• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.337-344
• /
• 2024

It is a complex project to construct the standard system of sports events. Sports events standard system covers from the implementation plan to the evaluation work after the smooth implementation of sports events, involving many links. Large-scale sports events have extremely high media value. However, the successful organization and operation of large-scale sports events face many problems to be overcome, especially in terms of event safety. Although the organizers and organizers of large-scale events have invested many resources for the safe holding of sports events, violence similar to "football hooligans" in Europe is endless. At present, compared with Western countries, the standardization of sports events in China is low, and there is a problem of a late start and huge difference with Western developed countries. Knowing the construction of the standardization system's situation in China, we have summarized the data related to 15 sports events held in Chengdu is the last 5 years. By analyzing the problems in the process of holding these 15 events and the reflections of participants on the experience of sports events, the problems in the development of the standard system of sports events are discussed in depth. The final conclusion is that the system structure of China's sports events is not so good and athletes have a poor experience. China's sports event system still has many problems. Finally, we built a sports event standardization model using Internet of Things, and after a practical test we found that it has a good effect. Finally, we combined the current situation of sports event standardization system in China and put forward the following suggestions: laws and regulations related to the standard system of sports events must be formulated at the national level. The implementation level must strengthen the degree of integration of sports events and technology. To improve the quality of human resources in the management of sports events. The article puts forward targeted solutions, which play a great role in promoting the perfection and completeness of China's standard system for sports events. At the same time, it also promotes economic development and improves China's international status.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1706-1725
• /
• 2024

The unique U-shaped structure of U-Net network makes it achieve good performance in image segmentation. This network is a lightweight network with a small number of parameters for small image segmentation datasets. However, when the medical image to be segmented contains a lot of detailed information, the segmentation results cannot fully meet the actual requirements. In order to achieve higher accuracy of medical image segmentation, a novel improved U-Net network architecture called multi-scale encoder-decoder U-Net+ (MEDU-Net+) is proposed in this paper. We design the GoogLeNet for achieving more information at the encoder of the proposed MEDU-Net+, and present the multi-scale feature extraction for fusing semantic information of different scales in the encoder and decoder. Meanwhile, we also introduce the layer-by-layer skip connection to connect the information of each layer, so that there is no need to encode the last layer and return the information. The proposed MEDU-Net+ divides the unknown depth network into each part of deconvolution layer to replace the direct connection of the encoder and decoder in U-Net. In addition, a new combined loss function is proposed to extract more edge information by combining the advantages of the generalized dice and the focal loss functions. Finally, we validate our proposed MEDU-Net+ MEDU-Net+ and other classic medical image segmentation networks on three medical image datasets. The experimental results show that our proposed MEDU-Net+ has prominent superior performance compared with other medical image segmentation networks.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.134-146
• /
• 2024

This study introduces and experimentally validates a novel approach that combines Instruction fine-tuning and Low-Rank Adaptation (LoRA) fine-tuning to optimize the performance of Large Language Models (LLMs). These models have become revolutionary tools in natural language processing, showing remarkable performance across diverse application areas. However, optimizing their performance for specific domains necessitates fine-tuning of the base models (FMs), which is often limited by challenges such as data complexity and resource costs. The proposed approach aims to overcome these limitations by enhancing the performance of LLMs, particularly in the analysis precision and efficiency of national Research and Development (R&D) data. The study provides theoretical foundations and technical implementations of Instruction fine-tuning and LoRA fine-tuning. Through rigorous experimental validation, it is demonstrated that the proposed method significantly improves the precision and efficiency of data analysis, outperforming traditional fine-tuning methods. This enhancement is not only beneficial for national R&D data but also suggests potential applicability in various other data-centric domains, such as medical data analysis, financial forecasting, and educational assessments. The findings highlight the method's broad utility and significant contribution to advancing data analysis techniques in specialized knowledge domains, offering new possibilities for leveraging LLMs in complex and resource-intensive tasks. This research underscores the transformative potential of combining Instruction fine-tuning with LoRA fine-tuning to achieve superior performance in diverse applications, paving the way for more efficient and effective utilization of LLMs in both academic and industrial settings.

