• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4043-4064
• /
• 2021

Night-time image quality evaluation is an urgent requirement in visual inspection. The lighting environment of night-time results in low brightness, low contrast, loss of detailed information, and colour dissonance of image, which remains a daunting task of delicately evaluating the image quality at night. A new blind quality assessment metric is presented for realistic night-time scenario through a comprehensive consideration of contrast, texture, and colour in this article. To be specific, image blocks' color-gray-difference (CGD) histogram that represents contrast features is computed at first. Next, texture features that are measured by the mean subtracted contrast normalized (MSCN)-weighted local binary pattern (LBP) histogram are calculated. Then statistical features in Lαβ colour space are detected. Finally, the quality prediction model is conducted by the support vector regression (SVR) based on extracted contrast, texture, and colour features. Experiments conducted on NNID, CCRIQ, LIVE-CH, and CID2013 databases indicate that the proposed metric is superior to the compared BIQA metrics.

• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.449-459
• /
• 2006

Product Line Engineering (PLE) has been widely accepted as a representative software reuse methodology by using core assets. As a key element of core assets, product line architecture (PLA) should be generic to a set of applications in the product line (PL). However, the difference between PLA and single system architecture has not been treated well enough, so evaluating PLA still remains as one of the difficult tasks in PLE. In this paper, we identify two intrinsic but overlooked issues in PLA; variability propagation chain and conflicts between architectural elements. And, we present a metric-based methodto evaluate PLA from the perspective of the two issues. We believe that the two issues in PLA and the evaluation method would make designing high-quality PLA more feasible and effective.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

• International Journal of Quality Innovation
• /
• v.10 no.1
• /
• pp.115-126
• /
• 2009

Video transmission effectiveness in the Ad Hoc network is becoming important recently, if different routing protocols are applied. Some researchers conclude that the reactive protocols are better for file transfer protocol (FTP) and constant bit rate (CBR) or hypertext transfer protocol (HTTP) transmission in an Ad Hoc wireless network but the performance report of video transmission is not much. This study adopts Qualnet (Network Simulator) as a simulation tool for environmental designing and performance testing, and employs an experimental design with eight groups. Our experiment shows that: (1) The performance of AODV (reactive) protocol is better than DSDV, ZRP and DSR when the transmission load has only one video stream; (2) Proactive (DSDV) and Hybrid protocols (ZRP) are better for a smaller Ad Hoc network when it transmits a video stream with some applications (VoIP, FTP and CBR). We conclude that packet loss rate is sensitive to the quality of video transmission and it has negative relationship with Peak Signal-to-Noise Ratio (PSNR) value. In addition, our experiment also shows that PSNR is a simple Metric for the performance evaluation of video transmission.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.59 no.2
• /
• pp.110-116
• /
• 2023

In this study, samples of sea anchor canopy cloth mainly used in Korean jigging fishing vessels were collected and tested for performance evaluation. The canopy cloth of sea anchor is a basic element of form composition that is known to have the greatest influence on anchor performance. In order to evaluate the performance of sea anchor canopy cloth, five types of samples were tested for new metric count, tensile strength, water vapour transmission rate and drying speed according to the national standard (KS), and some correlations were identified. As a result of the test, the new metric count of cloths was 335.5-443.4 denier in warp and 217-447.6 denier in weft, and the minimum tensile strength was 860 N in warp direction and 430 N in weft direction. The apparent number and tensile strength of cloth were proportional, the water vapour transmission rate of the sample was 206.8 g/m²h, and the drying speed was 90-100 min. This study partially confirmed the performance evaluation based on speculation by the standard test method, and further research is needed on the clear relationship between the research results and the performance of the sea anchor.

• ETRI Journal
• /
• v.27 no.4
• /
• pp.465-468
• /
• 2005

This paper presents a new trust evaluation scheme in an ad hoc network. To overcome the limited information about unfamiliar nodes and to reduce the required memory space, we propose a cluster-based trust evaluation scheme, in which neighboring nodes form a cluster and select one node as a cluster head. The head issues a trust value certificate that can be referred to by its non-neighbor nodes. In this way, an evaluation of an unfamiliar node's trust can be done very efficiently and precisely. In this paper, we present a trust evaluation metric using this scheme and some operations for forming and managing a cluster. An analysis of the proposed scheme over some security problems is also presented.

• Journal of Korean Society for Quality Management
• /
• v.33 no.2
• /
• pp.1-12
• /
• 2005

An extensive literature review has been made in this paper to build the evaluation hierarchy structure for the certification of electronic commerce services. In building the evaluation hierarchy structure, major candidate evaluation factors are selected by bench marking the various certification practices, including the Malcolm Baldrige award, ISO9000, and BSC(balanced scorecard) techniques. This paper deployed principal component analysis and factor analysis techniques to develop a statistically solid and systematic evaluation model. The final evaluation model, as presented in this paper as a model for the certification of electronic commerce services, produces a numeric score on the 100% scale, which can be served as a metric for the certification decision. The AHP technique was used in converting the various qualitative and quantitative evaluation values into a single measure for the certification decision.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.7
• /
• pp.809-813
• /
• 2010

Many studies on reverse skyline query processing have been done for company oriented services. The existing methods about reverse skyline are reverse skyline based on dynamic skyline. There is no reverse skyline query processing algorithm based on metric spaces for location-based services. In this paper we propose a reverse skyline query processing scheme that applies for a general skyline and considers distance spaces. The proposed method processes reverse skyline queries in the metric spaces using the existing spatial indexing scheme and considers both Monochromatic and Bichromatic environments. In order to show the superiority of the proposed scheme, we compare it with the basic skyline query processing scheme through performance evaluation. As a result, the proposed method excellent performance was about 5000 times more than conventional method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.7-14
• /
• 2005

In this paper we proposed the block-based color image segmentation method using the cylindrical metric to solve the problems such as long processing time and over segmentation due to noise and texture properties in the conventional methods. In the proposed method we define the new similarity function and the merge condition between regions to merge initial regions with the same size considering the color and texture properties of chromatic and achromatic regions which is defined according to the HSI color values, and we continue to merge boundary blocks into the adjacent region already segmented to maintain edges until the size of block is one. In the simulation results the proposed method is better than the conventional methods in the evaluation of the segmented regions of texture and edge region, and we found that the processing time is decreased by factor of two in the proposed method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.112-114
• /
• 2011

On multimedia databases, in order to realize the fast access method, indexing methods for the multidimension data space are used. However, since it is a premise to use the Euclid distance as the distance measure, this method lacks in flexibility. On the other hand, there are metric indexing methods which require only to satisfy distance axiom. Since metric indexing methods can also apply for distance measures other than the Euclid distance, these methods have high flexibility. This paper proposes an improved method of VP-tree which is one of the metric indexing methods. VP-tree follows the node which suits the search range from a route node at searching. And distances between a query and all objects linked from the leaf node which finally arrived are computed, and it investigates whether each object is contained in the search range. However, search speed will become slow if the number of distance calculations in a leaf node increases. Therefore, we paid attention to the candidates selection method using the triangular inequality in a leaf node. As the improved methods, we propose a method to use the nearest neighbor object point for the query as the datum point of the triangular inequality. It becomes possible to make the search range smaller and to cut down the number of times of distance calculation by these improved methods. From evaluation experiments using 10,000 image data, it was found that our proposed method could cut 5%~12% of search time of the traditional method.