• Journal of Biosystems Engineering
• /
• v.21 no.3
• /
• pp.325-335
• /
• 1996

Visual features are crucial for monitoring the growth state, indexing the drying performance, and grading the quality of oak mushrooms. A computer vision system with neural net information processing technique was utilized to quantize quality factors of a dried oak mushrooms distributed over the cap and gill sides. In this paper, visual feature extraction algorithm were integrated with the neural net processing to deal with various fuzzy patterns of mushroom shapes and to compensate the fault sensitiveness of the crisp criteria and heuristic rules derived from the image processing results. The proposed algorithm improved the segmentation of the skin features of each side, the identification of cap and gill surfaces, the identification of stipe states and removal of the stipe, etc. And the visual characteristics of dried oak mushrooms were analyzed and primary visual features essential to tile quality evaluation were extracted and quantized. In this study, black and white gray images were captured and used for the algorithm development.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.113-120
• /
• 2023

Smart farms are steadily increasing in research to minimize labor, energy, and quantity put into crops as IoT technology and artificial intelligence technology are combined. However, research on efficiently managing crop growth information in smart farms has been insufficient to date. In this paper, we propose a management technique that can efficiently monitor crop growth information by applying autonomous sensors to smart farms. The proposed technique focuses on collecting crop growth information through autonomous sensors and then recycling the growth information to crop cultivation. In particular, the proposed technique allocates crop growth information to one slot and then weights each crop to perform load balancing, minimizing interference between crop growth information. In addition, when processing crop growth information in four stages (sensing detection stage, sensing transmission stage, application processing stage, data management stage, etc.), the proposed technique computerizes important crop management points in real time, so an immediate warning system works outside of the management criteria. As a result of the performance evaluation, the accuracy of the autonomous sensor was improved by 22.9% on average compared to the existing technique, and the efficiency was improved by 16.4% on average compared to the existing technique.

• Journal of the Korea Institute of Building Construction
• /
• v.24 no.1
• /
• pp.35-42
• /
• 2024

This research explores the potential of methyl methacrylate(MMA) as a material for road repair applications. It specifically examines two MMA formulations, referred to as type A and type B, in relation to their performance on concrete substrates. The evaluation criteria included drying time, tensile bond strength, and resistance to alkali. The condition of the substrate surface was varied across three curing environments: constant temperature and humidity(R), immersion in water(W), and immersion in water with chloride ions(N). The findings indicate that type B MMA exhibits a quicker drying time and superior resistance to alkali compared to type A. While type A demonstrated greater tensile bond strength, it failed to maintain adhesion with the concrete base. Based on the parameters tested in this study, type B MMA emerges as the more favorable option for road repair contexts. Nonetheless, the study underscores the necessity for additional testing on asphalt substrates to fully assess the material's durability and applicability for long-term road maintenance.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.275-287
• /
• 2024

Research on the integration of Knowledge Graphs (KGs) and Language Models (LMs) has been consistently explored over the years. However, studies focusing on the automatic generation of text using the structured knowledge from KGs have not been as widely developed. In this study, we propose a methodology for automatically generating specific domain-related research items (Related Work) at a level comparable to existing papers. This methodology involves: 1) selecting optimal prompts, 2) extracting triples through a four-step refinement process, 3) constructing a knowledge graph, and 4) automatically generating related research. The proposed approach utilizes GPT-4, one of the large language models (LLMs), and is desigend to automatically generate related research by applying the four-step refinement process. The model demonstrated performance metrics of 17.3, 14.1, and 4.2 in Triple extraction across #Supp, #Cont, and Fluency, respectively. According to the GPT-4 automatic evaluation criteria, the model's performamce improved from 88.5 points vefore refinement to 96.5 points agter refinement out of 100, indicating a significant capability to automatically generate related research at a level similar to that of existing papers.

