• Progress in Medical Physics
• /
• v.30 no.2
• /
• pp.39-48
• /
• 2019

Deep learning has been applied to various medical data. In particular, current deep learning models exhibit remarkable performance at specific tasks, sometimes offering higher accuracy than that of experts for discriminating specific diseases from medical images. The current status of deep learning applications to molecular imaging can be divided into a few subtypes in terms of their purposes: differential diagnostic classification, enhancement of image acquisition, and image-based quantification. As functional and pathophysiologic information is key to molecular imaging, this review will emphasize the need for accurate biomarker acquisition by deep learning in molecular imaging. Furthermore, this review addresses practical issues that include clinical validation, data distribution, labeling issues, and harmonization to achieve clinically feasible deep learning models. Eventually, deep learning will enhance the role of theranostics, which aims at precision targeting of pathophysiology by maximizing molecular imaging functional information.

• International Journal of Advanced Culture Technology
• /
• v.7 no.4
• /
• pp.295-301
• /
• 2019

Since the third artificial intelligence boom was triggered by deep learning, it has been 10 years. It is time to analyze and discuss the research trends of deep learning for the stable development of AI. In this regard, this study systematically analyzes the trends of research on deep learning over the past 10 years. We collected research literature on deep learning and performed LDA based topic modeling analysis. We analyzed trends by topic over 10 years. We have also identified differences among the major research countries, China, the United States, South Korea, and United Kingdom. The results of this study will provide insights into research direction on deep learning in the future, and provide implications for the stable development strategy of deep learning.

• Coupled systems mechanics
• /
• v.8 no.3
• /
• pp.259-271
• /
• 2019

This paper presents forced vibration analysis of sandwich deep beams made of functionally graded material (FGM) in face layers and a porous material in core layer. The FGM sandwich deep beam is subjected to a harmonic dynamic load. The FGM in the face layer is graded though the layer thickness. In order to get more realistic result for the deep beam problem, the plane solid continua is used in the modeling of The FGM sandwich deep beam. The equations of the problem are derived based the Hamilton procedure and solved by using the finite element method. The novelty in this paper is to investigate the dynamic responses of sandwich deep beams made of FGM and porous material by using the plane solid continua. In the numerical results, the effects of different material distributions, porosity coefficient, geometric and dynamic parameters on the dynamic responses of the FGM sandwich deep beam are investigated and discussed.

• Structural Engineering and Mechanics
• /
• v.77 no.2
• /
• pp.273-291
• /
• 2021

The strut-and-tie method (STM) has been widely accepted and used as a rational approach for the design of disturbed regions ('D' regions) of reinforced concrete members such as in corbels and deep beams, where traditional flexure theory does not apply. This paper evaluates the applicability of the equilibrium based STM in strength predictions of deep beams (with rectangular and circular cross-section) and corbels using the available experiments in literature. STM is found to give fairly good results for corbel and deep beams. The failure modes of these deep members are also studied, and an optimum amount of distribution reinforcement is suggested to eliminate the premature diagonal splitting failure. A comparison with existing empirical and semi empirical methods also show that STM gives more reliable results. The nonlinear finite element analysis (NLFEA) of 50 deep beams and 20 corbels could capture the complete behaviour of deep members including crack pattern, failure load and failure load accurately.

• Communications for Statistical Applications and Methods
• /
• v.28 no.4
• /
• pp.329-338
• /
• 2021

Deep learning methods have been developed, used in various fields, and they have shown outstanding performances in many cases. Many studies predicted a daily stock return, a classic example of time-series data, using deep learning methods. We also tried to apply deep learning methods to Korea's stock market data. We used Korea's stock market index (KOSPI) and several individual stocks to forecast daily returns and directions. We compared several deep learning models with other machine learning methods, including random forest and XGBoost. In regression, long short term memory (LSTM) and gated recurrent unit (GRU) models are better than other prediction models. For the classification applications, there is no clear winner. However, even the best deep learning models cannot predict significantly better than the simple base model. We believe that it is challenging to predict daily stock return data even if we use the latest deep learning methods.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.164-170
• /
• 2023

