• Industry Promotion Research
• /
• v.6 no.4
• /
• pp.1-9
• /
• 2021

The purpose of this study is to manufacture lightweight aggregates for recycling water treatment sludge, to identify the physical properties of the aggregates, and present a method of utilizing the manufactured lightweight aggregates. The chemical composition and thermal properties were examined via a raw materials analysis. The aggregate examined here was fired by the rapid sintering method and the single-particle density and water absorption rate were measured. Water treatment sludge has high ignition loss and high fire resistance. When 30wt% of purified sludge was added, the single-particle density of the aggregates was in the range of 0.8~1.2g/cm³ at a temperature of 1,150~1,200℃. At temperatures of 1200℃ or higher, ultra-light aggregates having a single-particle density of 0.8 or less could be produced. When applied to concrete by replacing the general aggregate in the concrete, a specimen having strength values of 200 to 450 kgf/cm² on 28 days was obtained, and when applied as a filter material, the performance was equal to or higher than that of ordinary sand.

• Korean Journal of Agricultural Science
• /
• v.46 no.1
• /
• pp.67-78
• /
• 2019

The purpose of this study was to predict the water quality using the RNN (recurrent neutral network) and LSTM (long short-term memory). These are advanced forms of machine learning algorithms that are better suited for time series learning compared to artificial neural networks; however, they have not been investigated before for water quality prediction. Three water quality indexes, the BOD (biochemical oxygen demand), COD (chemical oxygen demand), and SS (suspended solids) are predicted by the RNN and LSTM. TensorFlow, an open source library developed by Google, was used to implement the machine learning algorithm. The Okcheon observation point in the Geum River basin in the Republic of Korea was selected as the target point for the prediction of the water quality. Ten years of daily observed meteorological (daily temperature and daily wind speed) and hydrological (water level and flow discharge) data were used as the inputs, and irregularly observed water quality (BOD, COD, and SS) data were used as the learning materials. The irregularly observed water quality data were converted into daily data with the linear interpolation method. The water quality after one day was predicted by the machine learning algorithm, and it was found that a water quality prediction is possible with high accuracy compared to existing physical modeling results in the prediction of the BOD, COD, and SS, which are very non-linear. The sequence length and iteration were changed to compare the performances of the algorithms.

• Journal of odor and indoor environment
• /
• v.16 no.2
• /
• pp.139-149
• /
• 2017

In order to reduce odor and methane emission from the landfill, open biocovers and a closed biofilter were applied to the landfill site. Three biocovers and the biofilter are suitable for relatively small-sized landfills with facilities that cannot resource methane into recovery due to small volumes of methane emission. Biocover-1 consists only of the soil of the landfill site while biocover-2 is mixed with the earthworm casts and artificial soil (perlite). The biofilter formed a bio-layer by adding mixed food waste compost as packing material of biocover-2. The removal efficiency decreased over time on biocover-1. However, biocover-2 and the biofilter showed stable odor removal efficiency. The rates of methane removal efficiency were in order of biofilter (94.9%)>, biocover-1(42.3%)>, and biocover-2 (37.0%). The methane removal efficiency over time in biocover-1 was gradually decreased. However, drastic efficiency decline was observed in biocover-2 due to the hardening process. As a result of overturning the surface soil where the hardening process was observed, methane removal efficiency increased again. The biofilter showed stable methane removal efficiency without degradation. The estimate methane oxidation rate in biocover-1 was an average of 10.4%. Biocover-2 showed an efficiency of 46.3% after 25 days of forming biocover. However, due to hardening process efficiency dropped to 4.6%. After overturn of the surface soil, the rate subsequently increased to 17.9%, with an evaluated average of 12.5%.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.58-66
• /
• 2019

Recognition of named entity such as proper nouns in conversation sentences is the most fundamental and important field of study for efficient conversational information prediction. The most important part of a task-oriented dialogue system is to recognize what attributes an object in a conversation has. The named entity recognition model carries out recognition of the named entity through the preprocessing, word embedding, and prediction steps for the dialogue sentence. This study aims at using user - defined dictionary in preprocessing stage and finding optimal parameters at word embedding stage for efficient dialogue information prediction. In order to test the designed object name recognition model, we selected the field of daily chemical products and constructed the named entity recognition model that can be applied in the task-oriented dialogue system in the related domain.

