• Smart Media Journal
• /
• v.13 no.3
• /
• pp.53-61
• /
• 2024

This paper presents a novel M-shaped encoder-decoder architecture for skin lesion segmentation, achieving better performance than existing approaches. The proposed architecture utilizes the left and right legs to enable multi-scale feature extraction and is further enhanced by integrating an attention module within the skip connection. The image is partitioned into four distinct patches, facilitating enhanced processing within the encoder-decoder framework. A pivotal aspect of the proposed method is to focus more on critical image features through an attention mechanism, leading to refined segmentation. Experimental results highlight the effectiveness of the proposed approach, demonstrating superior accuracy, precision, and Jaccard Index compared to existing methods

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.6
• /
• pp.619-627
• /
• 2016

Cells of a PV (photovoltaic) module can suffer defects due to various causes resulting in a loss of power output. As a malfunctioning cell has a higher temperature than adjacent normal cells, it can be easily detected with a thermal infrared sensor. A conventional method of PV cell inspection is to use a hand-held infrared sensor for visual inspection. The main disadvantages of this method, when applied to a large-scale PV power plant, are that it is time-consuming and costly. This paper presents an algorithm for automatically detecting defective PV panels using images captured with a thermal imaging camera from an UAV (unmanned aerial vehicle). The proposed algorithm uses statistical analysis of thermal intensity (surface temperature) characteristics of each PV module to verify the mean intensity and standard deviation of each panel as parameters for fault diagnosis. One of the characteristics of thermal infrared imaging is that the larger the distance between sensor and target, the lower the measured temperature of the object. Consequently, a global detection rule using the mean intensity of all panels in the fault detection algorithm is not applicable. Therefore, a local detection rule was applied to automatically detect defective panels using the mean intensity and standard deviation range of each panel by array. The performance of the proposed algorithm was tested on three sample images; this verified a detection accuracy of defective panels of 97% or higher. In addition, as the proposed algorithm can adjust the range of threshold values for judging malfunction at the array level, the local detection rule is considered better suited for highly sensitive fault detection compared to a global detection rule. In this study, we used a panel area extraction method that we previously developed; fault detection accuracy would be improved if panel area extraction from images was more precise. Furthermore, the proposed algorithm contributes to the development of a maintenance and repair system for large-scale PV power plants, in combination with a geo-referencing algorithm for accurate determination of panel locations using sensor-based orientation parameters and photogrammetry from ground control points.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.4 no.2
• /
• pp.114-119
• /
• 2003

This study is to remove several organic pollutants from wastewater by non-dispersive membrane solvent extraction technique. The distribution coefficients of several solvents were determined and the experimental system was operated counter-currently and cocurrently with respect to the aqueous phase and solvent. In these experiments, as the flow rate of aqueous solution inclosed, due to being shortened contact time to solvent, the rate of removal of organic pollutants decreased and as the flow rate of solvent increased, the rate of removal increased. Meanwhile, the rate of removal of organic pollutants for the countercurrent flow system was higher than that for the occurrent flow system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.238-240
• /
• 2002

If there is an Information Retrieval system which comprehends the semantic content of documents and knows the preference of users. the system can search the information better on the Internet, or improve the IR performance. Therefore we propose the IR model which combines semantic based indexing and fuzzy relevance model. In addition to the statistical approach, we chose the semantic approach in indexing, lexical chains, because we assume it would improve the performance of the index term extraction. Furthermore, we combined the semantic based indexing with the fuzzy model, which finds out the exact relevance of the user preference and index terms. The proposed system works as follows: First, the presented system indexes documents by the efficient index term extraction method using lexical chains. And then, if a user tends to retrieve the information from the indexed document collection, the extended IR model calculates and ranks the relevance of user query. user preference and index terms by some metrics. When we experimented each module, semantic based indexing and extended fuzzy model. it gave noticeable results. The combination of these modules is expected to improve the information retrieval performance.

