• Smart Media Journal
• /
• v.12 no.7
• /
• pp.43-51
• /
• 2023

As online transactions increase, the image of clothing has a great influence on consumer purchasing decisions. The importance of image information for clothing materials has been emphasized, and it is important for the fashion industry to analyze clothing images and grasp the materials used. Textile materials used for clothing are difficult to identify with the naked eye, and much time and cost are consumed in sorting. This study aims to classify the materials of textiles from clothing images based on deep learning algorithms. Classifying materials can help reduce clothing production costs, increase the efficiency of the manufacturing process, and contribute to the service of recommending products of specific materials to consumers. We used machine vision-based deep learning algorithms ResNet and Vision Transformer to classify clothing images. A total of 760,949 images were collected and preprocessed to detect abnormal images. Finally, a total of 167,299 clothing images, 19 textile labels and 20 fabric labels were used. We used ResNet and Vision Transformer to classify clothing materials and compared the performance of the algorithms with the Top-k Accuracy Score metric. As a result of comparing the performance, the Vision Transformer algorithm outperforms ResNet.

• International Journal of Computer Science & Network Security
• /
• v.24 no.9
• /
• pp.30-40
• /
• 2024

Building an accurate 3-D spatial road network model has become an active area of research now-a-days that profess to be a new paradigm in developing Smart roads and intelligent transportation system (ITS) which will help the public and private road impresario for better road mobility and eco-routing so that better road traffic, less carbon emission and road safety may be ensured. Dealing with such a large scale 3-D road network data poses challenges in getting accurate elevation information of a road network to better estimate the CO₂ emission and accurate routing for the vehicles in Internet of Vehicle (IoV) scenario. Clustering and regression techniques are found suitable in discovering the missing elevation information in 3-D spatial road network dataset for some points in the road network which is envisaged of helping the public a better eco-routing experience. Further, recently Explainable Artificial Intelligence (xAI) draws attention of the researchers to better interprete, transparent and comprehensible, thus enabling to design efficient choice based models choices depending upon users requirements. The 3-D road network dataset, comprising of spatial attributes (longitude, latitude, altitude) of North Jutland, Denmark, collected from publicly available UCI repositories is preprocessed through feature engineering and scaling to ensure optimal accuracy for clustering and regression tasks. K-Means clustering and regression using Support Vector Machine (SVM) with radial basis function (RBF) kernel are employed for 3-D road network analysis. Silhouette scores and number of clusters are chosen for measuring cluster quality whereas error metric such as MAE ( Mean Absolute Error) and RMSE (Root Mean Square Error) are considered for evaluating the regression method. To have better interpretability of the Clustering and regression models, SHAP (Shapley Additive Explanations), a powerful xAI technique is employed in this research. From extensive experiments , it is observed that SHAP analysis validated the importance of latitude and altitude in predicting longitude, particularly in the four-cluster setup, providing critical insights into model behavior and feature contributions SHAP analysis validated the importance of latitude and altitude in predicting longitude, particularly in the four-cluster setup, providing critical insights into model behavior and feature contributions with an accuracy of 97.22% and strong performance metrics across all classes having MAE of 0.0346, and MSE of 0.0018. On the other hand, the ten-cluster setup, while faster in SHAP analysis, presented challenges in interpretability due to increased clustering complexity. Hence, K-Means clustering with K=4 and SVM hybrid models demonstrated superior performance and interpretability, highlighting the importance of careful cluster selection to balance model complexity and predictive accuracy.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1413-1425
• /
• 2023

The increasing frequency of wildfires due to climate change is causing extreme loss of life and property. They cause loss of vegetation and affect ecosystem changes depending on their intensity and occurrence. Ecosystem changes, in turn, affect wildfire occurrence, causing secondary damage. Thus, accurate estimation of the areas affected by wildfires is fundamental. Satellite remote sensing is used for forest fire detection because it can rapidly acquire topographic and meteorological information about the affected area after forest fires. In addition, deep learning algorithms such as convolutional neural networks (CNN) and transformer models show high performance for more accurate monitoring of fire-burnt regions. To date, the application of deep learning models has been limited, and there is a scarcity of reports providing quantitative performance evaluations for practical field utilization. Hence, this study emphasizes a comparative analysis, exploring performance enhancements achieved through both model selection and data design. This study examined deep learning models for detecting wildfire-damaged areas using Landsat 8 satellite images in California. Also, we conducted a comprehensive comparison and analysis of the detection performance of multiple models, such as U-Net and High-Resolution Network-Object Contextual Representation (HRNet-OCR). Wildfire-related spectral indices such as normalized difference vegetation index (NDVI) and normalized burn ratio (NBR) were used as input channels for the deep learning models to reflect the degree of vegetation cover and surface moisture content. As a result, the mean intersection over union (mIoU) was 0.831 for U-Net and 0.848 for HRNet-OCR, showing high segmentation performance. The inclusion of spectral indices alongside the base wavelength bands resulted in increased metric values for all combinations, affirming that the augmentation of input data with spectral indices contributes to the refinement of pixels. This study can be applied to other satellite images to build a recovery strategy for fire-burnt areas.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.48-60
• /
• 2007

