• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3507-3522
• /
• 2022

Model pruning methods have attracted huge attention owing to the increasing demand of deploying models on low-resource devices recently. Most existing methods use the weight norm of filters to represent their importance, and discard the ones with small value directly to achieve the pruning target, which ignores the contribution of the small norm filters. This is not only results in filter contribution waste, but also gives comparable performance to training with the random initialized weights [1]. In this paper, we point out that the small norm filters can harm the performance of the pruned model greatly, if they are discarded directly. Therefore, we propose a novel filter contribution recycle (FCR) method for structured model pruning to resolve the fore-mentioned problem. FCR collects and reassembles contribution from the small norm filters to obtain a mixed contribution collector, and then assigns the reassembled contribution to other filters with higher probability to be preserved. To achieve the target FLOPs, FCR also adopts a weight decay strategy for the small norm filters. To explore the effectiveness of our approach, extensive experiments are conducted on ImageNet2012 and CIFAR-10 datasets, and superior results are reported when comparing with other methods under the same or even more FLOPs reduction. In addition, our method is flexible to be combined with other different pruning criterions.

• Fourth Industrial Review
• /
• v.2 no.2
• /
• pp.11-23
• /
• 2022

Purpose - The ability to meet the high demand for education in Nigeria is lacking, making the region remain backwards in education. Given this reason, the study investigates the role of innovation capability in the relationship between intellectual capital and competitive advantage in tertiary institutions in Nigeria. Research design, data, and methodology - The study is cross-sectional research, a total of 427 questionnaires were administered to respondents. The study distributed its questionnaire across 12 faculties at the University of Ibadan using a random sampling technique. Data were analyzed using ADANCO 2.1.1. Result - The study reveals that human capital, structural capital, relational capital, and innovation capability positively affect competitive advantage. Innovation capability mediates the relationship between human capital and relational capital. However, structural capital was not mediated by innovation capability. Conclusion - The study concludes that intellectual capitals and innovation capability are crucial to maintaining a competitive advantage over their peers. Achieving more significant success in the variables mentioned earlier will help Nigeria's tertiary institutions compete locally and internationally.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2473-2489
• /
• 2022

Urban development has brought about the increasing saturation of urban traffic demand, and traffic congestion has become the primary problem in transportation. Roads are in a state of waiting in line or even congestion, which seriously affects people's enthusiasm and efficiency of travel. This paper mainly studies the discrete domain path planning method based on the flow data. Taking the traffic flow data based on the highway network structure as the research object, this paper uses the deep learning theory technology to complete the path weight determination process, optimizes the path planning algorithm, realizes the vehicle path planning application for the expressway, and carries on the deployment operation in the highway company. The path topology is constructed to transform the actual road information into abstract space that the machine can understand. An appropriate data structure is used for storage, and a path topology based on the modeling background of expressway is constructed to realize the mutual mapping between the two. Experiments show that the proposed method can further reduce the interpolation error, and the interpolation error in the case of random missing is smaller than that in the other two missing modes. In order to improve the real-time performance of vehicle path planning, the association features are selected, the path weights are calculated comprehensively, and the traditional path planning algorithm structure is optimized. It is of great significance for the sustainable development of cities.

• The Journal of Economics, Marketing and Management
• /
• v.11 no.4
• /
• pp.65-76
• /
• 2023

Purpose: It suggests that in order to compare economic development between large cities, this paper aims to exclude factors such as GDP, trade, manpower, R&D, then present newly an analysis of others (inflation, exports, middle-class, competitiveness, digital). Research design, data, and methodology: In the period of rapid digitalization of the world, we would like to deal with different analysis factors than before. This is because digitalization and prices have the greatest impact on the region in terms of national competitiveness. Random sampling was used as the sample size of this study to generate various values for the annual income of the middle class and the competitiveness index, and the analysis method was used. This is because the income of the middle class can lead the digitalization of the country and accelerate it to standardization. Results: Based on these analysis, it is necessary to reduce the inflation rate of digitalization, it is necessary to lower inflation rates. This can be more fundamental than interest rates. If the demand for digitalization is reduced, national competitiveness, national competitiveness will lower national competitiveness. By building a hub for middle class, you can reduce this inflation rate without China's oversupply. Conclusion: This is because it is difficult to maintain competitiveness through interest rate control, as prices rise, and inflation can become unstable. This study can seek digital acceptance by the middle class as a solution to problems like the regional economic confrontation of new globalization inflation environment.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.114-114
• /
• 2020