• Journal of ILASS-Korea
• /
• v.29 no.3
• /
• pp.105-111
• /
• 2024

Although the classic Kelvin-Helmholtz model of aerodynamically driven jet breakup(primary breakup) has been widely employed in engine CFD codes for the last three decades, the model is not generally predictive. This lack of predictive capability points to the likelihood of an incorrect physical basis for the model formulation. As such, there have been more recent spray-model development efforts that incorporate additional sources of jet instability and breakup, including nozzle-generated turbulence and cavitation but predictive capabilities have remained elusive. Meanwhile, it should be noted that modern combustors increasingly operate under low-temperature combustion(LTC) conditions, where ambient densities and aerodynamic forces are much lower than under classical operating conditions. Therefore, further consideration of physical model formulation is needed. The previous literature introduced a new primary atomization modeling approach premised on experimental measurements by the Faeth group, which demonstrate that breakup is governed by nozzle-generated turbulence under low ambient density conditions. In this new modeling approach, termed the KH-Faeth model, two different primary breakup models are combined to allow the hybrid breakup modeling approach, i.e. Kelvin- Helmholtz instability breakup mechanism and turbulence-induced breakup are competed via dominant breakup rate evaluation. In the current work, we implement this hybrid KH-Faeth model within the open-source CFD framework OpenFOAM and validate the model against detailed drop sizing measurements stemming from collaborative experiments between Georgia Tech and Argonne National Laboratory.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.687-692
• /
• 2024

Recently, electric skateboards have been used as a means of personal transportation due to their convenience and simplicity of operation, but the conventional skateboards driven by timing belts or hub motors have disadvantages such as low driving torque, high current and vibration. Therefore, in this paper, we propose a new type of electric skateboard that can run at high speeds for long periods of time so that it can be used as a auxiliary means of transportation. The planetary gear and motor unit are combined and installed inside one drive wheel, and power is supplied to the wheel through the integrated driving unit to prevent high currents and enable high-speed driving. First, the allowable current and running speed of the electric skateboard were set for efficient personal transportation and the appropriate reduction ratio, modules, and planetary gear dimensions were determined by comparing the torque required for the wheel axis and the maximum output torque of the motor. Additionally, an appropriate suspension device was added to reduce driving vibration for user convenience, and the feasibility of the proposed in-wheel gearbox was experimentally verified through fabrication.

• Convergence Security Journal
• /
• v.21 no.4
• /
• pp.49-57
• /
• 2021

The 4th industrial revolution will develop the network environment of future warfare through the increase of IoT devices, individual warrior platforms, the operation of manned and unmanned weapon systems, intelligent command post. They are leading to the weapon system combined with hundreds or thousands of sensors will be used for surveillance and reconnaissance, electronic warfare, and deception operations on the battlefield. This change to the environment brings superiority in operational performance on the battlefield, but if the weapon system is exposed to the outside, it will lead to fatal results. In this paper, we analyze the network environment that is changing in the future warfare environment, focusing on the currently used network. In addition, it considers information security issues that must correspond to the evolving network technology and suggests various security measures to suggest the direction our military should take in the future.

