• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.808-826
• /
• 2017

Most of conventional DSS's(Digital Signage Systems) have been built based on LAMP framework. Recent researches have shown that MEAN or MERN stack framework is simpler, more flexible, faster and more suitable for web-based application than LAMP stack framework. In this paper, we propose a design and implementation of MEARN (ME(A+R)N) stack-based real-time digital signage system, MR-DSS, which supports handing real-time tasks like urgent/instant messaging, system status monitoring and so on, efficiently in addition to conventional digital signage CMS service tasks. MR-DSCMS, CMS of MR-DSS, is designed to provide most of its normal services by REST APIs and real-time services like urgent/instant messaging by Socket.IO base under MEARN stack environment. In addition to architecture description of components composing MR-DSS, design and implementation issues are clarified in more detail. Through experimental testing, it is shown that 1) MR-DSS works functionally well, 2) the networking load performance of MR-DSCMS's REST APIs is better compared to a well-known open source Xibo CMS, and 3) real-time messaging via Socket.IO works much faster than REST APIs.

• Journal of Multimedia Information System
• /
• v.8 no.3
• /
• pp.147-158
• /
• 2021

Versatile Video Coding (VVC) is the latest video coding standard developed by Joint Video Exploration Team (JVET). In VVC, the quadtree plus multi-type tree (QT+MTT) structure of coding unit (CU) partition is adopted, and its computational complexity is considerably high due to the brute-force search for recursive rate-distortion (RD) optimization. In this paper, we aim to reduce the time complexity of inter-picture prediction mode since the inter prediction accounts for a large portion of the total encoding time. The problem can be defined as classifying the split mode of each CU. To classify the split mode effectively, a novel convolutional neural network (CNN) called multi-level tree (MLT-CNN) architecture is introduced. For boosting classification performance, we utilize additional information including inter-picture information while training the CNN. The overall algorithm including the MLT-CNN inference process is implemented on VVC Test Model (VTM) 11.0. The CUs of size 128×128 can be the inputs of the CNN. The sequences are encoded at the random access (RA) configuration with five QP values {22, 27, 32, 37, 42}. The experimental results show that the proposed algorithm can reduce the computational complexity by 11.53% on average, and 26.14% for the maximum with an average 1.01% of the increase in Bjøntegaard delta bit rate (BDBR). Especially, the proposed method shows higher performance on the sequences of the A and B classes, reducing 9.81%~26.14% of encoding time with 0.95%~3.28% of the BDBR increase.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.292-298
• /
• 2019

Mobile-based software development methodology has been vigorously researched from using object-oriented development methodology and component-based development methodology previous structural developing methodology. There are two types of OS in mobile platform which are android and iOS. There is a problem that the application to be developed is developed depending on the device type. To resolve this problem, first, the system structure and design method should be managed effectively. Second, a basic design guide that can be commonly adapted to the each project is required. In this paper, we define a mobile cross platform meta model based on MDA-development methodology, focusing on reusability, portability and interoperability about non - dependent part of the mobile platform. If the proposed meta-model is applied to manage the related information and all the types of Mobile-Apps become available through independent mobile app development process, henceforward, it will be much of help establishing formulaic mobile-app developmental methodology.

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.558-572
• /
• 2019

Anthropomorphism is the attribution of human traits, emotions, or intentions to non-human entities. Anthropomorphic animal face masking is the process by which human characteristics are plotted on the animal kind. In this research, we are proposing a compact system which finds the resemblance between a human face and animal face using Deep Convolutional Neural Network (DCNN) and later applies morphism between them. The whole process is done by firstly finding which animal most resembles the particular human face through a DCNN based animal face classification. And secondly, doing triangulation based morphing between the particular human face and the most resembled animal face. Compared to the conventional manual Control Point Selection system using an animator, we are proposing a Viola-Jones algorithm based Control Point selection process which detects facial features for the human face and takes the Control Points automatically. To initiate our approach, we built our own dataset containing ten thousand animal faces and a fourteen layer DCNN. The simulation results firstly demonstrate that the accuracy of our proposed DCNN architecture outperforms the related methods for the animal face classification. Secondly, the proposed morphing method manages to complete the morphing process with less deformation and without any human assistance.

