• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.49-54
• /
• 2022

With the recent widespread adoption of general-purpose GPUs (GPGPUs) in cloud systems, maximizing the resource utilization through multitasking in GPGPU has become an important issue. In this article, we show that resource allocation based on the workload classification of computing-bound and memory-bound is not sufficient with respect to resource utilization, and present a new thread block scheduling policy for GPGPU that makes use of fine-grained resource utilizations of each workload. Unlike previous approaches, the proposed policy reduces scheduling overhead by separating profiling and scheduling, and maximizes resource utilizations by co-locating workloads with different bottleneck resources. Through simulations under various virtual machine scenarios, we show that the proposed policy improves the GPGPU throughput by 130.6% on average and up to 161.4%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1247-1260
• /
• 2021

For more efficient energy management of nodes in wireless sensor networks, research has been conducted on mobile sink nodes that deliver data from sensor nodes to server recently. UAV (Unmanned Aerial vehicle) is used as a representative mobile sink node. Also, most studies on UAV propose algorithms for calculating optimal paths and have produced rapid advances in the IoD (Internet of Drones) environment. At the same time, some papers proposed mutual authentication and secure key exchange considering nature of the IoD, which requires efficient creation of multiple nodes and session keys in security perspective. However, most papers that proposed secure communication in mobile sink nodes did not protect end-to-end data privacy. Therefore, in this paper, we propose integrated security model that authentication between mobile sink nodes and sensor nodes to securely relay sensor data to base stations. Also, we show informal security analysis that our scheme is secure from various known attacks. Finally, we compare communication overhead with other key exchange schemes previously proposed.

• Korean Journal of Applied Biomechanics
• /
• v.32 no.4
• /
• pp.128-133
• /
• 2022

Objective: This study was executed to compare and analyze shoulder muscle activation while using an inelastic bar and elastic bar during overhead press exercise. The stability and coordination of shoulder joints will be investigated by measuring and analyzing the EMG of the upper and lower arm muscles. Method: A total of 20 university male students were recruited by dividing into 2 groups; 10 elastic bar participants (age: 20.17 ± 0.41 yrs, height: 174.31 ± 3.34 cm, weight: 74.68 ± 5.65 kg) and 10 inelastic bar participants (age: 20.09 ± 0.23 yrs, height: 173.53 ± 4.11 cm, weight: 75.32 ± 3.31 kg) participated in this study. Results: The EMG analysis results of the four muscles measured in this study showed that there was no difference between the left and right muscles between the groups in Upper Trapezius muscle. In Deltoid, Infraspinatus, and Rectus Abdominis muscles, the elastic bar group was significantly higher than the inelastic bar group between groups, and there was no difference between left and right. Conclusion: Among the four muscles measured in this study, there was no difference between left and right in Deltoid, Infraspinatus, and Rectus Abdominis, but the elastic bar showed significantly higher muscle activity than the inelastic bar. Therefore, it was found that the elastic bar increases muscle activation during exercise than the inelastic bar, and in particular, it further increases muscle activation of the arms and torso, and exercise using the elastic bar can increase neuromuscular stabilization.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.12
• /
• pp.419-428
• /
• 2022

Since in-place updates for pages are not allowed in flash memory, all new page writes should be written in an out-of-place manner. The old overwritten pages are invalidated. Such invalidated pages eventually trigger the costly garbage collection process. Since the garbage collection causes numerous read and write operations, it is one of the flash memory's major performance issues. In 2R, it modified the garbage collection algorithm, which applies the I/O characteristics of the On-Line Transaction Process workload to improve the Write Amplification Factor. However, this algorithm has a region pollution problem. Therefore, in this paper, we developed 2R++ that additionally separates pages with long access intervals to solve the region pollution problem. 2R++ introduces an extra bit per block to separate warm pages based on a second chance mechanism. Prevents warm pages from being misidentified as cold pages to solve region pollution problem. We conducted the experiments on TPC-C and Linkbench to make the performance comparison. The experiment showed that 2R++ achieved a Write Amplification Factor improvement of 57.8% and 13.8% compared to 2R, respectively.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.12
• /
• pp.437-444
• /
• 2022