• Applied Chemistry for Engineering
• /
• v.30 no.2
• /
• pp.233-240
• /
• 2019

Molecular recognition technology has attracted considerable attention for improving the selectivity of a specific molecule by imprinting it on a polymer matrix. In this study, adsorption and release characteristics of chitosan based drug delivery films imprinted with sulindac (SLD) were investigated in terms of the plasticizer, temperature and pH and the results were also interpreted by the related mathematical models. The adsorption characteristics of target molecules on SLD-imprinted polymer films were better explained by the Freundlich and Sips equation than that of the Langmuir equation. The binding site energy distribution function was also useful for understanding the adsorption relationship between target molecules and polymer films. The drug release of SLD-imprinted polymer films followed the Fickian diffusion mechanism, whereas the drug release using artificial skin followed the non-Fickian diffusion behavior.

• Journal of Ginseng Research
• /
• v.45 no.1
• /
• pp.58-65
• /
• 2021

Background: Panax ginseng, as one of the most widely used herbal medicines worldwide, has been studied comprehensively in terms of the chemical components and pharmacology. The proteins from ginseng are also of great importance for both nutrition value and the mechanism of secondary metabolites. However, the proteomic studies are less reported in the absence of the genome information. With the completion of ginseng genome sequencing, the proteome profiling has become available for the functional study of ginseng protein components. Methods: We optimized the protein extraction process systematically by using SDS-PAGE and one-dimensional liquid chromatography mass spectrometry. The extracted proteins were then analyzed by two-dimensional chromatography separation and cutting-edge mass spectrometry technique. Results: A total of 2,732 and 3,608 proteins were identified from ginseng root and cauline leaf, respectively, which was the largest data set reported so far. Only around 50% protein overlapped between the cauline leaf and root tissue parts because of the function assignment for plant growing. Further gene ontology and KEGG pathway revealed the distinguish difference between ginseng root and leaf, which accounts for the photosynthesis and metabolic process. With in-deep analysis of functional proteins related to ginsenoside synthesis, we interestingly found the cytochrome P450 and UDP-glycosyltransferase expression extensively in cauline leaf but not in the root, indicating that the post glucoside synthesis of ginsenosides might be carried out when growing and then transported to the root at withering. Conclusion: The systematically proteome analysis of Panax ginseng will provide us comprehensive understanding of ginsenoside synthesis and guidance for artificial cultivation.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.227-233
• /
• 2021

Predictive maintenance has been one of important applications of data science technology that creates a predictive model by collecting numerous data related to management targeted equipment. It does not predict equipment failure with just one or two signs, but quantifies and models numerous symptoms and historical data of actual failure. Statistical methods were used a lot in the past as this predictive maintenance method, but recently, many machine learning-based methods have been proposed. Such proposed machine learning-based methods are preferable in that they show more accurate prediction performance. However, with the exception of some learning models such as decision tree-based models, it is very difficult to explicitly know the structure of learning models (Black-Box Model) and to explain to what extent certain attributes (features or variables) of the learning model affected the prediction results. To overcome this problem, a recently proposed study is an explainable artificial intelligence (AI). It is a methodology that makes it easy for users to understand and trust the results of machine learning-based learning models. In this paper, we propose an explainable AI method to further enhance the explanatory power of the existing learning model by targeting the previously proposedpredictive model [5] that learned data from a core facility (Hyper Compressor) of a domestic chemical plant that produces polyethylene. The ensemble prediction model, which is a black box model, wasconverted to a white box model using the Explainable AI. The proposed methodology explains the direction of control for the major features in the failure prediction results through the Explainable AI. Through this methodology, it is possible to flexibly replace the timing of maintenance of the machine and supply and demand of parts, and to improve the efficiency of the facility operation through proper pre-control.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.251-266
• /
• 2022

