Selected Papers from International Conference on Smart Media and Applications (SMA 2020)

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (31 March 2021) | Viewed by 27375

Special Issue Editors

AI Graduate School, Gwangju Institute of Science and Technology (GIST), Gwangju 61005, Republic of Korea
Interests: nature-inspired problem solving; evolutionary machine learning; creativity-model learning intelligence; AI music and arts; quantum AI
Special Issues, Collections and Topics in MDPI journals
Department of Computer Engineering, Chosun University, Gwangju 61452, Korea
Interests: semantic information processing and retrieval; semantic web; intelligence systems; system security

Special Issue Information

Dear Colleagues,

The 9th International Conference on Smart Media and Applications (SMA 2020), held in Jeju Island, Korea, 17–19 September 2020, will provide an excellent forum for addressing research issues in smart media and applications. SMA 2020 focuses on innovative solutions to complex problems in all areas of industry, engineering, and sciences using advanced techniques in smart media and computer science applications. This Special Issue on “Selected Papers from SMA 2020” is expected to publish excellent papers presented at SMA 2020 on topics including smart media, smart software applications, smart information, smart services, and so forth. The main goal of Special Issue is to discover new scientific knowledge relevant but not limited to the following topics:

  • Intelligent/cloud/distributed computing and systems
  • Artificial intelligence, image/audio processing, computer graphics, HCI
  • Information processing, information security, mobile communication, IOT
  • Content convergence, game, animation, web/mobile, and smart learning
  • Design management/marketing/methodology, UI/UX
  • Media convergence, storytelling and production creation/publishing
  • e-business, ERP, social network, smart logistics
  • Smart life/finance/agriculture, smart city, and transformation

Prof. Dr. Chang Wook Ahn
Prof. Dr. Pankoo Kim
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Smart media and applications
  • Contents and services
  • Artificial intelligence
  • Information systems

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

14 pages, 20814 KiB  
Article
Multiple Instance Learning with Differential Evolutionary Pooling
by Kamanasish Bhattacharjee, Arti Tiwari, Millie Pant, Chang Wook Ahn and Sanghoun Oh
Electronics 2021, 10(12), 1403; https://doi.org/10.3390/electronics10121403 - 10 Jun 2021
Cited by 1 | Viewed by 2514
Abstract
While implementing Multiple Instance Learning (MIL) through Deep Neural Networks, the most important task is to design the bag-level pooling function that defines the instance-to-bag relationship and eventually determines the class label of a bag. In this article, Differential Evolutionary (DE) pooling—an MIL [...] Read more.
While implementing Multiple Instance Learning (MIL) through Deep Neural Networks, the most important task is to design the bag-level pooling function that defines the instance-to-bag relationship and eventually determines the class label of a bag. In this article, Differential Evolutionary (DE) pooling—an MIL pooling function based on Differential Evolution (DE) and a bio-inspired metaheuristic—is proposed for the optimization of the instance weights in parallel with training the Deep Neural Network. This article also presents the effects of different parameter adaptation techniques with different variants of DE on MIL. Full article
Show Figures

Figure 1

13 pages, 5924 KiB  
Article
Survival Prediction of Lung Cancer Using Small-Size Clinical Data with a Multiple Task Variational Autoencoder
by Thanh-Hung Vo, Guee-Sang Lee, Hyung-Jeong Yang, In-Jae Oh, Soo-Hyung Kim and Sae-Ryung Kang
Electronics 2021, 10(12), 1396; https://doi.org/10.3390/electronics10121396 - 10 Jun 2021
Cited by 7 | Viewed by 3205
Abstract
Due to the increase of lung cancer globally, and particularly in Korea, survival analysis for this type of cancer has gained prominence in recent years. For this task, mathematical and traditional machine learning approaches are commonly used by medical doctors. While the deep [...] Read more.
Due to the increase of lung cancer globally, and particularly in Korea, survival analysis for this type of cancer has gained prominence in recent years. For this task, mathematical and traditional machine learning approaches are commonly used by medical doctors. While the deep learning approach has had proven success in computer vision tasks, natural language processing and other AI techniques are also adopted for this task. Due to the privacy issues and management process, data in medicine are difficult to collect, which leads to a paucity of samples. The small number of samples makes it difficult to use deep learning and renders this approach unusable. In this investigation, we propose a network architecture that combines a variational autoencoder (VAE) with the typical DNN architecture to solve the survival analysis task. With a training size of n = 4107, MVAESA achieves a C-index of 0.722 while CoxCC, CoxPH, and CoxTime achieved scores of 0.713, 0.703, and 0.710, respectively. With a small training size of n = 379, MVAESA achieves a C-index of 0.707, compared with 0.689, 0.688 and 0.690 for CoxCC, CoxPH, and CoxTime, respectively. The results show that the combination of a VAE with a target task makes the network more stable and that the network could be trained using a small-sized sample. Full article
Show Figures

