• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.26 no.12
• /
• pp.605-619
• /
• 2014

This article reviews the papers published in the Korean Journal of Air-Conditioning and Refrigeration Engineering during 2013. It is intended to understand the status of current research in the areas of heating, cooling, ventilation, sanitation, and indoor environments of buildings and plant facilities. Conclusions are as follows. (1) The research works on the thermal and fluid engineering have been reviewed as groups of fluid machinery, pipes and relative parts including orifices, dampers and ducts, fuel cells and power plants, cooling and air-conditioning, heat and mass transfer, two phase flow, and the flow around buildings and structures. Research issues dealing with home appliances, flows around buildings, nuclear power plant, and manufacturing processes are newly added in thermal and fluid engineering research area. (2) Research works on heat transfer area have been reviewed in the categories of heat transfer characteristics, pool boiling and condensing heat transfer and industrial heat exchangers. Researches on heat transfer characteristics included the results for general analytical model for desiccant wheels, the effects of water absorption on the thermal conductivity of insulation materials, thermal properties of Octadecane/xGnP shape-stabilized phase change materials and $CO_2$ and $CO_2$-Hydrate mixture, effect of ground source heat pump system, the heat flux meter location for the performance test of a refrigerator vacuum insulation panel, a parallel flow evaporator for a heat pump dryer, the condensation risk assessment of vacuum multi-layer glass and triple glass, optimization of a forced convection type PCM refrigeration module, surface temperature sensor using fluorescent nanoporous thin film. In the area of pool boiling and condensing heat transfer, researches on ammonia inside horizontal smooth small tube, R1234yf on various enhanced surfaces, HFC32/HFC152a on a plain surface, spray cooling up to critical heat flux on a low-fin enhanced surface were actively carried out. In the area of industrial heat exchangers, researches on a fin tube type adsorber, the mass-transfer kinetics of a fin-tube-type adsorption bed, fin-and-tube heat exchangers having sine wave fins and oval tubes, louvered fin heat exchanger were performed. (3) In the field of refrigeration, studies are categorized into three groups namely refrigeration cycle, refrigerant and modeling and control. In the category of refrigeration cycle, studies were focused on the enhancement or optimization of experimental or commercial systems including a R410a VRF(Various Refrigerant Flow) heat pump, a R134a 2-stage screw heat pump and a R134a double-heat source automotive air-conditioner system. In the category of refrigerant, studies were carried out for the application of alternative refrigerants or refrigeration technologies including $CO_2$ water heaters, a R1234yf automotive air-conditioner, a R436b water cooler and a thermoelectric refrigerator. In the category of modeling and control, theoretical and experimental studies were carried out to predict the performance of various thermal and control systems including the long-term energy analysis of a geo-thermal heat pump system coupled to cast-in-place energy piles, the dynamic simulation of a water heater-coupled hybrid heat pump and the numerical simulation of an integral optimum regulating controller for a system heat pump. (4) In building mechanical system research fields, twenty one studies were conducted to achieve effective design of the mechanical systems, and also to maximize the energy efficiency of buildings. The topics of the studies included heating and cooling, HVAC system, ventilation, and renewable energies in the buildings. Proposed designs, performance tests using numerical methods and experiments provide useful information and key data which can improve the energy efficiency of the buildings. (5) The field of architectural environment is mostly focused on indoor environment and building energy. The main researches of indoor environment are related to infiltration, ventilation, leak flow and airtightness performance in residential building. The subjects of building energy are worked on energy saving, operation method and optimum operation of building energy systems. The remained studies are related to the special facility such as cleanroom, internet data center and biosafety laboratory. water supply and drain system, defining standard input variables of BIM (Building Information Modeling) for facility management system, estimating capability and providing operation guidelines of subway station as shelter for refuge and evaluation of pollutant emissions from furniture-like products.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.24 no.3
• /
• pp.375-388
• /
• 2019

