• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.195-207
• /
• 2022

COVID-19 has remained one of the most serious health crises in recent history, resulting in the tragic loss of lives and significant economic impacts on the entire world. The difficulty of controlling COVID-19 poses a threat to the global health sector. Considering that Artificial Intelligence (AI) has contributed to improving research methods and solving problems facing diverse fields of study, AI algorithms have also proven effective in disease detection and early diagnosis. Specifically, acoustic features offer a promising prospect for the early detection of respiratory diseases. Motivated by these observations, this study conceptualized a speech-based diagnostic model to aid in COVID-19 diagnosis. The proposed methodology uses speech signals from confirmed positive and negative cases of COVID-19 to extract features through the pre-trained Visual Geometry Group (VGG-16) model based on Mel spectrogram images. This is used in addition to the K-means algorithm that determines effective features, followed by a Genetic Algorithm-Support Vector Machine (GA-SVM) classifier to classify cases. The experimental findings indicate the proposed methodology's capability to classify COVID-19 and NOT COVID-19 of varying ages and speaking different languages, as demonstrated in the simulations. The proposed methodology depends on deep features, followed by the dimension reduction technique for features to detect COVID-19. As a result, it produces better and more consistent performance than handcrafted features used in previous studies.

• Journal of Korea Trade
• /
• v.24 no.6
• /
• pp.157-172
• /
• 2020

Purpose - This research empirically proves the extent to which export insurance promotes Korean exports to research object countries among New Southern countries. The outcome of this research will present implications for the operations of export insurance for exports to these countries. Design/methodology - For the empirical analysis, the export equation was composed using a basic gravity model. Based on this, the determinants of Korea's exports to research object countries were analyzed. In this study, a panel unit root test and panel cointegration test were conducted. As a result of the panel unit root test, it was confirmed that the variables of the panel data are not belonging to I(0), but to I(1). As a result of the panel cointegration test, it was established that there are long-term stable relationships among all variables. Accordingly, the gravity model was estimated using original data in order to reduce the information loss caused by the first difference, in spite of individual data belonging to I(1). Findings - For the estimated results of panel OLS, the estimated coefficient of short-term export insurance was 0.56-0.64, with statistically significant results at the significance level of 1%. In addition, for the analysis results of the random effect model, the estimated coefficient of short-term export insurance was 0.59-0.64%, with a statistically significant result at the 1% significance level. This could indicate that Korean export insurance has positive influences on export promotion to New Southern countries. Originality/value - The research implies that export insurance has a 4.1 to 4.7 multiplier effect in expanding exports to the New Southern countries for Korea. This research has intensively analyzed the effects of export insurance on the promotion of exports to a selected area by a government foreign economic policy, which is the originality and value of this paper.

• The Plant Pathology Journal
• /
• v.37 no.3
• /
• pp.215-231
• /
• 2021

Brown leaf spot disease caused by Nigrospora guilinensis on Phellodendron chinense occurs in a large area in Dayi County, Chengdu City, Sichuan Province, China each year. This outbreak has severely reduced the production of Chinese medicinal plants P. chinense and caused substantial economic losses. The bacterial isolate JKB05 was isolated from the healthy leaves of P. chinense, exhibited antagonistic effects against N. guilinensis and was identified as Bacillus megaterium. The following fermentation medium and conditions improved the inhibitory effect of B. megaterium JKB05 on N. guilinensis: 2% glucose, 0.1% soybean powder, 0.1% KCl, and 0.05% MgSO₄; initial concentration 6 × 10⁶ cfu/ml, and a 42-h optimal fermentation time. A composite of 0.1% nano-SiO₂ JKB05 improved the thermal stability, acid-base stability and ultraviolet resistance by 16%, 12%, and 38.9%, respectively, and nano-SiO₂ was added to the fermentation process. The best formula for the wettable powder was 35% kaolin, 4% polyethylene glycol, 8% Tween, and 2% humic acid. The following quality test results for the wettable powder were obtained: wetting time 87.0 s, suspension rate 80.33%, frequency of microbial contamination 0.08%, pH 7.2, fineness 95.8%, drying loss 1.47%, and storage stability ≥83.5%. A pot experiment revealed that the ability of JKB05 to prevent fungal infections on P. chinense increased considerably and achieved levels of control as high as 94%. The use of nanomaterials significantly improved the ability of biocontrol bacteria to control this disease.

