626/JOK.2020.47.2.136
Recently, attempts have been made to directly execute various convolutional neural network applications in resource-constrained embedded systems such as IoT. However, since embedded systems have limited computational capability and memory, the size of the neural network model that can be executed is restricted and may not satisfy real-time constraints. Therefore, in this paper, we propose a framework that automatically compresses a given neural network model to satisfy memory and execution time requirements and automatically generates code that can be executed on the target embedded system. Using the proposed framework, we demonstrate that the given neural network models can be automatically optimized for two STM32 Nucleo series boards with different HW specifications for various execution time and memory requirements.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr