• The Journal of Korea Robotics Society
• /
• v.12 no.4
• /
• pp.395-401
• /
• 2017

In this paper, we introduce a robot-assisted medical diagnostic system that enables remote ultrasound (US) imaging to be applied to the conventional telemedicine, which has been possible only with interviewing or a visual exam. In particular, a master-slave robot system is developed that ultrasonic diagnosis specialist can control the position and orientation of US probe in the remote place. The slave robot is designed to be compact, lightweight, and hand-held so that it can easily transfer to the remote healthcare center. Moreover, 6-degree-of-freedom (DOF) probe motion is possible by the robot design based on Stewart platform. The master device is also based on a similar structure of the slave robot. To connect master and slave system in the wide area network (WAN) environment, a hardware CODEC was developed. In this paper, we introduce the detail of each component and the results of the recent experiments conducted in the remote sites by the developed robotic ultrasound imaging system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6121-6144
• /
• 2019

Numerous privacy-preserving authentication schemes have been proposed but vehicular ad hoc networks (VANETs) still suffer from security and privacy issues as well as computation and communication overheads. In this paper, we proposed a robust conditional privacy-preserving authentication scheme based on pseudonym root with cuckoo filter to meet security and privacy requirements and reduce computation and communication overheads. In our proposed scheme, we used a new idea to generate pseudonyms for vehicles where each on-board unit (OBU) saves one pseudonym, named as "pseudonym root," and generates all pseudonyms from the same pseudonym. Therefore, OBU does not need to enlarge its storage. In addition, the scheme does not use bilinear pairing operation that causes computation overhead and has no certification revocation list that leads to computation and communication overheads. The proposed scheme has lightweight mutual authentication among all parties and just for once. Moreover, it provides strong anonymity to preserve privacy and resists ordinary attacks. We analyzed our proposed scheme and showed that it meets security and privacy requirements of VANETs and is more efficient than traditional schemes. The communication and computation overheads were also discussed to show the cost-effectiveness of the proposed scheme.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2660-2679
• /
• 2017

Crypton is a SP-network block cipher that attracts much attention because of its excellent performance on hardware. Based on Crypton, mCrypton is designed as a lightweight block cipher suitable for Internet of Things (IoT) and Radio Frequency Identification (RFID). The security of Crypton and mCrypton under meet-in-the-middle attack is analyzed in this paper. By analyzing the differential properties of cell permutation, several differential characteristics are introduced to construct generalized ${\delta}-sets$. With the usage of a generalized ${\delta}-set$ and differential enumeration technique, a 6-round meet-in-the-middle distinguisher is proposed to give the first meet-in-the-middle attack on 9-round Crypton-192 and some improvements on the cryptanalysis of 10-round Crypton-256 are given. Combined with the properties of nibble permutation and substitution, an improved meet-in-the-middle attack on 8-round mCrypton is proposed and the first complete attack on 9-round mCrypton-96 is proposed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.3
• /
• pp.43-52
• /
• 2005

MIPv4 supports node mobility, manages MN's binding list and provides seamless communication through registration protocol. Since the registration protocol usually operating in the wireless environment involves authenticating MNs, it is a general approach to introduce the AAA infrastructure as key distribution center for the purpose of authentication. In this paper, we propose an efficient registration protocol with lightweight AAA based on domain key. Proposed protocol also withstands various replay attacks, and provides non-repudiation service for the accounts of the usage of the network service.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.1
• /
• pp.20-34
• /
• 2021

Today, IoT devices are flooding, and traffic is increasing rapidly. The Internet of Things creates a variety of added value through connections between devices, while many devices are easily targeted by attackers due to security vulnerabilities. In the IoT environment, security diagnosis has problems such as having to provide different solutions for different types of devices in network situations where various types of devices are interlocked, personal leakage of security solutions themselves, and high cost, etc. To avoid such problems, a TCP-based active scan was presented. However, the TCP-based active scan has limitations that it is difficult to be applied to real-time systems due to long detection times. To complement this, this study uses UDP-based approaches. Specifically, a lightweight active scan algorithm that effectively identifies devices using UPnP protocols (SSDP, MDNS, and MBNS) that are most commonly used by manufacturers is proposed. The experimental results of this study have shown that devices can be distinguished by more than twice the true positive and recall at an average time of 1524 times faster than Nmap, which has a firm position in the field.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.367-374
• /
• 2022

The acceleration of neural networks has become an important topic in the field of computer vision. An accelerator is absolutely necessary for accelerating the lightweight model. Most accelerator-supported operators focused on direct convolution operations. If the accelerator does not provide GEMM operation, it is mostly replaced by CPU operation. In this paper, we proposed an optimization technique for 2-stage tiling-based GEMM routines on VTA. We improved performance of the matrix multiplication routine by maximizing the reusability of the input matrix and optimizing the operation pipelining. In addition, we applied the proposed technique to the DarkNet framework to check the performance improvement of the matrix multiplication routine. The proposed GEMM method showed a performance improvement of more than 2.4 times compared to the non-optimized GEMM method. The inference performance of our DarkNet framework has also improved by at least 2.3 times.

