• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.2
• /
• pp.105-110
• /
• 2008

Human being recognizes emotion fusing information of the other speech signal, expression, gesture and bio-signal. Computer needs technologies that being recognized as human do using combined information. In this paper, we recognized five emotions (normal, happiness, anger, surprise, sadness) through speech signal and facial image, and we propose to method that fusing into emotion for emotion recognition result is applying to multimodal method. Speech signal and facial image does emotion recognition using Principal Component Analysis (PCA) method. And multimodal is fusing into emotion result applying fuzzy membership function. With our experiments, our average emotion recognition rate was 63% by using speech signals, and was 53.4% by using facial images. That is, we know that speech signal offers a better emotion recognition rate than the facial image. We proposed decision fusion method using S-type membership function to heighten the emotion recognition rate. Result of emotion recognition through proposed method, average recognized rate is 70.4%. We could know that decision fusion method offers a better emotion recognition rate than the facial image or speech signal.

• Journal of Korean Neurosurgical Society
• /
• v.30 no.sup1
• /
• pp.55-60
• /
• 2001

Objective : The purpose of the present study was to examine neurologic changes, fusion rate and degree of kyphosis from the surgical results of those patients who underwent multi-level anterior interbody fusion and internal fixation. Methods : Among 63 cases of the patients who received multi-level anterior interbody fusion and internal fixation in 5 years between 1995 to 1999 at the neurosurgery department, we performed a retrospective study in 52 cases that could be followed up with dynamic view imaging ; the results were compared and analyzed. The analysis was based on the results of history taking, physical findings and radiologic findings, and Odom criteria were used to classify those cases with neurologic changes. Results : Among those 52 cases in whom the follow-up was possible for at least a year and dynamic view imaging was possible, bone fusion was seen in 93% of the trauma cases and 95% in the non-trauma cases and overall bone fusion was observed in 94% of the cases. Bone fusion was seen in 93% of the autobone cases, 95% of the allobone cases, and 94% of the Mesh cases. Radiologic changes were observed by comparing the lateral view after surgery ; kyphosis was seen in 53% of the autobone cases, in 70% of the allobone cases, and in 35% of Mesh cases ; in 45% and 60% of the non-trauma cases and trauma cases, respectively ; and in 55% of the 2 level fusion cases and 46% of the 3 level fusion cases. Neurologic changes classified according to Odom criteria showed excellent result in 48% of all the cases, good in 23%, fair in 4%, and poor in 25%. Conclusion : Even those cases with multi-level fusion, a high fusion rate could be obtained by performing anterior interbody fusion and internal fixation ; those cases with kyphosis were related more with the presence or absence of posterior compartment injury rather than the fusion level ; and those trauma cases showed not much difference in the fusion rate compared with non-trauma cases but had a high possibility of kyphosis.

• Journal of Korean Neurosurgical Society
• /
• v.59 no.6
• /
• pp.597-603
• /
• 2016

Introduction : Perioperative irradiation is often combined with spine tumor surgery. Radiation is known to be detrimental to healing process of bone fusion. We tried to investigate bone fusion rate in spine tumor surgery cases with perioperative radiation therapy (RT) and to analyze significant factors affecting successful bone fusion. Methods : Study cohort was 33 patients who underwent spinal tumor resection and bone graft surgery combined with perioperative RT. Their medical records and radiological data were analyzed retrospectively. The analyzed factors were surgical approach, location of bone graft (anterior vs. posterior), kind of graft (autologous graft vs. allograft), timing of RT (preoperative vs. postoperative), interval of RT from operation in cases of postoperative RT (within 1 month vs. after 1 month) radiation dose (above 38 Gy vs. below 38 Gy) and type of radiation therapy (conventional RT vs. stereotactic radiosurgery). The bone fusion was determined on computed tomography images. Result : Bone fusion was identified in 19 cases (57%). The only significant factors to affect bony fusion was the kind of graft (75% in autograft vs. 41 in allograft, p=0.049). Other factors proved to be insignificant relating to postoperative bone fusion. Regarding time interval of RT and operation in cases of postoperative RT, the time interval was not significant (p=0.101). Conclusion : Spinal fusion surgery which was combined with perioperative RT showed relatively low bone fusion rate (57%). For successful bone fusion, the selection of bone graft was the most important.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4395-4412
• /
• 2020

The multisource image fusion has become an active topic in the last few years owing to its higher segmentation rate. To enhance the accuracy of multimodal pig-body feature segmentation, a multisource image fusion method was employed. Nevertheless, the conventional multisource image fusion methods can not extract superior contrast and abundant details of fused image. To superior segment shape feature and detect temperature feature, a new multisource image fusion method was presented and entitled as NSST-GF-IPCNN. Firstly, the multisource images were resolved into a range of multiscale and multidirectional subbands by Nonsubsampled Shearlet Transform (NSST). Then, to superior describe fine-scale texture and edge information, even-symmetrical Gabor filter and Improved Pulse Coupled Neural Network (IPCNN) were used to fuse low and high-frequency subbands, respectively. Next, the fused coefficients were reconstructed into a fusion image using inverse NSST. Finally, the shape feature was extracted using automatic threshold algorithm and optimized using morphological operation. Nevertheless, the highest temperature of pig-body was gained in view of segmentation results. Experiments revealed that the presented fusion algorithm was able to realize 2.102-4.066% higher average accuracy rate than the traditional algorithms and also enhanced efficiency.