• Journal of Veterinary Science
• /
• v.21 no.2
• /
• pp.24.1-24.11
• /
• 2020

The pandemic of avian influenza viruses (AIVs) in Asia has caused enormous economic loss in poultry industry and human health threat, especially clade 2.3.4.4 H5 and H7 subtypes in recent years. The endemic chicken H6 virus in Taiwan has also brought about human and dog infections. Since wild waterfowls is the major AIV reservoir, it is important to monitor the diversified subtypes in wildfowl flocks in early stage to prevent viral reassortment and transmission. To develop a more efficient and sensitive approach is a key issue in epidemic control. In this study, we integrate multiplex reverse transcription recombinase polymerase amplification (RT-RPA) and capillary electrophoresis (CE) for high-throughput detection and differentiation of AIVs in wild waterfowls in Taiwan. Four viral genes were detected simultaneously, including nucleoprotein (NP) gene of all AIVs, hemagglutinin (HA) gene of clade 2.3.4.4 H5, H6 and H7 subtypes. The detection limit of the developed detection system could achieve as low as one copy number for each of the four viral gene targets. Sixty wild waterfowl field samples were tested and all of the four gene signals were unambiguously identified within 6 h, including the initial sample processing and the final CE data analysis. The results indicated that multiplex RT-RPA combined with CE was an excellent alternative for instant simultaneous AIV detection and subtype differentiation. The high efficiency and sensitivity of the proposed method could greatly assist in wild bird monitoring and epidemic control of poultry.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.9-17
• /
• 2023

In this paper, we propose a one-class vibration anomaly detection system for bearing defect diagnosis. In order to reduce the economic and time loss caused by bearing failure, an accurate defect diagnosis system is essential, and deep learning-based defect diagnosis systems are widely studied to solve the problem. However, it is difficult to obtain abnormal data in the actual data collection environment for deep learning learning, which causes data bias. Therefore, a one-class classification method using only normal data is used. As a general method, the characteristics of vibration data are extracted by learning the compression and restoration process through AutoEncoder. Anomaly detection is performed by learning a one-class classifier with the extracted features. However, this method cannot efficiently extract the characteristics of the vibration data because it does not consider the frequency characteristics of the vibration data. To solve this problem, we propose an AutoEncoder model that considers the frequency characteristics of vibration data. As for classification performance, accuracy 0.910, precision 1.0, recall 0.820, and f1-score 0.901 were obtained. The network design considering the vibration characteristics confirmed better performance than existing methods.

• Journal of Animal Science and Technology
• /
• v.64 no.4
• /
• pp.603-620
• /
• 2022

Human activities have caused an increase in greenhouse gas emissions, resulting in climate change that affects many factors of human life including its effect on water and food quality in certain areas with implications for human health. CH₄ and N₂O are known as potent non-CO₂ GHGs. The livestock industry contributes to direct emissions of CH₄ (38.24%) and N₂O (6.70%) through enteric fermentation and manure treatment, as well as indirect N₂O emissions via NH₃ volatilization. NH₃ is also a secondary precursor of particulate matter. Several approaches have been proposed to address this issue, including dietary management, manure treatment, and the possibility of inhibitor usage. Inhibitors, including urease and nitrification inhibitors, are widely used in agricultural fields. The use of urease and nitrification inhibitors is known to be effective in reducing nitrogen loss from agricultural soil in the form of NH₃ and N₂O and can further reduce CH₄ as a side effect. However, the effectiveness of inhibitors in livestock manure systems has not yet been explored. This review discusses the potential of inhibitor usage, specifically of N-(n-butyl) thiophosphoric triamide, dicyandiamide, and 3,4-dimethylpyrazole phosphate, to reduce emissions from livestock manure. This review focuses on the application of inhibitors to manure, as well as the association of these inhibitors with health, toxicity, and economic benefits.

