• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.281-298
• /
• 2023

Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.

• Journal of Bio-Environment Control
• /
• v.32 no.2
• /
• pp.97-105
• /
• 2023

Concentration of nitrogen, one of the major elements, and ratio of two nitrogen forms (NH₄⁺ and NO₃^-) in the nutrient solution affect the quality and food safety of fresh vegetable produce. This study was conducted to find an appropriate strength and NH₄⁺:NO₃^- ratio of a nutrient solution for growth and development of a Romaine lettuce (Lactuca sativa L. var. longiflora) 'Caesar Green', a representative leafy vegetable, grown in a home hydroponic system. In the first experiment, plants were grown using three types of nutrient solution: A commercial nutrient solution (Peters) and two strengths (GNU1 and GNU2) of a multipurpose nutrient solution (GNU solution) developed in a Gyeongsang National University lab. Plants grown with the GNU1 and GNU2 had greater shoot length, leaf length and width, and biomass yield than Peters. On the other hand, the root hairs of plants grown with Peters were short and dark in color. Tissue NH₄⁺ content in the Peters was higher than that of the GNU1 and GNU2. The higher contents of NH₄⁺ in this solution may have caused ammonium toxicity. In the second experiment, eight treatment solutions, combining GNU1 and GNU2 solutions with four ratios of NO₃^- :NH₄⁺ named as 1, 2, 3 and 4 were used. Both experiments showed more growth in the GNU2 group, which had a relatively low ionic strength of the nutrient solution. The growth of Romaine lettuce showed the greatest fresh weight along with low tissue NO₃^- content in the GNU2-2. This was more advantageous in terms of food safety in that it suppressed the accumulation of surplus NO₃^- in tissues due to the low ionic trength of the GNU2 subgroup. In addition, this is preferable in that it can reduce the absolute amount of the input of inorganic nutrients to the nutrient solution.

• Journal of agriculture & life science
• /
• v.50 no.2
• /
• pp.33-43
• /
• 2016

Pinellia tripartita(Blume) Schott is a herbaceous perennial plant belonging to the Araceae and distributed on Asia including of Korea, Japan, and China. P. tripartita is often used for gardening but has not been developed mass-breeding methods. In this study, we compared the tuber growth in different combinations of mixed soils used six compositions. Tubers used to study was cultured in vitro and divided into two groups. Type I was diameter more than 1cm and the group of Type II was diameter below than 1cm. Enlargement of tubers and growth of aerial parts were measuring the plant height, number of fresh leaves and dead leaves, number of bullets, tuber size, and fresh / dry weight. The size/weight and numbers of tubers from the mixed soil B (coir 68.0%, peat moss 14.7%, perlite 3.0%, vermiculite 7.0% and zeolite 7.0%) were the best grown up for eight weeks. In case of Type I, GI (Growth index) of tuber size and weight were 45% and 101%, respectively. The difference of growth was doubled compared to the bad growth treatment as the mixed soil E(Coir 14.3%, peat moss 14.3%, perlite 42.9%, vermiculite 14.3%, and zeolite 14.3%). These results could be used as the basic information for the similar experimental design for the P. ternata.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.20 no.1
• /
• pp.35-47
• /
• 2018

A edible mushroom, Clitocybe maxima (Lentinus giganteusis) commercially cultivated in China and Taiwan. However, the researches of cultivation and cultural characteristics were not reported in Korea. In this study, we conducted on cultural characteristics and artificial cultivation of C. maxima. Six isolates were collected from China(3 isolates, commercial strain), Taiwan(1 isolate, commercial strain) and Korea(2 isolates, wild type). C. maxima and L. giganteus collected in China and Taiwan, respectively, are the same in China and are estimated to be of the same species as cultured characteristics. The mycelial growth of the collected strains was not significantly different in agar medium but it showed the best growth in YPMG in liquid culture. Optimum temperature for mycelial growth and induction of fruit body were 25℃ and 30℃, respectively. In order to artificial cultivation of C. maxima, cultural characteristics and artificial cultivation were carried out using agricultural by-products and forestry by-products materials. Mycelial growth was suitable in rice straw, cottonwood sawdust, corncob and rice seed medium, and it was selected as a cultivation medium. The suitable medium for artificial cultivation of C. maxima was selected to mixed medium 2(compounding ratio(v/v): 55% of hardwood sawdust, 5% of cottonseed pellets, 10% of cottonseed, 15% of beet pulp, 15% of swollen rice husks). It took about 30 days to be able to harvest, it was faster than oyster mushrooms. The cultivation period was about 30days. A isolate, CMA-002 was not initiation to fruit body primordiuma on the used cultivation substrate. Other 5 isolates were initiate and development to fruit body on the substrate used in this study. The strain CMA-003 was initiated to be fruiting body by 8~10 days after induction of fruiting body in all of the substrates. Isolate CMA-003 was generate to a bundle fruit body. Other isolates, however, were form fruit body individually. The CMA-003 strain was likely highly recommendable strains for farming. The optimum conditions for the induction and growth of C. maxima fruit body were 25~30℃, 8 hr illumination per day with white fluorescent lamp, 90~95% relative humidity, and 1,500 ppm of CO₂ concentration in a cultivation room.

