• 한국정보과학회논문지:소프트웨어및응용
• /
• 제26권12호
• /
• pp.1383-1392
• /
• 1999

이미 학습된 다층퍼셉트론 신경망을 디지털 VLSI 기술을 사용하여 하드웨어로 구현할 경우 신경망의 가중치 및 뉴런 출력들을 양자화해야 하는 문제가 발생한다. 이러한 신경망 변수들의 양자화는 결과적으로 주어진 입력에 대한 신경망의 최종 출력에서의 왜곡을 초래한다. 본 논문에서는 먼저 이러한 양자화로 인한 신경망 출력에서의 왜곡을 통계적으로 분석하였다. 분석 결과에 의하면 입력패턴 각 성분의 제곱들의 합과 가중치의 크기들이 양자화 영향에 주로 기여하는 것으로 나타났다. 이러한 분석 결과를 이용하여 양자화를 위한 정밀도가 주어졌을 때, 양자화 영향이 최소화된 다층퍼셉트론 신경망을 설계하는 방법을 제시하였다. 그리고 제안된 방법에 의해 얻은 신경망과 오류역전파 학습방법에 의하여 얻은 신경망의 성능을 비교함으로써 제안된 방법의 효율성을 입증하였다. 실험결과는 낮은 양자화 정밀도에서도 제안된 방법이 더 좋은 성능을 보였다.Abstract When we implement a multilayer perceptron with the digital VLSI technology, we generally have to quantize the weights and the neuron outputs. These quantizations eventually cause distortion in the output of the network for a given input. In this paper first we made a statistical analysis about the effect caused by the quantization on the output of the network. The analysis revealed that the sum of the squared input components and the sizes of the weights are the major factors which contribute to the quantization effect. We present a design method for an MLP which minimizes the quantization effect when the precision of the quantization is given. In order to show the effectiveness of the proposed method, we developed a network by our method and compared it with the one developed by the regular backpropagation. We could confirm that the network developed by our method performs better even with a low precision of the quantization.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.916-937
• /
• 2023

Most of the existing Distributed Denial-of-Service mitigation schemes in Software-Defined Networking are only implemented in the network domain managed by a single controller. In fact, the zombies for attackers to launch large-scale DDoS attacks are actually not in the same network domain. Therefore, abnormal traffic of DDoS attack will affect multiple paths and network domains. A single defense method is difficult to deal with large-scale DDoS attacks. The cooperative defense of multiple domains becomes an important means to effectively solve cross-domain DDoS attacks. We propose an efficient multi-domain DDoS cooperative defense mechanism by integrating blockchain and SDN architecture. It includes attack traceability, inter-domain information sharing and attack mitigation. In order to reduce the length of the marking path and shorten the traceability time, we propose an AS-level packet traceability method called ASPM. We propose an information sharing method across multiple domains based on blockchain and smart contract. It effectively solves the impact of DDoS illegal traffic on multiple domains. According to the traceability results, we designed a DDoS attack mitigation method by replacing the ACL list with the IP address black/gray list. The experimental results show that our ASPM traceability method requires less data packets, high traceability precision and low overhead. And blockchain-based inter-domain sharing scheme has low cost, high scalability and high security. Attack mitigation measures can prevent illegal data flow in a timely and efficient manner.

• 디지털산업정보학회논문지
• /
• 제18권4호
• /
• pp.1-11
• /
• 2022

Recently, research on license plate recognition, which is a core technology of an intelligent transportation system(ITS), is being actively conducted. In this paper, we propose a method to extract numbers and characters from low-quality license plate images by applying the YOLOv4 algorithm. YOLOv4 is a one-stage object detection method using convolution neural network including BACKBONE, NECK, and HEAD parts. It is a method of detecting objects in real time rather than the previous two-stage object detection method such as the faster R-CNN. In this paper, we studied a method to directly extract number and character regions from low-quality license plate images without additional edge detection and image segmentation processes. In order to evaluate the performance of the proposed method we experimented with 500 license plate images. In this experiment, 350 images were used for training and the remaining 150 images were used for the testing process. Computer simulations show that the mean average precision of detecting number and character regions on vehicle license plates was about 93.8%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.3003-3029
• /
• 2023

The rapid evolution of the IoT has paved the way for new opportunities in smart city domains, including e-health, smart homes, and precision agriculture. However, this proliferation of services demands effective SLAs between customers and service providers, especially for critical services. Difficulties arise in maintaining the integrity of such agreements, especially in vulnerable wireless environments. This study proposes a novel SLA management model that uses an SDN-Enabled WSN consisting of wireless nodes to interact with smart contracts in a straightforward manner. The proposed model ensures the persistence of network metrics and SLA provisions through smart contracts, eliminating the need for intermediaries to audit payment and compensation procedures. The reliability and verifiability of the data prevents doubts from the contracting parties. To meet the high-performance requirements of the blockchain in the proposed model, low-cost algorithms have been developed for implementing blockchain technology in wireless sensor networks with low-energy and low-capacity nodes. Furthermore, a cryptographic signature control code is generated by wireless nodes using the in-memory private key and the dynamic random key from the smart contract at runtime to prevent tampering with data transmitted over the network. This control code enables the verification of end-to-end data signatures. The efficient generation of dynamic keys at runtime is ensured by the flexible and high-performance infrastructure of the SDN architecture.

