• Journal of the Korean Society for Precision Engineering
• /
• 제30권1호
• /
• pp.11-17
• /
• 2013

'Multi-scale mass-deployable cooperative robots' is a next generation robotics paradigm where a large number of robots that vary in size cooperate in a hierarchical fashion to collect information in various environments. While this paradigm can exhibit the effective solution for exploration of the wide area consisting of various types of terrain, its technical maturity is still in its infant state and many technical hurdles should be resolved to realize this paradigm. In this paper, we propose to develop new design and manufacturing methodologies for the multi-scale mass-deployable cooperative robots. In doing so, we present various fundamental technologies in four different research fields. (1) Adaptable design methods consist of compliant mechanisms and hierarchical structures which provide robots with a unified way to overcome various and irregular terrains. (2) Soft composite materials realize the compliancy in these structures. (3) Multi-scale integrative manufacturing techniques are convergence of traditional methods for producing various sized robots assembled by such materials. Finally, (4) the control and communication techniques for the massive swarm robot systems enable multiple functionally simple robots to accomplish the complex job by effective job distribution.

• Journal of the Korea Convergence Society
• /
• 제12권11호
• /
• pp.45-51
• /
• 2021

With the development of deep learning, semantic segmentation methods are being studied in various fields. There is a problem that segmenation accuracy drops in fields that require accuracy such as medical image analysis. In this paper, we improved PSPNet, which is a deep learning based segmentation method to minimized the loss of features during semantic segmentation. Conventional deep learning based segmentation methods result in lower resolution and loss of object features during feature extraction and compression. Due to these losses, the edge and the internal information of the object are lost, and there is a problem that the accuracy at the time of object segmentation is lowered. To solve these problems, we improved PSPNet, which is a semantic segmentation model. The multi-scale attention proposed to the conventional PSPNet was added to prevent feature loss of objects. The feature purification process was performed by applying the attention method to the conventional PPM module. By suppressing unnecessary feature information, eadg and texture information was improved. The proposed method trained on the Cityscapes dataset and use the segmentation index MIoU for quantitative evaluation. As a result of the experiment, the segmentation accuracy was improved by about 1.5% compared to the conventional PSPNet.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• 제43권1호
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권3호
• /
• pp.993-1014
• /
• 2021

This paper proposes a new image retrieval method called the 3D integrated multi-index to fuse SIFT (Scale Invariant Feature Transform) visual words with other features at the indexing level. The advantage of the 3D integrated multi-index is that it can produce finer subdivisions in the search space. Compared with the inverted indices of medium-sized codebook, the proposed method increases time slightly in preprocessing and querying. Particularly, the SIFT, contour and colour features are fused into the integrated multi-index, and the joint cooperation of complementary features significantly reduces the impact of false positive matches, so that effective image retrieval can be achieved. Extensive experiments on five benchmark datasets show that the 3D integrated multi-index significantly improves the retrieval accuracy. While compared with other methods, it requires an acceptable memory usage and query time. Importantly, we show that the 3D integrated multi-index is well complementary to many prior techniques, which make our method compared favorably with the state-of-the-arts.

• Molecules and Cells
• /
• 제44권7호
• /
• pp.433-443
• /
• 2021

Multi-omics approaches are novel frameworks that integrate multiple omics datasets generated from the same patients to better understand the molecular and clinical features of cancers. A wide range of emerging omics and multi-view clustering algorithms now provide unprecedented opportunities to further classify cancers into subtypes, improve the survival prediction and therapeutic outcome of these subtypes, and understand key pathophysiological processes through different molecular layers. In this review, we overview the concept and rationale of multi-omics approaches in cancer research. We also introduce recent advances in the development of multi-omics algorithms and integration methods for multiple-layered datasets from cancer patients. Finally, we summarize the latest findings from large-scale multi-omics studies of various cancers and their implications for patient subtyping and drug development.

