• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.9
• /
• pp.414-419
• /
• 2006

This paper presents a design of a multi-sensor data fusion filter for a Flight Test System. The multi-sensor data consist of positional information of the target from radars and a telemetry system. The data fusion filter has a structure of a federated Kalman filter and is based on the Singer dynamic target model. It consists of dedicated local filter for each sensor, generally operating in parallel, plus a master fusion filter. A fault detection and correction algorithms are included in the local filter for treating bad measurements and sensor faults. The data fusion is carried out in the fusion filter by using maximum likelihood estimation algorithm. The performance of the designed fusion filter is verified by using both simulation data and real data.

• 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.

• International Journal of CAD/CAM
• /
• v.9 no.1
• /
• pp.121-128
• /
• 2010

The purpose of this study is to clarify the mechanical behavior of human lumbar vertebrae (L3/L4) with and without fusion bone under physiological axial compression. The author has developed the program code to build the patient specific three-dimensional geometric model from the computed tomography (CT) images. The developed three-dimensional model provides the necessary information to the physicians and surgeons to visually interact with the model and if needed, plan the way of surgery in advance. The processed data of the model is versatile and compatible with the commercial computer aided design (CAD), finite element analysis (FEA) software and rapid prototyping technology. The actual physical model is manufactured using rapid prototyping technique to confirm the executable competence of the processed data from the developed program code. The patient specific model of L3/L4 vertebrae is analyzed under compressive loading condition by the FEA approach. By varying the spacer position and fusion bone with and without pedicle instrumentation, simulations were carried out to find the increasing axial stiffness so as to ensure the success of fusion technique. The finding was helpful in positioning the fusion bone graft and to predict the mechanical stress and deformation of body organ indicating the critical section.

• Journal of Biomedical Engineering Research
• /
• v.36 no.6
• /
• pp.276-282
• /
• 2015

Recently, during the multi-level fusion with pedicle screws, interspinous spacer are sometimes substituted for the most superior level of the fusion in an attempt to reduce the number of fusion level and likelihood of degeneration process at the adjacent level. In this study, a finite element (FE) study was performed to assess biomechanical efficacies of the interspinous spacer combined with posterior lumbar fusion with a previously-validated 3-dimensional FE model of the intact lumbar spine (L1-S1). The post-operative models were made by modifying the intact model to simulate the implantation of interspinous spacer and pedicle screws at the L3-4 and L4-5. Four different configurations of the post-op model were considered: (1) a normal spinal model; (2) Type 1, one-level fusion using posterior pedicle screws at the L4-5; (3) Type 2, two-level (L3-5) fusion; (4) Type 3, Type 1 plus Coflex$^{TM}$ at the L3-4. hybrid protocol (intact: 10 Nm) with a compressive follower load of 400N were used to flex, extend, axially rotate and laterally bend the FE model. As compared to the intact model, Type 2 showed the greatest increase in Range of motion (ROM) at the adjacent level (L2-3), followed Type 3, and Type 1 depending on the loading type. At L3-4, ROM of Type 2 was reduced by 34~56% regardless of loading mode, as compared to decrease of 55% in Type 3 only in extension. In case of normal bone strength model (Type 3_Normal), PVMS at the process and the pedicle remained less than 20% of their yield strengths regardless of loading, except in extension (about 35%). However, for the osteoporotic model (Type 3_Osteoporotic), it reached up to 56% in extension indicating increased susceptibility to fracture. This study suggested that substitution of the superior level fusion with the interspinous spacer in multi-level fusion may be able to offer similar biomechanical outcome and stability while reducing likelihood of adjacent level degeneration.

• Journal of Korean Neurosurgical Society
• /
• v.46 no.1
• /
• pp.45-51
• /
• 2009

Objective : To evaluate the potential effects of risedronate (RIS) which shows a higher anti-resorptive effect among bisphosphonates, after a posterolateral lumbar intertransverse process spinal fusion using both autograft and allograft in a rat model. Methods : A totoal of 28 Sprague-Dawley rats were randomized into 2 study groups. A posterolateral lumbar intertransverse process spinal fusion was peformed using both autograft and allograft in a rat model. Group I (control) received 0.1 mL of steril saline (placebo) and Group II (treatment) received risedronate, equivalent to human dose (10 ${\mu}g$/kg/week) for 10-weeks period. Results : The fusion rates as determined by manual palpation were 69% in the group I and 46% in the group II (p = 0.251). According to radiographic score, the spinal segment was considered to be fused radiographically in 7 (53%) of the 13 controls and 9 (69%) of the 13 rats treated with RIS (p = 0.851). The mean histological scores were 5.69 ${\pm}$ 0.13 and 3.84 ${\pm}$ 0.43 for the control and treatment groups, respectively. There was a significant difference between the both groups (p = 0.001). The mean bone density of the fusion masses was 86.9 ${\pm}$ 2.34 in the control group and 106.0 ${\pm}$ 3.54 in the RIS treatment group. There was a statistical difference in mean bone densities of the fusion masses comparing the two groups (p=0.001). Conclusion : In this study, risedronate appears to delay bone fusion in a rat model. This occurs as a result of uncoupling the balanced osteoclastic and osteoblastic activity inherent to bone healing. These findings suggest that a discontinuation of risedronate postoperatively during acute fusion period may be warranted.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.655-658
• /
• 2021

The purpose of multimodal medical image fusion (MMIF) is to integrate images of different modes with different details into a result image with rich information, which is convenient for doctors to accurately diagnose and treat the diseased tissues of patients. Encouraged by this purpose, this paper proposes a novel method based on a two-scale decomposer and detail preservation model. The first step is to use the two-scale decomposer to decompose the source image into the energy layers and structure layers, which have the characteristic of detail preservation. And then, structure tensor operator and max-abs are combined to fuse the structure layers. The detail preservation model is proposed for the fusion of the energy layers, which greatly improves the image performance. The fused image is achieved by summing up the two fused sub-images obtained by the above fusion rules. Experiments demonstrate that the proposed method has superior performance compared with the state-of-the-art fusion methods.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• Journal of Korean Neurosurgical Society
• /
• v.50 no.5
• /
• pp.409-414
• /
• 2011

Objective : The aim of this study was to evaluate the impact of sodium hyaluronate-sodium carboxymethyl cellulose (HA-CMC), an anti-adhesive material for spinal surgery, on bone fusion by applying it to rat spinal models after lumbar posterolateral fusion. Methods : Lumbar posterolateral fusion was performed at L4-5 using bone graft substitutes in 30 rats. HA-CMC was injected in 15 rats at a dose of 0.2 cc (HA-CMC group) and a saline solution of 0.2 cc in the other 15 rats (control group). Simple radiographs were taken until postoperative 9 weeks with an interval of one week. At postoperative 4 and 9 weeks, three dimensional computed tomography (3D CT) scanning was performed to observe the process of bone fusion. At 9 weeks, bone fusion was confirmed by gross examination and manual palpation. Results : There were no statistically significant differences in bone fusion between the two groups. 3D CT scanning did not reveal significant differences between the groups. The gross examination and manual palpation after autopsy performed at 9 weeks confirmed bone union in 93.3% of both groups. Conclusion : The anti-adhesive material used for spinal surgery did not have adverse effects on spinal fusion in rats.