Structural Health Monitoring (SHM) of critical infrastructure comprises a major pillar of maintenance management, shielding public safety and economic sustainability. Although SHM is usually associated with data-driven metrics and thresholds, expert judgement is essential, especially in cases where erroneous predictions can bear casualties or substantial economic loss. Considering that visual inspections are time consuming and potentially subjective, artificial-intelligence tools may be leveraged in order to minimize the inspection effort and provide objective outcomes. In this context, timely detection of sensor malfunctioning is crucial in preventing inaccurate assessment and false alarms. The present work introduces a sensor-fault detection and interpretation framework, based on the well-established support-vector machine scheme for anomaly detection, combined with a coalitional game-theory approach. The proposed framework is implemented in two datasets, provided along the 1st International Project Competition for Structural Health Monitoring (IPC-SHM 2020), comprising acceleration and cable-load measurements from two real cable-stayed bridges. The results demonstrate good predictive performance and highlight the potential for seamless adaption of the algorithm to intrinsically different data domains. For the first time, the term "decision trajectories", originating from the field of cognitive sciences, is introduced and applied in the context of SHM. This provides an intuitive and comprehensive illustration of the impact of individual features, along with an elaboration on feature dependencies that drive individual model predictions. Overall, the proposed framework provides an easy-to-train, application-agnostic and interpretable anomaly detector, which can be integrated into the preprocessing part of various SHM and condition-monitoring applications, offering a first screening of the sensor health prior to further analysis.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.15 no.1
• /
• pp.25-43
• /
• 2013

Tasmania with its clean air, isolated from mainland Australia, has been producing high-quality agricultural products and has been continually developing organic farming since 1946 when the Living Soil Association of Tasmania(LSAT) was established. The organic farming movement in Tasmania has been actively advocated through three steps: the philosophical embryonic period, the movement diffusion period and the industrialised development period. The campaigns for informing about the connection between healthy soil and life unfolded during the embryonic period. This was followed by the birth of publicity of organic farming and the certification system through the dissemination of organic farming techniques and various events related to agriculture in the diffusion period when the Organic Gardening and Farming Society(OGFS) was established in 1972. In the industrialised development period, The Organic Coalition of Tasmania (OCT) which is representative of Tasmania was organised in 2000 and has been leading the organic farming industry. The organic farming movement in Tasmania not only limits the use of artificial agricultural chemical but pursues the quality of food, environment, the health of life including all animals and plants, the issue of development in rural society, social justice, and equity in understanding. It is far more holistic in its philosophy. The output of organic food accounts for 1 % of the total amount of agricultural production and 150 certified organic farms have managed with 5,000ha of land in 2010. The supply channels for organic foods vary from farmer's market, specialty stores, supermarket chains, local store to the cooperative community. Also the consumers' behaviour for organic foods has been establishing as an alternative life style. The education of the value and role of organic farming on the environment should be enlarged for the consumption of the organic food. In addition, organising for small farmers who act individually and the link with differentiated local food have still remained issues.

• Economic and Environmental Geology
• /
• v.57 no.3
• /
• pp.319-327
• /
• 2024

Calcite and aragonite are polymorphs with the chemical formula CaCO₃. In this study, natural limestone and aragonite, as well as scallop and clam shells composed of calcite and aragonite, were used as the pH-raising neutralizing agents for model solutions containing various heavy metals such as Cd, Cu, Fe, Mn, and Zn to simulate acidic drainage. According to the experimental results, pH-raising effect is higher in the shell materials compared to natural ores for both the calcite and aragonite types. Natural calcite and scallop shells are found to be the most suitable media for Cd removal, while over 95% efficiency for Cu and Fe removal was observed in all four media. Zn removal efficiency is higher in aragonite and clam shells, while Mn removal efficiency is relatively low, to be below 50%, for all four media. Overall, the heavy metal removal efficiency, except for Mn, was over 90%, in the order of Fe > Cu > Cd > Zn > Mn.