• Smart Structures and Systems
• /
• 제19권1호
• /
• pp.67-90
• /
• 2017

The interdisciplinary research area of small scale energy harvesting has attracted tremendous interests in the past decades, with a goal of ultimately realizing self-powered electronic systems. Among the various available ambient energy sources which can be converted into electricity, wind energy is a most promising and ubiquitous source in both outdoor and indoor environments. Significant research outcomes have been produced on small scale wind energy harvesting in the literature, mostly based on piezoelectric conversion. Especially, modeling methods of wind energy harvesting techniques plays a greatly important role in accurate performance evaluations as well as efficient parameter optimizations. The purpose of this paper is to present a guideline on the modeling methods of small-scale wind energy harvesters. The mechanisms and characteristics of different types of aeroelastic instabilities are presented first, including the vortex-induced vibration, galloping, flutter, wake galloping and turbulence-induced vibration. Next, the modeling methods are reviewed in detail, which are classified into three categories: the mathematical modeling method, the equivalent circuit modeling method, and the computational fluid dynamics (CFD) method. This paper aims to provide useful guidance to researchers from various disciplines when they want to develop and model a multi-way coupled wind piezoelectric energy harvester.

• Journal of the Korea Convergence Society
• /
• 제9권10호
• /
• pp.393-406
• /
• 2018

The depression and anxiety are the most popular mental disorders and not easy to distinguish because of their lots of similarities in the diagnostic criteria, related theories, and clinical symptoms. In this article, we developed the affect scale for distinguishable diagnosis, utilized the relationships between the Positive and Negative affect, and the depression and anxiety. We made up the seed scale of the items which selected by partial correlation, and set the scoring up by multiple regression method. The Multi-dimentional affect scale is reliable and working similarly as the scales used before, but less correlated to each other. We conclude that the affect scale achieved the diagnosis for distinguish between depression and anxiety. Our suggestions for the further study are to redeem the cultural differences, modify by the elaborate methods, and validate by the actual clinical data.

• Journal of Korea Multimedia Society
• /
• 제19권8호
• /
• pp.1310-1319
• /
• 2016

Face detection is the first step in a wide range of face applications. However, detecting faces in the wild is still a challenging task due to the wide range of variations in pose, scale, and occlusions. Recently, many deep learning methods have been proposed for face detection. However, further improvements are required in the wild. Another important issue to be considered in the face detection is the computational complexity. Current state-of-the-art deep learning methods require a large number of patches to deal with varying scales and the arbitrary image sizes, which result in an increased computational complexity. To reduce the complexity while achieving better detection accuracy, we propose a fully convolutional network-based face detection that can take arbitrarily-sized input and produce feature maps (heat maps) corresponding to the input image size. To deal with the various face scales, a multi-scale network architecture that utilizes the facial components when learning the feature maps is proposed. On top of it, we design multi-task learning technique to improve detection performance. Extensive experiments have been conducted on the FDDB dataset. The experimental results show that the proposed method outperforms state-of-the-art methods with the accuracy of 82.33% at 517 false alarms, while improving computational efficiency significantly.

• Journal of Korea Multimedia Society
• /
• 제25권8호
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• 제28권8호
• /
• pp.1196-1202
• /
• 2004

A meshfree multi-scale method has been presented for efficient analysis of elasto-plastic problems. From the variational principle, problem is decomposed into a fine scale and a coarse scale problem. In the analysis only the plastic region is discretized using fine scale. Each scale variable is approximated using meshfree method. Adaptivity can easily and nicely be implemented in meshree method. As a method of increasing resolution, partition of unity based extrinsic enrichment is used. Each scale problem is solved iteratively. Iteration procedure is indispensable for the elasto-plastic deformation analysis. Therefore this kind of solution procedure is adequate to that problem. The proposed method is applied to Prandtl's punch test and shear band problem. The results are compared with those of other methods and the validity of the proposed method is demonstrated.