With the recent advances in AI (artificial intelligence) and HPC (high-performance computing) technologies, deep learning is proliferated in various domains of the 4th industrial revolution. As the workload volume of deep learning increasingly grows, analyzing the memory reference characteristics becomes important. In this article, we analyze the memory reference traces of deep learning workloads in comparison with traditional workloads specially focusing on read and write operations. Based on our analysis, we observe some unique characteristics of deep learning memory references that are quite different from traditional workloads. First, when comparing instruction and data references, instruction reference accounts for a little portion in deep learning workloads. Second, when comparing read and write, write reference accounts for a majority of memory references, which is also different from traditional workloads. Third, although write references are dominant, it exhibits low reference skewness compared to traditional workloads. Specifically, the skew factor of write references is small compared to traditional workloads. We expect that the analysis performed in this article will be helpful in efficiently designing memory management systems for deep learning workloads.

• Physical Therapy Korea
• /
• v.18 no.4
• /
• pp.1-10
• /
• 2011

This study compared the stability of the cervical spine according to the presence of neck pain and deep neck flexor performance. Thirty subjects with neck pain, and thirty subjects without neck pain were recruited for this study. The Cranio-cervical flexion (CCF) test was applied using a pressure biofeedback unit to classify the subjects into four subgroups; no cervical pain and good deep neck flexor performance (NG group), no cervical pain and poor deep neck flexor performance (NP group), cervical pain and good deep neck flexor performance (PG group), and cervical pain and poor deep neck flexor performance (PP group). The head sway angle was measured using a three-dimensional motion analysis system. A 3-kg weight was used for external perturbation with the subject sitting in a chair in the resting and erect head positions with voluntary contraction of the deep neck flexors. A one-way analysis of variance (ANOVA) was performed with a Bonferroni post hoc test. The deep neck flexor performance differed significantly among the four groups (p<.05). The NG group had significantly greater deep neck flexor performance than NP and PP groups. The stability of the cervical spine also differed significantly among the four groups in the resting head position (p<.05). The head sway angle was significantly smaller in NG group as compared with the other groups. The PP group had the greatest head sway angle in the resting head position. However, there was no significant difference in the stability of the cervical spine among the groups in the erect head position with voluntary contraction of deep neck flexors (p=.57). The results of this study suggest that the deep neck flexor performance is important for maintaining the stability of cervical spine from external perturbation.

• Journal of Crop Science and Biotechnology
• /
• v.10 no.2
• /
• pp.79-85
• /
• 2007

Rice bran application just after transplanting has been increasingly practiced as an herbicide-substitute for organic rice production in Korea. However, this practice is frequently reported to be unsatisfactory in weed suppression. An experiment with five treatments that combines flooding depth, rice bran application dose, and herbicide treatment was done in the paddy field to evaluate whether rice bran application under deep flooding can lead to a successful weed control in compensation for the single practice of rice bran application. Rice bran was broadcasted on the flood water surface just after deep flooding of 8 to 10cm that was started at seven days after transplanting. In the shallow flooding plot without herbicide six weed species were recorded: Monochoria vaginalis, Echinochloa crus-galli, Ludvigia prostrate, Cyperus amuricus, Aneima keisak, and Bidens tripartite. Among the first four dominant weed species, deep flooding significantly suppressed the occurrence of Echinochloa crus-galli and Cyperus amuricus while did not suppress the occurrence of Monochoria vaginalis and Ludwigia prostrate. On the contrary, rice bran application under deep flooding suppressed significantly Monochoria vaginalis and Ludwigia prostrate while didn't exert an additional suppression of Echinochloa crus-galli and Cyperus amuricus compared to deep flooding alone. Rice bran application and deep flooding suppressed complimentarily all the six weed species to a satisfactory extent except for Monochoria vaginalis of which suppression efficacy was 31.9%. Deep flooding reduced the panicle number substantially by inhibiting the tiller production, increased the spikelet number per panicle slightly, and leaded to a lower rice grain yield compared to shallow flooding with herbicide. Rice bran application under deep flooding mitigated the panicle reduction due to deep flooding, increased the spikelets per panicle significantly, and thus produced even higher grain yield in the rice bran application of 2000kg $ha^{-1}$ as compared to the shallow flooding treatment with herbicide. In conclusion, this practice applying rice bran under deep flooding would be promising to be incorporated as an integral practice for an organic rice farming system.