Water contamination in a water distribution network (WDN) is harmful since it directly induces the consumer's health problem and suspends water service in a wide area. Actions need to be taken rapidly to countermeasure a contamination event. A contaminant source ident ification (CSI) is an important initial step to mitigate the harmful event. Here, a CSI approach focused on determining the contaminant intrusion possible location and time (PLoT) is introduced. One of the methods to discover the PLoT is an inverse calculation to connect all the paths leading to the report specification of a sensor. A filtering procedure is then applied to narrow down the PLoT using the results from individual sensors. First, we spatially reduce the suspect intrusion points by locating the highly suspicious nodes that have similar intrusion time. Then, we narrow the possible intrusion time by matching the suspicious intrusion time to the reported information. Finally, a likelihood-score is estimated for each suspect. Another important aspect that needs to be considered in CSI is that there are inherent uncertainties, such as the variations in user demand and inaccuracy of sensor data. The uncertainties can lead to overlooking the real intrusion point and time. To reflect the uncertainties in the CSI process, the Monte-Carlo Simulation (MCS) is conducted to explore the ranges of PLoT. By analyzing all the accumulated scores through the random sets, a spread of contaminant intrusion PLoT can then be identified in the network.

• Journal of Wellbeing Management and Applied Psychology
• /
• v.7 no.1
• /
• pp.51-65
• /
• 2024

Purpose: This study is to propose the establishment and direction of a public health-medical cooperation system for rehabilitation medical services for people with physical and brain disabilities in Gangneung, Korea. Research design, data and methodology: The study focused on 30 individuals with these disabilities registered. Data was collected from December 20, 2021, to December 31, 2021, through structured surveys administered by researchers visiting disability-related facilities, utilizing convenience and random sampling methods. Descriptive statistics and cross-analysis were applied for analysis. Results: Specifically, among respondents with physical disabilities, a total of 20 needs were identified, with 'Visiting health services' (25.0%) and 'Oral health services' (20.0%) ranking highest. The survey results regarding visit-based rehabilitation services for disability support showed a high demand, emphasizing the necessity of service provision tailored to the needs of recipients, focusing on disability prevention, health management, and motor function recovery, rather than solely medical or therapeutic concepts. Conclusions: Gangwon National University Hospital, as the regional referral hospital in Gangwon, should collaborate with Gangwon Province Rehabilitation Hospital to provide prompt acute rehabilitation services. Moreover, cooperation and collaboration with Gangneung Asan Hospital, the tertiary hospital in the region, are essential to ensure continued acute and recovery phase rehabilitation therapy for a certain period in the Gangneung area.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.35-43
• /
• 2024

During the post-pandemic period, the interest in foreign language learning surged, leading to increased usage of language-learning apps. With the rising demand for these apps, analyzing app reviews becomes essential, as they provide valuable insights into user experiences and suggestions for improvement. This research focuses on extracting insights into users' opinions, sentiments, and overall satisfaction from reviews of HelloTalk, one of the most renowned language-learning apps. We employed topic modeling and emotion analysis approaches to analyze reviews collected from the Google Play Store. Several experiments were conducted to evaluate the performance of sentiment classification models with different settings. In addition, we identified dominant emotions and topics within the app reviews using feature importance analysis. The experimental results show that the Random Forest model with topics and emotions outperforms other approaches in accuracy, recall, and F1 score. The findings reveal that topics emphasizing language learning and community interactions, as well as the use of language learning tools and the learning experience, are prominent. Moreover, the emotions of 'admiration' and 'annoyance' emerge as significant factors across all models. This research highlights that incorporating emotion scores into the model and utilizing a broader range of emotion labels enhances model performance.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.4
• /
• pp.81-99
• /
• 2020

Origin-destination data have been collected and utilized for demand analysis and service design in various fields such as public transportation and traffic operation. As the utilization of big data becomes important, there are increasing needs to store raw origin-destination data for big data analysis. However, it is not practical to store and analyze the raw data for a long period of time since the size of the data increases by the power of the number of the collection points. To overcome this storage limitation and long-period pattern analysis, this study proposes a methodology for compression and origin-destination data analysis with the compressed data. The proposed methodology is applied to public transit data of Sejong and Seoul. We first measure the reconstruction error and the data size for each truncated matrix. Then, to determine a range of principal components for removing random data, we measure the level of the regularity based on covariance coefficients of the demand data reconstructed with each range of principal components. Based on the distribution of the covariance coefficients, we found the range of principal components that covers the regular demand. The ranges are determined as 1~60 and 1~80 for Sejong and Seoul respectively.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.655-667
• /
• 2023

