• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4816-4834
• /
• 2020

This paper proposes transfer learning and fine-tuning techniques for a deep learning model to detect three distinct brain tumors from Magnetic Resonance Imaging (MRI) scans. In this work, the recent YOLOv4 model trained using a collection of 3064 T1-weighted Contrast-Enhanced (CE)-MRI scans that were pre-processed and labeled for the task. This work trained with the partial 29-layer YOLOv4-Tiny and fine-tuned to work optimally and run efficiently in most platforms with reliable performance. With the help of transfer learning, the model had initial leverage to train faster with pre-trained weights from the COCO dataset, generating a robust set of features required for brain tumor detection. The results yielded the highest mean average precision of 93.14%, a 90.34% precision, 88.58% recall, and 89.45% F1-Score outperforming other previous versions of the YOLO detection models and other studies that used bounding box detections for the same task like Faster R-CNN. As concluded, the YOLOv4-Tiny can work efficiently to detect brain tumors automatically at a rapid phase with the help of proper fine-tuning and transfer learning. This work contributes mainly to assist medical experts in the diagnostic process of brain tumors.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.6
• /
• pp.69-78
• /
• 2017

Shannon of the 5G smartphone and Fourier of the signal processing meet in the sampling theorem (2 times the highest frequency 1). In this paper, the initial Shannon Theorem finds the Shannon capacity at the point-to-point, but the 5G shows on the Relay channel that the technology has evolved into Multi Point MIMO. Fourier transforms are signal processing with fixed parameters. We analyzed the performance by proposing a 2N-1 multivariate Fourier-Jacket transform in the multimedia age. In this study, the authors tackle this signal processing complexity issue by proposing a Jacket-based fast method for reducing the precoding/decoding complexity in terms of time computation. Jacket transforms have shown to find applications in signal processing and coding theory. Jacket transforms are defined to be $n{\times}n$ matrices $A=(a_{jk})$ over a field F with the property $AA^{\dot{+}}=nl_n$, where $A^{\dot{+}}$ is the transpose matrix of the element-wise inverse of A, that is, $A^{\dot{+}}=(a^{-1}_{kj})$, which generalise Hadamard transforms and centre weighted Hadamard transforms. In particular, exploiting the Jacket transform properties, the authors propose a new eigenvalue decomposition (EVD) method with application in precoding and decoding of distributive multi-input multi-output channels in relay-based DF cooperative wireless networks in which the transmission is based on using single-symbol decodable space-time block codes. The authors show that the proposed Jacket-based method of EVD has significant reduction in its computational time as compared to the conventional-based EVD method. Performance in terms of computational time reduction is evaluated quantitatively through mathematical analysis and numerical results.

• Journal of Radiation Protection and Research
• /
• v.36 no.4
• /
• pp.200-208
• /
• 2011

The neutron fluence measurement and evaluation technology is very important for material irradiation test. The most essential technology in this study is the neutron irradiation evaluation method using a fluence monitor. The fluence monitors were fabricated with metal wires of the purity ${\geq}$ 99.9%, whose dimensions were 0.1mm diameter, about 3 mm length, and around 150-200 ${\mu}g$ mass range. Three wire samples (Fe, Ni, Ti) were prepared for one irradiation aluminum capsule. Five capsules were irradiated in the OR5 hole of the HANARO reactor at 30 MW power for about 25 days. After irradiation tests, radiation activities were measured with the high purity germanium (HPGe) detector. The reaction rates were calculated by using the measured radiation activity data, and then neutron fluence were obtained from the reaction rates and the weighted neutron cross section with calculated neutron spectrum at the fluence monitor position.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.51 no.4
• /
• pp.535-544
• /
• 2015

Yield per recruit model is the most popular method for fisheries stock assessment. However, stock assessment using yield per recruit model can lead to recruitment overfishing as this model only considers the maximum yield per recruit without spawning biomass for reproduction. For this reason, spawning biomass per recruit model which reveals variations of spawning stock biomass per fishing mortality (F) and age at first capture ($t_c$) is considered as more proper method for stock assessment. There are mainly two methods for spawning biomass per recruit model known as age specific selectivity method and knife-edged selectivity method. In the knife-edged selectivity method, the spawning biomass per recruit has been often calculated using biomass per recruit value by multiplying the maturity ratio of the recruited age. But the maturity ratio in the previous method was not considered properly in previous studies. Therefore, a new method of the knife-edged selectivity model was suggested in this study using a weighted average of the maturity ratio for ages from the first capture to the lifespan. The optimum fishing mortality in terms of $F_{35%}$ which was obtained from the new method was compared to the old method for small yellow croaker stock in Korea. The value of $F_{35%}$ using the new knife-edged selectivity model was 0.302/year and the value using the old model was 0.349/year. However, the value of $F_{35%}$ using the age specific selectivity model was estimated as 0.320/year which was closer to the value from the new knife-edged selectivity model.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.18 no.1
• /
• pp.19-25
• /
• 2014

