• Journal of the Korean GEO-environmental Society
• /
• v.23 no.8
• /
• pp.29-36
• /
• 2022

The importance of subsurface information is becoming crucial in urban area due to increase of underground construction. The position of underground facilities should be identified precisely before excavation work. Geophyiscal exporation method such as ground penetration radar (GPR) can be useful to investigate the subsurface facilities. GPR transmits electromagnetic waves to the ground and analyzes the reflected signals to determine the location and depth of subsurface facilities. Unfortunately, the readability of GPR signal is not favorable. To overcome this deficiency and automate the GPR signal processing, deep learning technique has been introduced recently. The accuracy of deep learning model can be improved with abundant training data. The ground is inherently heteorogeneous and the spacially variable ground properties can affact on the GPR signal. However, the effect of ground heterogeneity on the GPR signal has yet to be fully investigated. In this study, ground heterogeneity is simulated based on the fractal theory and GPR simulation is carried out by using gprMax. It is found that as the fractal dimension increases exceed 2.0, the error of fitting parameter reduces significantly. And the range of water content should be less than 0.14 to secure the validity of analysis.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.4
• /
• pp.435-445
• /
• 2022

In this study, the reverberation of a bistatic sonar operated in southeastern coast in the East Sea in July 2020 was analyzed. The reverberation sensor data were collected through an LFM sound source towed by a research vessel and a horizontal line array receiver 1 km to 5 km away from it. The reverberation sensor data was analyzed by various methods including geo-plot after signal processing. Through this, it was confirmed that the angle reflected from the sound source through the scatterer to the receiver has a dominant influence on the distribution of the reverberation sound, and the probability distribution characteristics of bistatic sonar reverberation varies for each beam. In addition, parametric factors of K distribution and Rayleigh distribution were estimated from the sample through moment method estimation. Using the Kolmogorov-Smirnov test at the confidence level of 0.05, the distribution probability of the data was analyzed. As a result, it could be observed that the reverberation follows a Rayleigh probability distribution, and it could be estimated that this was the effect of a low reverberation to noise ratio.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1935-1943
• /
• 2022

The development and application of a high-resolution soil moisture mapping method using satellite imagery has been considered one of the major research themes in remote sensing. In this study, soil moisture mapping in the test area of Jeju Island was performed. The soil moisture was calculated with optical images using linearly adjusted Synthetic Aperture Radar (SAR) polarization images and incident angle. SAR Backscatter data, Analysis Ready Data (ARD) provided by Google Earth Engine (GEE), was used. In the soil moisture processing process, the optical image was applied to normalized difference vegetation index (NDVI) by surface reflectance of KOMPSAT-3 satellite images and the land cover map of Environmental Systems Research Institute (ESRI). When the SAR image and the optical images are fused, the reliability of the soil moisture product can be improved. To validate the soil moisture mapping product, a comparative analysis was conducted with normalized difference water index (NDWI) products by the KOMPSAT-3 image and those of the Landsat-8 satellite. As a result, it was shown that the soil moisture map and NDWI of the study area were slightly negative correlated, whereas NDWI using the KOMPSAT-3 images and the Landsat-8 satellite showed a highly correlated trend. Finally, it will be possible to produce precise soil moisture using KOMPSAT optical images and KOMPSAT SAR images without other external remotely sensed images, if the soil moisture calculation algorithm used in this study is further developed for the KOMPSAT-5 image.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.11-16
• /
• 2022

As an interest in the development of artificial intelligence(AI) technology in the water supply sector increases, we have developed an AI algorithm that can predict improvement decision-making ratings through repetitive learning using the data of pipe condition evaluation results, and present the most reliable prediction model through a verification process. We have developed the algorithm that can predict pipe ratings by pre-processing 12 indirect evaluation items based on the 2020 Han River Basin's basic plan and applying the AI algorithm to update weighting factors through backpropagation. This method ensured that the concordance rate between the direct evaluation result value and the calculated result value through repetitive learning and verification was more than 90%. As a result of the algorithm accuracy verification process, it was confirmed that all water pipe type data were evenly distributed, and the more learning data, the higher prediction accuracy. If data from all across the country is collected, the reliability of the prediction technique for pipe ratings using AI algorithm will be improved, and therefore, it is expected that the AI algorithm will play a role in supporting decision-making in the objective evaluation of the condition of aging pipes.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.1
• /
• pp.23-34
• /
• 2022