Figure 1

16 pages, 677 KiB  
Article
Efficiently Estimating Joining Cost of Subqueries in Regular Path Queries
by Van-Quyet Nguyen, Van-Hau Nguyen, Minh-Quy Nguyen, Quyet-Thang Huynh and Kyungbaek Kim
Electronics 2021, 10(9), 990; https://doi.org/10.3390/electronics10090990 - 21 Apr 2021
Cited by 1 | Viewed by 1651
Abstract
Evaluating Regular Path Queries (RPQs) have been of interest since they were used as a powerful way to explore paths and patterns in graph databases. Traditional automata-based approaches are restricted in the graph size and/or highly complex queries, which causes a high evaluation [...] Read more.
Evaluating Regular Path Queries (RPQs) have been of interest since they were used as a powerful way to explore paths and patterns in graph databases. Traditional automata-based approaches are restricted in the graph size and/or highly complex queries, which causes a high evaluation cost (e.g., memory space and response time) on large graphs. Recently, although using the approach based on the threshold rare label for large graphs has been achieving some success, they could not often guarantee the minimum searching cost. Alternatively, the Unit-Subquery Cost Matrix (USCM) has been studied and obtained the viability of the usage of subqueries. Nevertheless, this method has an issue, which is, it does not cumulate the cost among subqueries that causes the long response time on a large graph. In order to overcome this issue, this paper proposes a method for estimating joining cost of subqueries to accelerate the USCM based parallel evaluation of RPQs on a large graph, namely USCM-Join. Through real-world datasets, we experimentally show that the USCM-Join outperforms others and estimating the joining cost enhances the USCM based approach up to around 20% in terms of response time. Full article
Show Figures

Figure 1

7 pages, 286 KiB  
Article
Feature Extraction for StarCraft II League Prediction
by Chan Min Lee and Chang Wook Ahn
Electronics 2021, 10(8), 909; https://doi.org/10.3390/electronics10080909 - 11 Apr 2021
Cited by 3 | Viewed by 2065
Abstract
In a player-versus-player game such as StarCraft II, it is important to match players with others with similar skills. Studies modeling player skills were conducted, with 47.3% and 61.3% performance. In order to improve the performance, we collected 46,398 replays and compared features [...] Read more.
In a player-versus-player game such as StarCraft II, it is important to match players with others with similar skills. Studies modeling player skills were conducted, with 47.3% and 61.3% performance. In order to improve the performance, we collected 46,398 replays and compared features extracted from six sections of replays. Through the comparison of the six datasets we created, we propose a method for extracting features from a single replay. Two algorithms, k-Nearest Neighbors and Random Forest, which are most commonly used in related studies, are compared. Our research showed a outperforming accuracy of 75.3% compared to previous works. Although no direct comparison has been made with the current system, we conclude that our research can replace the placement games of five rounds. Full article
Show Figures

Figure 1

14 pages, 580 KiB  
Article
Supporting SLA via Adaptive Mapping and Heterogeneous Storage Devices in Ceph
by Sopanhapich Chum, Heekwon Park and Jongmoo Choi
Electronics 2021, 10(7), 847; https://doi.org/10.3390/electronics10070847 - 02 Apr 2021
Cited by 1 | Viewed by 1955
Abstract
This paper proposes a new resource management scheme that supports SLA (Service-Level Agreement) in a bigdata distributed storage system. Basically, it makes use of two mapping modes, isolated mode and shared mode, in an adaptive manner. In specific, to ensure different QoS (Quality [...] Read more.
This paper proposes a new resource management scheme that supports SLA (Service-Level Agreement) in a bigdata distributed storage system. Basically, it makes use of two mapping modes, isolated mode and shared mode, in an adaptive manner. In specific, to ensure different QoS (Quality of Service) requirements among clients, it isolates storage devices so that urgent clients are not interfered by normal clients. When there is no urgent client, it switches to the shared mode so that normal clients can access all storage devices, thus achieving full performance. To provide this adaptability effectively, it devises two techniques, called logical cluster and normal inclusion. In addition, this paper explores how to exploit heterogeneous storage devices, HDDs (Hard Disk Drives) and SSDs (Solid State Drives), to support SLA. It examines two use cases and observes that separating data and metadata into different devices gives a positive impact on the performance per cost ratio. Real implementation-based evaluation results show that this proposal can satisfy the requirements of diverse clients and can provide better performance compared with a fixed mapping-based scheme. Full article
Show Figures