Purpose: Integrated PET/MRI has been developed recently has become a lot of help to the point oncologic, neological, cardiological nuclear medicine. By using this PET/MRI, a ${\mu}-map$ is created some special MRI sequence which may be divided parts of the body for attenuation correction. However, because an MRI contrast agent is necessary in order to obtain an more MRI information, we will evaluate to see an effect of SUV on PET image that corrected attenuation by MRI with contrast agent. Materials and Methods: As PET/MRI machine, Biograph mMR (Siemens, Germany) was used. For phantom test, 1mCi $^{18}F-FDG$ was injected in cylinderical uniformity phantom, and then acquire PET data about 10 minutes with VIBE-DIXON, UTE MRI sequence image for attenuation correction. T1 weighted contrast media, 4 cc DOTAREM (GUERBET, FRANCE) was injected in a same phatnom, and then PET data, MRI data were acquired by same methodes. Using this PET, non-contrast MRI and contrast MRI, it was reconstructed attenuation correction PET image, in which we evanuated the difference of SUVs. Additionally, for let a high desity of contrast media, 500 cc 2 plastic bottles were used. We injected $^{18}F-FDG$ with 5 cc DOTAREM in first bottle. At second bottle, only $^{18}F-FDG$ was injected. and then we evaluated a SUVs reconstructed by same methods. For clinical patient study, rectal caner-pancreas cancer patients were selected. we evaluated SUVs of PET image corrected attenuastion by contrast weighted MRI and non-contrast MRI. Results: For a phantom study, although VIBE DIXON MRI signal with contrast media is 433% higher than non-contrast media MRI, the signals intensity of ${\mu}-map$, attenuation corrected PET are same together. In case of high contrast media density, image distortion is appeared on ${\mu}-map$ and PET images. For clinical a patient study, VIBE DIXON MRI signal on lesion portion is increased in 495% by using DOTAREM. But there are no significant differences at ${\mu}-map$, non AC PET, AC-PET image whether using contrast media or not. In case of whole body PET/MRI study, %diff between contras and non contrast MRAC at lung, liver, renal cortex, femoral head, myocardium, bladder, muscle are -4.32%, -2.48%, -8.05%, -3.14%, 2.30%, 1.53%, 6.49% at each other. Conclusion: In integrated PET/MRI, a segmentation ${\mu}-map$ method is used for correcting attenuation of PET signal. although MRI signal for attenuation correciton change by using contrast media, ${\mu}-map$ will not change, and then MRAC PET signal will not change too. Therefore, MRI contrast media dose not affect for attenuation correction PET. As well, not only When we make a flow of PET/MRI protocol, order of PET and MRI sequence dose not matter, but It's possible to compare PET images before and after contrast agent injection.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.7 no.1
• /
• pp.65-73
• /
• 1987

An efficient plate bending finite element has been developed using higher-order inplane displacement profiles of the plate. The 6-noded, 21-d.o.f. triangular element including shear deformation effect has been derived from the plate-like continuum by the Galerkin's weighted residual method. Square plate examples were tested with selected element meshes and several aspect ratios for their static behavior under uniformly distributed load. The result of the example tests indicated consistently good performance of the present higher-order plate bending element in comparison with the thin and thick plate solution and other existing finite element solutions.

• Journal of computational fluids engineering
• /
• v.2 no.1
• /
• pp.66-72
• /
• 1997

Optimum nozzle design exploiting the method of characteristic(M.O.C) has been in application as an efficient design methodology targeting a less weighted and short expansion nozzle. This paper treats the optimum nozzle design and the analysis of the inviscid compressible flow inside. Based on traditional Rao's method, the optimum nozzle design is coded with minor modifications for the identification of the control surface across which the mass flux should be conserved. Internal flow field is simulated numerically by M.O.C and implicit/explicit Taylor-Galerkin finite element method(F.E.M) with the aid of adaptive remeshing to capture the shock wave, hence improve the accuracy. Designed and calculated flow fields due to the separate analyses show that the mass flux predicted by optimum nozzle design with M.O.C is not conserved across the control surface and the sonic line should be located upstream of the nozzle throat. Rao's optimum nozzle design methodology exaggerates the momentum thrust and tends to overemphasize the engine performance loss.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4976-4994
• /
• 2018

The diffusion-based salient object detection methods have shown excellent detection results and more efficient computation in recent years. However, the current diffusion-based salient object detection methods still have disadvantage of detecting the object appearing at the image boundaries and different scales. To address the above mentioned issues, this paper proposes a multi-scale diffusion-based salient object detection algorithm with background and objectness seeds. In specific, the image is firstly over-segmented at several scales. Secondly, the background and objectness saliency of each superpixel is then calculated and fused in each scale. Thirdly, manifold ranking method is chosen to propagate the Bayessian fusion of background and objectness saliency to the whole image. Finally, the pixel-level saliency map is constructed by weighted summation of saliency values under different scales. We evaluate our salient object detection algorithm with other 24 state-of-the-art methods on four public benchmark datasets, i.e., ASD, SED1, SED2 and SOD. The results show that the proposed method performs favorably against 24 state-of-the-art salient object detection approaches in term of popular measures of PR curve and F-measure. And the visual comparison results also show that our method highlights the salient objects more effectively.

• 전기의세계
• /
• v.16 no.2
• /
• pp.1-8
• /
• 1967

From the discovery of Alago's disk, a number of trials and efforts have been concentrated on a small-sized and light-weighted induction motor. They have devoted themseleves, however, mainly to a improvement of cooling effect, a proper weight-distribution of copper and iron and desirable number of slots. In consequence, such an effort restricted only to the field of design, has resulted in unsatisfactory developments in the insulating materials consisting of the main parts of an induction motor. The quality of fibre and paper which are used as class-A insulation materials with their "compound" and "varnish" has been increased to some extent. Similarly Class-B insulation materials like asbest mica has been almost a combination of inorganic and binding materials. But nowadays synthesic chemistry is making a remarkable progress. So it comes possible for us to have silicon resin and other good ones of similar charateristics. And even a thin silicon resin insures us to get excellent heat-pro f and insulation, so a better space factor and cost-down in motor design have come possible in most advanced nations of the world, but not in our country. Furthermore, a consideration of productivity and economy in manufacturing process has been neglected by a majority of engineers. This is more unpleasant und more undesirable. I think this rational method of induction motor design using new synthesic resin will devote in making your productivity and economy better. And the nation-wide standard value of electric motor size is sited here. size is sited here.