• Geophysics and Geophysical Exploration
• /
• v.8 no.4
• /
• pp.270-279
• /
• 2005

Under the research project supported by Japanese Ministry of Education, Culture, Sports, Science and Technology (MEXT), we have conducted the development of GPR systems for landmine detection. Until 2005, we have finished development of two prototype GPR systems, namely ALIS (Advanced Landmine Imaging System) and SAR-GPR (Synthetic Aperture Radar-Ground Penetrating Radar). ALIS is a novel landmine detection sensor system combined with a metal detector and GPR. This is a hand-held equipment, which has a sensor position tracking system, and can visualize the sensor output in real time. In order to achieve the sensor tracking system, ALIS needs only one CCD camera attached on the sensor handle. The CCD image is superimposed with the GPR and metal detector signal, and the detection and identification of buried targets is quite easy and reliable. Field evaluation test of ALIS was conducted in December 2004 in Afghanistan, and we demonstrated that it can detect buried antipersonnel landmines, and can also discriminate metal fragments from landmines. SAR-GPR (Synthetic Aperture Radar-Ground Penetrating Radar) is a machine mounted sensor system composed of B GPR and a metal detector. The GPR employs an array antenna for advanced signal processing for better subsurface imaging. SAR-GPR combined with synthetic aperture radar algorithm, can suppress clutter and can image buried objects in strongly inhomogeneous material. SAR-GPR is a stepped frequency radar system, whose RF component is a newly developed compact vector network analyzers. The size of the system is 30cm x 30cm x 30 cm, composed from six Vivaldi antennas and three vector network analyzers. The weight of the system is 17 kg, and it can be mounted on a robotic arm on a small unmanned vehicle. The field test of this system was carried out in March 2005 in Japan.

• Asia pacific journal of information systems
• /
• v.17 no.4
• /
• pp.187-206
• /
• 2007

The development of computer and information technology has been combined with the information superhighway internet infrastructure, so information widely spreads not only in special fields but also in the daily lives of people. Information ubiquity influences the traditional way of transaction, and leads a new E-commerce which distinguishes from the existing E-commerce. Not only goods as physical but also service as non-physical come into E-commerce. As the scale of E-Commerce is being enlarged as well. It keeps people from finding information they want. Recommender systems are now becoming the main tools for E-Commerce to mitigate the information overload. Recommender systems can be defined as systems for suggesting some Items(goods or service) considering customers' interests or tastes. They are being used by E-commerce web sites to suggest products to their customers who want to find something for them and to provide them with information to help them decide which to purchase. There are several approaches of recommending goods to customer in recommender system but in this study, the main subject is focused on collaborative filtering technique. This study presents a possibility of pre-evaluation for the prediction performance of customer's preference in collaborative filtering before the process of customer's preference prediction. Pre-evaluation for the prediction performance of each customer having low performance is classified by using the statistical features of ratings rated by each customer is conducted before the prediction process. In this study, MovieLens 100K dataset is used to analyze the accuracy of classification. The classification criteria are set by using the training sets divided 80% from the 100K dataset. In the process of classification, the customers are divided into two groups, classified group and non classified group. To compare the prediction performance of classified group and non classified group, the prediction process runs the 20% test set through the Neighborhood Based Collaborative Filtering Algorithm and Correspondence Mean Algorithm. The prediction errors from those prediction algorithm are allocated to each customer and compared with each user's error. Research hypothesis : Two research hypotheses are formulated in this study to test the accuracy of the classification criterion as follows. Hypothesis 1: The estimation accuracy of groups classified according to the standard deviation of each user's ratings has significant difference. To test the Hypothesis 1, the standard deviation is calculated for each user in training set which is divided 80% from MovieLens 100K dataset. Four groups are classified according to the quartile of the each user's standard deviations. It is compared to test the estimation errors of each group which results from test set are significantly different. Hypothesis 2: The estimation accuracy of groups that are classified according to the distribution of each user's ratings have significant differences. To test the Hypothesis 2, the distributions of each user's ratings are compared with the distribution of ratings of all customers in training set which is divided 80% from MovieLens 100K dataset. It assumes that the customers whose ratings' distribution are different from that of all customers would have low performance, so six types of different distributions are set to be compared. The test groups are classified into fit group or non-fit group according to the each type of different distribution assumed. The degrees in accordance with each type of distribution and each customer's distributions are tested by the test of ${\chi}^2$ goodness-of-fit and classified two groups for testing the difference of the mean of errors. Also, the degree of goodness-of-fit with the distribution of each user's ratings and the average distribution of the ratings in the training set are closely related to the prediction errors from those prediction algorithms. Through this study, the customers who have lower performance of prediction than the rest in the system are classified by those two criteria, which are set by statistical features of customers ratings in the training set, before the prediction process.

