• Journal of Information Processing Systems
• /
• 제20권4호
• /
• pp.458-476
• /
• 2024

To address the issue of class imbalance in network traffic data, which affects the network intrusion detection performance, a combined framework using transformers is proposed. First, Tomek Links, SMOTE, and WGAN are used to preprocess the data to solve the class-imbalance problem. Second, the transformer is used to encode traffic data to extract the correlation between network traffic. Finally, a hybrid deep learning network model combining a bidirectional gated current unit and deep neural network is proposed, which is used to extract long-dependence features. A DNN is used to extract deep level features, and softmax is used to complete classification. Experiments were conducted on the NSLKDD, UNSWNB15, and CICIDS2017 datasets, and the detection accuracy rates of the proposed model were 99.72%, 84.86%, and 99.89% on three datasets, respectively. Compared with other relatively new deep-learning network models, it effectively improved the intrusion detection performance, thereby improving the communication security of network data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• 대한음성학회지:말소리
• /
• 제62호
• /
• pp.113-131
• /
• 2007

It is reported that the segmental feature based recognition system shows better results than conventional feature based system in the previous studies. On the other hand, the various studies of combining neural network and hidden Markov models within a single system are done with expectations that it may potentially combine the advantages of both systems. With the influence of these studies, tandem approach was presented to use neural network as the classifier and hidden Markov models as the decoder. In this paper, we applied the trend information of segmental features to tandem architecture and used posterior probabilities, which are the output of neural network, as inputs of recognition system. The experiments are performed on Auroral database to examine the potentiality of the trend feature based tandem architecture. From the results, the proposed system outperforms on very low SNR environments. Consequently, we argue that the trend information on tandem architecture can be additionally used for traditional MFCC features.

• ETRI Journal
• /
• 제25권2호
• /
• pp.140-143
• /
• 2003

In this paper, we present a probabilistic approach to determining whether extracted facial features from a video sequence are appropriate for creating a 3D face model. In our approach, the distance between two feature points selected from the MPEG-4 facial object is defined as a random variable for each node of a probability network. To avoid generating an unnatural or non-realistic 3D face model, automatically extracted 2D facial features from a video sequence are fed into the proposed probabilistic network before a corresponding 3D face model is built. Simulation results show that the proposed probabilistic network can be used as a quality control agent to verify the correctness of extracted facial features.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권3호
• /
• pp.166-173
• /
• 2005

Preserving image features, edges and details in the process of impulsive noise filtering is an important problem. To avoid image blurring, only corrupted pixels must be filtered. In this paper, we propose an effective impulse noise detection method using Self-Organizing Neural Network(SONN) which applies median filter selectively for removing random-valued impulse noises while preserving image features, edges and details. Using a $3\times3$ window, we obtain useful local features with which impulse noise patterns are classified. SONN is trained with sample image patterns and each pixel pattern is classified by its local information in the image. The results of the experiments with various images which are the noise range of $5-15\%$ show that our method performs better than other methods which use multiple threshold values for impulse noise detection.

• 대한의용생체공학회:의공학회지
• /
• 제16권1호
• /
• pp.33-42
• /
• 1995

A new neural network architecture for the recognition of patterns from images is proposed, which is partially based on the results of physiological studies. The proposed network is composed of multi-layers and the nerve cells in each layer are connected by spatial filters which approximate receptive fields in optic nerve fields. In the proposed method, patterns recognition for complicated images is carried out using global features as well as local features such as lines and end-points. A new generating method of matched filters representing global features is proposed in this network.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.150-161
• /
• 2018

We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.

• 한국정밀공학회지
• /
• 제15권7호
• /
• pp.26-35
• /
• 1998

This paper presents a visual inspection algorithm looking for solder joint defects of IC chips on PCBs (Printed Circuit Boards). In this algorithm, seven features are proposed in order to categorize the solder joints into four classes such as normal, insufficient, excess, and no solder, and optimal back-propagation network is determined by error evaluation which depend on the number of neurons in hidden and out-put layers and selection of the features. In the end, a good accuracy of classification performance, an optimal determination of network structure and the effectiveness of chosen seven features are examined by experiment using proposed inspection algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.832-854
• /
• 2019

Action recognition has been studied in computer vision field for years. We present an effective approach to recognize actions using a dimension reduction method, which is applied as a crucial step to reduce the dimensionality of feature descriptors after extracting features. We propose to use sparse matrix and randomized kd-tree to modify it and then propose modified Local Fisher Discriminant Analysis (mLFDA) method which greatly reduces the required memory and accelerate the standard Local Fisher Discriminant Analysis. For feature encoding, we propose a useful encoding method called mix encoding which combines Fisher vector encoding and locality-constrained linear coding to get the final video representations. In order to add more meaningful features to the process of action recognition, the convolutional neural network is utilized and combined with mix encoding to produce the deep network feature. Experimental results show that our algorithm is a competitive method on KTH dataset, HMDB51 dataset and UCF101 dataset when combining all these methods.

• 스마트미디어저널
• /
• 제12권2호
• /
• pp.9-14
• /
• 2023

이 논문에서는 gradCAM를 활용한 적은 데이터로 얼굴 전체 또는 더 다양한 feature을 사용하여 얼굴인식을 할 수 있는 새로운 앙상블 방법론을 제안하였다. 인공지능 모델의 판단 근거는 gradCAM을 통하여 saliency map으로 표현될 수 있다. 따라서 본 논문에서는 학습된 얼굴인식 모델이 어느 부분에 편향적으로 관찰하여 판단했는지 gradCAM으로 시각화한다. 계산된 saliency map에서 일정 수치 이상의 돌출된 부분을 추가 모델이 학습에 사용할 수 없도록 노이즈를 추가해 데이터를 생산한다. 노이즈를 추가해서 만든 데이터로 학습할 경우 노이즈 부분을 활용하여 학습을 할 수 없으므로 새로운 얼굴 부분을 사용하여 얼굴인식 네트워크를 학습하게 된다. 기본 데이터로 학습한 네트워크와 돌출 부분에 노이즈를 추가해서 학습한 모델은 얼굴의 서로 다른 얼굴 feature을 사용할 수밖에 없고, 앙상블로 결합했을 때 얼굴의 좀 더 다양한 부분들을 사용한 임베딩 feature를 만들 수 있다. 이 논문에서 제안하는 앙상블 기법은 일반적인 앙상블 모델보다 정확도는 1.79% 상승하였고 equal error rate (EER)은 0.01788 감소하였다.