• Journal of the Korean Society of Safety
• /
• v.34 no.6
• /
• pp.50-57
• /
• 2019

In this study, various types of deep learning models that have been proposed recently are classified according to data input / output types and analyzed to find the deep learning model suitable for constructing a crack detection model. First the deep learning models are classified into image classification model, object segmentation model, object detection model, and instance segmentation model. ResNet-101, DeepLab V2, Faster R-CNN, and Mask R-CNN were selected as representative deep learning model of each type. For the comparison, ResNet-101 was implemented for all the types of deep learning model as a backbone network which serves as a main feature extractor. The four types of deep learning models were trained with 500 crack images taken from real concrete structures and collected from the Internet. The four types of deep learning models showed high accuracy above 94% during the training. Comparative evaluation was conducted using 40 images taken from real concrete structures. The performance of each type of deep learning model was measured using precision and recall. In the experimental result, Mask R-CNN, an instance segmentation deep learning model showed the highest precision and recall on crack detection. Qualitative analysis also shows that Mask R-CNN could detect crack shapes most similarly to the real crack shapes.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.27-65
• /
• 2020

Many companies on information and communication technology make public their own developed AI technology, for example, Google's TensorFlow, Facebook's PyTorch, Microsoft's CNTK. By releasing deep learning open source software to the public, the relationship with the developer community and the artificial intelligence (AI) ecosystem can be strengthened, and users can perform experiment, implementation and improvement of it. Accordingly, the field of machine learning is growing rapidly, and developers are using and reproducing various learning algorithms in each field. Although various analysis of open source software has been made, there is a lack of studies to help develop or use deep learning open source software in the industry. This study thus attempts to derive a strategy for adopting the framework through case studies of a deep learning open source framework. Based on the technology-organization-environment (TOE) framework and literature review related to the adoption of open source software, we employed the case study framework that includes technological factors as perceived relative advantage, perceived compatibility, perceived complexity, and perceived trialability, organizational factors as management support and knowledge & expertise, and environmental factors as availability of technology skills and services, and platform long term viability. We conducted a case study analysis of three companies' adoption cases (two cases of success and one case of failure) and revealed that seven out of eight TOE factors and several factors regarding company, team and resource are significant for the adoption of deep learning open source framework. By organizing the case study analysis results, we provided five important success factors for adopting deep learning framework: the knowledge and expertise of developers in the team, hardware (GPU) environment, data enterprise cooperation system, deep learning framework platform, deep learning framework work tool service. In order for an organization to successfully adopt a deep learning open source framework, at the stage of using the framework, first, the hardware (GPU) environment for AI R&D group must support the knowledge and expertise of the developers in the team. Second, it is necessary to support the use of deep learning frameworks by research developers through collecting and managing data inside and outside the company with a data enterprise cooperation system. Third, deep learning research expertise must be supplemented through cooperation with researchers from academic institutions such as universities and research institutes. Satisfying three procedures in the stage of using the deep learning framework, companies will increase the number of deep learning research developers, the ability to use the deep learning framework, and the support of GPU resource. In the proliferation stage of the deep learning framework, fourth, a company makes the deep learning framework platform that improves the research efficiency and effectiveness of the developers, for example, the optimization of the hardware (GPU) environment automatically. Fifth, the deep learning framework tool service team complements the developers' expertise through sharing the information of the external deep learning open source framework community to the in-house community and activating developer retraining and seminars. To implement the identified five success factors, a step-by-step enterprise procedure for adoption of the deep learning framework was proposed: defining the project problem, confirming whether the deep learning methodology is the right method, confirming whether the deep learning framework is the right tool, using the deep learning framework by the enterprise, spreading the framework of the enterprise. The first three steps (i.e. defining the project problem, confirming whether the deep learning methodology is the right method, and confirming whether the deep learning framework is the right tool) are pre-considerations to adopt a deep learning open source framework. After the three pre-considerations steps are clear, next two steps (i.e. using the deep learning framework by the enterprise and spreading the framework of the enterprise) can be processed. In the fourth step, the knowledge and expertise of developers in the team are important in addition to hardware (GPU) environment and data enterprise cooperation system. In final step, five important factors are realized for a successful adoption of the deep learning open source framework. This study provides strategic implications for companies adopting or using deep learning framework according to the needs of each industry and business.