• The Journal of Korea Robotics Society
• /
• v.16 no.4
• /
• pp.327-335
• /
• 2021

In this paper, we propose an embedded robot system based on "ROS2 on Yocto" that can support various robots. We developed a lightweight OS based on the Yocto Project as a next-generation robot platform targeting cloud robotics. Yocto Project was adopted for portability and scalability in both software and hardware, and ROS2 was adopted and optimized considering a low specification embedded hardware system. We developed SLAM, navigation, path planning, and motion for the proposed robot system validation. For verification of software packages, we applied it to home cleaning robot and indoor delivery robot that were already commercialized by LG Electronics and verified they can do autonomous driving, obstacle recognition, and avoidance driving. Memory usage and network I/O have been improved by applying the binary launch method based on shell and mmap application as opposed to the conventional Python method. Finally, we verified the possibility of mass production and commercialization of the proposed system through performance evaluation from CPU and memory perspective.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.313-315
• /
• 2021

Timely and accurate diagnosis of lung diseases using Chest X-ray images has been gained much attention from the computer vision and medical imaging communities. Although previous studies have presented the capability of deep convolutional neural networks by achieving competitive binary classification results, their models were seemingly unreliable to effectively distinguish multiple disease groups using a large number of x-ray images. In this paper, we aim to build an advanced approach, so-called Ensemble Knowledge Distillation (EKD), to significantly boost the classification accuracies, compared to traditional KD methods by distilling knowledge from a cumbersome teacher model into an ensemble of lightweight student models with parallel branches trained with ground truth labels. Therefore, learning features at different branches of the student models could enable the network to learn diverse patterns and improve the qualify of final predictions through an ensemble learning solution. Although we observed that experiments on the well-established ChestX-ray14 dataset showed the classification improvements of traditional KD compared to the base transfer learning approach, the EKD performance would be expected to potentially enhance classification accuracy and model generalization, especially in situations of the imbalanced dataset and the interdependency of 14 weakly annotated thorax diseases.

• Steel and Composite Structures
• /
• v.49 no.6
• /
• pp.645-666
• /
• 2023

Due to the steadily declining supply of natural coarse aggregates, the concrete industry has shifted to substituting coarse aggregates generated from byproducts and industrial waste. Oil palm shell is a substantial waste product created during the production of palm oil (OPS). When considering the usage of OPSC, building engineers must consider its uniaxial compressive strength (UCS). Obtaining UCS is expensive and time-consuming, machine learning may help. This research established five innovative hybrid AI algorithms to predict UCS. Aquila optimizer (AO) is used with methods to discover optimum model parameters. Considered models are artificial neural network (AO - ANN), adaptive neuro-fuzzy inference system (AO - ANFIS), support vector regression (AO - SVR), random forest (AO - RF), and extreme gradient boosting (AO - XGB). To achieve this goal, a dataset of OPS-produced concrete specimens was compiled. The outputs depict that all five developed models have justifiable accuracy in UCS estimation process, showing the remarkable correlation between measured and estimated UCS and models' usefulness. All in all, findings depict that the proposed AO - XGB model performed more suitable than others in predicting UCS of OPSC (with R², RMSE, MAE, VAF and A_15-index at 0.9678, 1.4595, 1.1527, 97.6469, and 0.9077). The proposed model could be utilized in construction engineering to ensure enough mechanical workability of lightweight concrete and permit its safe usage for construction aims.

• Journal of Korea Multimedia Society
• /
• v.12 no.4
• /
• pp.550-558
• /
• 2009

In ubiquitous environment, more small, lightweight, cheap and movable device is used than one device used in wired network environment. Multimedia service which is anytime, anywhere, is provided by device. However, it does not ensure the fair use of multimedia contents and causes damage to the contents providers because of illegal copy and distribution and indiscriminate use of digital contents. For solving this problems, DRM is applied to wired network but it has the problems does not protect stored license and manage license completely because of depending on simple protection such as device authentication and cryptographic algorithm. This paper proposes the license management model using digital forensic and DRM that prevents contents and licenses from distributing illegally and also enables the creation of evidence for legal countermeasure and the protection of license in whole life cycle.