• Journal of Soil and Groundwater Environment
• /
• v.23 no.2
• /
• pp.1-14
• /
• 2018

The recent increase in demand for lithium has led to the development of new brine prospects, The brines are hosted in closed salar basin aquifers of two types that are mature halite salars and immature clastic salars. Salar brines also contain other elements of commercial interest, most notably potassium and boron. As a result, there has been a plethora of new exploration projects focused on the brines hosted in the aquifers of the intermontane-closed basins. The estimate of lithium resources and reserves in these salars depends on a detailed knowledge of aquifer geometry, porosity, and brine grade. Because the resource is in a fluid state, it has the propensity to move, mix, rearrange itself relatively rapidly during the course of a project lifetime, and lower recovery factors compared with most metalliferous and industrial mineral deposits due to reliance on pumping of the brine from wells for extraction. This is unlike any other type of metallic mineral resource and hence a different approach specially focusing on hydrogeology and brine hydrology is required for these prospects.

• Journal of Information Science Theory and Practice
• /
• v.9 no.2
• /
• pp.66-82
• /
• 2021

Recommender Systems have gained immense popularity due to their capability of dealing with a massive amount of information in various domains. They are considered information filtering systems that make predictions or recommendations to users based on their interests and preferences. The more recent technology, Linked Open Data (LOD), has been introduced, and a vast amount of Resource Description Framework data have been published in freely accessible datasets. These datasets are connected to form the so-called LOD cloud. The need for semantic data representation has been identified as one of the next challenges in Recommender Systems. In a LOD-enabled recommendation framework where domain awareness plays a key role, the semantic information provided in the LOD can be exploited. However, dealing with a big chunk of the data from the LOD cloud and its integration with any domain datasets remains a challenge due to various issues, such as resource constraints and broken links. This paper presents the challenges of interconnecting and extracting the DBpedia data with the MovieLens 1 Million dataset. This study demonstrates how LOD can be a vital yet rich source of content knowledge that helps recommender systems address the issues of data sparsity and insufficient content analysis. Based on the challenges, we proposed a few alternatives and solutions to some of the challenges.

• Journal of Forest and Environmental Science
• /
• v.37 no.2
• /
• pp.116-127
• /
• 2021

Predicting carbon distribution of soil aggregates is difficult due to complexity in organo-mineral formation. This limits global warming mitigation through soil carbon sequestration. Therefore, knowledge of land use effect on carbon stabilization requires quantification of soil mineral cations. The study was conducted to quantify carbon and base cations on soil mineral fractions in Natural Forest, Plantation Forest and Farm Land. Five 0.09 ha were demarcated alternately along 500 m long transect with an interval of 50 m in Natural Forest (NF), Plantation Forest (PF) and Farm Land (FL). Soil samples were collected with soil cores at 0-15, 15-30 and 30-45 cm depths in each plot. Soil core samples were oven-dried at 105℃ and soil bulk densities were computed. Sample (100 g) of each soil core was separated into >2.0, 2.0-1.0, 1.0-0.5, 0.5-0.05 and <0.05 mm aggregates using dry sieve procedure and proportion determined. Carbon concentration of soil aggregates was determined using Loss-on-ignition method. Mineral fractions of soil depths were obtained using dispersion, sequential extraction and sedimentation methods of composite soil samples and sieved into <0.05 and >0.05 mm fractions. Cation exchange capacity of two mineral fractions was measured using spectrophotometry method. Data collected were analysed using descriptive and ANOVA at α_0.05. Silt and sand particle size decreased while clay increased with increase in soil depth in NF and PF. Subsoil depth contained highest carbon stock in the PF. Carbon concentration increased with decrease in aggregate size in soil depths of NF and FL. Micro- (1-0.5, 0.5-0.05 and <0.05 mm) and macro-aggregates (>2.0 and 2-1.0 mm) were saturated with soil carbon in NF and FL, respectively. Cation exchange capacity of <0.05 mm was higher than >0.05 mm in soil depths of PF and FL. Fine silt (<0.05 mm) determine the cation exchange capacity in soil depths. Land use and mineral size influence the carbon and cation exchange capacity of Gambari Forest Reserve.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1053-1065
• /
• 2020

With the recent development of hardware performance and artificial intelligence technology, sophisticated fake videos that are difficult to distinguish with the human's eye are increasing. Face synthesis technology using artificial intelligence is called Deepfake, and anyone with a little programming skill and deep learning knowledge can produce sophisticated fake videos using Deepfake. A number of indiscriminate fake videos has been increased significantly, which may lead to problems such as privacy violations, fake news and fraud. Therefore, it is necessary to detect fake video clips that cannot be discriminated by a human eyes. Thus, in this paper, we propose a deep-fake detection model applied with Bidirectional Convolution LSTM and Attention Module. Unlike LSTM, which considers only the forward sequential procedure, the model proposed in this paper uses the reverse order procedure. The Attention Module is used with a Convolutional neural network model to use the characteristics of each frame for extraction. Experiments have shown that the model proposed has 93.5% accuracy and AUC is up to 50% higher than the results of pre-existing studies.

