• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

Non-small cell lung cancer (NSCLC) accounts for a high proportion of 85% among all lung cancer and has a significantly higher mortality rate (22.7%) compared to other cancers. Therefore, it is very important to predict the prognosis after surgery in patients with non-small cell lung cancer. In this study, the types of preoperative chest CT image patches for non-small cell lung cancer patients with tumor as a region of interest are diversified into five types according to tumor-related information, and performance of single classifier model, ensemble classifier model with soft-voting method, and ensemble classifier model using 3 input channels for combination of three different patches using pre-trained ResNet and EfficientNet CNN networks are analyzed through misclassification cases and Grad-CAM visualization. As a result of the experiment, the ResNet152 single model and the EfficientNet-b7 single model trained on the peritumoral patch showed accuracy of 87.93% and 81.03%, respectively. In addition, ResNet152 ensemble model using the image, peritumoral, and shape-focused intratumoral patches which were placed in each input channels showed stable performance with an accuracy of 87.93%. Also, EfficientNet-b7 ensemble classifier model with soft-voting method using the image and peritumoral patches showed accuracy of 84.48%.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.323-338
• /
• 2023

TV advertising with deep analysis of watching pattern of audiences is important to set-top box audience targeting. Applying session-based recommendation model(SBR) to internet commercial, or recommendation based on searching history of user showed its effectiveness in previous studies, but applying SBR to the TV advertising was difficult in South Korea due to data unavailabilities. Also, traditional SBR has limitations for dealing with user preferences, especially in data with user identification information. To tackle with these problems, we first obtain set-top box data from three major broadcasting companies in South Korea(SKB, KT, LGU+) through collaboration with Korea Broadcast Advertising Corporation(KOBACO), and this data contains of watching sequence of 4,847 anonymized users for 6 month respectively. Second, we develop personalized session-based recommendation model to deal with hierarchical data of user-session-item. Experiments conducted on set-top box audience dataset and two other public dataset for validation. In result, our proposed model outperformed baseline model in some criteria.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.29-37
• /
• 2024

In this paper, we propose an efficient image processing system to detect and track the movement of specific objects such as patients. The proposed system extracts the outline area of an object from a binarized difference image by applying a thinning algorithm that enables more precise detection compared to previous algorithms and is advantageous for mixed-mode design. The binarization and thinning steps, which require a lot of computation, are designed based on RTL (Register Transfer Level) and replaced with optimized hardware blocks through logic circuit synthesis. The designed binarization and thinning block was synthesized into a logic circuit using the standard 180n CMOS library and its operation was verified through simulation. To compare software-based performance, performance analysis of binary and thinning operations was also performed by applying sample images with 640 × 360 resolution in a 32-bit FPGA embedded system environment. As a result of verification, it was confirmed that the mixed-mode design can improve the processing speed by 93.8% in the binary and thinning stages compared to the previous software-only processing speed. The proposed mixed-mode system for object recognition is expected to be able to efficiently monitor patient movements even in an edge computing environment where artificial intelligence networks are not applied.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.7
• /
• pp.711-719
• /
• 2011

A study of miniaturization of an L-band orthomode transducer(OMT) for field experiments of radar backscatter is presented in this paper. The proposed OMT is not required the additional waveguide taper structures to connect with a standard adaptor by the newly designed junction structure which bases on a waveguide taper. Total length of the OMT for L-band is about 1.2 ${\lambda}_o$(310 mm) and it's a size of 60 % of the existing OMTs. And, to increase the matching and isolation performances of each polarization, two conducting posts are inserted. The bandwidth of 420 MHz and the isolation level of about 40 dB are measured in the operating frequency. The L-band scatterometer consisting of the manufactured OMT, a horn-antenna and network analyzer(Agilent 8753E) was used STCT and 2DTST to analysis the measurement accuracy of radar backscatter. The full-polarimetric RCSs of test-target, 55 cm trihedral corner reflector, measured by the calibrated scatterometer have errors of -0.2 dB and 0.25 dB for vv-/hh-polarization, respectively. The effective isolation level is about 35.8 dB in the operating frequency. Then, the horn-antenna used to measure has the length of 300 mm, the aperture size of $450{\times}450\;mm^2$, and HPBWs of $29.5^{\circ}$ and $36.5^{\circ}$ on the principle E-/H-planes.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.3
• /
• pp.70-82
• /
• 2023

