• Journal of The Korean Association of Information Education
• /
• v.11 no.4
• /
• pp.397-406
• /
• 2007

There are lots of studies going on about internet addiction in a point of view of psychology and sociology. The purpose of this paper is to examine the relation between the internet addiction and the services and functions of internet softwares in a point of view of developing softwares. For this, the first goal is to see the type of the software that used most by elementary school students addicted to internet, and the second is to examine the risk factors of addiction and their priority orders in the services and functions offered by that kind of software. The results of this paper can give instructive informations to every children who use internet and their parents and teachers and software developers.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.63-71
• /
• 2024

Deep reinforcement learning (RL) significantly influences autonomous vehicle development by optimizing decision-making and adaptation to complex driving environments through simulation-based training. In deep RL, an activation function is used, and various activation functions have been proposed, but their performance varies greatly depending on the application environment. Therefore, finding the optimal activation function according to the environment is important for effective learning. In this paper, we analyzed nine commonly used activation functions for RL to compare and evaluate which activation function is most effective when using deep RL for autonomous vehicles to learn highway merging. To do this, we built a performance evaluation environment and compared the average reward of each activation function. The results showed that the highest reward was achieved using Mish, and the lowest using SELU. The difference in reward between the two activation functions was 10.3%.

• Asia pacific journal of information systems
• /
• v.6 no.2
• /
• pp.107-124
• /
• 1996

This research studied future directions of Internet technology toward supporting group decision making. From the previous research, this study classified requirements of group decision support systems into three categories which are information transfer, information provision, and communication control. For each of the category, this study analyzed the limits of current Internet functions. Next, this research discussed technological solutions, for each of the OSI 7 layers, toward supporting group decision making. Additional functions in Internet which are required for group supporting are tracing communications, application dependent coding, selection of communication modes, and security handling. For high speed data communication in Internet, this research discussed the potential of cell-switching technology for the lower level link in Internet. The conclusions of this research can be used for designing future group decision support systems and development of Internet.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.17 no.4
• /
• pp.339-348
• /
• 1999

The information & Communication industry including internet is rapidly developing and expanding, which integrates our living space and provides diversity. Internet provides users with an variety of real-time information through networking. Also the functions and services of Geographic Information Systems are on a changing trend providing services for various organizations and users dispersed in different networks. It is necessary to understand that GIS is available not only on a desktop and server, but in any place where the network is connected using the web. Recently, Internet GIS for the search and subscription of spatial informations through the internet is receiving an active research field. So. this study aims to apply the Gas Disaster Management to the internet and develop the internet GIS techniques which make an effective utilization of GIS functions using MapObjects IMS, SDE, and Oracle.

• Journal of Internet Computing and Services
• /
• v.8 no.1
• /
• pp.125-132
• /
• 2007

This paper presents an approach to detect premature ventricular contractions(PVC) using the neural network with weighted fuzzy membership functions(NEWFM), NEWFM classifies normal and PVC beats by the trained weighted fuzzy membership functions using wavelet transformed coefficients extracted from the MIT-BIH PVC database. The eight most important coefficients of d3 and d4 are selected by the non-overlap area distribution measurement method. The selected 8 coefficients are used for 3 data sets showing reliable accuracy rates 99,80%, 99,21%, and 98.78%, respectively, which means the selected input features are less dependent to the data sets. The ECG signal segments and fuzzy membership functions of the 8 coefficients enable input features to interpret explicitly.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.63-68
• /
• 2022

Autonomous driving technology has recently made great progress with the introduction of deep reinforcement learning. In order to effectively use deep reinforcement learning, it is important to select the appropriate activation function. In the meantime, many activation functions have been presented, but they show different performance depending on the environment to be applied. This paper compares and evaluates the performance of 12 activation functions to see which activation functions are effective when using reinforcement learning to learn autonomous driving on highways. To this end, a performance evaluation method was presented and the average reward value of each activation function was compared. As a result, when using GELU, the highest average reward could be obtained, and SiLU showed the lowest performance. The average reward difference between the two activation functions was 20%.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.1
• /
• pp.136-141
• /
• 2022

A very complex task in deep learning such as image classification must be solved with the help of neural networks and activation functions. The backpropagation algorithm advances backward from the output layer towards the input layer, the gradients often get smaller and smaller and approach zero which eventually leaves the weights of the initial or lower layers nearly unchanged, as a result, the gradient descent never converges to the optimum. We propose a two-factor non-saturating activation functions known as Bea-Mish for machine learning applications in deep neural networks. Our method uses two factors, beta (𝛽) and alpha (𝛼), to normalize the area below the boundary in the Mish activation function and we regard these elements as Bea. Bea-Mish provide a clear understanding of the behaviors and conditions governing this regularization term can lead to a more principled approach for constructing better performing activation functions. We evaluate Bea-Mish results against Mish and Swish activation functions in various models and data sets. Empirical results show that our approach (Bea-Mish) outperforms native Mish using SqueezeNet backbone with an average precision (AP50val) of 2.51% in CIFAR-10 and top-1accuracy in ResNet-50 on ImageNet-1k. shows an improvement of 1.20%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.79-84
• /
• 2023

Apache Spark, which provides the fastest processing speed among recent distributed and parallel processing technologies, provides real-time functions and machine learning functions. Although official documentation guides for these functions are provided, a method for fusion of functions to predict a specific value in real time is not provided. Therefore, in this paper, we conducted a study to predict the value of data in real time by fusion of these functions. The overall configuration is collected by downloading stock price data provided by the Python programming language. And it creates a model of regression analysis through the machine learning function, and predicts the adjusted closing price among the stock price data in real time by fusing the real-time streaming function with the machine learning function.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.260-263
• /
• 2003

This paper has developed the computer integration manufacturing system and Internet based tele-operations. The functions of CIMS include production planing, material requirement planning, work order generation, process control, quality control, shipping planning, warehouse and inventory management and material cost accounting.[1] In this paper focuses on the automatic warehouse control and inventory management by developing the information system as well as the Internet-based integration. The system overview is divided into three parts, the mechanical system, the computer and developed software to control and manage the information and the communication system. The mechanical system consists of the warehouse machine and forklift mobile robot controlled by programmable logic controller (PLC). The computer works on many functions such as control station interfaces with PLC, managing database and inventory, and Internet server to broadcast the inventory database to users via World Wide Web and monitoring the operation on web camera. Our scheme the inventory database can be checked easily anywhere and anytime when the users connect to the Internet. In this article, the lead-time and inventory level can be reduced therefore the holding cost and operating time is also decreased.

• Korean Management Science Review
• /
• v.17 no.3
• /
• pp.181-201
• /
• 2000

This paper performs a case study on an Internet business networking company, oneQ.com. We define the functions of Internet business networker and discuss its characteristics such as network effect, lock-in effect, and increasing returns etc. Through reviewing the business models, strategies, and implemented technologies of the oneQ.com, we investigate the applicability and effectiveness of the Internet business networker as well as its research implications.