Search results for: Kensuke Tachiki

Authors: Kensuke Otsuyama

Abstract:

The United Nation World Conference on Disaster Risk Reduction was held in Sendai, Japan, in 2015 and priorities for actions until 2030 were adopted for the next 15 years. Although one of these priorities is to ‘build back better’, there is neither a consensus definition of better recovery, nor indicators to measure better recovery. However, the community is considered as a key driver of recovery nowadays, and participation is a key word for effective recovery. In order to understand more about participatory community recovery, the author investigated recovery from the Great East Japan Earthquake and Tsunami (GEJET) in Kesennuma, a severely affected city. The research sought to: 1) Identify the elements that contribute to better recovery at the community level, and 2) analyze the role of community volunteers for disaster risk reduction for better recovery. A Participatory Community Recovery Index (PCRI) was created as a tool to measure community recovery. The index adopts seven primary indicators and 20 tertiary indicators, including: socio-economic aspect, housing, health, environment, self-organization, transformation, and institution. The index was applied to nine districts in Kesennuma city. Secondary and primary data by questionnaire surveys with local residents’ organization leaders and interviews with crisis management department officials in city government were also obtained. The indicator results were transformed into scores among 1 to 5, and the results were shown for each district. Based on the result of PCRI, it was found that the s Local Social Welfare Council played an important role in facilitating better recovery, enhancing community volunteer involvement to allow elderly residents to initiate local volunteer work for more affected single-living elderly people. Volunteers for the elderly by the elderly played a crucial role to strengthen community bonding in Kesennuma. In this research, the potential of community volunteers and inter-linkage with DRR activities are discussed.

Keywords: recovery, participation, the great East Japan earthquake and tsunami, community volunteers

Procedia PDF Downloads 232

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 257

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 165

Authors: Stephanie Ann Houghton

Abstract:

SDG-driven intercultural citizenship education through performing arts and history research, combined with dance-fitness development inspired by performing arts, can provide a third space in which performing arts, local history, and contemporary society drive educational and social development, supporting the performing arts in student-generated ways, reflecting their sense, priorities, and goals. Within a string of rugged volcanic peninsulas along the north-western coastline of the Ariake Sea, Kyushu, southern Japan, are found a range of traditional performing arts endangered in Japan’s ageing society, including Menburyu mask dance. From 2017, Menburyu culture and history were explored with Menburyu veterans and students within Houghton’s FURYU Educational Program (FEP) at Saga University. Through collaboration with professional fitness instructor Kazuki Miyata, basic Menburyu movements and concepts were blended into aerobics routines to generate Menburyu-Inspired Dance-Fitness (MIDF). Drawing on history, legends, and myths, three important storylines for understanding Menburyu, captured in students’ bilingual (English/Japanese) exhibition panels, emerged: harvest, demons and gods, and the Battle of Tadenawate 1530. Houghton and Miyata performed the first MIDF routine at the 22nd Traditional Performing Arts Festival at Yutoku Inari Shrine, Kashima, in September 2019. FEP exhibitions, dance-fitness events, and MIDF performance have been reported in the media locally and nationally. In an action research case study, a classroom research project was conducted with four female Japanese students over fifteen three-hour online lessons (April-July 2020). Part 1 of each lesson focused on Menburyu history. This included a guest lecture by Kensuke Ryuzoji. The three Menburyu storylines served as keys for exploring Menburyu history from international standpoints.Part 2 focused on the development of MIDF basic steps and an online MIDF event with outside guests. Through post-lesson reflective diaries and reports/videos documenting their experience, students engaged in heritage management, intercultural dialogue, health/fitness, technology and art generation activities within the FEP, centring on UN Sustainable Development Goals (SDGs) including health and wellness (SDG3), and quality education (SDG4), taking a glocal approach. In this presentation, qualitative analysis of student-generated reflective diary and reports will be presented to reveal educational processes, learning outcomes,and apparent areas of (potential) social impact of this classroom research project. Data will be presented in two main parts: (1) The mutually beneficial relationship between local traditional performing arts research and local history researchwill be addressed. One has the power both inform and illuminate the other given their deep connections. This can drive the development of students’ intercultural history competence related to and through the performing arts. (2) The development of dance-fitness inspired by traditional performing arts provides a third space in which performing arts, local history and contemporary society can be connected through SDG-driven education inside the classroom in ways that can also drive social innovation outside the classroom, potentially supporting the performing arts itself in student-generated ways, reflecting their own sense, priorities and social goals. Links will be drawn with intercultural citizenship, strengths and weaknesses of this teaching approach will be highlighted, and avenues for future research in this exciting new area will be suggested.

Keywords: cultural traditions, dance-fitness performance and participation, intercultural communication approach, mask dance origins

Procedia PDF Downloads 102