• 디지털산업정보학회논문지
• /
• 제18권3호
• /
• pp.9-23
• /
• 2022

This study aims to examine research trends on the Internet of Things and smart city based on papers from the United States, Japan, and Korea. We collected 7113 papers related to the Internet of Things and smart city published from 2016 to 2021 in Elsevier's Scopus. Keyword frequency and centrality analysis were performed based on the abstracts of the collected papers. We found keywords with high frequency of appearance by calculating keyword frequency and identified central research keywords through the centrality analysis by country. As a result of the analysis, research on security, machine learning, and edge computing related to the Internet of Things and smart city were the most central and highly mediating research conducted in each country. As an implication, studies related to deep learning, cybersecurity, and edge computing in Korea have lower degree centrality and betweenness centrality compared to the United States and Japan. To solve the problem it is necessary to combine these studies with various fields. The future research direction is to analyze research trends on the Internet of Things and smart city in various regions such as Europe and China.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3790-3803
• /
• 2018

Content-based image retrieval is an approach used to query images based on their semantics. Semantic based retrieval has its application in all fields including medicine, space, computing etc. Semantically generated binary hash codes can improve content-based image retrieval. These semantic labels / binary hash codes can be generated from unlabeled data using convolutional autoencoders. Proposed approach uses semi-supervised deep hashing with semantic learning and binary code generation by minimizing the objective function. Convolutional autoencoders are basis to extract semantic features due to its property of image generation from low level semantic representations. These representations of images are more effective than simple feature extraction and can preserve better semantic information. Proposed activation and loss functions helped to minimize classification error and produce better hash codes. Most widely used datasets have been used for verification of this approach that outperforms the existing methods.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권2호
• /
• pp.50-58
• /
• 2019

The clear and specific objective of this study is to design a false news discriminator algorithm for news articles transmitted on a text-based basis and an architecture that builds it into a system (H/W configuration with Hadoop-based in-memory technology, Deep Learning S/W design for bigdata and SNS linkage). Based on learning data on actual news, the government will submit advanced "fake news" test data as a result and complete theoretical research based on it. The need for research proposed by this study is social cost paid by rumors (including malicious comments) and rumors (written false news) due to the flood of fake news, false reports, rumors and stabbings, among other social challenges. In addition, fake news can distort normal communication channels, undermine human mutual trust, and reduce social capital at the same time. The final purpose of the study is to upgrade the study to a topic that is difficult to distinguish between false and exaggerated, fake and hypocrisy, sincere and false, fraud and error, truth and false.

• Asia pacific journal of information systems
• /
• 제16권1호
• /
• pp.1-21
• /
• 2006

e-Learning can be seen as not only one of Internet-based information technologies which can provide education services but also one of teaching-learning methods which can implement self-directed learning. Thus, for evaluation of e-Learning effectiveness, both information-technology-based learning environment and learners' abilities in self-learning and computer-using should be considered simultaneously. This study suggests a research model for evaluating the effectiveness of e-Learning, which is theoretically based on information systems success model, constructivism and self-efficacy. The model is composed of three parts: effectiveness, learning environment, and learners' self-efficacy. Effectiveness is a part of dependent variables: satisfaction and academic performance. Learning environment and learners' self-efficacy can be considered as two sets of explanation variables for effectiveness. The former consists of learning management system, learning contents, and interactions that are provided bye-Learning and the latter means learners' self-regulated efficacy and computer self-efficacy. We show validity of the model empirically by surveying the college students who have experienced e-Learning. In result, most of all hypotheses suggested in this model are accepted in low significant level.

• International Journal of Computer Science & Network Security
• /
• 제23권6호
• /
• pp.13-16
• /
• 2023

This study aims to explore the status of e-learning in the public sector institutes of the Sukkur region in Pakistan. A survey was conducted to collect data from students and teachers regarding their awareness, access, and use of e-learning resources. The results showed that although there is a widespread use of the internet and mobile devices for accessing information, there is a lack of awareness and access to e-learning resources. Barriers to accessing e-learning content and a lack of familiarity with e-learning content development technologies were also identified. The study concludes that there is a need for improved e-learning facilities and curriculum in the public sector institutes of the Sukkur region in Pakistan. Recommendations are provided for developing a correctness-centered e-learning based curriculum that is tailored to the specific needs of the students in the region. It is hoped that the findings of this study will inform efforts to improve the teaching and learning process in the region and provide students with greater flexibility and access to study materials.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4285-4299
• /
• 2019

