• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1778-1797
• /
• 2021

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

• The KIPS Transactions:PartD
• /
• v.14D no.2
• /
• pp.235-240
• /
• 2007

WebInterphone is a temporary composite word made with a Web and a Interphone, and the WebInterphone system has been developed as a new ahrdware/software solution under the .NET environment to remove the drawback of a Interphone which is used only if a host and a visitor should be in same place. In the WebInterphone system, a WebInterphone is connected to a home PC which is also connected to Internet such that a host and a visitor could have a real time communications even though nobody is at home. In this paper, the structure of the WebInterphone system and its operation process are discussed.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.1
• /
• pp.39-49
• /
• 2002

The purpose of this study was to characterize the effect of Net fashion value regarding to the factors of purchase-decision at internet shopping mall and the preference for fashion design. The subjects for this sample survey, were junior high school and university students who had dwelled at pusan and ulsan in south korea. This study had 824 samples of each aged from 13 to 24 who had purchasing ability of fashion apparels at the interned shopping mal1. The sampling data in this survey was analyzed by frequency analysis, factor analysis, T-test, LSD-test, MANOVA and ANOVA of SPSS WIN package. The results of this study was as follows; 1. It was proved that advertising, pursuit of services and products, pursuit of information were considered first from Net generations fashion value. Next things were perception of danger and pursuit of convenience. It was proved that they considered it important A/S, recall, exchange and post management. 2. It was proved that there was difference at the preference for fashion design of according to Net generations fashion value. Color was considered to be the most important one. 3. Men had higher political value than women and 1318 teenagers had higher fashion value than semi-adult. Under high school educational course Net generation had more theoretical value than above university educational course Net generation did. Also, with the factor of average monthly income, political value was considered to be the most important. People whose monthly expenditure on purchase was above 50,000 won had higher social value than people whose expenditure was under 50,000 won but under 50,000 won had higher political value than above 50,000 won did.

• Journal of Internet Computing and Services
• /
• v.25 no.2
• /
• pp.49-55
• /
• 2024

This paper proposes PredFeed Net, a neural network model that mimics the food distribution of fish farming experts. Unlike existing food distribution automation systems, PredFeed Net predicts food distribution by learning the food distribution patterns of experts. This has the advantage of being able to learn using only existing environmental data and food distribution records from food distribution experts, without the need to experiment by changing food distribution variables according to the environment in an actual aquarium. After completing training, PredFeed Net predicts the next food ration based on the current environment or fish condition. Prediction of feed ration is a necessary element for automating feed ration, and feed ration automation contributes to the development of modern fish farming such as smart aquaculture and aquaponics systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.126-146
• /
• 2024

Caladium bicolor is one of the most popular plants in Thailand. The original species of Caladium bicolor was found a hundred years ago. Until now, there are more than 500 species through multiplication. The classification of Caladium bicolor can be done by using its color and shape. This study aims to develop a model to classify Caladium bicolor using a transfer learning technique. This work also presents a proof of concept, GUI design, and web application deployment using the user-design-center method. We also evaluated the performance of the following pre-trained models in this work, and the results are as follow: 87.29% for AlexNet, 90.68% for GoogleNet, 93.59% for XceptionNet, 93.22% for MobileNetV2, 89.83% for RestNet18, 88.98% for RestNet50, 97.46% for RestNet101, and 94.92% for InceptionResNetV2. This work was implemented using MATLAB R2023a.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.9-16
• /
• 2020

In the Image processing and computer vision, the problem of reconstructing from one image to another or generating a new image has been steadily drawing attention as hardware advances. However, the problem of computer-generated images also continues to emerge when viewed with human eyes because it is not natural. Due to the recent active research in deep learning, image generating and improvement problem using it are also actively being studied, and among them, the network called Generative Adversarial Network(GAN) is doing well in the image generating. Various models of GAN have been presented since the proposed GAN, allowing for the generation of more natural images compared to the results of research in the image generating. Among them, pix2pix is a conditional GAN model, which is a general-purpose network that shows good performance in various datasets. pix2pix is based on U-Net, but there are many networks that show better performance among U-Net based networks. Therefore, in this study, images are generated by applying various networks to U-Net of pix2pix, and the results are compared and evaluated. The images generated through each network confirm that the pix2pix model with Attention, R2, and Attention-R2 networks shows better performance than the existing pix2pix model using U-Net, and check the limitations of the most powerful network. It is suggested as a future study.

• Journal of Information Technology Services
• /
• v.10 no.2
• /
• pp.75-94
• /
• 2011

The industrial ecosystem around the Internet services has been evolving since the Internet was first introduced. The Net Neutrality issue best represents the process of the evolution and presents an inevitable challenge that the industry should overcome. This paper deals with this structural change with the Two-Sided Market framework and provides a System Dynamics(SD) model to evaluate the economic implications of the net neutrality policy. In particular, our approach analyzes the policy impacts when two competing platforms (network providers) play a role of the platform in a typical two-sided market, which connects Content Providers(CPs) with users. Previous studies show that the indirect network externality between these two markets makes the entire system tip to one platform. When the multi-homing in the CP market is allowed as in our model, however, their argument may lose its validity. To examine the system behavior, conducted here is SD simulations of our model. The simulation results show that co-existence of the competing platforms persists with the network effects over a certain threshold. The net neutrality policy seems to lower the threshold based on our experimental outcomes.

• Journal of Korean Society for Quality Management
• /
• v.44 no.4
• /
• pp.869-881
• /
• 2016

Purpose: The objective of this study is to verify the economic validation of quality management integrated train freight car by analyzing economic evaluation indicators such as benefit and cost, net present value, and inter rate of return. Methods: First, we itemize benefit and cost field by reviewing literatures; Benefit consists of 1)Safety, 2)Operation, and 3)Maintenance; Cost consists of 1)Set-up fee, 2)Wireless internet fee, and 3)Cloud storage using fee. Second, based on these estimated values, we conduct an economic evaluation analysis. Among them, benefit and cost, net present value, and internal rate of return are selected. Results: As a result, all estimated values are highly over criterion of economic validity($$B/C{\geq}_-1$$, $$NPV{\geq}_-0$$, $$IRR{\geq}_-R$$); 1)benefit over cost ratio is 28.22, 2)Net present value is 8,121.66million KRW, and 3)Internal rate of return value is 2272%. Conclusion: The findings of this study will help making a decision when train industry adopts IoT technology for improving the effectiveness.

• Journal of the Korean Society of Costume
• /
• v.50 no.6
• /
• pp.21-31
• /
• 2000

The purpose of this study was to characterize the attitudes of Net generation customers toward purchasing fashion products or apparels through Cyber communication media. This study targeted 333 individuals aged from 14 to 24 purchasing fashion apparels through the Interned or PC communication. The data were analyzed by using frequency analysis, factor analysis, t-test, ANOVA by SASS package. The results of this study are as follows : 1. Fashion life-style of Net generation is classified into four groups - Fashion attached type, Web entertainment type, Web information type, Web media purchasing type. Net-Generation shows a little preference for brand. 2. As a result of the statistical analysis of each group's demographic variables, price is not so important when purchasing and according to the analysis of age, it proves that twenties are trendier than teenagers. 3. The most significant factor of information search is watching others' clothes and the most popular place for purchase is wholesale mall. Net-Generation has a little intention to purchase through Cyber communication media.