Figure 1

12 pages, 995 KiB  
Article
An Empirical Study of Korean Sentence Representation with Various Tokenizations
by Danbi Cho, Hyunyoung Lee and Seungshik Kang
Electronics 2021, 10(7), 845; https://doi.org/10.3390/electronics10070845 - 01 Apr 2021
Cited by 3 | Viewed by 2168
Abstract
It is important how the token unit is defined in a sentence in natural language process tasks, such as text classification, machine translation, and generation. Many studies recently utilized the subword tokenization in language models such as BERT, KoBERT, and ALBERT. Although these [...] Read more.
It is important how the token unit is defined in a sentence in natural language process tasks, such as text classification, machine translation, and generation. Many studies recently utilized the subword tokenization in language models such as BERT, KoBERT, and ALBERT. Although these language models achieved state-of-the-art results in various NLP tasks, it is not clear whether the subword tokenization is the best token unit for Korean sentence embedding. Thus, we carried out sentence embedding based on word, morpheme, subword, and submorpheme, respectively, on Korean sentiment analysis. We explored the two-sentence representation methods for sentence embedding: considering the order of tokens in a sentence and not considering the order. While inputting a sentence, which is decomposed by token unit, to the two-sentence representation methods, we construct the sentence embedding with various tokenizations to find the most effective token unit for Korean sentence embedding. In our work, we confirmed: the robustness of the subword unit for out-of-vocabulary (OOV) problems compared to other token units, the disadvantage of replacing whitespace with a particular symbol in the sentiment analysis task, and that the optimal vocabulary size is 16K in subword and submorpheme tokenization. We empirically noticed that the subword, which was tokenized by a vocabulary size of 16K without replacement of whitespace, was the most effective for sentence embedding on the Korean sentiment analysis task. Full article
17 pages, 6272 KiB  
Article
Defective Product Classification System for Smart Factory Based on Deep Learning
by Huy Toan Nguyen, Gwang-Huyn Yu, Nu-Ri Shin, Gyeong-Ju Kwon, Woo-Young Kwak and Jin-Young Kim
Electronics 2021, 10(7), 826; https://doi.org/10.3390/electronics10070826 - 31 Mar 2021
Cited by 10 | Viewed by 3332
Abstract
Smart factories merge various technologies in a manufacturing environment in order to improve factory performance and product quality. In recent years, these smart factories have received a lot of attention from researchers. In this paper, we introduce a defective product classification system based [...] Read more.
Smart factories merge various technologies in a manufacturing environment in order to improve factory performance and product quality. In recent years, these smart factories have received a lot of attention from researchers. In this paper, we introduce a defective product classification system based on deep learning for application in smart factories. The key component of the proposed system is a programmable logic controller (PLC) artificial intelligence (AI) embedded board; we call this an AI Edge-PLC module. A pre-trained defective product classification model is uploaded to a cloud service from where the AI Edge-PLC can access and download it for use on a certain product, in this case, electrical wiring. Next, we setup the system to collect electrical wiring data in a real-world factory environment. Then, we applied preprocessing to the collected data in order to extract a region of interest (ROI) from the images. Due to limitations on the availability of appropriate labeled data, we used the transfer learning method to re-train a classification model for our purposes. The pre-trained models were then optimized for applications on AI Edge-PLC boards. After carrying out classification tasks, on our electrical wire dataset and on a previously published casting dataset, using various deep neural networks including VGGNet, ResNet, DenseNet, and GoogLeNet, we analyzed the results achieved by our system. The experimental results show that our system is able to classify defective products quickly with high accuracy in a real-world manufacturing environment. Full article
Show Figures

