• International Journal of Contents
• /
• v.8 no.1
• /
• pp.23-29
• /
• 2012

Multiple expression levels of genes obtained using time series microarray experiments have been exploited effectively to enhance understanding of a wide range of biological phenomena. However, the unique nature of microarray data is usually in the form of large matrices of expression genes with high dimensions. Among the huge number of genes presented in microarrays, only a small number of genes are expected to be effective for performing a certain task. Hence, discounting the majority of unaffected genes is the crucial goal of gene selection to improve accuracy for disease diagnosis. In this paper, a non-Gaussian weight matrix obtained from an incremental model is proposed to extract useful features of multivariate time series microarrays. The proposed method can automatically identify a small number of significant features via discovering hidden variables from a huge number of features. An unsupervised hierarchical clustering representative is then taken to evaluate the effectiveness of the proposed methodology. The proposed method achieves promising results based on predictive accuracy of clustering compared to existing methods of analysis. Furthermore, the proposed method offers a robust approach with low memory and computation costs.

• IE interfaces
• /
• v.22 no.2
• /
• pp.126-134
• /
• 2009

As product quality and yield are essential factors in semiconductor manufacturing, monitoring the main manufacturing steps is a critical task. For the purpose, FDC(Fault detection and classification) is used for diagnosing fault states in the processes by monitoring data stream collected by equipment sensors. This paper proposes an FDC model based on decision tree which provides if-then classification rules for causal analysis of the processing results. Unlike previous decision tree approaches, we reflect the structural aspect of the data stream to FDC. For this, we segment the data stream into multiple subregions, define structural features for each subregion, and select the features which have high relevance to results of the process and low redundancy to other features. As the result, we can construct simple, but highly accurate FDC model. Experiments using the data stream collected from etching process show that the proposed method is able to classify normal/abnormal states with high accuracy.

• Journal of Information Processing Systems
• /
• v.10 no.4
• /
• pp.503-522
• /
• 2014

In the cursive handwriting recognition process, script trajectory segmentation and modeling represent an important task for large or open lexicon context that becomes more complicated in multi-writer applications. In this paper, we will present a developed system of Arabic online handwriting modeling based on graphemes segmentation and the extraction of its geometric features. The main contribution consists of adapting the Fourier descriptors to model the open trajectory of the segmented graphemes. To segment the trajectory of the handwriting, the system proceeds by first detecting its baseline by checking combined geometric and logic conditions. Then, the detected baseline is used as a topologic reference for the extraction of particular points that delimit the graphemes' trajectories. Each segmented grapheme is then represented by a set of relevant geometric features that include the vector of the Fourier descriptors for trajectory shape modeling, normalized metric parameters that model the grapheme dimensions, its position in respect to the baseline, and codes for the description of its associated diacritics.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.301-303
• /
• 2003

The extraction of 3D road network from high-resolution aerial images is still one of the current challenges in digital photogrammetry and computer vision. For many years, there are many researcher groups working for this task, but unt il now, there are no papers for doing this with TLS (Three linear scanner), which has been developed for the past several years, and has very high-resolution (about 3 cm in ground resolution). In this paper, we present a methodology of road extraction from high-resolution digital imagery taken over urban areas using this modern photogrammetry’s scanner (TLS). The key features of the approach are: (1) Because of high resolution of TLS image, our extraction method is especially designed for constructing 3D road map for next -generation digital navigation map; (2) for extracting road, we use the global context of the intensity variations associated with different features of road (i.e. zebra line and center line), prior to any local edge. So extraction can become comparatively easy, because we can use different special edge detector according different features. The results achieved with our approach show that it is possible and economic to extract 3D road data from Three Linear Scanner to construct next -generation digital navigation road map.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.754-771
• /
• 2021

In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2078-2093
• /
• 2019

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.685-694
• /
• 2022

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.991-1003
• /
• 2021

Automatic modulation classification is essential in radar emitter identification. We propose a cascade classifier by combining a support vector machine (SVM) and convolutional neural network (CNN), considering that noise might be taken as radar signals. First, the SVM distinguishes noise signals by the main ridge slice feature of signals. Second, the complex envelope features of the predicted radar signals are extracted and placed into a designed CNN, where a modulation classification task is performed. Simulation results show that the SVM-CNN can effectively distinguish radar signals from noise. The overall probability of successful recognition (PSR) of modulation is 98.52% at 20 dB and 82.27% at -2 dB with low computation costs. Furthermore, we found that the accuracy of intermediate frequency estimation significantly affects the PSR. This study shows the possibility of training a classifier using complex envelope features. What the proposed CNN has learned can be interpreted as an equivalent matched filter consisting of a series of small filters that can provide different responses determined by envelope features.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.704-707
• /
• 2021

Pigs' aggressive behavior represents one of the common issues that occur inside pigpens and which harm pigs' health and welfare, resulting in a financial burden to farmers. Continuously monitoring several pigs for 24 hours to identify those behaviors manually is a very difficult task for pig caretakers. In this study, we propose a lightweight video-based approach for monitoring pigs' aggressive behavior that can be implemented even in small-scale farms. The proposed system receives sequences of frames extracted from an RGB video stream containing pigs and uses MnasNet with a DM value of 0.5 to extract image features from pigs' ROI identified by predefined annotations. These extracted features are then forwarded to a lightweight LSTM to learn temporal features and perform behavior recognition. The experimental results show that our proposed model achieved 0.92 in recall and F1-score with an execution time of 118.16 ms/sequence.