• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.1-9
• /
• 2021

Deep learning in computer vision has made accelerated improvement over a short period but large-scale learning data and computing power are still essential that required time-consuming trial and error tasks are involved to derive an optimal network model. In this study, we propose a similar image classification performance improvement method based on CR (Confusion Rate) that considers only the characteristics of the data itself regardless of network optimization or data reinforcement. The proposed method is a technique that improves the performance of the deep learning model by calculating the CRs for images in a dataset with similar characteristics and reflecting it in the weight of the Loss Function. Also, the CR-based recognition method is advantageous for image identification with high similarity because it enables image recognition in consideration of similarity between classes. As a result of applying the proposed method to the Resnet18 model, it showed a performance improvement of 0.22% in HanDB and 3.38% in Animal-10N. The proposed method is expected to be the basis for artificial intelligence research using noisy labeled data accompanying large-scale learning data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1195-1204
• /
• 2021

In this paper, we present an optimal design method for wave power generators using the response surface analysis. Especially, in our method, we reduce the mechanical loss by selecting the linear generator whose linear movement can be converted to the electrical energy directly with the vertical movement of waves. Therefore, we calculate the exciting force acting on the drive device in a slow-wave condition and determine the winding process with a ratio of the slots and poles for the improvement of energy conversion efficiency. In addition, we employ the regression analysis for deriving the shape factors of the stator and the translator, which have a significant effect on the performance of a generator. We choose the best design variables through the response surface analysis, and then we study the optimization method for designing the efficient experiment using the analysis results. Finally, we show the validity of the proposed method through the simulation results.

• Journal of the Microelectronics and Packaging Society
• /
• v.28 no.4
• /
• pp.63-67
• /
• 2021

In order to detect fires that may not be visible to the naked eye, an IoT module that uses changes in Carbon dioxide (CO₂) levels and temperature to effectively identify ambers (dying flames) was developed. Finite element analysis was then used to optimize the packaging for this module. Given the nature of ambers, the low power long range LoRa (Long Range) technology was used in the development of this module. To protect the module, a number of packages were designed, and comparative analysis performed on the stress generated when they fall. The results of which show that Model C showed the lowest stress. In addition, unlike other models in which stress concentration was predicted in the module mounting part of the package, in this model the stress concentration phenomenon was predicted in the wing part. It was therefore determined that this approach is ideal for protecting the internal module, and a package to which this was applied was manufactured.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.9
• /
• pp.78-84
• /
• 2022

An air circuit breaker (ACB) is an electrical protection device that interrupts abnormal fault currents that result from overloads or short circuits in a low-voltage power distribution line. The ACB consists of a main circuit part for current flow, mechanism part for the opening and closing operation of movable conductors, and arc-extinguishing part for arc extinction during the breaking operation. The driving mechanism of the ACB is a spring energy charging type. The faster the contact opening speed of the movable conductors during the opening process, the better the breaking performance. However, there is a disadvantage that the durability of mechanism decreases in inverse proportion to the use of a spring capable of accumulating high energy to configure the breaking speed faster. Therefore, to simultaneously satisfy the breaking performance and mechanical endurance of the ACB, its driving mechanism must be optimized. In this study, a dynamic model of the ACB was developed using the MDO(Mechanism Dynamics Option) module of CREO, which is widely used in multibody dynamics analysis. To improve the opening velocity, the Taguchi design method was applied to optimize the design parameters of an ACB with many linkages. In addition, to evaluate the improvement in the operating characteristics, the simulation and experimental results were compared with the MDO model and improved prototype sample, respectively.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.211-220
• /
• 2021

The aim of the study is to implement a factor analysis of the determinants of pricing in a state-regulated competitive market using economic and mathematical modelling methods and to develop ways to improve the pricing environment of the market under study. The purpose of the work defines the main objectives: (i) to investigate the features of the competitive model of the Ukrainian flour market; (ii) to analyse the current price conjuncture of the flour market and the dynamics of the main determinants of pricing; (iii)to develop ways of improving the price situation on the flour market on the basis of the factor analysis on the results of economic and mathematical modelling. In order to ensure the reliability and validity of the research results, the following methods were applied: the logical-dialectical method of scientific knowledge in the study of the main theoretical aspects of flour market functioning, the method of logical generalisation and synthesis, comparison, factor analysis, correlation and regression analysis, the graphical method, etc. It has been shown that pricing in a state-regulated competitive market has its own characteristics. For example, in the flour market the price of goods cannot be influenced by producers (sellers) by any methods, therefore determinants of pricing by indirect influence have been taken into account. The five-factor power model of wheat flour price has been constructed. It was substantiated that the price of wheat flour in Ukraine is mostly influenced by consumer price index (0.92 %). The received complex model of wheat flour price may be used also for medium-term forecasting and working out the ways of price formation optimization in the flour market.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.728-735
• /
• 2022