• The Plant Pathology Journal
• /
• v.37 no.6
• /
• pp.521-532
• /
• 2021

Knowledge and better understanding of functions of the microbial community are pivotal for crop management. This study was conducted to study bacterial structures including Acidovorax species community structures and diversity from the watermelon cultivated soils in different regions of South Korea. In this study, soil samples were collected from watermelon cultivation areas from various places of South Korea and microbiome analysis was performed to analyze bacterial communities including Acidovorax species community. Next generation sequencing (NGS) was performed by extracting genomic DNA from 92 soil samples from 8 different provinces using a fast genomic DNA extraction kit. NGS data analysis results revealed that, total, 39,367 operational taxonomic unit (OTU), were obtained. NGS data results revealed that, most dominant phylum in all the soil samples was Proteobacteria (37.3%). In addition, most abundant genus was Acidobacterium (1.8%) in all the samples. In order to analyze species diversity among the collected soil samples, OTUs, community diversity, and Shannon index were measured. Shannon (9.297) and inverse Simpson (0.996) were found to have the highest diversity scores in the greenhouse soil sample of Gyeonggi-do province (GG4). Results from NGS sequencing suggest that, most of the soil samples consists of similar trend of bacterial community and diversity. Environmental factors play a key role in shaping the bacterial community and diversity. In order to address this statement, further correlation analysis between soil physical and chemical parameters with dominant bacterial community will be carried out to observe their interactions.

• Journal of Space Technology and Applications
• /
• v.1 no.3
• /
• pp.356-363
• /
• 2021

It was common knowledge in textbooks that images acquired using mid-infrared ray were not suitable for measuring temperature near room temperature. But a recent satellite image using a mid-infrared sensor show the possibility that the result measured using the mid-infrared sensor can also measure the temperature near room temperature. In this paper, the possibility and accuracy of extraction room temperature information from satellite images with mid-infrared sensors are reviewed. The mid-infrared satellite image reviewed in this paper showed the temperature of room temperature well, and regarding the reliability as an absolute value of the measured temperature, the effect of the heat transfer amount due to the direct reflection of sunlight on the surface and the effect of the infrared absorption amount absorbed in the atmosphere can be seen as a relatively small or constant value. However, the problem of uncertainty in the radiation coefficient due to physical properties, which is the limit of the non-contact thermometer, remained a problem to be solved.

• Imaging Science in Dentistry
• /
• v.52 no.3
• /
• pp.239-244
• /
• 2022

Purpose: Despite the proliferation of numerous morphometric and anthropometric methods for sex identification based on linear, angular, and regional measurements of various parts of the body, these methods are subject to error due to the observer's knowledge and expertise. This study aimed to explore the possibility of automated sex determination using convolutional neural networks(CNNs) based on lateral cephalometric radiographs. Materials and Methods: Lateral cephalometric radiographs of 1,476 Iranian subjects (794 women and 682 men) from 18 to 49 years of age were included. Lateral cephalometric radiographs were considered as a network input and output layer including 2 classes(male and female). Eighty percent of the data was used as a training set and the rest as a test set. Hyperparameter tuning of each network was done after preprocessing and data augmentation steps. The predictive performance of different architectures (DenseNet, ResNet, and VGG) was evaluated based on their accuracy in test sets. Results: The CNN based on the DenseNet121 architecture, with an overall accuracy of 90%, had the best predictive power in sex determination. The prediction accuracy of this model was almost equal for men and women. Furthermore, with all architectures, the use of transfer learning improved predictive performance. Conclusion: The results confirmed that a CNN could predict a person's sex with high accuracy. This prediction was independent of human bias because feature extraction was done automatically. However, for more accurate sex determination on a wider scale, further studies with larger sample sizes are desirable.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.147-152
• /
• 2023

Mostly in motor fault detection the instantaneous values 3 axis vibration and 3phase current in time domain are acquired and converted to frequency domain. Vibrations are more useful in diagnosing the mechanical faults and motor current has remained more useful in electrical fault diagnosis. With having some experience and knowledge on the behavior of acquired data the electrical and mechanical faults are diagnosed through signal processing techniques or combine machine learning and signal processing techniques. In this paper, a single-layer LSTM based condition monitoring system is proposed in which the instantaneous values of three phased motor current are firstly acquired in simulated motor in in health and supply imbalance conditions in each of three stator currents. The acquired three phase current in time domain is then used to train a LSTM network, which can identify the type of fault in electrical supply of motor and phase in which the fault has occurred. Experimental results shows that the proposed single layer LSTM algorithm can identify the electrical supply faults and phase of fault with an average accuracy of 88% based on the three phase stator current as raw data without any processing or feature extraction.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.11-19
• /
• 2024

Multi-agent systems can be utilized in various real-world cooperative environments such as battlefield engagements and unmanned transport vehicles. In the context of battlefield engagements, where dense reward design faces challenges due to limited domain knowledge, it is crucial to consider situations that are learned through explicit sparse rewards. This paper explores the collaborative potential among allied agents in a battlefield scenario. Utilizing the Multi-Robot Warehouse Environment(RWARE) as a sparse reward environment, we define analogous problems and establish evaluation criteria. Constructing a learning environment with the QMIX algorithm from the reinforcement learning library Ray RLlib, we enhance the Agent Network of QMIX and integrate Random Network Distillation(RND). This enables the extraction of patterns and temporal features from partial observations of agents, confirming the potential for improving the acquisition of sparse reward experiences through intrinsic rewards.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.6
• /
• pp.847-856
• /
• 1995

When a human recognizes nouns in a sentence, s/he associates them with the hyper concepts of onus. For computer to simulate the human's word recognition, it should build the knowledge base (WordNet)for the hyper concepts of words. Until now, works for the WordNet haven't been performed in Korea, because they need lots of human efforts and time. But, as the power of computer is radically improved and common MRD becomes available, it is more feasible to automatically construct the WordNet. This paper proposes the method that automatically builds the WordNet of Korean nouns by using the descripti on of onus in Korean MRD, and it proposes the rules for extracting the hyper concepts (hypernyms)by analyzing structrual characteristics of Korean. The rules effect such characteristics as a headword lies on the rear part of sentences and the descriptive sentences of nouns have special structure. In addition, the WordNet prototype of Korean Nouns is developed, which is made by combining the hypernyms produced by the rules mentioned above. It extracts the hypernyms of about 2,500 sample words, and the result shows that about 92per cents of hypernyms are correct.