• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.374-386
• /
• 2022

Nowadays, research in deep learning leveraged automated computing and networking paradigm evidenced rapid contributions in terms of Software Defined Networking (SDN) and its diverse security applications while handling cybercrimes. SDN plays a vital role in sniffing information related to network usage in large-scale data centers that simultaneously support an improved algorithm design for automated detection of network intrusions. Despite its security protocols, SDN is considered contradictory towards DDoS attacks (Distributed Denial of Service). Several research studies developed machine learning-based network intrusion detection systems addressing detection and mitigation of DDoS attacks in SDN-based networks due to dynamic changes in various features and behavioral patterns. Addressing this problem, this research study focuses on effectively designing a multistage hybrid and intelligent deep learning classifier based on modified deep forest classification to detect DDoS attacks in SDN networks. Experimental results depict that the performance accuracy of the proposed classifier is improved when evaluated with standard parameters.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.116-118
• /
• 2022

MPEG-VCM(Video Coding for Machine)은 입력된 이미지/비디오의 특징(feature)를 압축하는 Track 1 과 입력 이미지/비디오를 직접 압축하는 Track 2 로 나뉘어 표준화가 진행 중이다. 본 논문은 Track 1 의 비전임무 네트워크로 사용하는 Detectron2 의 FPN(Feature Pyramid Network)에서 추출한 멀티-스케일 특징을 효율적으로 압축하는 MSFC 기반의 압축 모델의 개선 기법을 제시한다. 제안기법은 해상도를 줄여서 단일-스케일 압축맵을 압축하는 기존의 압축 모델에서 저해상도 특징맵을 고해상도 특징맵에 바텀-업(Bottom-Up) 구조로 합성하여 단일-스케일 특징맵을 구성하는 바텀-업 MSFF 를 가지는 압축 모델을 제시한다. 제안방법은 기존의 모델 보다 BPP-mAP 성능에서 1 ~ 2.7%의 개선된 BD-rate 성능을 보이며 VCM 의 이미지 앵커(image anchor) 대비 최대 -85.94%의 BD-rate 성능향상을 보인다.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.335-340
• /
• 2005

In many urban cities, mixed-use development is becoming increasingly essential for the creation of an attractive and sustainable environment that promotes economic vitality, social equity and environmental quality. Due to the differences in scale, scope and intent, certain aspects within the project delivery process of mixed-use are not the same as "conventional" single-use projects. The objective of this paper is to highlight these aspects. Two cases in Southeast Asia serve to illustrate the uniqueness and challenges of mixed-use. In conclusion, the differences between mixed-use and single-use are evident in terms of the diversity of team members, the necessity of multiple market analyses, and a multi-layer (versus single-source) financing structure. Finally, issues concerning ownership tangles, land assembly, planning and application procedures, investment criteria of institutions have been identified as major pitfalls.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1311-1314
• /
• 2022

DNN을 사용하여 객체 인식 과정에서 객체를 잘 분류하기 위해서는 시각적 설명성이 요구된다. 시각적 설명성은 object class에 대한 예측을 pixel-wise attribution으로 표현해 예측 근거를 해석하기 위해 제안되었다, Scale-invariant한 특징을 제공하도록 설계된 pyramidal features 기반 backbone 구조는 object detection 및 classification 등에서 널리 쓰이고 있으며, 이러한 특징을 갖는 feature pyramid를 trainable attention mechanism에 적용하고자 할 때 계산량 및 메모리의 복잡도가 증가하는 문제가 있다. 본 논문에서는 일반적인 FPN에서 객체 인식 성능과 설명성을 높이기 위한 피라미드-주의집중 계층네트워크 (FPN-Attention Layered Network) 방식을 제안하고, 실험적으로 그 특성을 평가하고자 한다. 기존의 FPN만을 사용하였을 때 객체 인식 과정에서 설명성을 향상시키는 방식이 객체 인식에 미치는 정도를 정량적으로 평가하였다. 제안된 모델의 적용을 통해 낮은 computing 오버헤드 수준에서 multi-level feature를 고려한 시각적 설명성을 개선시켜, 결괴적으로 객체 인식 성능을 향상 시킬 수 있음을 실험적으로 확인할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.143-145
• /
• 2022

MPEG-VCM(Video Coding for Machine)은 입력된 비디오 특징(feature)를 압축하는 Track1 과 입력 영상을 직접 압축하는 Track2 로 나뉘어 표준화가 진행중이다. 본 논문은 VCM Track 1 에 해당하는 Detectron2 FPN(Feature Pyramid Network)에서 추출한 다중 스케일 특징맵을 VVC 로 압축하는 MSFC(Multi-Scale Feature Compression)을 구조를 제안한다. 본 논문의 MSFC 에서는 다중 스케일 특징을 결합하여 부호화/복호화하는 기존의 구조에서 특징맵의 해상도를 줄여 압축하는 개선된 MSFC 를 제시한다. 제안 방법은 VCM 의 Track2 의 영상 앵커(image anchor) 보다 우수한 BPP-mAP 성능을 보이고 최대 -84.98%의 BD-rate 성능향상을 보인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.539-540
• /
• 2022

