• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1530-1544
• /
• 2023

Data monitoring is an important foundation of modern science. In most cases, the monitoring data is time-series data, which has high application value. The deep learning algorithm has a strong nonlinear fitting capability, which enables the recognition of time series by capturing anomalous information in time series. At present, the research of time series recognition based on deep learning is especially important for data monitoring. Deep learning algorithms require a large amount of data for training. However, abnormal sample is a small sample in time series, which means the number of abnormal time series can seriously affect the accuracy of recognition algorithm because of class imbalance. In order to increase the number of abnormal sample, a data augmentation method called GANBATS (GAN-based Bi-LSTM and Attention for Time Series) is proposed. In GANBATS, Bi-LSTM is introduced to extract the timing features and then transfer features to the generator network of GANBATS.GANBATS also modifies the discriminator network by adding an attention mechanism to achieve global attention for time series. At the end of discriminator, GANBATS is adding averagepooling layer, which merges temporal features to boost the operational efficiency. In this paper, four time series datasets and five data augmentation algorithms are used for comparison experiments. The generated data are measured by PRD(Percent Root Mean Square Difference) and DTW(Dynamic Time Warping). The experimental results show that GANBATS reduces up to 26.22 in PRD metric and 9.45 in DTW metric. In addition, this paper uses different algorithms to reconstruct the datasets and compare them by classification accuracy. The classification accuracy is improved by 6.44%-12.96% on four time series datasets.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.1
• /
• pp.27-39
• /
• 2023

This study was to quantitatively evaluate periodic and maximum energy loads for broiler-standard design models by the Ministry of Agriculture, Food and Rural Affairs (2016). Building energy simulation method was used to compute heating and cooling loads of the designed broiler houses according to regional locations and insulation characteristics of wall and roof. It considered sensible and latent heat generation from broilers, dynamic operation of ventilation system according to environment variations. It was found that variation of periodic heating loads was relatively higher than that of periodic cooling loads according to thickness changes of wall and roof. Assuming that broiler was raised at every even-month, periodic heating and cooling loads were 6 and 18% lower, respectively than odd-month raising condition. When recommendation rules of insulation characteristics (wall and roof thickness) by the Ministry of Land, Infrastructure and Transport was adopted, periodic heating load of Jeju-si was 20.3% higher than national average values. Based on the BES computed periodic and maximum energy loads under the designed experimental condition, these results can contribute to reestablishing standard design of broiler houses, especially for insulation characteristics, and designing management strategies for efficient energy uses.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.3D
• /
• pp.303-311
• /
• 2010

There have been various forms of systems such as a digital speedometer or a black box etc. to meet the social requirement for reducing traffic accidents and safe driving. However that systems are based on after-accident vehicle data, there is limit to prevent the accident before. So in our previous research, by storing, analyzing the Vehicle-dynamic information coming from driver's behavior, we are developing the decision-device which could provide driver with Alerting-Information in real-time to enhance the driver's safety drive. but the performance valuation is not yet executed. Finally, this study developed positional recognition system by using the DGPS for pre-developed risky driving decision device. The result of test analyzed with the same that the aggregated vehicle dynamics data in DGPS and dangerous risky driving decision device. If the performance of risky driving decision device is verified by precisely positional recognition system, the risky driving management of vehicle would be effected.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.6B
• /
• pp.533-540
• /
• 2010

Recently management of vegetation distributed in the watercourse is very important not only for safety but also for river restoration. In general, vegetations in the watercourse increase hydraulic resistance and accordingly decrease conveyance capacity which may yield levee overflow. This paper simulates water level rise using 1D and 2D hydro dynamic model to check the possibility of overflow in downstream of the Soyang Reservoir by assigning different roughness coefficient corresponding to different types of vegetation. In this study, 3 different vegetation types of tree, shrub, and main channel were considered and corresponding Manning's roughness coefficient n was assigned based on the vegetation map generated from the site investigation. As results, the water level raised about 0.1 to 0.7 m comparing with the case without considering vegetation and a proper measurements is necessary where overflow occurs due to low level levee.

• Steel and Composite Structures
• /
• v.48 no.1
• /
• pp.103-111
• /
• 2023

The caving property of top coal is a key factor to the success of top coal caving mining. The influence law of cyclic loading and unloading of hydraulic support on top coal caving is of great significance to improve the recovery rate of top coal. The similar simulation methods were used to study the dynamic evolution of the top coal cracks under the multi-cycle action of the support, and the parameters of top coal cracks were analyzed quantitatively in this paper. The results show that the top coal cracks can be divided into horizontal cracks and vertical cracks under the cyclic loading and unloading of the support. With the increase of the times of the support cycles loading and unloading, the load on the support decreases, the fractal dimension of the cracks increases, the number and total length of the top coal cracks increases, and the top coal caving is getting better. With the increase of the times of multi-cycle loading and unloading, the fractal dimension, total crack length and crack rate of top coal show a trend of rapid increase first and then increase slowly. Both the total length of the top coal cracks and the crack rate basically show linear growth with the change of the fractal dimension. The top coal caving can be well improved and the coal resource recovery rate increased through the multi-cycle loading and unloading.

