• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5634-5653
• /
• 2018

Internet of things (IoT) is based on a global dynamic information network with cloud services where a great number of devices (things) exchange data to provide added-value services and products. There are several commercial and open source IoT platforms available in the market to connect devices to internet; however, they have cost and operational constraints that make them not suitable for academic projects. In this work, an IoT platform, known as Novus-io, is introduced in order to support academic projects for undergraduate students. With this platform and proper training, undergraduate students from different majors (not only from information technology and electronics) are capable to upgrade their school projects with IoT functionalities. The objective of this approach is to provide to any undergraduate student skills and knowledge on IoT, so they will be prepared, in their imminent step toward professionalism, to understand the relevance of digital services in today's world.

• 한국융합학회논문지
• /
• 제8권2호
• /
• pp.27-33
• /
• 2017

인터넷을 통해 사용자에게 클라우드 컴퓨팅 서비스를 효율적으로 제공하기 위해서는 데이터 센터에 가상화와 분산 컴퓨팅 기술을 기반으로 하여 IT 자원을 구성해야 한다. 본 논문은 폭넓은 분야에서 새로운 훈련 데이터가 언제라도 추가될 수 있고, 또한 언제라도 훈련 데이터에 새로운 속성이 추가될 수 있다는 문제에 특별히 초점을 맞춘다. 이러한 경우, 기존 속성 집합들을 가지는 훈련 데이터로 생성된 규칙은 쓸모없게 된다. 더구나 새롭게 추가된 데이터나 속성을 가지는 새로운 데이터는 기존 규칙과 결합될 수 없다. 본 논문은 이와 같은 경우를 자연스럽게 처리할 수 있는 보다 진보된 새 추론 엔진을 제안한다. 이 방법에서 기존의 데이터로 부터 생성된 규칙은 개선된 규칙을 생성하기 위한 새로운 데이터 집합과 결합될 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권6호
• /
• pp.1462-1477
• /
• 2024

With the evolving complexity of connected vehicle features, the volume and diversity of data generated during driving continue to escalate. Enabling data sharing among interconnected vehicles holds promise for improving users' driving experiences and alleviating traffic congestion. Yet, the unintentional disclosure of users' private information through data sharing poses a risk, potentially compromising the interests of vehicle users and, in certain cases, endangering driving safety. Federated learning (FL) is a newly emerged distributed machine learning paradigm, which is expected to play a prominent role for privacy-preserving learning in autonomous vehicles. While FL holds significant potential to enhance the architecture of the Internet of Vehicles (IoV), the dynamic mobility of vehicles poses a considerable challenge to integrating FL with vehicular networks. In this paper, a novel clustered FL framework is proposed which is efficient for reducing communication and protecting data privacy. By assessing the similarity among feature vectors, vehicles are categorized into distinct clusters. An optimal vehicle is elected as the cluster head, which enhances the efficiency of personalized data processing and model training while reducing communication overhead. Simultaneously, the Local Differential Privacy (LDP) mechanism is incorporated during local training to safeguard vehicle privacy. The simulation results obtained from the 20newsgroups dataset and the MNIST dataset validate the effectiveness of the proposed scheme, indicating that the proposed scheme can ensure data privacy effectively while reducing communication overhead.

• 인터넷정보학회논문지
• /
• 제21권1호
• /
• pp.191-199
• /
• 2020

사이버전 훈련은 사이버전 역량 제고를 위한 핵심 수단이다. 일반적으로 사이버전 훈련은 시나리오에 의해 진행되며, 훈련의 질을 높여줄 수 있는 다양한 요소를 시나리오에 포함시킴으로써 훈련의 효과를 배가시킬 수 있다. 본 논문에서는 훈련 시나리오에 포함시킬 요소로 식별된 훈련 정보, 네트워크 맵, 트래픽 발생 정책, 위협/방어 행위를 소개하고, 이를 계층화하여 조합하는 방식으로 다양한 훈련 시나리오를 저작하는 방법을 제시한다. 그리고 각 시나리오 계층을 통합적으로 관리하기 위한 데이터베이스 설계를 제안한다. 계층적 훈련 시나리오 저작 방법은 기 저작된 계층들의 재사용을 통한 저작 편의성의 증대와, 계층 간의 다양한 조합을 바탕으로 훈련 시나리오를 확장시킬 수 있다는 장점을 가진다.

• 인터넷정보학회논문지
• /
• 제20권4호
• /
• pp.47-53
• /
• 2019

일반적으로 어지럼증은 여러 가지 복합적인 원인에 의해서 발생하지만 그 중에서 신경계에 속하는 전정계통의 기능 장애에 의한 증상이 가장 환자에게 심한 증상으로 다가오며, 구역질과 구토를 동반하게 된다. 이러한 어지럼증에 대한 치료는 약물요법, 수술요법, 재활치료 등이 있으며, 약물요법이나 수술요법은 대체적으로 후유증의 위험 때문에 재활치료요법인 전정재활훈련을 많이 시행하고 있다. 전정재활훈련은 안구훈련, 자세안정훈련, 보행훈련 등이 있는데 그 중 보행훈련은 의사 또는 전문치료사의 감독하에 일정한 공간에서 진행되므로 시간적, 공간적 부담이 가중되어 환자들이 훈련을 진행기 불편한 단점을 가진다. 이를 해결하고자 본 논문에서는 증강현실 기술을 활용해 사용자가 직접 보행재활훈련을 진행 할 수 있는 보행훈련 콘텐츠를 구현하였다. 추후 어지럼증 환자를 대상으로 한 임상시험을 통해 의료 환경에서 사용 가능한 어지럼증 재활 콘텐츠로 활용 가능할 것으로 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.958-979
• /
• 2023

