• 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 IKEEE
• /
• v.28 no.3
• /
• pp.412-418
• /
• 2024

This paper proposes an effective method for detecting hacking attacks in automotive CAN bus using the RANSAC (Random Sample Consensus) algorithm. Conventional deep learning-based detection techniques are difficult to be applied to resource-constrained environments such as vehicles. In this paper, the attack detection performance in vehicular CAN communication has been improved by utilizing the lightweight nature and efficiency of the RANSAC algorithm. The RANSAC algorithm can perform effective detection with minimal computational resources, providing a practical hacking detection solution for vehicles.

• 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.

• Journal of KIISE:Software and Applications
• /
• v.37 no.10
• /
• pp.736-744
• /
• 2010

Log data collected from mobile devices contain diverse and meaningful personal information. However, it is not easy to implement a context-aware mobile agent using this personal information due to the inherent limitation in mobile platform such as memory capacity, computation power and its difficulty of analysis of the data. We propose a method of selective inference for modular Bayesian Network for context-aware mobile agent with effectiveness and reliability. Each BN module performs inference only when it can change the result by comparing to the history module which contains evidences and posterior probability, and gets results effectively using a method of influence score of the modules. We adopt memory decay theory and virtual linking method for the evaluation of the reliability and conservation of casual relationship between BN modules, respectively. Finally, we confirm the usefulness of the proposed method by several experiments on mobile phones.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.16 no.2
• /
• pp.97-104
• /
• 2011

This paper deals with the quick and precise disaster prevention automation system (DPAS) based on information communication technology (IT) that detects fire and disasters in the building automatically and quickly and then activates the facilities to extinguish fire and disasters, monitoring such situation in a real time through wire-wireless communication network. The proposed DPAS is applied a programmable logic controller (PLC) of one-chip type which is smallsize and lightweight and also has highly sensitive-precise reliabilities. The one-chip type PLC analyzes detected signals from sensors in a case of fire and disasters, then activates fire extinguishing facilities for rapid suppression. The detected data is also transferred to a remote situation room through wire-wireless network of RS232c and bluetooth communication. The transferred data sounds an emergency alarm signal, and operates a monitoring program. The proposed DPAS based on IT will minimize the life and wealth loss from rapid measures while prevents fire and disasters.

• The KIPS Transactions:PartC
• /
• v.18C no.1
• /
• pp.15-22
• /
• 2011

Usually time synchronization is performed after routing tree is constructed. This thesis proposes a time synchronization algorithm combined with single-flooding routing tree construction algorithm in a single path. TSRA (Time Synchronization Routing Algorithm) uses routing packets to construct a routing tree. Two types of time information are added to the routing packet: one is the packet receiving time, and the other is the packet sending time. Time offset and transmission time-delay between parent node and child node could be retrieved from the added time information using LTS (Lightweight Time Synchronization) algorithm. Then parent node sends the time offset and transmission time to children nodes and children nodes can synchronize their time to the parent node time along the routing tree. The performance of proposed algorithm is compared to the TPSN (Timing-sync Protocol for Sensor Networks) which is known to have high accuracy using NS2 simulation tool. The simulation result shows that the accuracy of time synchronization is comparable to TPSN, the synchronization time of all sensor nodes is faster than TPSN, and the energy consumption is less than TPSN.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.327-330
• /
• 2017

In recent years, Drone(lightweight unmanned aerial vehicle) is used for broadcast shooting, disaster scene, leisure, observation and military purposes. However, as the use of drones increases the threat of hacking is also rising. Especially when a flying drone is seized, a dangerous situation can occur which is abused regardless of the driver's intention. Already in Iran and China, there is a case of hacking and stealing the drones of other countries under reconnaissance. In this paper, we analyze the security vulnerabilities of Wi-Fi and Bluetooth communication in wireless network which are used in drones for stealing the commercial drones. The results provide a countermeasure to safeguard the drones against attempts by the unauthorized attacker to take out the drones.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.535-544
• /
• 2017

In this paper, to overcome the limitation of information transmission and reception according to the RF system of UAV, it is necessary to check the position of many UAVs in flight on the basis of mobile communication and to make the LTE modem lightweight and low power And UAVs that are in operation are received and controlled. Through this study, we proposed a method to control real-time location tracking by connecting high-resolution images to the network anytime and anywhere. For this purpose, we propose the requirements and requirements of LTE modem using real-time high-speed data communication technology (3G, 4G LTE, Bluetooth) by presenting the communication module system of LTE-based UAV. N:N control system concept and implementation technology(Control system structure, control data flow chart, flight planning and transmission, real-time location tracking).