• Journal of Bio-Environment Control
• /
• v.27 no.1
• /
• pp.34-39
• /
• 2018

This research was conducted to estimate moisture content in cucurbitaceae seedlings, such as cucumber and watermelon, using hyperspectral imagery. Using a hyperspectral image acquisition system, the reflectance of leaf area of cucumber and watermelon seedlings was calculated after providing water stress. Then, moisture content in each seedling was measured by using a dry oven. Finally, using reflectance and moisture content, the moisture content estimation models were developed by PLSR analysis. After developing the estimation models, performance of the cucumber showed 0.73 of $R^2$, 1.45% of RMSE, and 1.58% of RE. Performance of the watermelon showed 0.66 of $R^2$, 1.06% of RMSE, and 1.14% of RE. The model performed slightly better after removing one sample from cucumber seedlings as outlier and unnecessary. Hence, the performance of new model for cucumber seedlings showed 0.79 of $R^2$, 1.10% of RMSE, and 1.20% of RE. The model performance combined with all samples showed 0.67 of $R^2$, 1.26% of RMSE, and 1.36% of RE. The model of cucumber showed better performance than the model of watermelon. This is because variables of cucumber are consisted of widely distributed variation, and it affected the performance. Further, accuracy and precision of the cucumber model were increased when an insignificant sample was eliminated from the dataset. Finally, it is considered that both models can be significantly used to estimate moisture content, as gradients of trend line are almost same and intersected. It is considered that the accuracy and precision of the estimating models possibly can be improved, if the models are constructed by using variables with widely distributed variation. The improved models will be utilized as the basis for developing low-priced sensors.

• Ocean Science Journal
• /
• v.40 no.1
• /
• pp.25-44
• /
• 2005

Long-term, continuous, and real-time ocean monitoring has been undertaken in order to evaluate various oceanographic phenomena and processes in the East/Japan Sea. Recent technical advances combined with our concerted efforts have allowed us to establish a real-time monitoring system and to accumulate considerable knowledge on what has been taking place in water properties, current systems, and circulation in the East Sea. We have obtained information on volume transport across the Korea Strait through cable voltage measurements and continuous temperature and salinity profile data from ARGO floats placed throughout entire East Sea since 1997. These ARGO float data have been utilized to estimate deep current, inertial kinetic energy, and changes in water mass, especially in the northern East Sea. We have also developed the East Sea Real-time Ocean Buoy (ESROB) in coastal regions and made continual improvements till it has evolved into the most up-to-date and effective monitoring system as a result of remarkable technical progress in data communication systems. Atmospheric and oceanic measurements by ESROB have contributed to the recognition of coastal wind variability, current fluctuations, and internal waves near and off the eastern coast of Korea. Long-tenn current meter moorings have been in operation since 1996 between Ulleungdo and Dokdo to monitor the interbasin deep water exchanges between the Japanese and Ulleung Basins. In addition, remotely sensed satellite data could facilitate the investigation of atmospheric and oceanic surface conditions such as sea surface temperature (SST), sea surface height, near-surface winds, oceanic color, surface roughness, and so on. These satellite data revealed surface frontal structures with a fairly good spatial resolution, seasonal cycle of SST, atmospheric wind forcing, geostrophic current anomalies, and biogeochemical processes associated with physical forcing and processes. Since the East Sea has been recognized as a natural laboratory for global oceanic changes and a clue to abrupt climate change, we aim at constructing a 4-D continuous real-time monitoring system, over a decade at least, using the most advanced techniques to understand a variety of oceanic processes in the East Sea.