• Asian-Australasian Journal of Animal Sciences
• /
• v.24 no.11
• /
• pp.1483-1503
• /
• 2011

To advance the effectiveness of the current Hanwoo improvement system, we developed a general simulation that compared a series of breeding schemes under realistic user circumstances. We call this system the Integrated General Model (IGM) and it allows users to control the breeding schemes and selection methods by manipulating the input parameters. The Current Hanwoo Performance and Progeny Test (CHPPT) scheme was simulated with a Modified Hanwoo Performance and Progeny Test (MHPPT) scheme using a Hanwoo Breeding Farm cow population of the Livestock Improvement Main Center (LOMC) of the National Agricultural Cooperatives Federation (NACF). To compare the two schemes, a new method, the Simple Hanwoo Performance Test (SHPT), which uses ultrasound technology for measuring the carcass traits of live animals, was developed. These three models, including the CHPPT, incorporated three types of selection criteria: phenotype (PH), true breeding value (TBV), and estimated breeding value (EBV). The simulation was scheduled to mimic an actual Hanwoo breeding program; thus, the simulation was run to include the years 1983-2020 for each breeding method and was replicated 10 times. The parameters for simulation were derived from the literature. Approximately 642,000 animals were simulated per replication for the CHPPT scheme; 129,000 animals were simulated for the MHPPT scheme and 112,000 animals for the SHPT scheme. Throughout the 38-year simulation, all estimated parameters of each simulated population, regardless of population size, showed results similar to the input parameters. The deviations between input and output values for the parameters in the large populations were statistically acceptable. In this study, we integrated three simulated models, including the CHPPT, in an attempt to achieve the greatest genetic gains within major economic traits including body weight at 12 months of age (BW12), body weight at 24 months of age (BW24), average daily gain from 6 to 12 months (ADG), carcass weight (CWT), carcass longissimus muscle area (CLMA), carcass marbling score (CMS), ultrasound scanned longissimus muscle area (ULMA), and ultrasound scanned marbling score (UMS).

• Journal of Korean Society of Steel Construction
• /
• v.26 no.6
• /
• pp.511-522
• /
• 2014

In this study, an innovative steel stair system is presented which enables rapid erection and high quality control in both residential and office building construction. This system features two lightweight steel stringers of box shape, bolted connections easy to absorb construction tolerance, and stair steps movable transversely (or sliding steps) such that the work space needed for concrete stairway wall could be easily provided. In this type of stairway system, other than providing robust connecting details, ensuring vibration performance is especially important since this system may be vibration-sensitive due to lightweight nature and/or probable low damping. To tackle these issues, a series of full-scale mock-up tests were conducted by using box-shape stringer members with or without concrete-fill. The connection system was shown to be sufficiently stiff and strong, or it remained elastic even under the 160% of service load level. Among the seven stringer alternatives, five exhibited satisfactory vibration performance according to the related North American and European acceptance criteria.

• The Journal of Industrial Distribution & Business
• /
• v.11 no.7
• /
• pp.29-40
• /
• 2020

Purpose: In modern society, many urban problems are occurring, such as aging, hollowing out old city centers and polarization within cities. In this study, we intend to apply big data and machine learning methodologies to predict depression symptoms in the elderly population early on, thus contributing to solving the problem of elderly depression. Research design, data and methodology: Machine learning techniques used random forest and analyzed the correlation between CES-D10 and other variables, which are widely used worldwide, to estimate important variables. Dependent variables were set up as two variables that distinguish normal/depression from moderate/severe depression, and a total of 106 independent variables were included, including subjective health conditions, cognitive abilities, and daily life quality surveys, as well as the objective characteristics of the elderly as well as the subjective health, health, employment, household background, income, consumption, assets, subjective expectations, and quality of life surveys. Results: Studies have shown that satisfaction with residential areas and quality of life and cognitive ability scores have important effects in classifying elderly depression, satisfaction with living quality and economic conditions, and number of outpatient care in living areas and clinics have been important variables. In addition, the results of a random forest performance evaluation, the accuracy of classification model that classify whether elderly depression or not was 86.3%, the sensitivity 79.5%, and the specificity 93.3%. And the accuracy of classification model the degree of elderly depression was 86.1%, sensitivity 93.9% and specificity 74.7%. Conclusions: In this study, the important variables of the estimated predictive model were identified using the random forest technique and the study was conducted with a focus on the predictive performance itself. Although there are limitations in research, such as the lack of clear criteria for the classification of depression levels and the failure to reflect variables other than KLoSA data, it is expected that if additional variables are secured in the future and high-performance predictive models are estimated and utilized through various machine learning techniques, it will be able to consider ways to improve the quality of life of senior citizens through early detection of depression and thus help them make public policy decisions.

