• Journal of the Korea Society of Computer and Information
• /
• 제29권1호
• /
• pp.31-40
• /
• 2024

In the realm of domestic online fashion platform industry the manual registration of product information by individual business owners leads to inconvenience and reliability issues, especially when dealing with simultaneous registrations of numerous product groups. Moreover, bias is significantly heightened due to the low quality of product images and an imbalance in data quantity. Therefore, this study proposes a ResNet50 model aimed at minimizing data bias through oversampling techniques and conducting multiple classifications for 13 fashion categories. Transfer learning is employed to optimize resource utilization and reduce prolonged learning times. The results indicate improved discrimination of up to 33.4% for data augmentation in classes with insufficient data compared to the basic convolution neural network (CNN) model. The reliability of all outcomes is underscored by precision and affirmed by the recall curve. This study is suggested to advance the development of the domestic online fashion platform industry to a higher echelon.

• Smart Media Journal
• /
• 제12권11호
• /
• pp.145-153
• /
• 2023

In a P2P-based distributed storage system where peers frequently join and leave, it is essential to guarantee not only data availability but also playback quality comparable to that provided by local storage devices when playing back video files with real-time constraints. In addition, cloud storage services based on distributed storage systems provide each user with the functionality to share their files with other users, so when multiple users request playback of the same video file at the same time, all playback should be supported seamlessly in real time. Therefore, in this paper, we propose a scheme that process multiple simultaneous playback requests for each video file in real time as well as data availability in a P2P-based distributed storage system that supports file sharing. This scheme can support real-time simultaneous playback and efficiently use storage space by adjusting the amount of redundant data encoded through erasure coding according to the number of concurrent playback requests for each video file.

• Journal of The Korean Institute of Defense Technology
• /
• 제5권2호
• /
• pp.17-22
• /
• 2023

In the midst of the development of science and technology based on the 4th industrial revolution, the ROK Army is moving forward with the ARMY TIGER 4.0 system, a ground combat system that combines future advanced science and technology. The system is developing around an AI-based hyper-connected ground combat system, and has mobility, intelligence, and networking as core concepts. Especially, the dronebot combat system is used as a compound word that refers to unmanned combat systems including drones and ground unmanned systems. In future battlefields, it is expected that the use of unmanned and artificial intelligence-based weapon systems will increase. During the transition to a complete unmanned system, it is a very important issue to ensure connectivity individual unmanned systems themselves or between manned and unmanned systems on the battlefield. This paper introduces the Multiplexer Allocation Problem (MAP) for effective command control and communication of UAV/UGV, and proposes a heuristic algorithm. In addition, the performance of the proposed algorithm is analyzed by comparing the solutions and computing time. Also, we discuss future research area for the MAP.

• Journal of the Korean Society of Food Science and Nutrition
• /
• 제42권1호
• /
• pp.102-113
• /
• 2013

The purpose of this study was to examine parental perceptions on the importance, performance level, and satisfaction with foodservice quality at daycare centers in the Compensation and Welfare Service institute. The questionnaire was developed to measure thirty-two attributes of foodservice operations are administered to 598 parents and 23 foodservice supervisors from June 22, 2009 to July 10, 2009. The parents placed a high importance on the need for foodservices, earning 4.70 points out of 5 points. Their perceptions of foodservice quality menu, foodservice ingredients and effects, facilities, sanitation, and service scored even higher than performance. The overall satisfaction level for foodservice compared to performance was 4.33 and 4.03 points out of 5 points, respectively. Multiple regression analysis indicated that 98.6% of the variance in parents' overall satisfaction scores was explained by six dimensions.

• KIPS Transactions on Computer and Communication Systems
• /
• 제4권6호
• /
• pp.185-196
• /
• 2015