In this work, we investigated a high-voltage (~4.5 kV) 4H-SiC power DMOSFET with modifications of current spreading layer (CSL), which was introduced below the p-well region for low on-resistance. These include the following: 1) a thickness of CSL (T_CSL) from 0 um to 0.9 um; 2) a doping concentration of CSL (N_CSL) from 1×10¹⁶ cm^-3 to 5×10¹⁶ cm^-3. The design is optimized using TCAD 2D-simulation, and we found that CSL helps to reduce specific on-resistance but also breakdown voltage. The resulting structures exhibit a specific on-resistance (R_on,sp) of 59.61 mΩ·cm², a breakdown voltage (V_B) of 5 kV, and a Baliga's Figure of Merit (BFOM) of 0.43 GW/cm².

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.1070-1077
• /
• 2022

The International Maritime Organization has recently strengthened its marine environment regulations. The energy efficiency index has long been an important indicator of ship design, and now, energy efficiency is being enforced for existing ships as well as new ships. To increase the energy efficiency of existing ships, methods such as retrofitting the bow bulb, selecting an optimized trim during ship operation, and installing an energy saving device have been applied. In this study, the ship resistance was numerically simulated using computational fluid dynamics (CFD) under various bow and stern trim conditions. In addition, the bulb was redesigned to further improve the resistance performance under the selected trim conditions. When the improved bulb was applied, the effective horse power increased by approximately 5%. It is, however, necessary to verify whether the redesigned bulb can reduce ship resistance in waves.

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.37-50
• /
• 2022

Modern supply chains include multiple activities from collecting raw materials to transferring final products. These activities involve many parties who share a huge amount of valuable data, which makes managing supply chain systems a challenging task. Current supply chain management (SCM) systems adopt digital technologies such as the Internet of Things (IoT) and blockchain for optimization purposes. Although these technologies can significantly enhance SCM systems, they have their own limitations that directly affect SCM systems. Security, performance, and scalability are essential components of SCM systems. Yet, confidentiality and scalability are one of blockchain's main limitations. Moreover, IoT devices are lightweight and have limited power and storage. These limitations should be considered when developing blockchain-based IoT-SCM systems. In this paper, the requirements of efficient supply chain systems are analyzed and the role of both IoT and blockchain technologies in providing each requirement are discussed. The limitations of blockchain and the challenges of IoT integration are investigated. The limitations of current literature in the same field are identified, and a secure and scalable blockchain-based IoT-SCM system is proposed. The proposed solution employs a Hyperledger fabric blockchain platform and tackles confidentiality by implementing private data collection to achieve confidentiality without decreasing performance. Moreover, the proposed framework integrates IoT data to stream live data without consuming its limited resources and implements a dualstorge model to support supply chain scalability. The proposed framework is evaluated in terms of security, throughput, and latency. The results demonstrate that the proposed framework maintains confidentiality, integrity, and availability of on-chain and off-chain supply chain data. It achieved better performance through 31.2% and 18% increases in read operation throughput and write operation throughput, respectively. Furthermore, it decreased the write operation latency by 83.3%.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.3080-3087
• /
• 2023

Thermoelectric (TE) materials working in radioisotope thermoelectric generators are irradiated by neutrons throughout its service; thus, investigating the neutron irradiation stability of TE devices is necessary. Herein, the influence of neutron irradiation with fluences of 4.56 × 10¹⁰ and 1 × 10¹³ n/cm² by pulsed neutron reactor on the electrical and thermal transport properties of n-type Bi₂Te_2.7Se_0.3 and p-type Bi_0.5Sb_1.5Te₃ thermoelectric alloys prepared by cold-pressing and molding is investigated. After neutron irradiation, the properties of thermoelectric materials fluctuate, which is related to the material type and irradiation fluence. Different from p-type thermoelectric materials, neutron irradiation has a positive effect on n-type Bi₂Te_2.7Se_0.3 materials. This result might be due to the increase of carrier mobility and the optimization of electrical conductivity. Afterward, the effects of p-type and n-type TE devices with different treatments on the output performance of TE devices are further discussed. The positive and negative effects caused by irradiation can cancel each other to a certain extent. For TE devices paired with p-type Bi_0.5Sb_1.5Te₃ and n-type Bi₂Te_2.7Se_0.3 thermoelectric legs, the generated power and conversion efficiency are stable after neutron irradiation.