• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.234-236
• /
• 2020

Content-adaptive training and transmission of the model parameters of neural networks can boost up the SR performance with higher restoration fidelity. In this case, efficient transmission of neural network parameters are essentially needed. Thus, we propose a novel method of compressing the network model parameters based on the training of network model parameters in the sense that the residues of filter parameters and content loss are jointly minimized. So, the residues of filter parameters are only transmitted to receiver sides for different temporal portions of video under consideration. This is advantage for image restoration applications with receivers (user terminals) of low complexity. In this case, the user terminals are assumed to have a limited computation and storage resource.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.145-154
• /
• 1994

This paper proposes an efficient method for improving the training performance of the neural network by using a hybrid of a stochastic approximation and a backpropagation algorithm. The proposed method improves the performance of the training by appliying a global optimization method which is a hybrid of a stochastic approximation and a backpropagation algorithm. The approximate initial point for a stochastic approximation and a backpropagation algorihtm. The approximate initial point for fast global optimization is estimated first by applying the stochastic approximation, and then the backpropagation algorithm, which is the fast gradient descent method, is applied for a high speed global optimization. And further speed-up of training is made possible by adjusting the training parameters of each of the output and the hidden layer adaptively to the standard deviation of the neuron output of each layer. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to that of the backpropagation, the Baba's MROM, and the Sun's method with randomized initial point settings. The results of adaptive adjusting of the training parameters show that the proposed method further improves the convergence speed about 20% in training.

• PNF and Movement
• /
• v.18 no.1
• /
• pp.55-64
• /
• 2020

Purpose: The purpose of this study was to compare the strength and walking ability of chronic stroke patients following either proprioceptive neuromuscular facilitation (PNF) pattern training with pressure biofeedback units (feedback group) or PNF pattern training without pressure biofeedback units (control group). Methods: Eighteen participants with chronic stroke were recruited from a rehabilitation hospital. They were divided into two groups: a feedback group (n = 8) and a control group (n = 10). They all received 30 minutes of neurodevelopmental therapy and PNF training for 15 minutes five times a week for three weeks. Muscle strength and spatiotemporal gait parameters were measured. Muscle strength was measured by hand-held dynamometer; gait parameters were measured by the Biodex Gait trainer treadmill system. Results: After the training periods, the feedback group showed a significant improvement in hip abductor muscle strength, hip extensor muscle strength, step length of the unaffected limb, and step time of the affected limb (p<0.05). Conclusion: The results of this study showed that proprioceptive neuromuscular facilitation pattern training with pressure biofeedback units was more effective in improving hip muscle strength and walking ability than the proprioceptive neuromuscular facilitation pattern training without pressure biofeedback units. Therefore, to strengthen hip muscles and improve the walking ability of stroke patients, using pressure biofeedback units to improve trunk stability should be considered.

• Phonetics and Speech Sciences
• /
• v.8 no.2
• /
• pp.23-30
• /
• 2016

This paper describes some implementation schemes of CNN in view of mini-batch DNN training for efficient second order optimization. This uses same procedure updating parameters of DNN to train parameters of CNN by simply arranging an input image as a sequence of local patches, which is actually equivalent with mini-batch DNN training. Through this conversion, second order optimization providing higher performance can be simply conducted to train the parameters of CNN. In both results of image recognition on MNIST DB and syllable automatic speech recognition, our proposed scheme for CNN implementation shows better performance than one based on DNN.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.5
• /
• pp.1813-1816
• /
• 2015

Background: The aim of this study was to research the importance of the neutrophil to lymphocyte ratio (NLR) in prediction of PSA recurrence after radical prostatectomy, which has not been reported so far. Materials and Methods: The data of 175 patients who were diagnosed with localised prostate cancer and underwent retropubic radical prostatectomy was retrospectively examined. Patient pre-operative hemogram parameters of neutrophil count, lymphocyte count and NLR were assessed. The patients whose PSAs were too low to measure after radical prostatectomy in their follow-ups, and then had PSAs of 0,2 ng/mL were considered as patients with PSA recurrence. Patients with recurrence made up Group A and patients without recurrence made up Group B. Results: In terms of the power of NLR value in distinguishing recurrence, the area under OCC was statistically significant (p<0.001) .The value of 2.494 for NLR was found to be a cut-off value which can be used in order to distinguish recurrence according to Youden index. According to this, patients with a higher NLR value than 2.494 had higher rates of PSA recurrence with 89.7% sensitivity and 92.6% specificity. Conclusions: There are certain parameters used in order to predict recurrence with today's literature data.We think that because NLR is easy to use in clinics and inexpensive, and also has high sensitivity and specificity values, it has the potential to be one of the parameters used in order to predict biochemical recurrence in future.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.5
• /
• pp.2507-2511
• /
• 2016