• Korean Journal of Cognitive Science
• /
• v.34 no.3
• /
• pp.153-180
• /
• 2023

Previous research on the action effect had shown how simple action towards a stimulus can enhance the processing of that stimulus in subsequent visual search task (Buttaccio & Hahn, 2011; Weidler & Abrams, 2014). In four experiments, we investigated whether semantic representation of action word can induce the same attentional boost towards that stimulus and whether the type of action performed can modulate the action effect. In experiment 1, we replicated the same experimental paradigm displayed in previous studies. Participants were first shown an action word cue - "go" or "no". When the action cue was "go", participants were to press a designated key, but not to when the action cue was "no". Next, participants performed a visual search task, in which they reported the orientation of a tilted bar. The target could appear on top of the previously shown prime object (valid), or not (invalid). Reaction times (RTs) to the search task were measure for analysis and comparison, and the action effect had been replicated. In experiment 2, participants were instructed to respond with the keyboard for the action task, and to respond with the joystick for the visual search task. In experiment 3, participants were instructed not to press any key on the onset of prime, and then perform the visual search task to isolate the effect of semantic representation. Lastly, in experiment 4, participants were instructed to press separate keys for "go" and "no" on the onset of prime, and then perform the visual search task. Results indicate that semantic representation alone did not modulate the action effect, regardless of type of action and medium of action.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.49 no.4
• /
• pp.313-321
• /
• 2023

Platycodon grandiflorus (P. grandiflorus) flower is a perennial plant belonging to the family Campanulaceae and has many excellent pharmacological effects, so it has been used as a medicinal ingredient since ancient times. In addition, anthocyanin is a purple or blue natural pigment contained in plant flowers and fruits, and is known as a powerful antioxidant. The purpose of this study was to confirm the dermatological functionality of P. grandiflorus flower extract and the value of the bluish anthocyanin contained in flowers as a cosmetic material as a natural pigment. Firstly, 50% ethanol and 80% ethanol were added to the P. grandiflorus flower and extracted under reflux for 4 h at 25, 60, and 80 ℃, and the pH of each treatment group was similar. Based on the anthocyanin content and chromaticity (E^*ab), 50% ethanol 60 ℃ extraction conditions showing the color development most similar to the natural color of the P. grandifloras flower were selected, and a sample was prepared by concentrating and lyophilizing. The analysis results showed that the total phenol, total flavonoid, and total anthocyanin contents were in the ranges of 23 ㎍/mL, 16 ㎍/mL, and 0.17 ㎍/mL, respectively. The P. grandiflorus flower extract suppressed the production of nitric oxide (NO) and interleukin-6 (IL-6) in lipopolysaccharide (LPS) induced RAW264.7 cells. Furthermore, the P. grandiflorus flower extract showed wound healing effects through the promotion of skin cell migration in TNF-α stimulated human keratinocytes. The stability of anthocyanin and extract color was studied during a storage period of 50 days at various temperatures (4 ℃, 25 ℃, and 45 ℃). Color values (L, a, and b) of the P. grandiflorus flower extract changed over 50 days, whereas the bluish-purple color of the extract was stabilized using 5% maltodextrin. These results suggest that P. grandiflorus flower extract may be useful as a natural cosmetic pigment.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.589-597
• /
• 2023