본 논문에서는 정확한 장기 시계열 예측을 위해 시계열 데이터의 다양한 스케일 (시간 규모)에서 표현을 학습하는 트랜스포머 모델을 제안한다. 제안하는 모델은 시계열의 다중 스케일 특징을 추출하고, 이를 트랜스포머에 반영하여 예측 시계열을 생성하는 구조로 되어 있다. 스케일 정규화 과정을 통해 시계열의 전역적 및 지역적인 시간 정보를 효율적으로 융합하여 종속성을 학습한다. 3 가지의 다변량 시계열 데이터를 이용한 실험을 통해 제안하는 방법의 우수성을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.653-669
• /
• 2024

Dynamic scene deblurring is a complex computer vision problem owing to its difficulty to model mathematically. In this paper, we present a novel approach for image deblurring with the help of the sharp reference image, which utilizes the reference image for high-quality and high-frequency detail results. To better utilize the clear reference image, we develop an encoder-decoder network and two novel modules are designed to guide the network for better image restoration. The proposed Reference Extraction and Aggregation Module can effectively establish the correspondence between blurry image and reference image and explore the most relevant features for better blur removal and the proposed Spatial Feature Fusion Module enables the encoder to perceive blur information at different spatial scales. In the final, the multi-scale feature maps from the encoder and cascaded Reference Extraction and Aggregation Modules are integrated into the decoder for a global fusion and representation. Extensive quantitative and qualitative experimental results from the different benchmarks show the effectiveness of our proposed method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.4
• /
• pp.101-107
• /
• 2013

Generally the commercial high-resolution images have their coordinates, but the locations are locally different according to the pose of sensors at the acquisition time and relief displacement of terrain. Therefore, a process of image co-registration has to be applied to use the multi-temporal images together. However, co-registration is interrupted especially when images include the cloud-covered regions because of the difficulties of extracting matching points and lots of false-matched points. This paper proposes an automatic co-registration method for the cloud-covered high-resolution images. A scale-invariant feature transform (SIFT), which is one of the representative feature-based matching method, is used, and only features of the target (cloud-covered) images within a circular buffer from each feature of reference image are used for the candidate of the matching process. Study sites composed of multi-temporal KOMPSAT-2 images including cloud-covered regions were employed to apply the proposed algorithm. The result showed that the proposed method presented a higher correct-match rate than original SIFT method and acceptable registration accuracies in all sites.

• Journal of KIISE
• /
• v.41 no.9
• /
• pp.666-673
• /
• 2014

This paper proposes a scalable face recognition method for unconstrained face databases, and shows a simple experimental result. Existing face recognition research usually has focused on improving the recognition rate in a constrained environment where illumination, face alignment, facial expression, and background is controlled. Therefore, it cannot be applied in unconstrained face databases. The proposed system is face feature extraction algorithm for unconstrained face recognition. First of all, we extract the area that represent the important features(landmarks) in the face, like the eyes, nose, and mouth. Each landmark is represented by a high-dimensional LBP(Local Binary Pattern) histogram feature vector. The multi-scale LBP histogram vector corresponding to a single landmark, becomes a low-dimensional face feature vector through the feature reduction process, PCA(Principal Component Analysis) and LDA(Linear Discriminant Analysis). We use the Rank acquisition method and Precision at k(p@k) performance verification method for verifying the face recognition performance of the low-dimensional face feature by the proposed algorithm. To generate the experimental results of face recognition we used the FERET, LFW and PubFig83 database. The face recognition system using the proposed algorithm showed a better classification performance over the existing methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.10
• /
• pp.2026-2034
• /
• 2015

Wireless sensor networks (WSNs) consist of a lot of sensor nodes having limited transmission range. So multi-hop transmission is used for communication among nodes but the multi-hop transmission degrade the end-to-end reliability. Multipath routing and opportunistic routing are typical approaches for guaranteeing end-to-end reliability in WSNs. The existing protocols improve the reliability effectively in small networks but they suffer from rapid performance degradation in large networks. In this paper, we propose the opportunistic multipath routing protocol for guaranteeing end-to-end reliability in large WSNs. Applying multipath routing and opportunistic routing simultaneously is very hard because their conflicting routing features. The proposed protocol applies these approaches simultaneously by section-based routing thereby enhancing end-to-end reliability. Additionally, the proposed protocol guarantees required reliability by the concept of section reliability. The section reliability over a certain level might satisfy required end-to-end reliability. Our simulation results show that the proposed protocol is more suitable for guaranteeing reliability than existing protocols in large-scale WSNs.