• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.5
• /
• pp.85-91
• /
• 1989

In this paper, we propose a neural net system for speech recognition, which is composed of two neural networks. Firstly the self-supervised BP(Back Propagation) network generates the distributed concept corresponding to the activity pattern in the hidden units. And then the self-organizing neural network forms a concept map which directly displays the similarity relations between concepts. By doing the above, the difficulty in learning the conventional BP network is solved and the weak side of BP falling into a pattern matcher is gone, while the strong point of generating the various internal representations is used. And we have obtained the concept map which is more orderly than the Kohonen's SOFM. The proposed neural net system needs not any special preprocessing and has a self-learning ability.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.23-29
• /
• 2020

This paper presents an approach for dynamic hand gesture recognition by using algorithm based on 3D Convolutional Neural Network (3D_CNN), which is later extended to 3D Residual Networks (3D_ResNet), and the neural network based key frame selection. Typically, 3D deep neural network is used to classify gestures from the input of image frames, randomly sampled from a video data. In this work, to improve the classification performance, we employ key frames which represent the overall video, as the input of the classification network. The key frames are extracted by SegNet instead of conventional clustering algorithms for video summarization (VSUMM) which require heavy computation. By using a deep neural network, key frame selection can be performed in a real-time system. Experiments are conducted using 3D convolutional kernels such as 3D_CNN, Inflated 3D_CNN (I3D) and 3D_ResNet for gesture classification. Our algorithm achieved up to 97.8% of classification accuracy on the Cambridge gesture dataset. The experimental results show that the proposed approach is efficient and outperforms existing methods.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.760-770
• /
• 2019

Based on the growing demand for neural network technologies, various neural network inference engines are being developed. However, each inference engine has its own neural network storage format. There is a growing demand for standardization to solve this problem. This study presents interworking techniques for ensuring the compatibility of neural networks and data among the various deep learning frameworks. The proposed technique standardizes the graphic expression grammar and learning data storage format using the Neural Network Exchange Format (NNEF) of Khronos. The proposed converter includes a lexical, syntax, and parser. This NNEF parser converts neural network information into a parsing tree and quantizes data. To validate the proposed system, we verified that MNIST is immediately executed by importing AlexNet's neural network and learned data. Therefore, this study contributes an efficient design technique for a converter that can execute a neural network and learned data in various frameworks regardless of the storage format of each framework.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.97-99
• /
• 2022

For the early identification and treatment of colorectal cancer, accurate polyp segmentation is crucial. However, polyp segmentation is a challenging task, and the majority of current approaches struggle with two issues. First, the position, size, and shape of each individual polyp varies greatly (intra-class inconsistency). Second, there is a significant degree of similarity between polyps and their surroundings under certain circumstances, such as motion blur and light reflection (inter-class indistinction). U-net, which is composed of convolutional neural networks as encoder and decoder, is considered as a standard for tackling this task. We propose an updated U-net architecture replacing the encoder part with vision transformer network for polyp segmentation. The proposed architecture performed better than the standard U-net architecture for the task of polyp segmentation.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.187-193
• /
• 2021

Our final goal is to implement nursing robots that can recognize patient's faces and their medicine on prescription. They can help patients to take medicine on time and prevent its abuse for recovering their health soon. As the first step, we proposed a medicine classifier with a low computational network that is able to run on embedded PCs without GPU in order to be applied to universal nursing robots. We confirm that our proposed model called MedicineNet achieves an 99.99% accuracy performance for classifying 15 kinds of medicines and background images. Moreover, we realize that the calculation time of our MedicineNet is about 8 times faster than EfficientNet-B0 which is well known as ImageNet classification with the high performance and the best computational efficiency.

• Journal of Platform Technology
• /
• v.11 no.1
• /
• pp.72-84
• /
• 2023

With the rise of the Internet of Things, the security of such lightweight computing environments has become a hot topic. Lightweight block ciphers that can provide efficient performance and security by having a relatively simpler structure and smaller key and block sizes are drawing attention. Due to these characteristics, they can become a target for new attack techniques. One of the new cryptanalytic attacks that have been attracting interest is Neural cryptanalysis, which is a cryptanalytic technique based on neural networks. It showed interesting results with better results than the conventional cryptanalysis method without a great amount of time and cryptographic knowledge. The first work that showed good results was carried out by Aron Gohr in CRYPTO'19, the attack was conducted on the lightweight block cipher SPECK-/32/64 and showed better results than conventional differential cryptanalysis. In this paper, we first apply the Differential Neural Distinguisher proposed by Aron Gohr to the block ciphers HIGHT and GOST to test the applicability of the attack to ciphers with different structures. The performance of the Differential Neural Distinguisher is then analyzed by replacing the neural network attack model with five different models (Multi-Layer Perceptron, AlexNet, ResNext, SE-ResNet, SE-ResNext). We then propose a Related-key Neural Distinguisher and apply it to the SPECK-/32/64, HIGHT, and GOST block ciphers. The proposed Related-key Neural Distinguisher was constructed using the relationship between keys, and this made it possible to distinguish more rounds than the differential distinguisher.

• The KSFM Journal of Fluid Machinery
• /
• v.13 no.6
• /
• pp.19-24
• /
• 2010

The demands for small, high performance and high loaded aircraft compressor are increased in the world. But the design requirements become increasingly complex to design these high technical engines, the requirement of the design optimization become increased. The optimal design result of several disciplines show different tendencies and nonlinear characteristics of the compressor design, the multidisciplinary design optimization method must be considered in compressor design. Therefore, the artificial Neural Net method is adapted to make the approximation model of 3-stage axial compressor design optimization for considering the nonlinear characteristic. At last, the optimal result of this study is compared to that of previous study.

• Journal of Energy Engineering
• /
• v.26 no.3
• /
• pp.11-29
• /
• 2017

In recent years, the use of artificial intelligence technology such as deep neural net machine learning(deep learning) is becoming an effective and practical option in industrial manufacturing process. This study focuses on recent deep learning development environments and their applications in the manufacturing field.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.150-161
• /
• 2018

We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.