• Journal of Information Processing Systems
• /
• 제18권1호
• /
• pp.12-25
• /
• 2022

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct highresolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.

• 전자통신동향분석
• /
• 제38권5호
• /
• pp.12-22
• /
• 2023

The development of neural networks is evolving towards the adoption of transformer structures with attention modules. Hence, active research focused on extending the concept of lightweight neural network algorithms and hardware acceleration is being conducted for the transition from conventional convolutional neural networks to transformer-based networks. We present a survey of state-of-the-art research on lightweight neural network algorithms and hardware architectures to reduce memory usage and accelerate both inference and training. To describe the corresponding trends, we review recent studies on token pruning, quantization, and architecture tuning for the vision transformer. In addition, we present a hardware architecture that incorporates lightweight algorithms into artificial intelligence processors to accelerate processing.

• 센서학회지
• /
• 제30권1호
• /
• pp.15-19
• /
• 2021

Image processing is one of the major techniques that are used for computer vision. Nowadays, researchers are using machine learning and deep learning for the aforementioned task. In recent years, digit recognition tasks, i.e., automatic meter recognition approach using electric or water meters, have been studied several times. However, two major issues arise when we talk about previous studies: first, the use of the deep learning technique, which includes a large number of parameters that increase the computational cost and consume more power; and second, recent studies are limited to the detection of digits and not storing or providing detected digits to a database or mobile applications. This paper proposes a system that can detect the digital number of meter readings using a lightweight deep neural network (DNN) for low power consumption and send those digits to an Android mobile application in real-time to store them and make life easy. The proposed lightweight DNN is computationally inexpensive and exhibits accuracy similar to those of conventional DNNs.

• Computers and Concrete
• /
• 제19권2호
• /
• pp.217-226
• /
• 2017

This paper summarizes the results of experimental research, and artificial intelligence methods focused on determination of compressive strength of lightweight cement mortar with silica fume and fly ash after sulfate attack. The artificial neural network and the support vector machine were selected as artificial intelligence methods. Lightweight cement mortar mixtures containing silica fume and fly ash were prepared in this study. After specimens were cured in $20{\pm}2^{\circ}C$ waters for 28 days, the specimens were cured in different sulfate concentrations (0%, 1% $MgSO_4^{-2}$, 2% $MgSO_4^{-2}$, and 4% $MgSO_4^{-2}$ for 28, 60, 90, 120, 150, 180, 210 and 365 days. At the end of these curing periods, the compressive strengths of lightweight cement mortars were tested. The input variables for the artificial neural network and the support vector machine were selected as the amount of cement, the amount of fly ash, the amount of silica fumes, the amount of aggregates, the sulfate percentage, and the curing time. The compressive strength of the lightweight cement mortar was the output variable. The model results were compared with the experimental results. The best prediction results were obtained from the artificial neural network model with the Powell-Beale conjugate gradient backpropagation training algorithm.

• Computers and Concrete
• /
• 제25권5호
• /
• pp.401-409
• /
• 2020

Artificial neural networks are used as a useful tool in distinct fields of civil engineering these days. In order to control long-term quality of Self-Compacting Semi-Lightweight Concrete (SCSLC), the 90 days compressive strength is considered as a key issue in this paper. In fact, combined artificial neural networks are used to predict the compressive strength of SCSLC at 28 and 90 days. These networks are able to re-establish non-linear and complex relationships straightforwardly. In this study, two types of neural networks, including Radial Basis and Multilayer Perceptron, were used. Four groups of concrete mix designs also were made with two water to cement ratios (W/C) of 0.35 and 0.4, as well as 10% of cement weight was replaced with silica fume in half of the mixes, and different amounts of superplasticizer were used. With the help of rheology test and compressive strength results at 7 and 14 days as inputs, the neural networks were used to estimate the 28 and 90 days compressive strengths of above-mentioned mixes. It was necessary to add the 14 days compressive strength in the input layer to gain acceptable results for 90 days compressive strength. Then proper neural networks were prepared for each mix, following which four existing networks were combined, and the combinatorial neural network model properly predicted the compressive strength of different mix designs.

