• Journal of Broadcast Engineering
• /
• v.10 no.3
• /
• pp.348-356
• /
• 2005

In this paper, we propose a fast bitrate reduction transcoding method to convert a bitstream coded by H.264 into a lower bitrate H.264 bitstream. Block mode informations and motion vectors generated by H.264 decoder are used for probability-based block mode determination in the proposed transcoding method. And the motion vector reuse and motion vector refinement process are applied in the proposed transcoding. In the experiment results, the proposed methods achieves approximately 40 times improvement in computation complexity compared with the cascaded pixel domain transcoding, while the PSNR(Peak Signal to Noise Ratio) is degraded with only $0.1\~0.3$ dB.

• The KIPS Transactions:PartB
• /
• v.8B no.1
• /
• pp.43-49
• /
• 2001

이동통신 채널과 같이 에러 발생율이 높은 환경에서 부호화된 비디오를 전송할 때 채널에어에 손상된 비트스트림은 복호되기 어려울 뿐만 아니라, 비트스트림의 다른 부분으로까지 에러를 전파시킨다. 한 프레임에 손실블록이 있을 때 기존방법에서는 주변블록들의 움직임벡터 평균을 구하거나 비슷한 예측을 통해 손실블록의 움직임벡터를 복원한다. 그러나 손실블록이 움직이는 객체의 경계부근에서 발생할 때 기존방법은 효율적이지 못한다. 따라서 제안 알고리즘은 기존방법보다 정확한 움직임벡터를 예측하기 위해 손실블록의 주변블록들 중세서 동일한 움직임을 갖는 블록들로 구성된 영역을 찾은 후, 동일움직임영역에 포함된 블록들의 움직임벡터를 이용하여 손실된 블록을 복원한다. 실험결과 제안방법이 기존방법에 비해 PSNR과 시각적인 화질면에서 우수한 성능을 보임을 알 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.53-61
• /
• 2014

In this paper, we propose a method using an image received by the depth camera in order to separate the wall in a three-dimensional space indoor environment. Results of the paper may be used to provide valuable information on the three-dimensional space. For example, they may be used to recognize the indoor space, to detect adjacent objects, or to project a projector on the wall. The proposed method first detects a normal vector at each point by using the three dimensional coordinates of points. The normal vectors are then clustered into several groups according to similarity. The RANSAC algorithm is applied to separate out planes. The domain knowledge helps to determine the wall among planes in an indoor environment. This paper concludes with experimental results that show performance of the proposed method in various experimental environment.

• Journal of Multimedia Information System
• /
• v.6 no.2
• /
• pp.61-66
• /
• 2019

VANET (Vehicular Ad-hoc Network) is a mobile Ad-hoc Network which deals with the moving vehicles. VANET supports Intelligent Transport Systems (ITS) which is related to different modes of transport and traffic management techniques. VANETs enabled users to be informed and make them safer. VANET uses IEEE 802.11p standard wireless access protocol for communication. An important and necessary issue of VANET is to design routing protocols. In a network, communication takes place by the use of the routing protocols. There are mainly two types of communications used such as Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) in VANET. Vehicles can send and receive messages among them and also to and from infrastructure used. In this paper, AODV, DSR and DSDV are compared by analysing the results of simulation on various metrics such as average throughput, instant throughput, packet delivery ratio and residual energy. Findings indicates utilization of AODV and DSR is more applicable for these metrics as compared to DSDV. A network simulator (NS2) is used for simulation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1011-1016
• /
• 2020

Rapid change in network topology in high-speed VANET(: Vehicular Ad Hoc Network) is an important task for routing protocol design. Selecting the next hop relay node that affects the performance of the routing protocol is a difficult process. The disadvantages of AODV(: Ad Hoc On-Demand Distance Vector) related to VANET are end-to-end delay and packet loss. This paper proposes the AAODV (Advanced AODV) technique to reduce the number of RREQ (: Route Request) and RREP (: Route Reply) messages by modifying the AODV routing protocol and adding direction parameters and 2-step filtering. It can be seen that the proposed AAODV reduces packet loss and minimizes the effect of direction parameters, thereby increasing packet delivery rate and reducing end-to-end delay.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.89-100
• /
• 2021

Smart Grid Network (SGN) is a next generation electrical power network which digitizes the power distribution grid and achieves smart, efficient, safe and secure operations of the electricity. The backbone of the SGN is information communication technology that enables the SGN to get full control of network station monitoring and analysis. In any network where communication is involved security is essential. It has been observed from several recent incidents that an adversary causes an interruption to the operation of the networks which lead to the electricity theft. In order to reduce the number of electricity theft cases, companies need to develop preventive and protective methods to minimize the losses from this issue. In this paper, we have introduced a machine learning based SVM method that detects malicious nodes in a smart grid network. The algorithm collects data (electricity consumption/electric bill) from the nodes and compares it with previously obtained data. Support Vector Machine (SVM) classifies nodes into Normal or malicious nodes giving the statues of 1 for normal nodes and status of -1 for malicious -abnormal-nodes. Once the malicious nodes have been detected, we have done a trust evaluation based on the nodes history and recorded data. In the simulation, we have observed that our detection rate is almost 98% where the false alarm rate is only 2%. Moreover, a Trust value of 50 was achieved. As a future work, countermeasures based on the trust value will be developed to solve the problem remotely.