Energy aware server clusters aim to reduce power consumption at maximum while keeping QoS(Quality of Service) compared to energy non-aware server clusters. They adjust the power mode of each server in a fixed or variable time interval to let only the minimum number of servers needed to handle current user requests ON. Previous studies on energy aware server cluster put efforts to reduce power consumption further or to keep QoS, but they do not consider energy efficiency well. In this paper, we propose an energy efficient cluster management based on autonomous learning for energy aware server clusters. Using parameters optimized through autonomous learning, our method adjusts server power mode to achieve maximum performance with respect to power consumption. Our method repeats the following procedure for adjusting the power modes of servers. Firstly, according to the current load and traffic pattern, it classifies current workload pattern type in a predetermined way. Secondly, it searches learning table to check whether learning has been performed for the classified workload pattern type in the past. If yes, it uses the already-stored parameters. Otherwise, it performs learning for the classified workload pattern type to find the best parameters in terms of energy efficiency and stores the optimized parameters. Thirdly, it adjusts server power mode with the parameters. We implemented the proposed method and performed experiments with a cluster of 16 servers using three different kinds of load patterns. Experimental results show that the proposed method is better than the existing methods in terms of energy efficiency: the numbers of good response per unit power consumed in the proposed method are 99.8%, 107.5% and 141.8% of those in the existing static method, 102.0%, 107.0% and 106.8% of those in the existing prediction method for banking load pattern, real load pattern, and virtual load pattern, respectively.

• Management & Information Systems Review
• /
• 제36권3호
• /
• pp.167-184
• /
• 2017

In this study, we investigated the effect of offline banking trust on smart banking trust. As influencing factors of smart banking trust, this study compared offline banking trust, smart banking's system quality, and information quality. For the empirical study, 186 questionnaire data were collected from smart banking users and the data were analyzed using Smart-PLS 2.0. As results, it was verified that there is trust transfer in FinTech service, by the significant effect of offline banking trust on smart banking trust. And it was proved that the effect of offline banking trust on smart banking trust is lower than that of smart banking itself. The contribution of this study can be seen in both academic and industrial aspects. First, it is the contribution of the academic aspect. Previous studies on banking were focused on either offline banking or smart banking. But this study, focus on the relationship between offline banking and online banking, proved that offline banking trust affects smart banking trust. Next, it is the industrial contribution. This study showed that offline banking characteristics of traditional commercial banks affect the trust of emerging smart banking service. This means that the emerging FinTech companies are not advantageous in the competition of trust building compared to traditional commercial banks. Unlike traditional commercial banks, the emerging FinTech is innovating the convenience of customers by arming them with new technologies such as mobile Internet, social network, cloud technology, and big data. However, these FinTech strengths alone can not guarantee sufficient trust needed for financial transactions, because banking customers do not change a habit or an inertia that they already have during using traditional banks. Therefore, emerging FinTech companies should strive to create destructive value that reflects the connection with various Internet services and the strength of online interaction such as social services, which have an advantage over customer contacts. And emerging FinTech companies should strive to build service trust, focused on young people with low resistance to new services.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• 제62권4호
• /
• pp.275-284
• /
• 2017

Rice quality should be considered as a primary consumer requirement. Regarding marketing, characteristics such as appearance, physicochemical properties, and palatability of brand rice are of high economic importance. Therefore, this study was conducted to select the optimal rice cultivars representing the commercial rice brands of Gyeongsangbuk-do province in Korea. Various rice grain quality components, grain appearance, several physicochemical properties of rice grain, and texture or palatability of cooked rice grains of ten cultivars (namely 'top quality rice') cultivated at three different locations, such as inland mountainous and southern plain areas of Gyeongsangbuk-do province in 2013~2014, were evaluated, and the obtained data was analyzed. 'Hiami' showed slightly higher protein contents and lower palatability of cooked rice than the other rice cultivars. Rice production and head rice yield produced at Gumi were the highest. The protein content of milled rice produced at Andong, an inland mountainous region, was approximately 0.3% point lower than that from other locations, whereas the amylose content of milled rice was approximately 1% point higher than those from the other plain regions, Daegu and Gumi. We evaluated the texture, Glossiness value determined using a Toyo teste meter and palatability of cooked rice of ten cultivars. The hardness of cooked rice produced in Andong was slightly lower than that produced in Daegu and Gumi, and additionally, the palatability of cooked rice produced in Andong was the best, followed by that producted in Gumi and Daegu. Considering rice yield and grain quality in the major rice cultivation areas of Gyeongsangbuk-do province, the rice cultivars that may be suitable for each region could be recommended mid-late maturation: 'Younghojinmi' and 'Mipum' in Daegu, 'Daebo', 'Samgwang', Chilbo' and 'Younghojinmi' in Gumi, 'Samgwang', 'Jinsumi' and 'Sukwang' in Andong. These results obtained in this study imply that the selected cultivars with high yield and quality could be recommended with high priority to rice farmers in the regions.