Algal bloom outbreaks are frequently reported around the world, and serious water pollution problems arise every year in Korea. It is necessary to protect the aquatic ecosystem through continuous management and rapid response. Many studies using satellite images are being conducted to estimate the concentration of chlorophyll-a (Chl-a), an indicator of algal bloom occurrence. However, machine learning models have recently been used because it is difficult to accurately calculate Chl-a due to the spectral characteristics and atmospheric correction errors that change depending on the water system. It is necessary to consider the factors affecting algal bloom as well as the satellite spectral index. Therefore, this study constructed a dataset by considering water quality, hydrological and meteorological factors, and sentinel-2 images in combination. Representative ensemble models random forest and extreme gradient boosting (XGBoost) were used to predict the concentration of Chl-a in eight weirs located on the Nakdong river over the past five years. R-squared score (R²), root mean square errors (RMSE), and mean absolute errors (MAE) were used as model evaluation indicators, and it was confirmed that R² of XGBoost was 0.80, RMSE was 6.612, and MAE was 4.457. Shapley additive expansion analysis showed that water quality factors, suspended solids, biochemical oxygen demand, dissolved oxygen, and the band ratio using red edge bands were of high importance in both models. Various input data were confirmed to help improve model performance, and it seems that it can be applied to domestic and international algal bloom detection.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.67-83
• /
• 2018

The Korean film industry with significant increase every year exceeded the number of cumulative audiences of 200 million people in 2013 finally. However, starting from 2015 the Korean film industry entered a period of low growth and experienced a negative growth after all in 2016. To overcome such difficulty, stakeholders like production company, distribution company, multiplex have attempted to maximize the market returns using strategies of predicting change of market and of responding to such market change immediately. Since a film is classified as one of experiential products, it is not easy to predict a box office record and the initial number of audiences before the film is released. And also, the number of audiences fluctuates with a variety of factors after the film is released. So, the production company and distribution company try to be guaranteed the number of screens at the opining time of a newly released by multiplex chains. However, the multiplex chains tend to open the screening schedule during only a week and then determine the number of screening of the forthcoming week based on the box office record and the evaluation of audiences. Many previous researches have conducted to deal with the prediction of box office records of films. In the early stage, the researches attempted to identify factors affecting the box office record. And nowadays, many studies have tried to apply various analytic techniques to the factors identified previously in order to improve the accuracy of prediction and to explain the effect of each factor instead of identifying new factors affecting the box office record. However, most of previous researches have limitations in that they used the total number of audiences from the opening to the end as a target variable, and this makes it difficult to predict and respond to the demand of market which changes dynamically. Therefore, the purpose of this study is to predict the weekly number of audiences of a newly released film so that the stakeholder can flexibly and elastically respond to the change of the number of audiences in the film. To that end, we considered the factors used in the previous studies affecting box office and developed new factors not used in previous studies such as the order of opening of movies, dynamics of sales. Along with the comprehensive factors, we used the machine learning method such as Random Forest, Multi Layer Perception, Support Vector Machine, and Naive Bays, to predict the number of cumulative visitors from the first week after a film release to the third week. At the point of the first and the second week, we predicted the cumulative number of visitors of the forthcoming week for a released film. And at the point of the third week, we predict the total number of visitors of the film. In addition, we predicted the total number of cumulative visitors also at the point of the both first week and second week using the same factors. As a result, we found the accuracy of predicting the number of visitors at the forthcoming week was higher than that of predicting the total number of them in all of three weeks, and also the accuracy of the Random Forest was the highest among the machine learning methods we used. This study has implications in that this study 1) considered various factors comprehensively which affect the box office record and merely addressed by other previous researches such as the weekly rating of audiences after release, the weekly rank of the film after release, and the weekly sales share after release, and 2) tried to predict and respond to the demand of market which changes dynamically by suggesting models which predicts the weekly number of audiences of newly released films so that the stakeholders can flexibly and elastically respond to the change of the number of audiences in the film.