Accurate evaluation of sea-to-air $CO_2$ flux and its variability is crucial information to the understanding of global carbon cycle and the prediction of atmospheric $CO_2$ concentration. $fCO_2$ observations are sparse in space and time in the East Sea. In this study, we derived high resolution time series of surface $fCO_2$ values in the southwest East Sea, by feeding sea surface temperature (SST), salinity (SSS), chlorophyll-a (CHL), and mixed layer depth (MLD) values, from either satellite-observations or numerical model outputs, to three machine learning models. The root mean square error of the best performing model, a Random Forest (RF) model, was $7.1{\mu}atm$. Important parameters in predicting $fCO_2$ in the RF model were SST and SSS along with time information; CHL and MLD were much less important than the other parameters. The net $CO_2$ flux in the southwest East Sea, calculated from the $fCO_2$ predicted by the RF model, was $-0.76{\pm}1.15mol\;m^{-2}yr^{-1}$, close to the lower bound of the previous estimates in the range of $-0.66{\sim}-2.47mol\;m^{-2}yr^{-1}$. The time series of $fCO_2$ predicted by the RF model showed a significant variation even in a short time interval of a week. For accurate evaluation of the $CO_2$ flux in the Ulleung Basin, it is necessary to conduct high resolution in situ observations in spring when $fCO_2$ changes rapidly.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1463-1478
• /
• 2022

Maritime transport accounts for 99.7% of the exports and imports of the Republic of Korea; therefore, developing a vessel monitoring system for efficient operation is of significant interest. Several studies have focused on tracking and monitoring vessel movements based on automatic identification system (AIS) data; however, ships without AIS have limited monitoring and tracking ability. High-resolution optical satellite images can provide the missing layer of information in AIS-based monitoring systems because they can identify non-AIS vessels and small ships over a wide range. Therefore, it is necessary to investigate vessel monitoring and small vessel classification systems using high-resolution optical satellite images. This study examined the possibility of developing ship monitoring systems using Compact Advanced Satellite 500-1 (CAS500-1) satellite images by first training a deep learning model using satellite image data and then performing detection in other images. To determine the effectiveness of the proposed method, the learning data was acquired from ships in the Yellow Sea and its major ports, and the detection model was established using the You Only Look Once (YOLO) algorithm. The ship detection performance was evaluated for a domestic and an international port. The results obtained using the detection model in ships in the anchorage and berth areas were compared with the ship classification information obtained using AIS, and an accuracy of 85.5% and 70% was achieved using domestic and international classification models, respectively. The results indicate that high-resolution satellite images can be used in mooring ships for vessel monitoring. The developed approach can potentially be used in vessel tracking and monitoring systems at major ports around the world if the accuracy of the detection model is improved through continuous learning data construction.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.1
• /
• pp.21-40
• /
• 2023

This study analyzed the cold air characteristics of the Nakdong Jeongmaek, which is advantageous for the formation of cold air that can flow into the city, in order to suggest the wind ventilation corridor plans, which have recently been increasing interest as a way to improve the urban thermal environment. In addition, based on the watershed analysis, specific cold-air watershed areas were established and management plans were suggested to expand the cold air function of the Nakdong Jeongmaek. As a result of the analysis of cold air in the Nakdong Jeongaek, cold air was strongly generated in the northern forest of the Jeongamek, and flowed into nearby cities along the valley topography. On average, the speed of cold air was high in cities located to the east of the Jeongmaek, while the height of cold air layer was high in cities located to the west. By synthesizing these cold air characteristics and watershed analysis results, the cold-air watershed area was classified into 8 zones, And the plans were proposed to preserve and strengthen the temperature reduction of the Jeongmaek by designating the zones as 'Conservation area of Cold-air', 'Management area of Cold-air', and 'Intensive management area of Cold-air'. In addition, in order to verify the temperature reduction of cold air, the effect of night temperature reduction effect was compared with the cold air analysis using weather observation data. As a result, the temperature reduction of cold air was confirmed because the night temperature reduction was large at the observation station with strong cold air characteristics. This study is expected to be used as basic data in establishing a systematic preservation and management plan to expand the cold air function of the Nakdong Jeongmaek.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• Korean Journal of Environment and Ecology
• /
• v.30 no.6
• /
• pp.939-961
• /
• 2016