• Journal of Korea Multimedia Society
• /
• v.22 no.6
• /
• pp.655-664
• /
• 2019

In this paper, we propose a novel way of combining multiple deep convolutional neural network (DCNN) architectures which work well for accurate video face identification by adopting a serial combination of 3D and 2D DCNNs. The proposed method first divides an input video sequence (to be recognized) into a number of sub-video sequences. The resulting sub-video sequences are used as input to the 3D DCNN so as to obtain the class-confidence scores for a given input video sequence by considering both temporal and spatial face feature characteristics of input video sequence. The class-confidence scores obtained from corresponding sub-video sequences is combined by forming our proposed class-confidence matrix. The resulting class-confidence matrix is then used as an input for learning 2D DCNN learning which is serially linked to 3D DCNN. Finally, fine-tuned, serially combined DCNN framework is applied for recognizing the identity present in a given test video sequence. To verify the effectiveness of our proposed method, extensive and comparative experiments have been conducted to evaluate our method on COX face databases with their standard face identification protocols. Experimental results showed that our method can achieve better or comparable identification rate compared to other state-of-the-art video FR methods.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.661-669
• /
• 2022

The purpose of this study is to compare and analyze Deep Learning (DL) and Digital Image Processing (DIP) techniques using the results of the glottis segmentation of the two methods followed by the quantification of the asymmetric degree of the vocal cord mucosa. The data consists of 40 normal and abnormal images. The DL model is based on Deeplab V3 architecture, and the Canny edge detector algorithm and morphological operations are used for the DIP technique. According to the segmentation results, the average accuracy of the DL model and the DIP was 97.5% and 94.7% respectively. The quantification results showed high correlation coefficients for both the DL experiment (r=0.8512, p<0.0001) and the DIP experiment (r=0.7784, p<0.0001). In the conclusion, the DL model showed relatively higher segmentation accuracy than the DIP. In this paper, we propose the clinical applicability of this technique applying the segmentation and asymmetric quantification algorithm to the glottal area in the laryngoscopic images.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.440-449
• /
• 2022

In recent years, the air pollution and Air Quality Index (AQI) has been a pivotal point for researchers due to its effect on human health. Various research has been done in predicting the AQI but most of these studies, either lack dense temporal data or cover one or two air pollutant elements. In this paper, a hybrid Convolutional Neural approach integrated with recurrent neural network architecture (CNN-LSTM), is presented to find air pollution inference using a multivariate air pollutant elements dataset. The aim of this research is to design a robust and real-time air pollutant forecasting system by exploiting a neural network. The proposed approach is implemented on a 24-month dataset from Seoul, Republic of Korea. The predicted results are cross-validated with the real dataset and compared with the state-of-the-art techniques to evaluate its robustness and performance. The proposed model outperforms SVM, SVM-Polynomial, ANN, and RF models with 60.17%, 68.99%, 14.6%, and 6.29%, respectively. The model performs SVM and SVM-Polynomial in predicting O3 by 78.04% and 83.79%, respectively. Overall performance of the model is measured in terms of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE).

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1069-1074
• /
• 2022

IP mobility can be handled in different layers of the protocol. Mobile IP has been proposed to handle the mobility of Internet hosts in the network layer. Recently, a new method based on the SIGMA mobility architecture has been proposed to support mobility management with reduced packet loss and latency. The location management structure is not suitable for frequent mobile handover due to the high mobility of the user with this transport layer solution. In this paper, we propose a location management optimization method in a mobile communication network by applying hierarchical location management using MMPs(Mobility Management Points) for transport layer mobility management. Therefore, we propose an efficient hierarchical mobility management structure even between heterogeneous wireless networks using MMPs for the probability that a mobile terminal can change multiple location areas between two messages and calls. The proposed method shows reduction in location update cost and data retrieval cost using MMPs, and as opposed to mobility appearing in time intervals with the minimum cost required to reach 90% of the stabilized cost, the mobility location update search, location It was found that the message processing cost per area was reduced.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.1
• /
• pp.153-161
• /
• 2009

In this paper, we designed and implemented realtime DID(digital information display) system based on web server that displayed multimedia contents. The contents are weather, news information on the internet web sites and public relations or advertisements data on local systems. The DID system has client/server architecture that the server send to client that schedule informations and multimedia contents received form web server and the client displayed the contents though scheduled information. Therefore the systems overcome network fault for the mean time. Also, the system has realtime services of web page filtering function that extract the partial information of specific web pages.