• Journal of Korean Society of Transportation
• /
• v.21 no.5
• /
• pp.31-40
• /
• 2003

Unsignalized intersections are classified into two-way-stop-controlled(TWSC) and all-way-stop-controlled(AWSC) intersections for the analysis of capacity and level of service. There is no AWSC intersection in Korea, but non-controlled intersections are common. Non-controlled intersections are operated only by the driver's decision without any control. However, the study for the analysis of capacity and level of service of the non-controlled intersection has been rare. As the first stage research, this study aims to determine the measure-of-effectiveness (MOE) for the performance evaluation of non-controlled intersections. The relationships between traffic volume and the intersection passing time (delay) and number of conflicts on each intersection are analyzed. It was found that the number of conflicts were more sensitive to the traffic volume compared with the delay. It means that number of conflicts can be the MOE for the performance of non-controlled intersection. The analysis of the number of conflicts and traffic volume showed a linear relationship, so that traffic volume can also be an MOE. The level of service of non-controlled intersection can be determined with either of the MOE's. Since the performance is also influenced by the ratio of traffic volumes of crossing streets, the traffic volume should be adjusted by the ratio. The capacity of non-controlled intersection was suggested to be 2,000veh/hr referring that of AWSC intersection in the USHCM. The criteria was suggested by evenly dividing the traffic volumes based on the capacity.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.14 no.3
• /
• pp.9-17
• /
• 2015

In this paper, there are several analysis on G-SEED, Building Energy Efficiency Rating System, Energy Performance Index, Energy Saving Plan about how they are applied by classification and planning standard. The analysis result found out that G-SEED has low select percentage by having difficulties to managing and additional cost when the each class is selected. And also, Building Energy Efficiency Rating System in school is planed in comparably simple design and similar size and also mostly uses high efficient machines, which was in high lever comparing to the system in facilities in other uses. In the case of EPI, there are differences on acquiring grades by each region. Especially, Gyung-gi region has a low grade on architecture part comparing to other parts, which seems to acquire more grades by strengthen insulation performance. By the result from the three standards, many facilities has only formal plan to pass the required standard without considering specialities of each buildings, which has a tendency to have a pattern to have a minimum criteria. However, School has a symbolic building which has a obligation to be the base of the aim for growing green energy buildings and green education for students. Therefore, planning with understanding of specialities of the facility, having various and rational evaluation standards from the planning of the building is necessary.

• Journal of the Korean earth science society
• /
• v.22 no.1
• /
• pp.65-74
• /
• 2001

To evaluate the influence of meteorological conditions on the performance of DOAS (Differential Optical Absorption Spectroscopy) system, we analyzed the concentrations of three criteria pollutants and relevant environmental parameters measured during 14 month periods between Jun. 1999 and Oct. 2000. According to our study, the performance of DOAS can be sensitively influenced via various manners (such as among different chemicals and/or between different time periods). It turns out that O$_3$ exhibits most frequently the weakest agreement between two systems. When comparison was made among different meteorological parameters, the strongest variability was seen from such ones as windspeed, wind direction, and irradiance. In addition, the absolute differences in measured concentrations between two systems were compared against various environmental parameters by means of linear regression analysis. Results of this analysis indicated that the differences between the two tend to decrease with the increase of such parameters as windspeed. It is thus concluded on the basis of our study that the simultaneous evaluation of meteorological data should be an essential step toward the accurate assessment of pollutant concentration data obtained by DOAS measurement system.