• 한국정밀공학회지
• /
• 제16권1호통권94호
• /
• pp.132-140
• /
• 1999

This paper suggests a monitoring method for the pulsed laser spot welding of the thin metal sheets using a point IR(InfraRed) sensor. A new criterion was introduced and the experimental results guaranteed the efficiency. The ideal radiation feature was derived from the mathematical model and was simulated. The radiation feature is robust to withstand the change of measuring condition and can be used to detect the absorbed laser energy. In an experiment, the radiation feature was examined for the differect laser energy. The pulse width and the laser power was variated and the radiation feature was examined. In the other experiment, the relationship between the weld strength and radiation feature was examined. Artificial Neural Network(ANN) was employed to find out the relationship. The correlation coefficient between the real strength and the estimated strength is high as 0.94 and the mean square error is low as 0.64 kgf learned parts. Another group of the welds was used to appraise the learning efficiency. The correlation coefficient between the measured and the estimated weld strength is high as 0.91.

• 한국정밀공학회지
• /
• 제12권8호
• /
• pp.53-62
• /
• 1995

In recent years, the rapid development of the machine tool and tough insert has made metal removal rates increase, and automatic system without human supervision requires a higher degree reliability of machining process. Therefore the control of chips is one of the important topics which deserves much attention. The chip classification was made based upon standard deviation of the mean cutting force measured by a tool dynamometer. STS304was chosen as the workpiece which is known as the difficult-to-cut material and mainly saw-toothed chip produced, and the chip type according to the standard deviation of mean cutting force was classified into five categories in this experiment. Long continuous type chip which interrupts the normal cutting process, and damages the operator, tool and workpiece has low standard deviation value, while short broken type chip, which is favourable chip for disposal, has relatively large standard deviation value. In addition, we investigated the possibility that the chip type can be predicted analyzing the relationship between chip type and cutting condition by the trained neural network, and obtained favourable results by which the chip type can be predicted with cutting conditon before cutting process.

• 한국정밀공학회지
• /
• 제26권12호
• /
• pp.117-122
• /
• 2009

The hexagonal network-type PDMS microstructures were fabricated and they were employed to low-friction drag surfaces. While the lowest contact angle measured from the smooth surface was $108^{\circ}$ the highest contact angle measured from the microstructured surfaces was $145^{\circ}$ The moving speed of bullet-type capsule attached with a PDMS pad of smooth surface ($CA=108^{\circ}$) was 0.1261 m/s and that with a PDMS pad of microstructured surface ($CA=145^{\circ}$) was 0.1464 m/s. Compared with the smooth surface, the microstructured surface showed 16.1% higher moving speed. The network-type microstructures have a composite surface that is composed with air and PDMS solid. Therefore, the surface does not wet: rather water is lifted by the microstructures. Because of the composite surface, water shows slip-flow on the microstructures, and thus friction drag can be reduced.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3889-3903
• /
• 2022

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tri-training algorithms using only cross-entropy or K-nearest neighbor strategy.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.688-701
• /
• 2023

The conventional methods of network intrusion detection system (NIDS) cannot measure the trend of intrusiondetection targets effectively, which lead to low detection accuracy. In this study, a NIDS method which based on a deep neural network in a big-data environment is proposed. Firstly, the entire framework of the NIDS model is constructed in two stages. Feature reduction and anomaly probability output are used at the core of the two stages. Subsequently, a convolutional neural network, which encompasses a down sampling layer and a characteristic extractor consist of a convolution layer, the correlation of inputs is realized by introducing bidirectional long short-term memory. Finally, after the convolution layer, a pooling layer is added to sample the required features according to different sampling rules, which promotes the overall performance of the NIDS model. The proposed NIDS method and three other methods are compared, and it is broken down under the conditions of the two databases through simulation experiments. The results demonstrate that the proposed model is superior to the other three methods of NIDS in two databases, in terms of precision, accuracy, F1- score, and recall, which are 91.64%, 93.35%, 92.25%, and 91.87%, respectively. The proposed algorithm is significant for improving the accuracy of NIDS.

• 한국정보과학회논문지:정보통신
• /
• 제35권2호
• /
• pp.112-119
• /
• 2008

최근 홈 네트워크 기술에 대한 관심도가 높아지면서 가정 내 장치들의 통신 방법에 대한 표준이 절실히 요구되고 있다. IEEE 802.1 AVB (Audio/Video Bridging)는 이더넷을 이용해 이러한 가정 내장치들 사이에 실시간성 데이타들을 전송하는 방법을 규정하고 있다. 하지만 IEEE 802.1 AVB는 IEEE 1588 PTP(Precision Time Protocol)와 같이 시간을 동기화 하기위해 다수의 컨트를 메시지를 이용하고 있어 복잡한 처리과정과 이로 인한 전송 지연의 문제점을 가지고 있다. 따라서 본 논문에서는 단일 타임싱크 프레임을 이용하여 시간을 동기화하는 방법을 제안한다. 단일 타임싱크 프레임을 이용한 방법은 여러 메시지 형태의 프레임을 이용하지 않고 단일 프레임을 이용하여 모든 동작이 가능한 범위의 동기식 이더넷의 전자기기들 사이에서의 통신에 적합한 처리 복잡도와 낮은 전송 지연을 제공한다. 나아가 단일 타임싱크 프레임을 이용한 시간 동기 방법에 실시간성 데이타 전송을 보장하는 대역폭 예약 방법 및 전송 방법에 대한 연구가 연계되어 진행되어야 한다.