• Journal of agriculture & life science
• /
• v.50 no.5
• /
• pp.1-9
• /
• 2016

Plant growth and development strongly influenced by light quantity and its spectral composition. Young tomato plants were cultivated in growth cabinets under artificial light provided by red and blue light emitting diodes(LEDs) during 12 hours, then plants were exposed to monochromatic ultraviolet, blue, green and red lights as an end-of-day(EOD) treatment during 4 hours to study their effect on plant growth parameters. EOD lighting from various LEDs increased total fresh and dry weights as well as assimilation area compared to those in control. Blue light increased stem height, internode length and stem diameter. Monochromatic UV-A light reduced stem elongation, highly increased stomatal conductance. Compactness and health index of young tomato plants were increased in UV-A and red light treatments.

• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1271-1287
• /
• 2022

When abnormal operating conditions occur in nuclear power plants, operators must identify the occurrence cause and implement the necessary mitigation measures. Accordingly, the operator must rapidly and accurately analyze the symptom requirements of more than 200 abnormal scenarios from the trends of many variables to perform diagnostic tasks and implement mitigation actions rapidly. However, the probability of human error increases owing to the characteristics of the diagnostic tasks performed by the operator. Researches regarding diagnostic tasks based on Artificial Intelligence (AI) have been conducted recently to reduce the likelihood of human errors; however, reliability issues due to the black box characteristics of AI have been pointed out. Hence, the application of eXplainable Artificial Intelligence (XAI), which can provide AI diagnostic evidence for operators, is considered. In conclusion, the XAI to solve the reliability problem of AI is included in the AI-based diagnostic algorithm. A reliable intelligent diagnostic assistant based on a merged diagnostic algorithm, in the form of an operator support system, is developed, and includes an interface to efficiently inform operators.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.

• Journal of Ginseng Research
• /
• v.7 no.2
• /
• pp.172-192
• /
• 1983

Light environment and growth of Panax ginseng In habitat and cultivation under natural shade were renewed. Grower's experiences on ginseng stand In relation to light environment were assessed. Change of shading method and grower's concepts on light requirement of ginseng plant in Korea, Manchuria and Japan was counted. Growth of wild ginseng was better under rich light. Optimum crown density index appeared to be 0.7 In natural habitat and 0.4 to 0.7 for the cultivation in forest. Change of light Intensity in forest was greatest in May and reached near to constant value (from 40% to 3% for broad leaf deciduous forest and loom 4% to 2% for pine forest). Insufficient light condition induced long and thin stem, poor flowering and seed bearing, and sequent dormancy. Relation between light and ginseng strand was not clear but light Interception with cool weather was effective. Topography and orientation of bed have been deeply considered for light environment. Panel or bark of won were used for shading in deep forest manly In Manchuria while reed blind and straw thatch were used in Korea. Kinds and number of shades material and seasonal or daily schedule have been simplified probably by labor pressure due to eulargement of plantation. Post height has been greater while width of roof, bed and ditch has changed lisle. Scientific survey in the past omitted important light control methods (complete light hardening etc) which has been practiced in specific areas. The concept and technique of light control in the past in Korea were delicate and intensive including the control of temperature and moisture. For the application of old concept in modem cultivation precise Investigation of the technique including the measurement of light, temperature and moisture is needed.

• Journal of the Korean Solar Energy Society
• /
• v.33 no.1
• /
• pp.89-95
• /
• 2013

A DBLP(Double blind light pipe) daylight system can be installed at a building exterior wall or roof to replace artificial light during the day time. This system was consisted of a double blind light collector, a mirror duct type light transformer and a prism light pipe distributor. The double blinds were used to track the sun's altitude and azimuth movements to collect the sunlight throughout the day. The sunlight collected by the light collector was reflected on the first mirror and the second mirror and sent to the light pipe through the light transformer. The transformer was designed to deliver the sunlight into the light pipe efficiently. The light distributor plays a role in diffusing the sunlight coming in through the light collector to be used for indoor lighting. In this paper, a DBLP system has been designed, installed and tested at a KIER daylighting twin test cell. The DBLP daylighting system was applied to the experimental test cell which has an indoor area of 2.0 m wide ${\times}$ 2.4 m height ${\times}$ 3.8 m length. The experiment was conducted from January 30 to February 27, 2012, under clear skies and partially cloudy skies. Data was collected from 10:00 am to 16:00 pm every 2 minute and the average was calculated for every 30 minute of the data collection to obtain the system efficiency. The results indicated that the DBLP system efficiency was evaluated as 11.67%. The DBLP system indoor illumination energy reduction was predicted as 0.822 kWh/day. This could replace 4 sets of a 32W fluorescent lamp operating 6.4 hours per a day.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.969-976
• /
• 2019

A lightweight artificial intelligence hardware has made great strides in many application areas. In general, a lightweight artificial intelligence system consist of lightweight artificial intelligence engine and preprocessor including feature selection, generation, extraction, and normalization. In order to achieve optimal performance in broad range of applications, lightweight artificial intelligence system needs to choose a good preprocessing function and set their respective hyper-parameters. This paper proposes a unified framework for a lightweight artificial intelligence system and utilization method for finding models with optimal performance to use on a given dataset. The proposed unified framework can easily generate a model combined with preprocessing functions and lightweight artificial intelligence engine. In performance evaluation using handwritten image dataset and fall detection dataset measured with inertial sensor, the proposed unified framework showed building optimal artificial intelligence models with over 90% test accuracy.

