Earticle

As technologies related to sensor network are currently emerging and the use of GeoSensor is increasing along with the development of Internet of Things (IoT) technology, spatial query processing systems to efficiently process spatial sensor data are being actively studied. However, existing spatial query processing systems do not support a spatial-temporal data type and a spatial-temporal operator for processing spatialtemporal sensor data. Therefore, they are inadequate for processing spatial-temporal sensor data like GeoSensor. Accordingly, this paper developed a spatial-temporal query processing system, for efficient spatial-temporal query processing of spatial-temporal sensor data in a sensor network. Lastly, this paper verified the utility of System through a scenario, and proved that this system's performance is better than existing systems through performance assessment of performance time and memory usage.

The vast number of biomedical literature is an important source of biomedical interaction information discovery. However, it is complicated to obtain interaction information from them because most of them are not easily readable by machine. In this paper, we present a method for extracting biomedical interaction information assuming that the biomedical Named Entities (NEs) are already identified. The proposed method labels all possible pairs of given biomedical NEs as INTERACTION or NO-INTERACTION by using a Maximum Entropy (ME) classifier. The features used for the classifier are obtained by applying various NLP techniques such as POS tagging, base phrase recognition, parsing and predicate-argument recognition. Especially, specific verb predicates (activate, inhibit, diminish and etc.) and their biomedical NE arguments are very useful features for identifying interactive NE pairs. Based on this, we devised a twostep method: 1) an interaction verb extraction step to find biomedically salient verbs, and 2) an argument relation identification step to generate partial predicate-argument structures between extracted interaction verbs and their NE arguments. In the experiments, we analyzed how much each applied NLP technique improves the performance. The proposed method can be completely improved by more than 2% compared to the baseline method. The use of external contextual features, which are obtained from outside of NEs, is crucial for the performance improvement. We also compare the performance of the proposed method against the co-occurrence-based and the rule-based methods. The result demonstrates that the proposed method considerably improves the performance.

Bug report processing is a key element of bug fixing in modern software maintenance. Bug reports are not processed immediately after submission and involve several processes such as bug report deduplication and bug report triage before bug fixing is initiated; however, this method of bug fixing is very inefficient because all these processes are performed manually. Software engineers have persistently highlighted the need to automate these processes, and as a result, many automation techniques have been proposed for bug report processing; however, the accuracy of the existing methods is not satisfactory. Therefore, this study focuses on surveying to improve the accuracy of existing techniques for bug report processing. Reviews of each method proposed in this study consist of a description, used techniques, experiments, and comparison results. The results of this study indicate that research in the field of bug deduplication still lacks and therefore requires numerous studies that integrate clustering and natural language processing. This study further indicates that although all studies in the field of triage are based on machine learning, results of studies on deep learning are still insufficient.

Background/Objectives: Recently, as the usability of IoT devices increases, the kinds of information processed by IoT devices are also diversifying. For this reason, research to ensure the high-speed processing and integrity of information generated from IoT devices continues steadily. In particular, research using various hash techniques is actively underway to minimize IoT information errors. Methods/Statistical analysis: In this paper, instead of sending IoT information directly to the server (data center), we propose an AIoT technique that allows AIoT to pre-analyze and delivers only important information. Findings: The proposed technique allows easy control of IoT information operation after analyzing patterns of information collected from IoT devices to extract and analyze large amounts of IoT information. Furthermore, the proposed technique minimizes network delay as well as minimizes server (data center) processing and analysis time by reducing network traffic that can occur when information collected from numerous IoT devices is delivered to the server (data center). Improvements/Applications: AIoT, IoT information, Extract and Analysis, Artificial, Depp Learning, hash techniques Performance evaluation compared the storage efficiency of servers and the number of transactions of IoT information sent and received per second between IoT devices and AIoT devices while varying the hash length of IoT information from 16 bits to 128 bits.

With social media growing fast, user-generated content (UGC) has become a key factor in influencing how consumers decide what to buy, especially in the travel and hospitality sector. But there are a lot of fake and extreme reviews, which are making it hard for customers to make the right choice and making competition in the market unfair. The present study focuses on YouTube, a platform with high global activity, and proposes a systematic solution that combines Natural Language Processing (NLP) and machine learning methods (e.g., VADER Sentiment Analysis, Support Vector Machine SVM, and LDA Topic Modelling) for identifying and filtering fake and extreme remarks in hotel reviews. This approach has been shown to enhance the automation and precision of review screening processes. Furthermore, it provides a theoretical foundation and practical methodologies to improve the online information ecology, thereby enhancing the quality of user decision-making.