Recently, research on mobile edge services has been conducted to handle computationally intensive and latency-sensitive tasks occurring in wireless networks. However, MEC, which is fixed on the ground, cannot flexibly cope with situations where task processing requests increase sharply, such as commuting time. To solve this problem, a technology that provides edge services using UAVs (Unmanned Aerial Vehicles) has emerged. Unlike ground MEC servers, UAVs have limited battery capacity, so it is necessary to optimize energy efficiency through load balancing between UAV MEC servers. Therefore, in this paper, we propose a load balancing technique with consideration of the energy state of UAVs and the mobility of vehicles. The proposed technique is composed of task offloading scheme using genetic algorithm and task migration scheme using Q-learning. To evaluate the performance of the proposed technique, experiments were conducted with varying mobility speed and number of vehicles, and performance was analyzed in terms of load variance, energy consumption, communication overhead, and delay constraint satisfaction rate.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.12
• /
• pp.429-436
• /
• 2022

Temporary files are generated when the Hash Join is performed on tables larger than the memory. During the join process, each temporary file is deleted sequentially after it completes the I/O operations. This paper reveals for that the fallocate system call and file deletion-related trim options significantly impact the hash join performance when temporary files are managed on SSDs rather than hard disks. The experiment was conducted on various commercial and research SSDs using PostgreSQL, a representative open-source database. We find that it is possible to improve the join performance up to 3 to 5 times compared to the default combination depending on whether fallocate and trim options are used for temporary files. In addition, we investigate the write amplification and trim command overhead in the SSD according to the combination of the two options for temporary files.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.71-76
• /
• 2022

Buffer cache bridges the performance gap between memory and storage, but its effectiveness is limited due to periodic flush, performed to prevent data loss in smartphones. This paper shows that selective flushing technique with small persistent memory can reduce the flushing overhead of smartphone buffer cache significantly. This is due to our I/O analysis of smartphone applications in that a certain hot data account for most of file writes, while a large proportion of file data incurs single-writes. The proposed selective flushing policy performs flushing to persistent memory for frequently updated data, and storage flushing is performed only for single-write data. This eliminates storage write traffic and also improves the space efficiency of persistent memory. Simulations with popular smartphone application I/O traces show that the proposed policy reduces write traffic to storage by 24.8% on average and up to 37.8%.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.115-121
• /
• 2022

In surface mount technology (SMT), the screen printer, which is an equipment for applying solder cream, has a lot of poor coating as the pad becomes smaller. To solve this problem, a jet printer is being used recently. However, if the nozzle at the end of the valve applied to the jet printer head is not cleaned, solder cream remains or an error occurs. To prevent this, the nozzles should be cleaned periodically. In this paper, a more stable cleaning method than the existing technology is presented for the stable application of solder cream on a jet printer. In this method, cut a 35mm wide mujin cloth, wrap it in a roll, and rotate it with a DC geared motor on the other side to clean it. As a result, it was confirmed that the solder paste was not left on the nozzle surface and was well wiped when cleaning with about 2,000 dotting cycles.

• Journal of Aerospace System Engineering
• /
• v.17 no.1
• /
• pp.59-67
• /
• 2023

Recently, interest in flight simulators based on HMD and mixed reality is increasing. However, they have limitations in providing various interactions and a sense of presence to pilot wearing HMD. To overcome these limitations, a mixed reality image corresponding to the interaction under the actual cockpit environment must be generated in real time and provided to the pilot. For this purpose, we proposed a mixed reality image generation method, in which the cockpit area including the pilot's body could be extracted from real image obtained from the camera attached to the HMD and then composed with virtual image to generate a high-resolution mixed reality image. Simulation results showed that the proposed method could provide mixed reality images to HMD at 30 Hz frame rate with 99% image composition accuracy.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.2
• /
• pp.67-71
• /
• 2023

Recently, there are increasing cases of managing software labs by assigning virtual PCs in the cloud instead of physical PCs to each student. In this paper, we design and implement a Linux-based software practice platform that allows students to efficiently build their environments in the cloud. In our platform, instructors can create and control virtual machine templates for all students at once, and students practice on their own machines as administrators. Instructors can also troubleshoot each machine and restore its state. Meanwhile, the biggest obstacle to implementing this approach is the difficulty of predicting the costs of cloud services instantly. To cope with this situation, we propose a model that can estimate the cost of cloud resources used. By using daemons in each user's virtual machine, we instantly estimate resource usage and costs. Although our model has very low overhead, the predicted results are very close to the actual resource usage measured by cloud service providers. To further validate our model, we used the proposed platform in a Linux practice lecture for a semester and confirmed that the proposed model is very accurate.