• Food Science and Preservation
• /
• 제25권1호
• /
• pp.44-51
• /
• 2018

The purpose of this study is to present the results as basic data for establishing proper storage conditions and distribution conditions of actual farms at point of increasing concern about hygiene and palatabiltiy of consumers to food. In this study, three farmhouses of dried persimmons prepared using different storage conditions were selected in Sangju (Korea). The dried persimmons were stored for 90 days. Changes in temperature and humidity were measured with a temperature and humidity recorder under each storage condition, and physicochemical analysis and sensory evaluation were performed. The average temperatures of farmhouse A, B and C were approximately $-22--23^{\circ}C$, $-19--18^{\circ}C$ and $-25^{\circ}C$ respectively. The humidities of A, B and C were 62-63%, 59-60%, and 66-67%, respectively, and the moisture contents of all farmhouses increased during the storage period, with farmhouse B showing the most rapid increase. Free sugars increased, except for those from farmhouse C. Persimmons from farmhouse B showed the greatest changes in chewiness and hardness. The values of $a^*$ and $b^*$ were significantly decreased in persimmons from farmhouse B, and the color difference value of farmhouse B was dramatically increased. Sensory evaluation showed that the color preference tended to decrease compared with the initial value. Only farmhouse B showed decreased overall acceptability. Moreover, farmhouse B had the highest storage temperature and lowest humidity. Therefore, our results showed that storage at a low temperature and high humidity was important for manufacturing high-quality dried persimmons.

• Korean journal of applied entomology
• /
• 제52권2호
• /
• pp.115-123
• /
• 2013

A microbial insecticide "Bt-Plus" has been developed to enhance an insecticidal efficacy of an entomopathogenic bacterium, Bacillus thuringiensis (Bt). However, its wettable powder formulation is not preferred by farmers and industry producers due to relatively high cost. This study aimed to develop a soluble concentrate formulation of Bt-Plus. To this end, an optimal mixture ratio of two bacterial culture broths was determined to be 5:4 (v/v) of Bt and Xenorhabdus nematophila (Xn) along with 10% ethanol preservative. In addition, Bt broth was concentrated by 10 times to apply the mixture at 1,000 times fold dilution. The resulting liquid formulation was sprayed on cabbage crop field infested by late instar larvae of the diamondback moth, Plutella xylostella. The field assay showed about 77% control efficacy at 7 days after treatment, which was comparable to those of current commercial biopesticides targeting P. xylostella. For storage test in both low and room temperatures, the liquid formation showed a relatively stable control efficacy at least for a month. To develop a quality control technique to exhibit a stable control efficacy of Bt-Plus, Bt spore density ($5{\times}10^{11}$ spores/mL) and eight active component concentrations of Xn bacterial metabolites in the formulation products have been proposed in this study.

• Journal of Intelligence and Information Systems
• /
• 제20권3호
• /
• pp.1-18
• /
• 2014

Over the past years RFID/SN has been an elementary technology in a diversity of applications for the ubiquitous environments, especially for Internet of Things. However, one of obstacles for widespread deployment of RFID technology is the inherent unreliability of the RFID data streams by tag readers. In particular, the problem of false readings such as lost readings and mistaken readings needs to be treated by RFID middleware systems because false readings ultimately degrade the quality of application services due to the dirty data delivered by middleware systems. As a result, for the higher quality of services, an RFID middleware system is responsible for intelligently dealing with false readings for the delivery of clean data to the applications in accordance with the tag reading environment. One of popular techniques used to compensate false readings is a sliding window filter. In a sliding window scheme, it is evident that determining optimal window size intelligently is a nontrivial important task in RFID middleware systems in order to reduce false readings, especially in mobile environments. In this paper, for the purpose of reducing false readings by intelligent window adaption, we propose a new adaptive RFID data cleaning scheme based on window sliding for a single tag. Unlike previous works based on a binomial sampling model, we introduce the weight averaging. Our insight starts from the need to differentiate the past readings and the current readings, since the more recent readings may indicate the more accurate tag transitions. Owing to weight averaging, our scheme is expected to dynamically adapt the window size in an efficient manner even for non-homogeneous reading patterns in mobile environments. In addition, we analyze reading patterns in the window and effects of decreased window so that a more accurate and efficient decision on window adaption can be made. With our scheme, we can expect to obtain the ultimate goal that RFID middleware systems can provide applications with more clean data so that they can ensure high quality of intended services.