• Computers and Concrete
• /
• 제10권4호
• /
• pp.379-390
• /
• 2012

In this paper, the mechanical strength of different lightweight mortars made with 0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95 and 100 percentage of scoria instead of sand and 0.55 water-cement ratio and 350 $kg/m^3$ cement content is investigated. The experimental result showed 7.9%, 16.7% and 49% decrease in compressive strength, tensile strength and mortar density, respectively, by using 100% scoria instead of sand in the mortar. The normalized compressive and tensile strength data are applied for artificial neural network (ANN) generation using generalized regression neural network (GRNN). Totally, 90 experimental data were selected randomly and applied to find the best network with minimum mean square error (MSE) and maximum correlation of determination. The created GRNN with 2 input layers, 2 output layers and a network spread of 0.1 had minimum MSE close to 0 and maximum correlation of determination close to 1.

• Journal of Platform Technology
• /
• 제11권1호
• /
• 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.

• 전기전자학회논문지
• /
• 제27권4호
• /
• pp.524-530
• /
• 2023

본 논문에서는 경량화된 CNN(Convolutional Neural Network)을 사용하여 CAN(Controller Area Network) 버스 상의 공격을 탐지하는 효율적인 알고리즘을 제안하고, 이를 기반으로 하는 IDS(Intrusion Detection System)를 FPGA로 설계, 구현 및 검증하였다. 제안한 IDS는 기존의 CNN 기반 IDS에 비해 CAN 버스 상의 공격을 프레임 단위로 탐지할 수 있어서 정확하고 신속한 대응이 가능하다. 또한 제안한 IDS는 기존의 CNN 기반 IDS에 비해 컨볼루션 레이어를 하나만 사용하기 때문에 하드웨어를 크게 줄일 수 있다. 시뮬레이션 및 구현 결과는 제안된 IDS가 CAN 버스 상의 다양한 공격을 효과적으로 탐지한다는 것을 보여준다.

• 한국정보전자통신기술학회논문지
• /
• 제14권4호
• /
• pp.314-322
• /
• 2021

Skeleton-based action recognition has attracted considerable attention in human action recognition. Recent methods for skeleton-based action recognition employ spatiotemporal graph convolutional networks (GCNs) and have remarkable performance. However, most of them have heavy computational complexity for robust action recognition. To solve this problem, we propose a shuffle graph convolutional network (SGCN) which is a lightweight graph convolutional network using pointwise group convolution rather than pointwise convolution to reduce computational cost. Our SGCN is composed of spatial and temporal GCN. The spatial shuffle GCN contains pointwise group convolution and part shuffle module which enhances local and global information between correlated joints. In addition, the temporal shuffle GCN contains depthwise convolution to maintain a large receptive field. Our model achieves comparable performance with lowest computational cost and exceeds the performance of baseline at 0.3% and 1.2% on NTU RGB+D and NTU RGB+D 120 datasets, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권2호
• /
• pp.600-616
• /
• 2021

SIMON and SPECK are two families of lightweight block ciphers that have excellent performance on hardware and software platforms. At CRYPTO 2019, Gohr first introduces the differential cryptanalysis based deep learning on round-reduced SPECK32/64, and finally reduces the remaining security of 11-round SPECK32/64 to roughly 38 bits. In this paper, we are committed to evaluating the safety of SIMON cipher under the neural differential cryptanalysis. We firstly prove theoretically that SIMON is a non-Markov cipher, which means that the results based on conventional differential cryptanalysis may be inaccurate. Then we train a residual neural network to get the 7-, 8-, 9-round neural distinguishers for SIMON32/64. To prove the effectiveness for our distinguishers, we perform the distinguishing attack and key-recovery attack against 15-round SIMON32/64. The results show that the real ciphertexts can be distinguished from random ciphertexts with a probability close to 1 only by 2^8.7 chosen-plaintext pairs. For the key-recovery attack, the correct key was recovered with a success rate of 23%, and the data complexity and computation complexity are as low as 2⁸ and 2^20.1 respectively. All the results are better than the existing literature. Furthermore, we briefly discussed the effect of different residual network structures on the training results of neural distinguishers. It is hoped that our findings will provide some reference for future research.