Adversarial attack is a technique that causes a malfunction of classification models by adding noise that cannot be distinguished by humans, which poses a threat to a deep learning model. In this paper, we propose an efficient method to detect adversarial images using Gaussian process regression. Existing deep learning-based adversarial detection methods require numerous adversarial images for their training. The proposed method overcomes this problem by performing classification based on the statistical features of adversarial images and clean images that are extracted by Gaussian process regression with a small number of images. This technique can determine whether the input image is an adversarial image by applying Gaussian process regression based on the intermediate output value of the classification model. Experimental results show that the proposed method achieves higher detection performance than the other deep learning-based adversarial detection methods for powerful attacks. In particular, the Gaussian process regression-based detector shows better detection performance than the baseline models for most attacks in the case with fewer adversarial examples.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.206-221
• /
• 2019

Source localization in three-dimensional (3-D) wireless sensor networks (WSNs) is becoming a major research focus. Due to the complicated air-ground environments in 3-D positioning, many of the traditional localization methods, such as received signal strength (RSS) may have relatively poor accuracy performance. Benefit from prior learning mechanisms, fingerprinting-based localization methods are less sensitive to complex conditions and can provide relatively accurate localization performance. However, fingerprinting-based methods require training data at each grid point for constructing the fingerprint database, the overhead of which is very high, particularly for 3-D localization. Also, some of measured data may be unavailable due to the interference of a complicated environment. In this paper, we propose an efficient kernel based 3-D localization algorithm via tensor completion. We first exploit the spatial correlation of the RSS data and demonstrate the low rank property of the RSS data matrix. Based on this, a new training scheme is proposed that uses tensor completion to recover the missing data of the fingerprint database. Finally, we propose a kernel based learning technique in the matching phase to improve the sensitivity and accuracy in the final source position estimation. Simulation results show that our new method can effectively eliminate the impairment caused by incomplete sensing data to improve the localization performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2806-2825
• /
• 2018

Unsupervised learning has shown good performance on image, video and audio classification tasks, and much progress has been made so far. It studies how systems can learn to represent particular input patterns in a way that reflects the statistical structure of the overall collection of input patterns. Many promising deep learning systems are commonly trained by the greedy layerwise unsupervised learning manner. The performance of these deep learning architectures benefits from the unsupervised learning ability to disentangling the abstractions and picking out the useful features. However, the existing unsupervised learning algorithms are often difficult to train partly because of the requirement of extensive hyperparameters. The tuning of these hyperparameters is a laborious task that requires expert knowledge, rules of thumb or extensive search. In this paper, we propose a simple and effective unsupervised feature learning algorithm for image classification, which exploits an explicit optimizing way for population and lifetime sparsity. Firstly, a sparse target matrix is built by the competitive rules. Then, the sparse features are optimized by means of minimizing the Euclidean norm ($L_2$) error between the sparse target and the competitive layer outputs. Finally, a classifier is trained using the obtained sparse features. Experimental results show that the proposed method achieves good performance for image classification, and provides discriminative features that generalize well.

• 한국인터넷방송통신학회논문지
• /
• 제22권4호
• /
• pp.111-117
• /
• 2022

수십년간 매우 많은 소프트웨어 결함 예측 모델에 관한 연구들이 수행되었으며, 그들 중 기계학습 기법을 사용한 모델들이 가장 좋은 성능을 보였다. 딥러닝 기법은 기계학습 분야에서 가장 각광받는 기술이 되었지만 결함 예측 모델의 분류기로 사용된 연구는 거의 없었다. 몇몇 연구들은 모델의 입력 소스나 구문 데이터로부터 시맨틱 정보를 얻어내는데 딥러닝을 사용하였다. 본 논문은 3개 이상의 은닉층을 갖는 MLP를 이용하여 모델 구조와 하이퍼 파라미터를 변경하여 여러 모델들을 제작하였다. 모델 평가 실험 결과 MLP 기반 딥러닝 모델들은 기존 결함 예측 모델들과 Accuracy는 비슷한 성능을 보였으나 AUC는 유의미하게 더 우수한 성능을 보였다. 또한 또다른 딥러닝 모델인 CNN 모델보다도 더 나은 성능을 보였다.

• 한국인터넷방송통신학회논문지
• /
• 제24권2호
• /
• pp.205-211
• /
• 2024

본 연구는 유니티 게임 엔진과 유니티 ML-Agents를 이용하여 강화 학습을 통해 목표 추적 및 이동을 지능적으로 수행하는 에이전트를 구현하는 데 목적이 있다. 본 연구에서는 에이전트의 효과적인 강화 학습 훈련 방식을 모색하기 위해 단일 학습 시뮬레이션 환경에서 하나의 에이전트를 트레이닝하는 방식과 다중 학습 시뮬레이션 환경에서 여러 에이전트들을 동시에 병렬 트레이닝하는 방식 간의 학습 성능을 비교하기 위한 실험을 수행하였다. 실험 결과를 통해 병렬트레이닝 방식이 싱글 트레이닝 방식보다 학습 속도 측면에서 약 4.9배 빠르고, 학습 안정성 측면에서도 더 안정적으로 효과적인 학습이 일어남을 확인할 수 있었다.