Floating debris in large quantities from land during heavy rainfall has adverse social, economic, and environmental impacts, but the monitoring system for the concentration area and amount is insufficient. In this study, we proposed an efficient monitoring method for floating debris entering the river during heavy rainfall in Daecheong Lake, the largest water supply source in the central region, and applied remote sensing techniques to estimate the standing-stock of floating debris. To investigate the status of floating debris in the upper of Daecheong Lake, we used a tracking buoy equipped with a low-orbit satellite communication terminal to identify the movement route and behavior characteristics, and used a drone to estimate the potential concentration area and standing-stock of floating debris. The location tracking buoys moved rapidly during the period when the cumulative rainfall for 3 days increased by more than 200 to 300 mm. In the case of Hotan Bridge, which showed the longest distance, it moved about 72.8 km for one day, and the maximum moving speed at this time was 5.71 km/h. As a result of calculating the standing-stock of floating debris using a drone after heavy rainfall, it was found to be 658.8 to 9,165.4 tons, with the largest amount occurring in the Seokhori area. In this study, we were able to identify the main concentrations of floating debris by using location-tracking buoys and drones. It is believed that remote sensing-based monitoring methods, which are more mobile and quicker than traditional monitoring methods, can contribute to reducing the cost of collecting and processing large amounts of floating debris that flows in during heavy rain periods in the future.

• Sim-seong Yeon-gu
• /
• v.31 no.2
• /
• pp.113-150
• /
• 2016

Chobun refers to a temporary grave covered with straw thatch that contains a corpse until its flesh is gone. When all the flesh has rotted away, the straw grave is disassembled and only the bones are retrieved. Therefore, Chobun is an example of a secondary burial custom (German : Doppel Bestattung) that is composed of a first temporary funeral for processing the corpse's flesh, and a second permanent burial of the final remains (bones or ashes). The duration of the temporary burial is determined by the time needed for decomposing the flesh of the deceased. Building a Chobun progresses putrefaction and reduction to bone. In the literature of alchemy, putrefaction and new life occur simultaneously. The purpose of rotting is to make the flesh disappear, leaving only its essence. It is making the physical body enter a spiritual state, so that the dead can enter into a different world. One must endure the unstable rotting process until the smell of flesh has faded. The rotting process is the attitude of accepting the terrible, polluted aspect of the corpse, while maintaining a helpless, passive posture, in order to allow new possibilities. When we try to approach an archetypal aspect of the unconscious, it is often experienced in threatening, aggressive ways. In the individuation process, the unconscious offers us the blessing of a new spiritual awakening and renewed sense of life, only when we have the courage to see this terrifying and contaminated side of our psyche. This is exactly what putrefaction means. Bone and skeleton symbolize the indestructible, imperishable, and essential elements of life. Bone is the minimum unit and foundation for regeneration, where new life can grow. Reduction to bone is moving back to the origin of life, to the womb. Psychologically, it means discarding one's ego-centeredness and allowing the Self to lead the entire process of individuation. Going through the painful process of reduction to a skeleton for the purpose of further development is a declaration of the death of the ego, aiming at the liberation from perishable flesh and acquisition of the spiritual, regenerative, and immortal elements of life. Chobun also denotes the yearly decay and revival of life, especially of vegetal life. In Chobun, this symbolic meaning of the vegetal cycle of life is emphasized to represent the part of life that survives even after death. Vegetation related to Chobun deals with the continuity of life and psychologically with the Self. Images of vegetation are closely related to the existence of life beyond death, which is the existence of the Self, the source of energy that constantly renews and rejuvenates the consciousness.

• Journal of Life Science
• /
• v.34 no.5
• /
• pp.304-312
• /
• 2024

This study was conducted to characterize strain Y10, isolated from discarded chicken feathers. Strain Y10 was identified as Bacillus amyloliquefaciens through phenotypic and 16S rRNA gene analysis. B. amyloliquefaciens Y10 exhibited plant growth-promoting activities, including the production of fungal cell-degrading enzymes (cellulase, lipase, protease, and pectinase), siderophores, ammonia, and indoleacetic acid. Furthermore, strain Y10 was able to inhibit the mycelial growth of several phytopathogenic fungi. When 0.1% sucrose as a carbon source and 0.05% casein as a nitrogen source were added to the basal medium, adjusted to pH 10, and cultured at 35℃, the degradation rate of chicken feathers by strain Y10 was about two times higher than that of the basal medium, with the feathers almost completely degraded in four days. Strain Y10 also degraded various keratin substrates, including duck feathers, wool, and human nails. It was confirmed that the feather hydrolyzates prepared using strain Y10 exhibited antioxidant activities, such as 1,1-diphenyl-2-picrylhydrazyl radical scavenging activity (EC₅₀ = 0.38 mg/ml) and superoxide dismutase-like activity (EC₅₀ = 183.7 mg/ml). These results suggest that B. amyloliquefaciens Y10 is a potential candidate for the development of bioinoculants and feed additives applicable to the agricultural and livestock industries, as well as the microbiological treatment of keratin waste.