• Horticultural Science & Technology
• /
• v.30 no.6
• /
• pp.673-679
• /
• 2012

This study was conducted to examine the effect of artificial light source and photoperiod on the growth of leaf lettuce (Lactuca sativa L.) 'Seonhong Jeokchukmyeon' in a closed-type plant production system. Seedlings were grown under 3 light sources, fluorescent lamp (FL, Philips Co. Ltd., the Netherlands), WL #1 (Hepas Co. Ltd., Korea), and WL #2 (FC Poibe Co., Ltd., Korea), each with 3 photoperiods, 12/12, 18/6, and 24/0 (Light/Dark). An irradiance spectrum analysis showed that FL has various peaks in the 400-700 nm range, while WL #1 and WL #2 have only one monochromatic peak at 450 and 550 nm, respectively. The greatest plant height, fresh and dry weights were obtained in the 24/0 (Light/Dark) photoperiod. The 24/0 (Light/Dark) photoperiod treatment promoted vegetative growth of the leaf area. Length of the longest root, number of leaves, fresh weight, and total anthocyanin contents were greater in FL than in either WL #1 or #2. The greatest chlorophyll fluorescence (Fv/Fm) was found in the 12/12 (Light/Dark) photoperiod with FL treatment. The energy use efficiency of the LED increased by about 35-46% as compared to FL. Results suggest a possibility of LED being used as a substitute light source for fluorescent lamp for lettuce cultivation in a plant factory system.

• Journal of Plant Biotechnology
• /
• v.48 no.1
• /
• pp.62-70
• /
• 2021

We analyzed the growth and quality characteristics of barley sprouts grown under artificial light sources consisting of a fluorescent lamp or light-emitting diode (LED) in an aquaculture system (grown with water only, without nutrients). At the end of the observation period, the shoots grown under the fluorescent lamp treatment were the longest, followed by the LED treatment and natural light-treatment. It was also observed that growth was faster for sprouts subjected to a non-sterilizing treatment than those subjected to a 70% ethanol treatment. As the seed sowing rate for planting trays increased, the yield of harvested barley sprouts increased; among light treatments, the natural light treatment resulted in the lowest yield, while the fluorescent light treatment resulted in the highest. The total phenol and total flavonoid contents of extracts of the barley sprouts were highest for the natural light treatment, but TEAC and FRAP were both highest for the fluorescent lamp treatment. The essential amino acid content ranged from 41.64 to 45.93 mg/g and was relatively higher for the natural light treatment than the other two treatments, while the content of non-essential amino acids was highest for the LED treatment. The total amino acid content was highest for the LED treatment at 97.47 ± 6.30 mg/g, for which the content of non-essential amino acids (53.17%) was higher than that of essential amino acids (46.83%).

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.5
• /
• pp.327-337
• /
• 2021

The paper acknowledges that many human resources are needed on the research and development (R&D) process of artificial intelligence (AI), and discusses on factors to consider on the current method of development. Enfin, in order to enhance efficiency of AI development, it seems possible through labour division of a few managers and numerous ordinary workers as a type of light industry. Thus, the research team names the development process of AI, which maximizes production efficiency by handling digital resources named 'data' with mechanical equipment called 'computer', as digital light industry of fourth industrial era. As experienced during the previous Industrial Revolution, if human resources are efficiently distributed and utilized, digital light industry would be able to expect progress no less than the second Industrial Revolution, and human resources development for this is considered urgent.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11c
• /
• pp.632-638
• /
• 2000

This paper represents the characteristics of evapotranspiration rate (EVTR) and graft-taking of watermelon grafted seedlings in a graft-taking enhancement system using fluorescent lamps as artificial lighting source. Four air temperature levels of 23, 25, 27 and 29C, three humidity levels of 85, 90 and 95%R.H. and two photosynthetic photon flux (PPF) levels of 30 and 50 ${\mu}$mol m$\^$-2/ S$\^$-1/ were provided to investigate the effects of air temperature, relative humidity and light intensity on EVTR and graft-taking of grafted seedlings. EVTR of grafted seedlings increased with increasing air temperature and the passage of time after grafting. Also EVTR increased with decreasing relative humidity. As relative humidity decreased and air temperature increased, vapor pressure deficit increased and thus EVTR increased. It is required to maintain a low level vapor pressure deficit for suppressing EVTR of grafted seedlings during first 1-2 days after grafting. Therefore, less EVTR at initial stage after grafting would be adequate for smooth joining of the scion and rootstock.