The recent surge of IT and data acquisition is shifting the paradigm in all aspects of life, and these advances are also affecting academic fields. Research topics and methods are being improved through academic exchange and connections. In particular, data-based research methods are employed in various academic fields, including landscape architecture, where continuous research is needed. Therefore, this study aims to investigate the possibility of developing a landscape preference evaluation and prediction model using machine learning, a branch of Artificial Intelligence, reflecting the current situation. To achieve the goal of this study, machine learning techniques were applied to the landscaping field to build a landscape preference evaluation and prediction model to verify the simulation accuracy of the model. For this, wind power facility landscape images, recently attracting attention as a renewable energy source, were selected as the research objects. For analysis, images of the wind power facility landscapes were collected using web crawling techniques, and an analysis dataset was built. Orange version 3.33, a program from the University of Ljubljana was used for machine learning analysis to derive a prediction model with excellent performance. IA model that integrates the evaluation criteria of machine learning and a separate model structure for the evaluation criteria were used to generate a model using kNN, SVM, Random Forest, Logistic Regression, and Neural Network algorithms suitable for machine learning classification models. The performance evaluation of the generated models was conducted to derive the most suitable prediction model. The prediction model derived in this study separately evaluates three evaluation criteria, including classification by type of landscape, classification by distance between landscape and target, and classification by preference, and then synthesizes and predicts results. As a result of the study, a prediction model with a high accuracy of 0.986 for the evaluation criterion according to the type of landscape, 0.973 for the evaluation criterion according to the distance, and 0.952 for the evaluation criterion according to the preference was developed, and it can be seen that the verification process through the evaluation of data prediction results exceeds the required performance value of the model. As an experimental attempt to investigate the possibility of developing a prediction model using machine learning in landscape-related research, this study was able to confirm the possibility of creating a high-performance prediction model by building a data set through the collection and refinement of image data and subsequently utilizing it in landscape-related research fields. Based on the results, implications, and limitations of this study, it is believed that it is possible to develop various types of landscape prediction models, including wind power facility natural, and cultural landscapes. Machine learning techniques can be more useful and valuable in the field of landscape architecture by exploring and applying research methods appropriate to the topic, reducing the time of data classification through the study of a model that classifies images according to landscape types or analyzing the importance of landscape planning factors through the analysis of landscape prediction factors using machine learning.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.6
• /
• pp.1-10
• /
• 2009

In a network-based approach such as Proxy Mobile IPv6 (PMIPv6), the serving network controls the mobility management on behalf of a Mobile Node (MN), thereby eliminating a MN from any mobility-related signaling. Although PMIPv6 is being standardized by the IETF NetLMM WG, PMIPv6 still suffers from a lengthy handover latency and the on-the-fly packet loss during a handover. Therefore, this paper presents an enhanced fast handover scheme for PMIPv6. The proposed handover scheme uses the Neighbor Discovery message of IPv6 to reduce the handover latency and packet buffering at the Mobile Access Gateway (MAG) to avoid the on-the-fly packet loss during a handover. In addition, it uses an additional packet buffering at the Local Mobility Anchor (LMA) to solve the packet ordering problem. We evaluate the performance of the proposed handover scheme using both analytical model and simulation. The numerical analysis shows that the proposed scheme has a relatively shorter handover latency. Simulation results demonstrate that the proposed scheme could avoid the on-the-fly packet loss and ensure the packet sequence.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.575-584
• /
• 2013

Data types used for big-data analysis are very widely, such as news, blog, SNS, papers, patents, sensed data, and etc. Particularly, the utilization of web documents offering reliable data in real time is increasing gradually. And web crawlers that collect web documents automatically have grown in importance because big-data is being used in many different fields and web data are growing exponentially every year. However, existing web crawlers can't collect whole web documents in a web site because existing web crawlers collect web documents with only URLs included in web documents collected in some web sites. Also, existing web crawlers can collect web documents collected by other web crawlers already because information about web documents collected in each web crawler isn't efficiently managed between web crawlers. Therefore, this paper proposed a distributed web crawler. To resolve the problems of existing web crawler, the proposed web crawler collects web documents by RSS of each web site and Google search API. And the web crawler provides fast crawling performance by a client-server model based on RMI and NIO that minimize network traffic. Furthermore, the web crawler extracts core content from a web document by a keyword similarity comparison on tags included in a web documents. Finally, to verify the superiority of our web crawler, we compare our web crawler with existing web crawlers in various experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.8
• /
• pp.1631-1636
• /
• 2015

With the advance of wireless communication technology in terrestrial area, underwater communication is also evolving very fast from a simple point-to-point transmission to an elaborate networked communications. Underwater acoustic channel has quite different features comparing with the terrestrial radio channel in terms of propagation delay, Doppler shift, multipath, and path loss. Thus, existing technologies developed for terrestrial communication might not work properly in underwater channel. Especially medium access control (MAC) protocols which highly depend on propagation phenomenon should be newly designed for underwater network. CSMA/CA has drawn lots of attention as a candidate of underwater MAC protocol, since it is able to resolve a packet collision and the hidden node problem. However, a received signal could be degraded by the interferences from the nodes locating outside the receiver's propagation radius. In this paper, we study the effects of interference on the CSMA/CA based underwater network. We derived the SNR with the interference using the sonar equation and analyzed the degradation of the RTS/CTS effects. These results are compared with the terrestrial results to understand the differences. Finally we summarized the design considerations in CSMA/CA based underwater network.

• Journal of Information Management
• /
• v.39 no.3
• /
• pp.95-113
• /
• 2008

In todays environment in which scientific technologies are changing very fast than ever, companies have to monitor and search emerging technologies to gain competitiveness. Actually many nations try to do that. Most of them use Dephi approach based on experts review as a searching method. But experts review has been criticised for probability of inclination and its derivative problems in the sense that it is accomplished only by expert's subjectivity. To overcome such problems, we used Scientometric Method for identifying emerging technology that had been done by Delphi as a rule. We made three particular efforts in order to improve the Quality of the result. Firstly, we selected one alternative database between SCI and Scopus hoping to see evenly-distributing results in wide fields on the front burner. Secondly we used Fractional citation counting in counting citation number in the stage of linear regression analysis. Lastly, we verified Scientometric result with experts opinions to minimize probable errors in a Scientometric research. As a result, we derived 290 emerging technologies from Scientometric analysis with Scopus Database, and visualized them on 2-dimension map with data mining system named KnowledgeMatrix which was developed by KISTI.