• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.188-195
• /
• 2024

This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a neural network-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such as hazing and low contrast occur, it is hard to apply conventional simultaneous localization and mapping (SLAM) methods. At the same time, the behavior of Autonomous Underwater Vehicle (AUV) is computationally constrained. In this paper, we utilize a neural network-based image enhancement method to improve pose estimation and mapping quality and apply a sliding window-based mesh expansion method to enable lightweight, fast, and photorealistic mapping. To validate our results, we utilize real-world and indoor synthetic datasets. We performed qualitative validation with the real-world dataset and quantitative validation by modeling images from the indoor synthetic dataset as underwater scenes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2505-2528
• /
• 2023

The field of facial expression recognition (FER) has been actively researched to improve human-computer interaction. In recent years, deep learning techniques have gained popularity for addressing FER, with numerous studies proposing end-to-end frameworks that stack or widen significant convolutional neural network layers. While this has led to improved performance, it has also resulted in larger model sizes and longer inference times. To overcome this challenge, our work introduces a novel lightweight model architecture. The architecture incorporates three key factors: Depth-wise Separable Convolution, Residual Block, and Attention Modules. By doing so, we aim to strike a balance between model size, inference speed, and accuracy in FER tasks. Through extensive experimentation on popular benchmark FER datasets, our proposed method has demonstrated promising results. Notably, it stands out due to its substantial reduction in parameter count and faster inference time, while maintaining accuracy levels comparable to other lightweight models discussed in the existing literature.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1464-1479
• /
• 2018

In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn't need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFacel, which uses pairs of face images as inputs and maps them to target space so that the $L_2$ norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.

• Journal of Advanced Navigation Technology
• /
• v.26 no.5
• /
• pp.365-372
• /
• 2022

Compared to sensors mainly used in human activity recognition (HAR) systems, inertial measurement unit (IMU) sensors are small and light, so can achieve lightweight system at low cost. Therefore, in this paper, we propose a binary neural network (BNN) based gait pattern analysis system using IMU sensor, and present the design and implementation results of an FPGA-based accelerator for computational acceleration. Six signals for gait are measured through IMU sensor, and a spectrogram is extracted using a short-time Fourier transform. In order to have a lightweight system with high accuracy, a BNN-based structure was used for gait pattern classification. It is designed as a hardware accelerator structure using FPGA for computation acceleration of binary neural network. The proposed gait pattern analysis system was implemented using 24,158 logics, 14,669 registers, and 13.687 KB of block memory, and it was confirmed that the operation was completed within 1.5 ms at the maximum operating frequency of 62.35 MHz and real-time operation was possible.

• Journal of Advanced Navigation Technology
• /
• v.28 no.4
• /
• pp.428-435
• /
• 2024

In this paper, a human activity regeneration (HAR) system based on multiple input multiple output frequency modulation continuous wave (MIMO FMCW) radar was designed and implemented. Using point cloud data from MIMO radar sensors has advantages in terms of privacy, safety, and accuracy. For the implementation of the HAR system, a customized neural network based on PointPillars and depthwise separate convolutional neural network (DS-CNN) was developed. By processing high-resolution point cloud data through a lightweight network, high accuracy and efficiency were achieved. As a result, the accuracy of 98.27% and the computational complexity of 11.27M multiply-accumulates (Macs) were achieved. In addition, the developed neural network model was implemented on Raspberry-Pi embedded system and it was confirmed that point cloud data can be processed at a speed of up to 8 fps.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4080-4097
• /
• 2020

In recent years, convolutional neural network (CNN) has become the primary method for face detection. But its shortcomings are obvious, such as expensive calculation, heavy model, etc. This makes CNN difficult to use on the mobile devices which have limited computing and storage capabilities. Therefore, the design of lightweight CNN for face detection is becoming more and more important with the popularity of smartphones and mobile Internet. Based on the CPU real-time face detector FaceBoxes, we propose a multi-task lightweight face detector, which has low computing cost and higher detection precision. First, to improve the detection capability, the squeeze and excitation modules are used to extract attention between channels. Then, the textual and semantic information are extracted by shallow networks and deep networks respectively to get rich features. Finally, the landmark detection module is used to improve the detection performance for small faces and provide landmark data for face alignment. Experiments on AFW, FDDB, PASCAL, and WIDER FACE datasets show that our algorithm has achieved significant improvement in the mean average precision. Especially, on the WIDER FACE hard validation set, our algorithm outperforms the mean average precision of FaceBoxes by 7.2%. For VGA-resolution images, the running speed of our algorithm can reach 23FPS on a CPU device.

• Advances in nano research
• /
• v.13 no.5
• /
• pp.499-512
• /
• 2022

This study investigates the efficiency of ensemble machine learning for predicting the lightweight-aggregate concrete (LWC) characteristics. A stacking ensemble (STEN) approach was proposed to estimate the dry density (DD) and 28 days compressive strength (Fc-28) of LWC using two meta-models called random forest regressor (RFR) and extra tree regressor (ETR), and two novel ensemble models called STEN-RFR and STEN-ETR, were constructed. Four standalone machine learning models including artificial neural network, gradient boosting regression, K neighbor regression, and support vector regression were used to compare the performance of the proposed models. For this purpose, a sum of 140 LWC mixtures with 21 influencing parameters for producing LWC with a density less than 1000 kg/m³, were used. Based on the experimental results with multiple performance criteria, it can be concluded that the proposed STEN-ETR model can be used to estimate the DD and Fc-28 of LWC. Moreover, the STEN-ETR approach was found to be a significant technique in prediction DD and Fc-28 of LWC with minimal prediction error. In the validation phase, the accuracy of the proposed STEN-ETR model in predicting DD and Fc-28 was found to be 96.79% and 81.50%, respectively. In addition, the significance of cement, water-cement ratio, silica fume, and aggregate with expanded glass variables is efficient in modeling DD and Fc-28 of LWC.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.531-536
• /
• 2023

This paper proposes a sliding window method with frame feature insertion for immediate attack detection on in-vehicle networks. This method guarantees real-time attack detection by labeling based on the attack status of the current frame. Experiments show that the proposed method improves detection performance by giving more weight to the current frame in CNN computation. The proposed model was designed based on a lightweight LeNet-5 architecture and it achieves 100% detection for DoS attacks. Additionally, by comparing the complexity with conventional models, the proposed model has been proven to be more suitable for resource-constrained devices like ECUs.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.193-200
• /
• 2023

Cryptanalysis can be performed by various techniques such as known plaintext attack, differential attack, side-channel analysis, and the like. Recently, many studies have been conducted on cryptanalysis using deep learning. A known-plaintext attack is a technique that uses a known plaintext and ciphertext pair to find a key. In this paper, we use deep learning technology to perform a known-plaintext attack against S-PRESENT, a reduced version of the lightweight block cipher PRESENT. This paper is significant in that it is the first known-plaintext attack based on deep learning performed on a reduced lightweight block cipher. For cryptanalysis, MLP (Multi-Layer Perceptron) and 1D and 2D CNN(Convolutional Neural Network) models are used and optimized, and the performance of the three models is compared. It showed the highest performance in 2D convolutional neural networks, but it was possible to attack only up to some key spaces. From this, it can be seen that the known-plaintext attack through the MLP model and the convolutional neural network is limited in attackable key bits.