• Journal of Welding and Joining
• /
• v.34 no.1
• /
• pp.68-74
• /
• 2016

Adoption of narrow gap welding shall be increased for the butt joint of thick plate, because the deformation and welding cost is reduced by decrease of cross-sectional area. However, sometimes narrow gap causes defects such as lack of fusion since it has small groove angle and narrow groove width. Therefore, GMAW, GTAW and SAW process shall be adopted to narrow gap welding with small bead hight and low deposition rate. In this study, Super-TIG welding using C-type strip was applied to semi-narrow gap butt joint in order to increase the welding productivity. High deposition rate 10kg/hr was obtained by high current 600A without undercut, humping bead and other welding defects. Measuring the mean and standard deviation of the melting depth to evaluate the developed processes, the fusion line type was determined by measuring the difference between maximum and minium melting depth. Furthermore, a model on arch fusion line and linear fusion line was suggested in order to prevent LF on groove wall in narrow gap butt welding.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.361-368
• /
• 2018

As autonomous driving research is rapidly developing, pedestrian detection study is also successfully investigated. However, most of the study utilizes color image datasets and those are relatively easy to detect the pedestrian. In case of color images, the scene should be exposed by enough light in order to capture the pedestrian and it is not easy for the conventional methods to detect the pedestrian if it is the other case. Therefore, in this paper, we propose deep neural network (DNN)-based multi-spectrum pedestrian detection method using color and thermal images. Based on single-shot multibox detector (SSD), we propose fusion network structures which simultaneously employ color and thermal images. In the experiment, we used KAIST dataset. We showed that proposed SSD-H (SSD-Halfway fusion) technique shows 18.18% lower miss rate compared to the KAIST pedestrian detection baseline. In addition, the proposed method shows at least 2.1% lower miss rate compared to the conventional halfway fusion method.

• Reproductive and Developmental Biology
• /
• v.35 no.1
• /
• pp.17-22
• /
• 2011

This study was designed to determine the effect of electric field strength, duration and fusion buffer in fusion parameters on the rate of membrane fusion between the somatic cell and cytoplast for Korean cattle (HanWoo) somatic cell nuclear transfer (SCNT) procedure. Following electrofusion, effect of 5 or $10\;{\mu}M$ $Ca^{2+}$-ionophore of activation treatment on subsequent development was also evaluated. Cell fusion rates were significantly increased from 23.1% at 20 V/mm to 59.7% at 26 V/mm and 52.9% at 27 V/mm (p<0.05). Due to higher cytoplasmic membrane rupture or cellular lysis, overall efficiency was decreased when the strength was increased to 30 V/mm (18.5%) and 40 V/mm (6.3%) and the fusion rate was also decreased when the strength was at 25 V/mm or below. The optimal duration of electric stimulation was significantly higher in $25\;{\mu}s$ than 20 and $30\;{\mu}s$ (18.5% versus 9.3% and 6.3%, respectively, p<0.05). Two nonelectrolyte fusion buffers, Zimmermann's (0.28 M sucrose) and 0.28 M mannitol solution for cell fusion, were used for donor cell and ooplast fusion and the fusion rate was significantly higher in Zimmermann's cell fusion buffer than in 0.28 M mannitol (91.1% versus 48.4%, respectively, p<0.05). The cleavage and blastocyst formation rates of SCNT bovine embryos activated by $5\;{\mu}M$ $Ca^{2+}$-ionophore was significantly higher than the rates of the embryos activated with $10\;{\mu}M$ of $Ca^{2+}$-ionophore (70.0% versus 42.9% and 22.5% versus 14.3%, respectively; p<0.05). This result is the reverse to that of parthenotes which shows significantly higher cleavage and blastocyst rates in $10\;{\mu}M$ $Ca^{2+}$-ionophore than $5\;{\mu}M$ counterpart (65.6% versus 40.3% and 19.5% versus 9.7%, respectively; p<0.05). In conclusion, SCNT couplet fusion by single pulse of 26 V/mm for $25\;{\mu}s$ in Zimmermann's fusion buffer followed by artificial activation with $5\;{\mu}M$ $Ca^{2+}$-ionophore are suggested as optimal fusion and activation methods in Korean cattle SCNT protocol.

