• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.3
• /
• pp.181-187
• /
• 2003

For the moving objects with environmental sensors such as object tracking moving robot with audio and video sensors, environmental information acquired from sensors keep changing according to movements of objects. In such case, due to lack of adaptability and system complexity, conventional control schemes show limitations on control performance, and therefore, sensory-motor systems, which can intuitively respond to various types of environmental information, are desirable. And also, to improve the system robustness, it is desirable to fuse more than two types of sensory information simultaneously. In this paper, based on Braitenberg's model, we propose a sensory-motor based fusion system, which can trace the moving objects adaptively to environmental changes. With the nature of direct connecting structure, sensory-motor based fusion system can control each motor simultaneously, and the neural networks are used to fuse information from various types of sensors. And also, even if the system receives noisy information from one sensor, the system still robustly works with information from other sensors which compensates the noisy information through sensor fusion. In order to examine the performance, sensory-motor based fusion model is applied to object-tracking four-foot robot equipped with audio and video sensors. The experimental results show that the sensory-motor based fusion system can tract moving objects robustly with simpler control mechanism than model-based control approaches.

• The Korean Journal of Zoology
• /
• v.35 no.1
• /
• pp.29-36
• /
• 1992

The present study describes the production of monoclonal antibodies against cultured chick myoblast to pursue critical proteins in muscle cell fusion. Among a panel of monoclonal antibodies, three, Mll-3H 13, Mll-3Hl8 and Mll-3H35 were inhibited movblast fusion. A single 101-kDa antigen reactive with monoclonal antibody Mll-3H35 was detected by radioimmu-noprecipitation or by immunoblotting. During the course of myogenesis, the level of the protein remarkably decreased as the cells there differentiated. These results suggest that the protein platys a direct role in the process of myoblast fusion mechanism.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1405-1419
• /
• 2018

An image fusion method is proposed on the basis of depth model segmentation to overcome the shortcomings of noise interference and artifacts caused by infrared and visible image fusion. Firstly, the deep Boltzmann machine is used to perform the priori learning of infrared and visible target and background contour, and the depth segmentation model of the contour is constructed. The Split Bregman iterative algorithm is employed to gain the optimal energy segmentation of infrared and visible image contours. Then, the nonsubsampled contourlet transform (NSCT) transform is taken to decompose the source image, and the corresponding rules are used to integrate the coefficients in the light of the segmented background contour. Finally, the NSCT inverse transform is used to reconstruct the fused image. The simulation results of MATLAB indicates that the proposed algorithm can obtain the fusion result of both target and background contours effectively, with a high contrast and noise suppression in subjective evaluation as well as great merits in objective quantitative indicators.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.

• Journal of Internet Computing and Services
• /
• v.11 no.6
• /
• pp.61-72
• /
• 2010

Spectrum scarcity problem and increasing spectrum demand for new wireless applications have embossed the importance of cognitive radio technology; the technology enables the sharing of channels among secondary (unlicensed) and primary (licensed) users on a non-interference basis after sensing the vacant channel. To enhance the accuracy of sensing, distributed spectrum sensing is proposed. However, it is necessary to provide the robustness against the compromised sensing nodes in the distributed spectrum sensing. RDSS, a fusion mechanism based on the reputation of sensing nodes and WSPRT (weighted sequential probability ratio test), was proposed. However, in RDSS, the execution number of WSPRT could increase according to the order of inputted sensing values, and the fast defense against the forged values is difficult. In this paper, we propose an enhanced fusion mechanism to input the sensing values in reputation order and exclude the sensing values with the high possibility to be compromised, using the trend of reputation variation. We evaluate our mechanism through simulation. The results show that our mechanism improves the robustness against attack with the smaller number of sensing values and more accurate detection ratio than RDSS.

• The Korean Journal of Zoology
• /
• v.26 no.4
• /
• pp.235-251
• /
• 1983

Several approaches have been made to access the mechanism of fusion in chick myoblast in vitro. Lactoperoxidase-catalyzed iodination was applied to labell cell surface proteins during myogenesis. Quantitative as well as qualitative changes were observed in $^131$I surface components of prefusion and postfusion cells. Two proteins with a molecular weight of 165K and 93K daltons were observed to appear at the onset of fusion as compared to prefusion stage. At the same time, 245K dalton protein decreased whereas the low molecular weight proteins increased consistently. The decrease of high molecular weight proteins appears to be associated with the cell cycle of myoblast during differentiation. The increased appearance of low molecular weight proteins might be due to the proteolytic cleavage of the high molecular weight proteins. Examination of intracellulr cAMP levels during fusion has revealed that a large but transient increase in cAMP occurs before the onset of fusion. This result suggests a causal relationship between the increase of cAMP and the onset of fusion, and further, that differentiating myoblasts are synthronized to a high degree. During the course of myoblast differentiation, at least four lowe molecular weight proteins, which different from major surface proteins iodinated, were identifiable in the culture medium. These proteins could be ascribed to be released from the membrane by proteolytic cleavage of surface proteins in the course of myoblast fusion. The significance of cell surface alterations and the released proteins during the fusion, the involvement of cAMP in the onset of fusion and the possibility that fusion is promoted by external factor(s) are discussed.

• Journal of Powder Materials
• /
• v.24 no.2
• /
• pp.141-146
• /
• 2017

$Bi_2Te_3$ powders are recovered by wet chemical reduction for waste n-type thermoelectric chips, and the recovered particles with different morphologies are prepared using various surfactants such as cetyltrimethylammonium bromide (CTAB), sodium dodecylbenzenesulfonate (SDBS), and ethylenediaminetetraacetic acid (EDTA). When citric acid is added as the surfactant, the shape of the aggregated particles shows no distinctive features. On the other hand, rod-shaped particles are formed in the sample with CTAB, and sheet-like particles are synthesized with the addition of SDBS. Further, particles with a tripod shape are observed when EDTA is added as the surfactant. The growth mechanism of the particle shapes depending on the surfactant is investigated, with a focus on the nucleation and growth phenomena. These results help to elucidate the intrinsic formation mechanism of the rod, plate, and tripod structures of the $Bi_2Te_3$ recovered by the wet reduction process.

• 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.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.4
• /
• pp.444-452
• /
• 2003

An integration system with multi-measurement sets can be realized via combined application of a centralized and federated Kalman filter. It is difficult for the centralized Kalman filter to remove a failed sensor in comparison with the federated Kalman filter. All varieties of Kalman filters monitor innovation sequence (residual) for detection and isolation of a failed sensor. The innovation sequence, which is selected as an indicator of real time estimation error plays an important role in adaptive mechanism design. In this study, the centralized Kalman filter with adaptive measurement fusion is introduced by means of innovation sequence. The objectives of adaptive measurement fusion are automatic isolation and recovery of some sensor failures as well as inherent monitoring capability. The proposed adaptive filter is applied to the GPS/SDINS integration system with an additional sensor. Simulation studies attest that the proposed adaptive scheme is effective for isolation and recovery of immediate sensor failures.