For effective conservation of endangered wild plants, it is necessary to understand their interactions with environmental factors in each habitat together with life traits of target species. First, the characteristics of their distribution were investigated followed by their monitoring for 4 years focusing on the habitats in the lagoon. Also, their life traits were compared including production of hibernacles, fruits, and seeds by the soil fertilization and light intensities. Next, the information on the species was secured by germination experiment using the generated seeds from the cultivation experiment. The habitat of Glaux maritima var. obtusifolia Fernald in Korea was located in the rear edge of the worldwide distribution and its four habitats were isolated and distributed far away each other. Two of them were located in small salt-marsh and fine sand estuaries formed in the rocky area of the seashore, and the other two were inhabited with the sandy soil in the lagoon which was connected by river-mouth to the sea. Glaux maritima var. obtusifolia Fernald tends to be distributed in the sites where the establishment and growth of the competitor were inhibited by salinity, periodic flooding, and lower layer of the soil to extend a roots. It maintained its population by recruitments of hibernacles and seedling. The production of hibernacle was assumed to be affected by the particle consist of the sand together with organic matters in the soil. Seedling recruitment was observed only in the salt-marsh area located in the rear sites of sand ridge where was the shore of the lagoon. Glaux maritima var. obtusifolia Fernald was observed to have different threatening factors by each population. Its population in Pohang seemed the sedimentation of fine sand which affected the recruitment of hibernacles had been eroded due to the construction of the coastal road. The population in Ulsan appeared rapid expansion of competitor and reduction of its distribution area due to the interruption of eluted water supplied to the habitat. On the other hand, the habitat in the lagoon maintained the population relatively stable. Especially, the population in Songji-ho was determined to be the most stable one. To sustain the population of Glaux maritima var. obtusifolia Fernald distributed in the lagoon, it is suggested that the wide ranged scale of conservational activities is necessary to maintain the mechanisms including the entrance of seawater which belongs to the lagoon, and periodic flooding.

• Korean Journal of Environment and Ecology
• /
• v.30 no.6
• /
• pp.1032-1046
• /
• 2016

The purpose of this study was to provide basic information on ecological forest management in Janggunbong, Bonghwa-Gun. Vegetation data were collected from Janggunbong, Bonghwa-Gun, from July, 2014 to October, 2015. We carried out an analysis of vegetation types on the physiognomically dominant species of 111 quadrates. In the natural forest area, the vegetation community was classified into Quercus mongolica, Betula schmidtii, Pinus densiflora, Quercus variabilis and Tilia amurensis. In the plantation area, the vegetation community was classified into Pinus koraiensis, Larix kaempferi, Fraxinus rhynchophylla and Betula platyphylla var. japonica. Based on the analysis of the importance value of the species in the slope area, it was seen that the tree layers of the natural forest were dominated by Quercus mongolica at 44.3, and Pinus densiflora at 12.1. The importance values of the subtree layer of the natural forest were found to be 27.6 for Quercus mongolica, and 12.4 for Fraxinus sieboldiana. Also, the importance values of the tree layers in the plantation areas were found to be 22.6 for Pinus koraiensis, 15.4 for Larix kaempferi, and 13.3 for Fraxinus rhynchophylla, while those of the subtree layers of the plantation area were found to be17.9 for Quercus variabilis, 14.1 for Parthenocissus tricuspidata, and 10.4 for Quercus mongolica in that order. Vine plants showed higher importance values in the plantation area than in the natural forest area. Species diversity in the valley area was 2.334 in the natural forest area, and 1.734 in the plantation area. That of natural forest area was 1.931, and that of plantation area was 1.927 in slope area. For management of the forest vegetation in Mt. Janggunbong, a distinct forest management plan, customized for each topography and physiognomical community unit should be made Particularly, the administration is required to consider strategies to reduce the higher importance value for vine plants in the plantation areas.

• Archives of design research
• /
• v.19 no.1 s.63
• /
• pp.201-214
• /
• 2006

Modern society is an age of vagueness and confusion. In addition, vagueness, complexity and variety are seen throughout art including modern philosophy, literature, and environmental design. A phenomenon like this shows that modern society has integrated different components as an organic relationship frequently crossing the boundary of fields. This feature can be regarded as hybrid related with accepting contradictory components and binding them into one under relationship between part and whole. As new design concept, presented are attitude to accept the two instead of attitude to select one of the alternatives, abundance instead of dearness, and ambiguity instead of simplicity. This principle has a crucial influence on creative design providing opposing contradiction and several alternative plans as non-deterministic form not completed one and, above all, useful information in mutual dependence and mutual relationship. When it comes to hybrid, therefore, a strategy is needed to consider layer of several fields getting out of standardizing space into a single space. As an event of this situation and concept, space experience means behaving freely based on experience of users' body. It can be known that this experience brings about users' more dynamic experience in comparison with the experience of seeing environmental design from a viewpoint of visual ism on the existing simplicity. Such a practical experience is subjective, synesthetic, and non-observational one. Therefore, hybrid has brought active users to the stage, which is distinguished from synesthesia felt through body's experience, not through observational attitude and visual space which achieve former balance and harmony with non-determination. That's because hybrid creatures are turning to a product resulted from creative imagination instead of from reappearance which makes text visualized. Such experience performed by user's active participation collapses the boundary between special elite-centered art and daily life and it is the present progressive form showing creation process of future events and new esthetic experience.