• Journal of Wetlands Research
• /
• v.24 no.2
• /
• pp.123-141
• /
• 2022

Wetland also known as "Jheelon" in Hindi language is one of the most important natural resources, contributing various economic and ecological benefits. The study gave a short review of the current status of Ramsar wetlands in India. The wildlife species, conservation measures, and their significance in Indian wetlands were also explored in this review paper. As of 2022, there are 49 Ramsar sites in India covering approximately 1,09363.6 km² of land. The largest Ramsar wetland is Sundarbans, while the smallest is Chandertal. It was found that preventing wetland loss is important even though studies about wetland degradation in various nations including India, caused directly by human activities is still limited. Since Monitoring and protecting natural wetlands, supporting scientific studies on preservation and restoration of wetlands, demand on imposing regulations for limiting pollutant discharges were recommended allowing researchers, policymakers, and practitioners to better maintain wetland and its ecosystem services.

• Computers and Concrete
• /
• v.31 no.3
• /
• pp.185-195
• /
• 2023

Antalya is located south part of minor Asia, one of the biggest cities in Türkiye. As a result of population growth and vast migration to Antalya, many parts of the city that were not suitable for construction due to its geological conditions have become urban areas, and most of these urban areas are full of poorly engineered buildings. Poor engineering has been combined with unplanned urbanization, that causes utter vulnerability to disasters in Antalya. When an earthquake-prone city, Antalya faces with an earthquake risk, fear arises in society. To overcome this problem, it has become necessary to investigate the building stock, expressed in hundreds of thousands, in a fast and reliable way and then perform an urban transformation to create the perception of structural safety. However, the excessive building stock, labor, and economic problems made the implementation stage challenging and revealed the necessity of finding alternative solutions in the field. The present study presents a novel approach for assessment and model based on a rapid visual inspection method to transform areas under earthquake risk in Türkiye. The approach aimed to rank the interventions for decision-making mechanisms by making comparisons in the scale hierarchy. In the present study, to investigate the proposed approach, over 26,000 buildings were examined in Antalya, which is the fifth largest city in Türkiye that has a population of over 2.5 Million. In the results of the study, the risk classification was defined in the framework of building, block, street, neighborhood, and district scales.

• Journal of Industrial Convergence
• /
• v.21 no.1
• /
• pp.87-93
• /
• 2023

Determining the timing of buying and selling in stock investment is one of the most important factors to increase the return on stock investment. Buying low and selling high makes a profit, but buying high and selling low makes a loss. The price is determined by the quantity of buying and selling, which determines the price of a stock, and buying and selling is also related to corporate performance and economic indicators. The fear and greed index provided by CNN uses seven factors, and by assigning weights to each element, the weighted average defined as greed and fear is calculated on a scale between 0 and 100 and published every day. When the index is close to 0, the stock market sentiment is fearful, and when the index is close to 100, it is greedy. Therefore, we analyze the trading criteria that generate the maximum return when buying and selling the US S&P 500 index according to CNN fear and greed index, suggesting the optimal buying and selling timing to suggest a way to increase the return on stock investment.

• Korean Journal of Veterinary Service
• /
• v.45 no.4
• /
• pp.293-304
• /
• 2022

Among several diseases of calves, diarrhea is the most prevalent disease and has been a major cause of economic loss to the cattle industry. The main etiologic agents of diarrhea in calves are bacteria, viruses, and protozoa, but non-infectious factors including foreign bodies obstruction in the digestive system also focused as the cause of calf diarrhea in the recent days. Because there is still limited information for foreign body-related diarrhea in calves, especially in Hanwoo, the present retrospective study reviewed the medical records for diarrheic calves with foreign body in the digestive system (n=32). The morbidity was determined as 3.03% and more than half of them presented the acidosis, hyponatremia, and azotemia. The mortality in laparotomy-operated calves to remove foreign bodies or in non-operated ones was 28% or 85.7%, respectively, implied the importance of aggressive decision for laparotomy when the foreign bodies were determined in the digestive system in diarrheic calves. During laparotomy, trichobezoars (hair balls) and hays were the main foreign bodies and prevalently placed in the abomasum. In the trials to predict prognosis by several clinical factors, the time for laparotomy over 2 days after first diagnosis, acidosis, and foreign body in the abomasum were highly associated with mortality. Therefore, we believe that prompt surgical procedure (laparotomy) is necessary upon obstruction in the digestive system by foreign bodies is tentatively diagnosed in the diarrheic calf. In addition, when differential diagnosis list is made, foreign body-related diarrhea is necessary to be included in case of diarrheic calf.