With the development of network technology, the application area has also been diversified, and protocols for various purposes have been developed and the amount of traffic has exploded. Therefore, it is difficult for the network administrator to meet the stability and security standards of the network with the existing traditional switching and routing methods. Software Defined Networking (SDN) is a new networking paradigm proposed to solve this problem. SDN enables efficient network management by programming network operations. This has the advantage that network administrators can flexibly respond to various types of attacks. In this paper, we design a threat level management module, an attack detection module, a packet statistics module, and a flow rule generator that collects attack information through the controller and switch, which are components of SDN, and detects attacks based on these attributes of SDN. It proposes a method to block denial of service attacks (DoS) of advanced attackers by programming and applying honeypot. In the proposed system, the attack packet can be quickly delivered to the honeypot according to the modifiable flow rule, and the honeypot that received the attack packets analyzed the intelligent attack pattern based on this. According to the analysis results, the attack detection module and the threat level management module are adjusted to respond to intelligent attacks. The performance and feasibility of the proposed system was shown by actually implementing the proposed system, performing intelligent attacks with various attack patterns and attack levels, and checking the attack detection rate compared to the existing system.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.1-10
• /
• 2022

Deep neural networks are widely used to solve various problems. In a fully connected neural network, the nonlinear activation function is a function that nonlinearly transforms the input value and outputs it. The nonlinear activation function plays an important role in solving the nonlinear problem, and various nonlinear activation functions have been studied. In this study, we propose a combined parametric activation function that can improve the performance of a fully connected neural network. Combined parametric activation functions can be created by simply adding parametric activation functions. The parametric activation function is a function that can be optimized in the direction of minimizing the loss function by applying a parameter that converts the scale and location of the activation function according to the input data. By combining the parametric activation functions, more diverse nonlinear intervals can be created, and the parameters of the parametric activation functions can be optimized in the direction of minimizing the loss function. The performance of the combined parametric activation function was tested through the MNIST classification problem and the Fashion MNIST classification problem, and as a result, it was confirmed that it has better performance than the existing nonlinear activation function and parametric activation function.

• Analytical Science and Technology
• /
• v.34 no.6
• /
• pp.251-258
• /
• 2021

Knives are most frequently used as weapons in violent crimes. Criminals leave behind knife sheaths made of paper and tape at crime scenes. It is difficult to develop fingerprints using tape attached to a porous surface, resulting in the need to explore effective techniques for identifying fingerprints as well as the distribution of fingerprints on each surface, when evidence such as paper knife sheaths are found. In this study, 50 knife sheaths were prepared. The cyanoacrylate fuming (CA fuming) method was applied to develop fingerprints on the non-adhesive side of the tape, and a dual-purpose 1,2-indanedione/Zn (1,2-IND/Zn) reagent was used to separate tape from paper while simultaneously developing fingerprints on the paper. The fingerprints on the adhesive side of the tape were developed using Wet Powder Black^®. Using the R statistical analysis program (The R Foundation for Statistical Computing), we used a heat map to indicate the location of fingerprints developed from each surface. More fingerprints were detected at the ends than in the center of the adhesive side of the tape, and although the non-adhesive sides of tape and paper did not present clear distribution patterns, many fingerprints were developed that had sufficient clarity for personal identification. The results of this study may be applicable for processing evidence when paper sheaths are found at crime scenes.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.11
• /
• pp.119-129
• /
• 2021

The process of constructing the DB in the current geotechnical information DB system needs a lot of human and time resource consumption. In addition, it causes accuracy problems frequently because the current input method is a person viewing the PDF and directly inputting the results. Therefore, this study proposes building an automatic digital DB using AI (artificial intelligence) of boring logs. In order to automatically construct DB for various boring log formats without exception, the boring log forms were classified using the deep learning model ResNet 34 for a total of 6 boring log forms. As a result, the overall accuracy was 99.7, and the ROC_AUC score was 1.0, which separated the boring log forms with very high performance. After that, the text in the PDF is automatically read using the robotic processing automation technique fine-tuned for each form. Furthermore, the general information, strata information, and standard penetration test information were extracted, separated, and saved in the same format provided by the geotechnical information DB system. Finally, the information in the boring log was automatically converted into a DB at a speed of 140 pages per second.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.3
• /
• pp.241-264
• /
• 2022

Bibliographic metadata can help researchers effectively utilize essential publications that they need and grasp academic trends of their own fields. With the manual creation of the metadata costly and time-consuming. it is nontrivial to effectively automatize the metadata construction using rule-based methods due to the immoderate variety of the article forms and styles according to publishers and academic societies. Therefore, this study proposes a two-step extraction process based on rules and deep neural networks for generating bibliographic metadata of scientific articlles to overcome the difficulties above. The extraction target areas in articles were identified by using a deep neural network-based model, and then the details in the areas were analyzed and sub-divided into relevant metadata elements. IThe proposed model also includes a model for generating reference summary information, which is able to separate the end of the text and the starting point of a reference, and to extract individual references by essential rule set, and to identify all the bibliographic items in each reference by a deep neural network. In addition, in order to confirm the possibility of a model that generates the bibliographic information of academic papers without pre- and post-processing, we conducted an in-depth comparative experiment with various settings and configurations. As a result of the experiment, the method proposed in this paper showed higher performance.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.323-332
• /
• 2022

As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.