• Journal of Intelligence and Information Systems
• /
• v.9 no.2
• /
• pp.19-38
• /
• 2003

In this research, we propose the mechanism to develop self-evolving expert systems (SEES) based on data mining (DM), fuzzy neural networks (FNN), and relational database (RDB)-driven forward/backward inference engine. Most researchers had tried to develop a text-oriented knowledge base (KB) and inference engine (IE). However, this approach had some limitations such as 1) automatic rule extraction, 2) manipulation of ambiguousness in knowledge, 3) expandability of knowledge base, and 4) speed of inference. To overcome these limitations, knowledge engineers had tried to develop an automatic knowledge extraction mechanism. As a result, the adaptability of the expert systems was improved. Nonetheless, they didn't suggest a hybrid and generalized solution to develop self-evolving expert systems. To this purpose, we propose an automatic knowledge acquisition and composite inference mechanism based on DM, FNN, and RDB-driven inference engine. Our proposed mechanism has five advantages. First, it can extract and reduce the specific domain knowledge from incomplete database by using data mining technology. Second, our proposed mechanism can manipulate the ambiguousness in knowledge by using fuzzy membership functions. Third, it can construct the relational knowledge base and expand the knowledge base unlimitedly with RDBMS (relational database management systems) module. Fourth, our proposed hybrid data mining mechanism can reflect both association rule-based logical inference and complicate fuzzy relationships. Fifth, RDB-driven forward and backward inference time is shorter than the traditional text-oriented inference time.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11b
• /
• pp.300-306
• /
• 2000

This paper introduces a new concept of automation for bio-production with tele-operative system. The proposed system showed practical and feasible way of automation for the volatile bio-production process. Based on the proposition, recognition of the job environment with object identification was performed using computer vision system. A man-machine interactive hybrid decision-making, which utilized a concept of tele-operation was proposed to overcome limitations of the capability of computer in image processing and feature extraction from the complex environment image. Identifying watermelons from the outdoor scene of the cultivation field was selected to realize the proposed concept. Identifying watermelon from the camera image of the outdoor cultivation field is very difficult because of the ambiguity among stems, leaves, shades, and especially fruits covered partly by leaves or stems. The analog signal of the outdoor image was captured and transmitted wireless to the host computer by R.F module. The localized window was formed from the outdoor image by pointing to the touch screen. And then a sequence of algorithms to identify the location and size of the watermelon was performed with the local window image. The effect of the light reflectance of fruits, stems, ground, and leaves were also investigated.

• Current Photovoltaic Research
• /
• v.7 no.1
• /
• pp.21-27
• /
• 2019

Lifetime of Si photovoltaics modules are about 25 years and a large amount of waste modules are expected to be discharged in the near future. Therefore, the extraction and collection of valuable metals out of discharged Si modules will be one of the important technologies. In this study, we demonstrated that supercritical $CO_2$ extraction method can be effectively used to remove Cu, one of the abundant elements in the module, as well as its oxide form, $Cu_2O$. Especially, we proved that the addition of hexane as co-solvent is effective for the removal of both materials. The optimal ratio of $CO_2$ and hexane was 4:1 at a fixed temperature and pressure of $250^{\circ}C$ and 250 bar, respectively. In addition, it was proven that the removal of $Cu_2O$ was preceded via reduction of $Cu_2O$ to Cu.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• Water for future
• /
• v.28 no.2
• /
• pp.115-124
• /
• 1995

A GIS is capable of extracting various hydrological factors from DEM(digital elevation model). One of important tasks for hydrological analysis is the division of watershed. It can be an essential factor among various geometric characteristics of watershed. In this study, watershed itself and other geometric factors of watershed are extracted from DEM by using GIS technique. The manual process of tasks to obtain geometric characteristics of watershed is automated by using the functions of ARC/INFO software as GIS package. Scanned data was used for this study and it is converted to DEM data. Various forms of representation of spatial data are handled in main module and GRID module of ARC/INFO. GRID module is used on a stream in order to define watershed boundary, so it would be possible to obtain the watersheds. Also, a flow direction, stream networks and orders are generated. The results show that GIS can aid watershed management and research and surveillance. Also the geometric characteristics parameters of watershed can be quantified with ease using GIS technique and the hardsome process can be automated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.