In previous researches for iris feature extraction, they transform a original iris image into rectangular one by stretching and interpolation, which causes the distortion of iris patterns. Consequently, it reduce iris recognition accuracy. So we are propose the method that extracts iris feature by using polar coordinates without distortion of iris patterns. Our proposed method has three strengths compared with previous researches. First, we extract iris feature directly from polar coordinate circular iris image. Though it requires a little more processing time, there is no degradation of accuracy for iris recognition and we compares the recognition performance of polar coordinate to rectangular type using by Hamming Distance, Cosine Distance and Euclidean Distance. Second, in general, the center position of pupil is different from that of iris due to camera angle, head position and gaze direction of user. So, we propose the method of iris feature detection based on polar coordinate circular iris region, which uses pupil and iris position and radius at the same time. Third, we overcome override point from iris patterns by using polar coordinates circular method. each overlapped point would be extracted from the same position of iris region. To overcome such problem, we modify Gabor filter's size and frequency on first track in order to consider low frequency iris patterns caused by overlapped points. Experimental results showed that EER is 0.29%, d' is 5,9 and EER is 0.16%, d' is 6,4 in case of using conventional rectangular image and proposed method, respectively.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.73-81
• /
• 2003

The construction industry has been experiencing a major challenge in its work force, 'the shortage of skilled craft workers.' This problem has been caused by several factors such as the poor image of the construction industry, lack of training and education, unclear career path, declining wages, and changing work force demographics. A 'step-change' approach called the 'Two-Tier Work Force Strategy' has been proposed by the Center for Construction Industry Studies (CCIS) to deal with the work force related issues in a radical way. It is composed of two separate strategies, Tier I and II. The Tier I strategy uses less skilled and task trained craft workers, and has a larger administrative site management team than the Tier II strategy. The Tier II strategy utilizes fewer, better-educated, and higher skilled workers who perform some lower-management functions in addition to craft functions. They are paid more, but produce more through higher skills, stay on the job longer through multi-skilling, and deliver improved project performance in safety, quality, schedule, and cost The Two-Tier Work Force Strategy has the potential to resolve the current work force problems and foster a better work force environment in the future.

• The KIPS Transactions:PartD
• /
• v.10D no.5
• /
• pp.793-804
• /
• 2003

In the latest, it's increasing an applied technology to be related with growth of industry circles. It's one of them a software to be used in industry circles. and It's most important part to apply an industrial equipment, so software to take charge of major part is indicative performance of quipment. At this time, it's inspired an evaluation and measurement of software quality to have within industrial equipment, and it's forming the research and development by the inside and outside of the country. For this, it's constructed a valuation metric to be based on ISO/IEC 12119, the International Standard for general the terms desired of quality of software and ISO/IEC 9126-2, the International Standard of the terms valuation of qualify for evaluation and measure, and for this accomplishment, It has been designed and developed industrial software international standard compatible approval system which approve a quality based on quality test result of industrial software using the ISO/IEC 14598-6 that international standard for organization of evaluation module.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.47 no.4
• /
• pp.399-405
• /
• 2014