Figure 1

14 pages, 6709 KiB  
Article
Single Image Dehazing Using End-to-End Deep-Dehaze Network
by Masud An-Nur Islam Fahim and Ho Yub Jung
Electronics 2021, 10(7), 817; https://doi.org/10.3390/electronics10070817 - 30 Mar 2021
Cited by 8 | Viewed by 2785
Abstract
Haze is a natural distortion to the real-life images due to the specific weather conditions. This distortion limits the perceptual fidelity, as well as information integrity, of a given image. Image dehazing for the observed images is a complicated task because of its [...] Read more.
Haze is a natural distortion to the real-life images due to the specific weather conditions. This distortion limits the perceptual fidelity, as well as information integrity, of a given image. Image dehazing for the observed images is a complicated task because of its ill-posed nature. This study offers the Deep-Dehaze network to retrieve haze-free images. Given an input, the proposed architecture uses four feature extraction modules to perform nonlinear feature extraction. We improvise the traditional U-Net architecture and the residual network to design our architecture. We also introduce the l1 spatial-edge loss function that enables our system to achieve better performance than that for the typical l1 and l2 loss function. Unlike other learning-based approaches, our network does not use any fusion connection for image dehazing. By training the image translation and dehazing network in an end-to-end manner, we can obtain better effects of both image translation and dehazing. Experimental results on synthetic and real-world images demonstrate that our model performs favorably against the state-of-the-art dehazing algorithms. We trained our network in an end-to-end manner and validated it on natural and synthetic hazy datasets. Our method shows favorable results on these datasets without any post-processing in contrast to the traditional approach. Full article
Show Figures

Figure 1

16 pages, 5935 KiB  
Article
Evaluation of a LoRa Mesh Network for Smart Metering in Rural Locations
by Anup Marahatta, Yaju Rajbhandari, Ashish Shrestha, Ajay Singh, Anup Thapa, Francisco Gonzalez-Longatt, Petr Korba and Seokjoo Shin
Electronics 2021, 10(6), 751; https://doi.org/10.3390/electronics10060751 - 22 Mar 2021
Cited by 9 | Viewed by 3797
Abstract
Accompanying the advancement on the Internet of Things (IoT), the concept of remote monitoring and control using IoT devices is becoming popular. Digital smart meters hold many advantages over traditional analog meters, and smart metering is one of application of IoT technology. It [...] Read more.
Accompanying the advancement on the Internet of Things (IoT), the concept of remote monitoring and control using IoT devices is becoming popular. Digital smart meters hold many advantages over traditional analog meters, and smart metering is one of application of IoT technology. It supports the conventional power system in adopting modern concepts like smart grids, block-chains, automation, etc. due to their remote load monitoring and control capabilities. However, in many applications, the traditional analog meters still are preferred over digital smart meters due to the high deployment and operating costs, and the unreliability of the smart meters. The primary reasons behind these issues are a lack of a reliable and affordable communication system, which can be addressed by the deployment of a dedicated network formed with a Low Power Wide Area (LPWA) platform like wireless radio standards (i.e., LoRa devices). This paper discusses LoRa technology and its implementation to solve the problems associated with smart metering, especially considering the rural energy system. A simulation-based study has been done to analyse the LoRa technology’s applicability in different architecture for smart metering purposes and to identify a cost-effective and reliable way to implement smart metering, especially in a rural microgrid (MG). Full article
Show Figures

Figure 1

12 pages, 1566 KiB  
Article
Ensemble-Based Out-of-Distribution Detection
by Donghun Yang, Kien Mai Ngoc, Iksoo Shin, Kyong-Ha Lee and Myunggwon Hwang
Electronics 2021, 10(5), 567; https://doi.org/10.3390/electronics10050567 - 28 Feb 2021
Cited by 6 | Viewed by 2239
Abstract
To design an efficient deep learning model that can be used in the real-world, it is important to detect out-of-distribution (OOD) data well. Various studies have been conducted to solve the OOD problem. The current state-of-the-art approach uses a confidence score based on [...] Read more.
To design an efficient deep learning model that can be used in the real-world, it is important to detect out-of-distribution (OOD) data well. Various studies have been conducted to solve the OOD problem. The current state-of-the-art approach uses a confidence score based on the Mahalanobis distance in a feature space. Although it outperformed the previous approaches, the results were sensitive to the quality of the trained model and the dataset complexity. Herein, we propose a novel OOD detection method that can train more efficient feature space for OOD detection. The proposed method uses an ensemble of the features trained using the softmax-based classifier and the network based on distance metric learning (DML). Through the complementary interaction of these two networks, the trained feature space has a more clumped distribution and can fit well on the Gaussian distribution by class. Therefore, OOD data can be efficiently detected by setting a threshold in the trained feature space. To evaluate the proposed method, we applied our method to various combinations of image datasets. The results show that the overall performance of the proposed approach is superior to those of other methods, including the state-of-the-art approach, on any combination of datasets. Full article
Show Figures

Figure 1

Back to TopTop