• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.428-442
• /
• 2022

A reliable automatic passenger counting (APC) system is a key point in transportation related to the efficient scheduling and management of transport routes. In this study, we introduce a lightweight head detection network using deep learning applicable to an embedded system. Currently, object detection algorithms using deep learning have been found to be successful. However, these algorithms essentially need a graphics processing unit (GPU) to make them performable in real-time. So, we modify a Tiny-YOLOv3 network using certain techniques to speed up the proposed network and to make it more accurate in a non-GPU environment. Finally, we introduce an APC system, which is performable in real-time on embedded systems, using the proposed head detection algorithm. We implement and test the proposed APC system on a Samsung ARTIK 710 board. The experimental results on three public head datasets reflect the detection accuracy and efficiency of the proposed head detection network against Tiny-YOLOv3. Moreover, to test the proposed APC system, we measured the accuracy and recognition speed by repeating 50 instances of entering and 50 instances of exiting. These experimental results showed 99% accuracy and a 0.041-second recognition speed despite the fact that only the CPU was used.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2483-2504
• /
• 2023

Most existing low-light enhancement algorithms either use a large number of training parameters or lack generalization to real-world scenarios. This paper presents a novel lightweight and robust pixel-wise polynomial approximation-based deep network for low-light image enhancement. For mapping the low-light image to the enhanced image, pixel-wise higher-order polynomials are employed. A deep convolution network is used to estimate the coefficients of these higher-order polynomials. The proposed network uses multiple branches to estimate pixel values based on different receptive fields. With a smaller receptive field, the first branch enhanced local features, the second and third branches focused on medium-level features, and the last branch enhanced global features. The low-light image is downsampled by the factor of 2b-1 (b is the branch number) and fed as input to each branch. After combining the outputs of each branch, the final enhanced image is obtained. A comprehensive evaluation of our proposed network on six publicly available no-reference test datasets shows that it outperforms state-of-the-art methods on both quantitative and qualitative measures.

• 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 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 Information Processing Systems
• /
• v.2 no.1
• /
• pp.48-51
• /
• 2006

To achieve security in wireless sensor networks (WSN), it is important to be able to encrypt messages sent among sensor nodes. We propose a new cryptographic key management protocol, which is based on the clustering scheme but does not depend on the probabilistic key. The protocol can increase the efficiency to manage keys since, before distributing the keys by bootstrap, the use of public keys shared among nodes can eliminate the processes to send or to receive keys among the sensors. Also, to find any compromised nodes safely on the network, it solves safety problems by applying the functions of a lightweight attack-detection mechanism.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.296-301
• /
• 2004

The Wireless Sensor Network is technology that makes possible utilize the information collected from rescue, the agricultural and livestock management system, and the home automation system by using an ultra-small sized, ultra-lightweight sensor module. This study proposes the routing protocol with directional nature that can improve the utilization by higher energy efficiency and reliability than those of existing studies on data transmission, and we also analyze the current studies, make a comparison of them in performance.

• Journal of Korea Multimedia Society
• /
• v.21 no.9
• /
• pp.1090-1098
• /
• 2018

MQTT is a lightweight messaging protocol that can be used for low power IoT devices. The MQTT basically uses single MQTT broker to indirectly share message information between publishers and subscribers. This approach has a weakness in regard to traffic overflow, connection fault, security, etc. In this paper, we propose a distributed MQTT broker architecture that solves the problems in single MQTT broker structure. The distributed MQTT broker architecture is expected to support new application services that cannot be supported by a conventional MQTT architecture. We have designed and implemented a distributed MQTT broker architecture based on the RPL protocol that has been widely used for IoT network. The experiment results show that the proposed MQTT broker architecture represents better publishing/subscribing latency and network stability than the conventional MQTT broker architecture.

• Annual Conference of KIPS
• /
• 2005.11a
• /
• pp.973-976
• /
• 2005

In IEEE 802.15.4 (Low-Rate Wireless Personal Area Network) specification, a successful reception and validation of a data or MAC command frame can be confirmed with an acknowledgment. However, the specification does not support security for acknowledgment frame; the lack of a MAC covering acknowledgments allows an adversary to forge an acknowledgment for any frame. This paper proposes an identity authentication mechanism at the link layer for acknowledgment frame in IEEE 802.15.4 network. With the proposed mechanism there is only three bits for authentication, which can greatly reduce overhead. The encrypted bit stream for identity authentication will be transmitted to device by coordinator within association process. Statistical method indicates that our mechanism is successful in handling MAC layer attack.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06c
• /
• pp.277-279
• /
• 2006

본 논문에서는 Wireless Sensor Networks(WSNs)에서 에너지 소모를 줄이기 위해 사용되는 In-network processing에 대하여 보안이 강화된 레벨 키 기반의 Infrastructure를 설계하여 노드의 전복 공격에 대해 안전한 패킷 포워딩을 보장하는 프로토콜을 제시한다. 이러한 계층적 구조를 가지는 보안 Framework는 노드의 추가 혹은 퇴거가 발생했을 때 Re-keying 비용을 획기적으로 줄일 수 있다. 시뮬레이션 결과, 전체 네트워크 중 전복된 노드가 40%를 차지할 때, 제안된 프로토콜을 사용하게 되면 약 3%의 추가적인 라우팅 오버헤드 비용으로 15%의 향상된 종단간 패킷 전송률을 보여준다. 또한 Re-keying을 할 때 OFT와 비교하여 통신비용을 현저하게 줄일 뿐만 아니라 서버의 도움 없이 키를 업데이트 하기 때문에 분산환경에 적합한 특징을 갖는다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1226-1228
• /
• 2022

FHD 이상을 넘어선 UHD급의 고해상도 동영상 콘텐츠의 수요 및 공급이 증가함에 따라 전반적인 산업 영역에서 네트워크 자원을 효율적으로 이용하여 동영상 콘텐츠를 제공하는 데에 관심을 두게 되었다. 기존 방법을 통한 bi-cubic, bi-linear interpolation 등의 방법은 딥 러닝 기반의 모델에 비교적 인풋 이미지의 특징을 잘 잡아내지 못하는 결과를 나타내었다. 딥 러닝 기반의 초 해상화 기술의 경우 기존 방법과 비교 시 연산을 위해 더 많은 자원을 필요로 하므로, 이러한 사용 조건에 따라 본 논문은 초 해상화가 가능한 딥 러닝 모델을 경량화 기법을 사용하여 기존에 사용된 모델보다 비교적 적은 자원을 효율적으로 사용할 수 있도록 연구 개발하는 데 목적을 두었다. 연구방법으로는 structure pruning을 이용하여 모델 자체의 구조를 경량화 하였고, 학습을 진행해야 하는 파라미터를 줄여 하드웨어 자원을 줄이는 연구를 진행했다. 또한, Residual Network의 개수를 줄여가며 PSNR, LPIPS, tOF등의 결과를 비교했다.