Purpose: To study the diagnostic accuracies of serum human epididymis protein 4 (HE-4) levels, virtual organ computer-aided analysis (VOCAL) parameters and endometrial volume in endometrial cancer cases. Materials and Methods: One hundred and seven patients (37 with endometrial cancer and 70 with benign endometrial pathology) were included in this study. VOCAL parameters and serum HE-4 levels were compared between the groups. Results: Area under the curve (AUC) values were 0.702, 0.658, 0.706 for vascularization index (VI), the flow index (FI) and the vascularization flow index (VFI), respectively. A cut off value of 0.568 for VI demonstrated 70% sensitivity, 72% specificity, 56% positive predictive value (PPV) and a81% negative predictive value (NPV). A cut off value of 25.8 for showed a senitivith of 70% and a specificity of 58% with aPPV of 46% and NPV of 78%, and with a cut off value of 0.12 for VFI 70%, 69%, 54% and 81%, respectively. The area under the curve for HE-4 was 0.814. A cut off value of 458 pmol/L was predictive of malignancy with 86% sensitivity and 63% specificity. Conclusions: VOCAL parameters and serum HE-4 levels were statistically significantly higher in the endometrial cancer patients. Serum HE-4 levels provided a greater sensitivity compared to power doppler angiography for predicting malignancy or benign endometrial pathology.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.26 no.2
• /
• pp.67-73
• /
• 2013

Antheraea mylitta Drury is basically a crossbreeding species, as such it seems to be potentially a good material for the exploitation of heterosis. In the present study F1 hybrid of wild ecorace Laria (L) and semi-domestic Daba (D) was raised and evaluated for various quantitative traits and biochemical parameters during larval stage. Improved fecundity ($+18{\pm}1.8%$ and higher egg hatching rate ($+10.96{\pm}1.3%$) was recorded in the F1hybrid ($L{\times}D$). Biochemical parameters studied in the hemolymph, midgut and fatbody of the larva showed significantly higher (P<0.05) total proteins and carbohydrate concentration besides digestive enzyme activity. Correspondingly SDS-PAGE revealed more number of protein bands in the hemolymph sample of F1s, ranging between 29 kDa to 66 kDa compared to parental lines. The present study demonstrates the positive heterosis effect in the F1 hybrid of Laria ${\times}$ Daba. Biochemical analysis indicates that, there is possibilities of exploitation of hybrids with specific parents targeted for desirable commercial traits (silk yield and fecundity). Moreover, most of these biochemical parameters can be used as markers to analyze the genetic improvement in the tasar silkworms.

• Korean Journal of Remote Sensing
• /
• v.20 no.5
• /
• pp.353-359
• /
• 2004

This study proposes an approach to unsupervisedly estimate the number of classes and the parameters of defining the classes in order to train the classifier. In the proposed method, the image is segmented using a spatial region growing based on hierarchical clustering, and fuzzy training is then employed to find the sample classes that well represent the ground truth. For cluster validation, this approach iteratively estimates the class-parameters in the fuzzy training for the sample classes and continuously computes the log-likelihood ratio of two consecutive class-numbers. The maximum ratio rule is applied to determine the optimal number of classes. The experimental results show that the new scheme proposed in this study could be used to select the regions with different characteristics existed on the scene of observed image as an alternative of field survey that is so expensive.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1999.03b
• /
• pp.84-87
• /
• 1999

This paper presents a preform design method that combines the analytic method and inference of known knowledge with neural network. The analytic method is a finite element method that is used to simulate backward extrusion with pre-defined process parameters. The multi-layer network and back-propagation algorithm are utilized to learn the training examples from the simulation results. The design procedures are utilized to learn the training examples from the simulation results. The design procedures are two methods the first the neural network infer the deformed shape from the pre-defined processes parameters. The other the network infer the processes parameters from deformed shape. Especially the latest method is very useful to design the preform From the desired feature it is possible to determine the processes parameters such as friction stroke and tooling geometry. The proposed method is useful for shop floor to decide the processes parameters and preform shapes for producing sound product.

• The Journal of Korean Physical Therapy
• /
• v.32 no.3
• /
• pp.185-190
• /
• 2020

Purpose: Gait and cognitive impairment in stroke patients exacerbate fall risk and mobility difficulties during multi-task walking. Virtual reality can provide interesting and challenging training in a community setting. This study evaluated the effect of community-based virtual reality gait training (VRGT) using a 360-degree image on the gait ability of chronic stroke patients. Methods: Forty-five chronic stroke patients who were admitted to a rehabilitation hospital participated in this study. Patients meeting the selection criteria were randomly divided into a VRGT group (n=23) and a control group (n=22). Both these groups received general rehabilitation. The VRGT group was evaluated using a 360-degree image that was recorded for 50 minutes a day, 5 days per week for a total of 6 weeks after their training. The control group received general treadmill training for the same amount of time as that of the VRGT group. The improvement in the spatiotemporal parameters of gait was evaluated using a gait analyzer system before and after training. Results: The spatiotemporal gait parameters showed significant improvements in both groups compare with the baseline measurements (p<0.05), and the VRGT group showed more improvement than the control group (p<0.05). Conclusion: Community-based VRGT has been shown to improve the walking ability of chronic stroke patients and is expected to be used in rehabilitation of stroke patients in the future.