We investigated the effects of feeding rate on the growth performance, blood components, and histology of growing olive flounder Paralichthys olivaceus. Optimum feeding rate (initial fish mean weight : $316.7{\pm}6.18g$) was determined under the optimum water temperature. Two replicated groups of fish were fed a commercial diet at rates of 0%, 0.4%, 0.6%, and 0.8% of body weight (BW) per day, and to satiation. Feeding trial was conducted using a flow-through system with 10 1.2-metric ton aquaria receiving filtered seawater at $21-24^{\circ}C$ for 3 weeks. Weight gain (WG) and specific growth rate (SGR) were significantly higher in fish fed to satiation (1.0% BW/day) than in those in other treatments. These parameters were negative and significantly lower in the starved fish than in fish fed the experimental diet at all feeding rates. There were no significant differences in WG and SGR among fish fed at 0.4%, 0.6%, and 0.8% BW/day. Hematocrit and hemoglobin in fish fed to satiation were significantly lower than those in other treatments. Histological changes of fish fed at 0.6% BW/day indicated that this group was in the best condition; differences were not found in tissues of fish fed at 0%, 0.6% and 1.0% BW/day. Broken-line regression analysis of weight gain showed that the optimum feeding rate of olive flounder weighing 317 g was 0.99% BW per day at the optimum water temperature.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.47 no.3
• /
• pp.234-240
• /
• 2014

We investigated the effects of feeding rate on the growth performance, blood components, and histology of growing olive flounder Paralichthys olivaceus. We determined the optimum feeding rate (initial fish mean weight of $240{\pm}10.9$ g) at the optimum water temperature. Two replicated groups of fish were fed a commercial diet at rates of 0%, 0.5%, 0.75%, and 1.0% body weight (BW) per day, and to satiation. Feeding trial was conducted using a flow-through system with 10 1.2-metric ton aquaria receiving filtered seawater at $19-21^{\circ}C$ for three weeks. Weight gain (WG) for fish fed to satiation was significantly higher than that of unfed fish and fish fed at 0.5% and 0.75% BW per day. The WG of fish fed at 1.0% BW per day was significantly higher than that of unfed fish and of fish fed at 0.5% BW per day. However, there were no significant differences in WG between fish fed at 0.5% BW per day and those fed at 0.75% BW per day, between fish fed at 0.75% BW per day and those fed at 1.0% BW per day, and between fish fed at 1.0% BW per day and those fed to satiation. The specific growth rates of fish fed at 1.0% BW per day and those fed to satiation were significantly higher than those of unfed fish and of fish fed at 0.5% BW per day. Broken-line regression analysis of weight gain showed that the optimum feeding rate of olive flounder weighing 240 g was 1.09% BW per day at the optimum water temperature.

• The KIPS Transactions:PartC
• /
• v.14C no.7
• /
• pp.571-582
• /
• 2007

Vehicular ad-hoc networks is temporarily established through inter-vehicle communication without any additional infrastructure aids. It requires a immediate message propagation because it mainly deals with critical traffic information such as traffic accidents. The distance-based broadcast scheme is one of the representative broadcast schemes for vehicular ad-hoc network. In this scheme, a node to disseminate messages is selected based on a distance from a source node. However, a message propagation delay will be increased if the relay nodes are not placed at the border of transmission range of the source node. In particular, when the node density is low, the message propagation delay is getting longer. In this paper, we propose a time-window reservation based relay node selection scheme. A node receiving the alert message from the source node has its time-window and randomly selects its waiting time within the given time-window range. A proportional time period of the given time-window is reserved in order to reduce the message propagation delay. The experimental results show that the proposed scheme has shorter message propagation delay than the distance-based broadcast scheme irrespective of node density in VANET. In particular, when the node density is low, the proposed scheme shows about 26% shorter delay and about 46% better performance in terms of compound metric, which is a function of propagation latency and network traffic.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.12
• /
• pp.106-115
• /
• 2003

Diverse multimedia services will be deployed at hand on 3G-and-beyond multi-service CDMA systems in order to satisfy different quality of service (QoS) according to traffic types. In order to use appropriate resources efficiently the call admission control (CAC) as a major resource control mechanism needs to be used to take care of efficient utilization of limited resources. In this paper, we propose a QoS-aware CAC (QCAC) that is enabled to provide service fairness and service differentiation in accordance with priority order and that applies the different thresholds in received power considering different QoS requirements such as different bit error rates (BER) when adopting total received power as the ceil load estimation. The proposed QCAC calculates the different thresholds of the different traffic types based on different required BER applies it for admission policy, and can get service fairness and differentiation in terms of call dropping probability as a main performance metric. The QCAC is aware of the QoS requirement per traffic type and allows admission discrimination according to traffic types in order to minimize the probability of QoS violation. Also the CAC needs to consider the resource allocation schemes such as complete sharing (CS), complete partitioning (CP), and priority sharing(PS) in order to provide fairness and service differentiation among traffic types. Among them, PS is closely related with the proposed QCAC having differently calculated threshold per each traffic type according to traffic priority orders.