• International Journal of Computer Science & Network Security
• /
• v.21 no.1
• /
• pp.40-48
• /
• 2021

Content-Based Image Retrieval (CBIR) system plays a vital role to retrieve the relevant images as per the user perception from the huge database is a challenging task. Images are represented is to employ a combination of low-level features as per their visual content to form a feature vector. To reduce the search time of a large database while retrieving images, a novel image retrieval technique based on feature dimensionality reduction is being proposed with the exploit of metaheuristic optimization techniques based on Genetic Algorithm (GA), Extended Binary Cuckoo Search (EBCS) and Whale Optimization Algorithm (WOA). Each image in the database is indexed using a feature vector comprising of fuzzified based color histogram descriptor for color and Median binary pattern were derived in the color space from HSI for texture feature variants respectively. Finally, results are being compared in terms of Precision, Recall, F-measure, Accuracy, and error rate with benchmark classification algorithms (Linear discriminant analysis, CatBoost, Extra Trees, Random Forest, Naive Bayes, light gradient boosting, Extreme gradient boosting, k-NN, and Ridge) to validate the efficiency of the proposed approach. Finally, a ranking of the techniques using TOPSIS has been considered choosing the best feature selection technique based on different model parameters.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.242-248
• /
• 2022

The article presents the analysis of modern methods of automatic comparison of original and unoriginal text to detect textual plagiarism. The study covers two types of plagiarism - literal, when plagiarists directly make exact copying of the text without changing anything, and intelligent, using more sophisticated techniques, which are harder to detect due to the text manipulation, like words and signs replacement. Standard techniques related to extrinsic detection are string-based, vector space and semantic-based. The first, most common and most successful target models for detecting literal plagiarism - N-gram and Vector Space are analyzed, and their advantages and disadvantages are evaluated. The most effective target models that allow detecting intelligent plagiarism, particularly identifying paraphrases by measuring the semantic similarity of short components of the text, are investigated. Models using neural network architecture and based on natural language sentence matching approaches such as Densely Interactive Inference Network (DIIN), Bilateral Multi-Perspective Matching (BiMPM) and Bidirectional Encoder Representations from Transformers (BERT) and its family of models are considered. The progress in improving plagiarism detection systems, techniques and related models is summarized. Relevant and urgent problems that remain unresolved in detecting intelligent plagiarism - effective recognition of unoriginal ideas and qualitatively paraphrased text - are outlined.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.419-422
• /
• 2024

본 논문에서는 다항식 보간법의 일종인 이동최소자승법(Moving least squares, MLS)을 네트워크로 학습하여, Divergence-constrained MLS 벡터장을 효율적으로 표현하는 방법을 제안한다. 벡터장을 구성하기 위해 MLS는 스칼라가 아닌 벡터 보간을 해야 하므로 행렬과 벡터의 크기가 더 커지며, 이는 계산량이 커짐을 나타낸다. 고차 보간(High-order interpolation)이 가능한 특징은 장점이 되지만, 계산량이 매우 크기 때문에 시뮬레이션에는 활용이 어렵다. Divergence-constrained MLS를 유체 시뮬레이션에 적용한 경우가 있지만, 실제로 슈퍼컴퓨터(Supercomputer)를 해야 장면 제작이 가능하므로 효용성이 떨어진다. 본 논문에서는 이러한 문제를 해결하기 위해 네트워크 학습을 통한 Divergence-constrained MLS 벡터장을 표현할 수 있는 결과를 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1540-1561
• /
• 2024

This research proposes a novel approach for Tamil Handwritten Character Recognition (THCR) that combines feature selection and ensemble learning techniques. The Tamil script is complex and highly variable, requiring a robust and accurate recognition system. Feature selection is used to reduce dimensionality while preserving discriminative features, improving classification performance and reducing computational complexity. Several feature selection methods are compared, and individual classifiers (support vector machines, neural networks, and decision trees) are evaluated through extensive experiments. Ensemble learning techniques such as bagging, and boosting are employed to leverage the strengths of multiple classifiers and enhance recognition accuracy. The proposed approach is evaluated on the HP Labs Dataset, achieving an impressive 95.56% accuracy using an ensemble learning framework based on support vector machines. The dataset consists of 82,928 samples with 247 distinct classes, contributed by 500 participants from Tamil Nadu. It includes 40,000 characters with 500 user variations. The results surpass or rival existing methods, demonstrating the effectiveness of the approach. The research also offers insights for developing advanced recognition systems for other complex scripts. Future investigations could explore the integration of deep learning techniques and the extension of the proposed approach to other Indic scripts and languages, advancing the field of handwritten character recognition.