• Genomics & Informatics
• /
• v.21 no.3
• /
• pp.30.1-30.13
• /
• 2023

Ephs belong to the largest family of receptor tyrosine kinase and are highly conserved both sequentially and structurally. The structural organization of Eph is similar to other receptor tyrosine kinases; constituting the extracellular ligand binding domain, a fibronectin domain followed by intracellular juxtamembrane kinase, and SAM domain. Eph binds to respective ephrin ligand, through the ligand binding domain and forms a tetrameric complex to activate the kinase domain. Eph-ephrin regulates many downstream pathways that lead to physiological events such as cell migration, proliferation, and growth. Therefore, considering the importance of Eph-ephrin class of protein in tumorigenesis, 7,620 clinically reported missense mutations belonging to the class of variables of unknown significance were retrieved from cBioPortal and evaluated for pathogenicity. Thirty-two mutations predicted to be pathogenic using SIFT, Polyphen-2, PROVEAN, SNPs&GO, PMut, iSTABLE, and PremPS in-silico tools were found located either in critical functional regions or encompassing interactions at the binding interface of Eph-ephrin. However, seven were reported in nonsmall cell lung cancer (NSCLC). Considering the relevance of receptor tyrosine kinases and Eph in NSCLC, these seven mutations were assessed for change in the folding pattern using molecular dynamic simulation. Structural alterations, stability, flexibility, compactness, and solvent-exposed area was observed in EphA3 Trp790Cys, EphA7 Leu749Phe, EphB1 Gly685Cys, EphB4 Val748Ala, and Ephrin A2 Trp112Cys. Hence, it can be concluded that the evaluated mutations have potential to alter the folding pattern and thus can be further validated by in-vitro, structural and in-vivo studies for clinical management.

• Journal of Distribution Science
• /
• v.21 no.12
• /
• pp.1-13
• /
• 2023

Purpose: the study aims to examine the impact of ICT on the formation of digital hubs in regions of Kazakhstan, specifically the influence of ICT costs on the level of innovation activity of enterprises, the number of its actors as legal entities by size and region, small and medium enterprises, universities and research and development organisations. Research design, data and methodology: the research methodology is based on the collection of secondary data from the official statistical yearbooks of the Bureau of National Statistics of the Republic of Kazakhstan and the use of quantitative methods, in particular, correlation analysis and multiple regression. Five indicators related to the formation of digital hubs in the regions of the country were selected. Results: the study revealed that ICT spending has an impact on the formation of digital hubs in regions, in particular on the development of the number of legitimate enterprises, SMEs and R&D organisations as actors in digital hubs. A positive dynamic in the growth of the number of actors is visible. However, the hypotheses on the impact of ICT costs on the number of universities and the level of innovation activity were not supported. Conclusions: based on the results of the study, recommendations such as government proposals on strategy development, funding projects of innovation and digital hubs, and business proposals on engaging local entities in digital transformation for the formation of digital hubs in the country's regions have been developed.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.81-89
• /
• 2023

Kubernetes is a representative open-source software for container orchestration, playing a crucial role in monitoring and managing resources allocated to containers. As container environments become prevalent, security threats targeting containers continue to rise, with resource exhaustion attacks being a prominent example. These attacks involve distributing malicious crypto-mining software in containerized form to hijack computing resources, thereby affecting the operation of the host and other containers that share resources. Previous research has focused on detecting resource depletion attacks, so technology to respond when attacks occur is lacking. This paper proposes a reinforcement learning-based dynamic resource management framework for detecting and responding to resource exhaustion attacks and malicious containers running in Kubernetes environments. To achieve this, we define the environment's state, actions, and rewards from the perspective of responding to resource exhaustion attacks using reinforcement learning. It is expected that the proposed methodology will contribute to establishing a robust defense against resource exhaustion attacks in container environments

• Information Systems Review
• /
• v.19 no.3
• /
• pp.179-199
• /
• 2017

As users' cross-over shopping behaviors become more popular, many studies have attempted to describe a theoretical mechanism in multichannel environments. Apart from explaining a simplified multichannel user behavior, relevant researchers must deeply understand the mechanism of users' cross-over shopping behavior, which cannot be discovered by employing either existing theories or traditional research methods. Thus, this study explores why, how, and when users conduct cross-over shopping behaviors in multichannel environments by employing a grounded theory approach. In this study, we have interviewed 25 participants who have prior experiences in cross-over shopping. By analyzing the interview manuscripts using the grounded theory approach, we have extracted 118 codes in the coding steps and ultimately presented 28 categories by incorporating similar concepts from those codes. In this qualitative grounded theory study, we have discussed why, how, and when users do cross-over shopping behavior based on our selected codes and categories as well as by listening to the stories of our interviewees. By grounding our proposed framework, which can capture both dynamic information search and purchasing behavior, this study provides an alternative research approach to explain user behavior, thereby bolstering our current understanding of the cross-over shopping behavior of users in multichannel environments.

• Journal of the Korean Society of Safety
• /
• v.39 no.1
• /
• pp.62-69
• /
• 2024

Ensuring swift on-site access to fire engines is crucial in preserving the golden time and minimizing damage. However, various mobility constraints in alleyways hinder the timely entry of fire engines to the fire scene, significantly impairing their initial response capabilities. Therefore, this study analyzed the significant mobility constraints of fire engines, focusing on Seoul, which has many old town areas. By leveraging survey responses from firefighting experts and actual observations, this study quantitatively assessed the frequency and severity of mobility constraint factors affecting the disaster responses of fire engines. Survey results revealed a consistent set of top five factors regarding the frequency and disturbance level, including illegally parked cars, narrow paths, motorcycles, poles, and awnings/banners. A comparison with actual road-view images showed notable consistency between the survey and observational results regarding the appearance frequency of mobility constraint factors in vulnerable areas in Seoul. Furthermore, the study emphasized the importance of tailored management strategies for each mobility constraint factor, considering its characteristics, such as dynamic or static. The findings of this study can serve as foundational data for creating more detailed fire safety maps and advancing technologies that monitor the mobility of fire engines through efficient vision-based inference using CCTVs in the future.