Due to laws, regulations, privacy, etc., between 70-90 percent of providers do not share medical data, forming a "data island". It is essential to collaborate across multiple institutions without sharing patient data. Most existing methods adopt distributed learning and centralized federal architecture to solve this problem, but there are problems of resource heterogeneity and data heterogeneity in the practical application process. This paper proposes a collaborative deep learning modelling method based on the blockchain network. The training process uses encryption parameters to replace the original remote source data transmission to protect privacy. Hyperledger Fabric blockchain is adopted to realize that the parties are not restricted by the third-party authoritative verification end. To a certain extent, the distrust and single point of failure caused by the centralized system are avoided. The aggregation algorithm uses the FedProx algorithm to solve the problem of device heterogeneity and data heterogeneity. The experiments show that the maximum improvement of segmentation accuracy in the collaborative training mode proposed in this paper is 11.179% compared to local training. In the sequential training mode, the average accuracy improvement is greater than 7%. In the parallel training mode, the average accuracy improvement is greater than 8%. The experimental results show that the model proposed in this paper can solve the current problem of centralized modelling of multicenter data. In particular, it provides ideas to solve privacy protection and break "data silos", and protects all data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2720-2736
• /
• 2013

Multi-view face detection has become an active area for research in the last few years. In this paper, a novel multi-view human face detection algorithm based on improved real Adaboost is presented. Real Adaboost algorithm is improved by weighted combination of weak classifiers and the approximately best combination coefficients are obtained. After that, we proved that the function of sample weight adjusting method and weak classifier training method is to guarantee the independence of weak classifiers. A coarse-to-fine hierarchical face detector combining the high efficiency of Haar feature with pose estimation phase based on our real Adaboost algorithm is proposed. This algorithm reduces training time cost greatly compared with classical real Adaboost algorithm. In addition, it speeds up strong classifier converging and reduces the number of weak classifiers. For frontal face detection, the experiments on MIT+CMU frontal face test set result a 96.4% correct rate with 528 false alarms; for multi-view face in real time test set result a 94.7 % correct rate. The experimental results verified the effectiveness of the proposed approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2199-2213
• /
• 2024

To enhance the quality of defect detection for Printed Circuit Board Assembly (PCBA) during electronic product manufacturing, this study primarily focuses on optimizing the YOLOv7-based method for PCBA defect detection. In this method, the Mish, a smoother function, replaces the Leaky ReLU activation function of YOLOv7, effectively expanding the network's information processing capabilities. Concurrently, a Squeeze-and-Excitation attention mechanism (SEAM) has been integrated into the head of the model, significantly augmenting the precision of small target defect detection. Additionally, considering angular loss, compared to the CIoU loss function in YOLOv7, the SIoU loss function in the paper enhances robustness and training speed and optimizes inference accuracy. In terms of data preprocessing, this study has devised a brightness adjustment data enhancement technique based on split-filtering to enrich the dataset while minimizing the impact of noise and lighting on images. The experimental results under identical training conditions demonstrate that our model exhibits a 9.9% increase in mAP value and an FPS increase to 164 compared to the YOLOv7. These indicate that the method proposed has a superior performance in PCBA defect detection and has a specific application value.

• 인터넷정보학회논문지
• /
• 제23권1호
• /
• pp.87-93
• /
• 2022

군(軍) PC의 99%는 윈도우 운영체제를 사용하고 있어 안전한 국방사이버공간을 유지하기 위해서는 윈도우 기반 악성코드의 탐지 및 대응이 상당히 중요하다. 본 연구에서는 윈도우 PE(Portable Executable) 포맷의 악성코드를 탐지할 수 있는 모델을 제안한다. 탐지모델을 구축함에 있어서는 탐지의 정확도보다는 급증하는 악성코드에 효율적으로 대처하기 위한 탐지모델의 신속한 업데이트에 중점을 두었다. 이에 학습 속도를 향상시키기 위해 복잡한 전처리 과정 없이 최소한의 시퀀스 데이터만으로도 악성코드 탐지가 가능한 Bidirectional LSTM(Long Short Term Memory) 네트워크를 기반으로 탐지모델을 설계하였다. 실험은 EMBER2018 데이터셋을 활용하여 진행하였으며, 3가지의 시퀀스 데이터(Byte-Entropy Histogram, Byte Histogram, String Distribution)로 구성된 특성 집합을 모델에 학습시킨 결과 90.79%의 Accuracy를 달성하였다. 한편, 학습 소요시간은 기존 탐지모델 대비 1/4로 단축되어 급증하는 신종 악성코드에 대응하기 위한 탐지모델의 신속한 업데이트가 가능함을 확인하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.124-131
• /
• 2024

Breast cancer classification using ultrasound, while widely employed, faces challenges due to its relatively low predictive value arising from significant overlap in characteristics between benign and malignant lesions, as well as operator-dependency. To alleviate these challenges and reduce dependency on radiologist interpretation, the implementation of automatic breast cancer classification in ultrasound image can be helpful. To deal with this problem, we propose a semi-supervised deep learning framework for breast cancer classification. In the proposed method, we could achieve reasonable performance utilizing less than 50% of the training data for supervised learning in comparison to when we utilized a 100% labeled dataset for training. Though it requires more modification, this methodology may be able to alleviate the time-consuming annotation burden on radiologists by reducing the number of annotation, contributing to a more efficient and effective breast cancer detection process in ultrasound images.