• Journal of Korean Neurosurgical Society
• /
• v.56 no.6
• /
• pp.469-474
• /
• 2014

Objective : The use of direct lumbar interbody fusion (DLIF) has gradually increased; however, no studies have directly compared DLIF and transforaminal lumbar interbody fusion (TLIF). We compared DLIF and TLIF on the basis of clinical and radiological outcomes. Methods : A retrospective review was performed on the medical records and radiographs of 98 and 81 patients who underwent TLIF and DLIF between January 2011 and December 2012. Clinical outcomes were compared with a visual analog scale (VAS) and the Oswestry disability index (ODI). The preoperative and postoperative disc heights, segmental sagittal/coronal angles, and lumbar lordosis were measured on radiographs. Fusion rates, operative time, estimated blood loss (EBL), length of hospital stay, and complications were assessed. Results : DLIF was superior to TLIF regarding its ability to restore disc height, foraminal height, and coronal balance (p<0.001). As the extent of surgical level increased, DLIF displayed significant advantages over TLIF considering the operative time and EBL. However, fusion rates at 12 months post-operation were lower for DLIF (87.8%) than for TLIF (98.1%) (p=0.007). The changes of VAS and ODI between the TLIF and DLIF were not significantly different (p>0.05). Conclusion : Both DLIF and TLIF are less invasive and thus good surgical options for treating degenerative lumber diseases. DLIF has higher potential in increasing neural foramina and correcting coronal balance, and involves a shorter operative time and reduced EBL, in comparison with TLIF. However, DLIF displayed a lower fusion rate than TLIF, and caused complications related to the transpsoas approach.

• Journal of Korean Neurosurgical Society
• /
• v.45 no.2
• /
• pp.81-84
• /
• 2009

Objective : Many biomechanical and clinical studies on adjacent segment degeneration (ASD) have addressed cranial segment. No study has been conducted on caudal segment degeneration after upper segment multiple lumbar fusions. This is a retrospective investigation of the L5-S1 segment after spinal fusion at and above L4-5, which was undertaken to analyze the rate of caudal ASD at L5-S1 after spinal fusion on and above L4-5 and to determine that factors that might have influenced it. Methods : The authors included 67 patients with L4-5, L3-5, or L2-5 posterior fusions. Among these patients, 28 underwent L4-5 fusion, 23 L3-5, and 16 L2-5 fusions. Pre- and postoperative radiographs were analyzed to assess degenerative changes at L5-S1. Also, clinical results after fusion surgery were analyzed. Results : Among the 67 patients, 3 had pseudoarthrosis, and 35 had no evidence of ASD, cranially and caudally. Thirteen patients (19.4%) showed caudal ASD, 23 (34.3%) cranial ASD, and 4 (6.0%) both cranial and caudal ASD. Correlation analysis for caudal ASD at L5-S1 showed that pre-existing L5-S1 degeneration was most strongly correlated. In addition, numbers of fusion segments and age were also found to be correlated. Clinical outcome was not correlated with caudal ASD at L5-S1. Conclusion : If caudal and cranial ASD are considered, the overall occurrence rate of ASD increases to 50%. The incidence rate of caudal ASD at L5-S1 was significantly lower than that of cranial ASD. Furthermore, the occurrence of caudal ASD was found to be significantly correlated with pre-existing disc degeneration.

• Journal of Korean Neurosurgical Society
• /
• v.52 no.1
• /
• pp.27-31
• /
• 2012

Objective : Although hydroxyapatite (HA) spacer has been used for laminoplasty, there have been no reports on factors associated with fusion and on the effects of HA shape. Methods : During January 2004 and January 2010, 45 patients with compressive cervical myelopathy underwent midline-splitting open door laminoplasty with winged (33 cases) and wingless (12 cases) HAs by a single surgeon. Minimal and mean follow up times were 12 and 28.1 months, respectively. Japanese Orthopedic Association (JOA) score was used for clinical outcome measurement. Cervical X-rays were taken preoperatively, immediately post-operatively, and after 3, 6, and 12 months and computed tomography scans were performed preoperatively, immediately post-operatively and after 12 months. Cervical lordosis, canal dimension, fusion between lamina and HA, and affecting factors of fusion were analyzed. Results : All surgeries were performed on 142 levels, 99 in the winged and 43 in the wingless HA groups. JOA scores of the winged group changed from $10.4{\pm}2.94$ to $13.3{\pm}2.35$ and scores of the wingless group changed from $10.8{\pm}2.87$ to $13.8{\pm}3.05$. There was no significant difference on lordotic and canal dimensional change between two groups. Post-operative 12 month fusion rate between lamina and HA was significantly lower in the winged group (18.2 vs. 48.8% p=0.001). Multivariate analysis showed that ossification of the posterior longitudinal ligament, male gender, and wingless type HA were significantly associated with fusion. Conclusion : Clinical outcome was similar in patients receiving winged and wingless HA, but the wingless type was associated with a higher rate of fusion between HA and lamina at 12 months post-operatively.