과거 양식장에서 어류 질병은 세균성이었던 반면 최근은 바이러스성 및 혼합된 형태가 되면서 어류 질병의 빈도가 높아졌다. 양식장이라는 밀폐된 공간에서 바이러성 질병은 확산속도가 높으므로 집단 폐사로 이어질 확률이 매우 높다. 집단 폐사를 방지하기 위해서는 어류 질병의 빠른 식별이 중요하다. 그러나 어류의 질병 진단은 고도의 전문지식이 필요하고 매번 어류의 상태를 눈으로 확인하기 어렵다. 질병의 확산을 막기 위해서는 병이든 어류의 자동식별 시스템이 필요하다. 본 논문에서는 딥러닝 기반의 넙치의 질병 식별 시스템의 성능을 높이기 위해서 기존 전처리 방법을 비교 실험한다. 대상 질병은 넙치에서 가장 빈번히 발생하는 3가지 질병 스쿠티카병, 비브리오증, 림포시스티스를 선정하였고 이미지 전처리 방법으로 RGB, HLS, HSV, LAB, LUV, XYZ, YCRCV를 사용하였다. 실험결과 일반적인 RGB를 사용하는 것보다 HLS가 가장 좋은 결과를 얻을 수 있었다. 간단한 방법으로 질병의 인식률을 향상해 어류 질병 식별 시스템을 고도화 할 수 있을 것으로 예상한다.

In the past, fish diseases were bacterial in aqua farms, but in recent years, the frequency of fish diseases has increased as they have become viral and mixed. Viral diseases in an enclosed space called a aqua farm have a high spread rate, so it is very likely to lead to mass death. Fast identification of fish diseases is important to prevent group death. However, diagnosis of fish diseases requires a high level of expertise and it is difficult to visually check the condition of fish every time. In order to prevent the spread of the disease, an automatic identification system of diseases or fish is needed. In this paper, in order to improve the performance of the disease identification system of Paralichthys olivaceus based on deep learning, the existing pre-processing method is compared and tested. Target diseases were selected from three most frequent diseases such as Scutica, Vibrio, and Lymphocystis in Paralichthys olivaceus. The RGB, HLS, HSV, LAB, LUV, XYZ, and YCRCV were used as image pre-processing methods. As a result of the experiment, HLS was able to get the best results than using general RGB. It is expected that the fish disease identification system can be advanced by improving the recognition rate of diseases in a simple way.

The determination of soil dry unit weight is crucial for assessing the stability of diverse geotechnical structures. While empirical regression methods have been proposed to predict dry unit weight using data from various sounding techniques (e.g., CPT, SPT, and DCPT), these approaches may exhibit uncertainties when applied across different regions or soil types, thus compromising their reliability. This study investigates the efficacy of Bayesian regression analysis in conjunction with outlier processing techniques for the probabilistic prediction of dry unit weight, utilizing Dynamic Cone Penetration Test (DCPT) and in-situ density test data. The findings demonstrate that Bayesian methods, coupled with outlier processing, effectively quantify prediction uncertainty and leverage prior information to yield more robust and accurate predictions. The proposed methodology facilitates reliable and precise probabilistic estimations of dry unit weight using the cost-effective and straightforward DCPT. Moreover, this approach offers the advantage of deriving site-specific prediction models by integrating both the distribution of data from previous studies and a limited amount of field data, as opposed to directly applying generalized formulas. The results underscore the potential of this methodology in enhancing the accuracy and reliability of dry unit weight predictions in geotechnical engineering. Further research exploring the influence of varied soil conditions and the quantity of field data on prediction outcomes may enhance the generality and applicability of these findings.

Establishment of appropriate data in certain formats is essential for agricultural water cycle analysis, which involves complex interactions and uncertainties such as climate change, social & economic change, and watershed environmental change. The main objective of this study was to develop web-based Data processing and Model linkage Techniques for Agricultural Water-Resource analysis (AWR-DMT). The developed techniques consisted of database development, data processing technique, and model linkage technique. The watershed of this study was the upper Cheongmi stream and Geunsam-Ri. The database was constructed using MS SQL with data code, watershed characteristics, reservoir information, weather station information, meteorological data, processed data, hydrological data, and paddy field information. The AWR-DMT was developed using Python. Processing technique generated probable rainfall data using non-stationary frequency analysis and evapotranspiration data. Model linkage technique built input data for agricultural watershed models, such as the TANK and Agricultural Watershed Supply (AWS). This study might be considered to contribute to the development of intelligent watercycle analysis by developing data processing and model linkage techniques for agricultural water-resource analysis.

Lamb waves are extensively used in plate-like structure inspection because of their guided nature. However, their dispersive properties often limit their use in flaw detection and other applications. Dispersion weakens and defocuses interrogating Lamb waves and makes it difficult to accurately interpret signals reflected from defects or boundaries. Time reversal (TR) processing can be applied to compensate for the effect of dispersive Lamb waves. Thus, the TR operation will enable the amplification of dispersive Lamb wave signals by signal compression in time. In this study, experiments are performed in order to examine the refocusing and recovering the initial input waveform in the long range propagation of dispersive Lamb waves in a plate. Two different time reversal processes (regular TR and reciprocal TR or inverse filtering) are tested and the experimental results are compared.

최근 IoT와 연계된 서비스들이 다양한 환경에서 활용되면서 IoT와 인공지능 기술이 융합되고 있다. 그러나, IoT 데이터를 안정적으로 처리하는 기술들이 완벽하게 지원되고 있지 않아 이를 위한 연구가 필요한 상황이다. 본 논문에서는 IoT 데이터를 머신러닝 기반으로 임베디드 벡터를 생성한 후 IoT 데이터를 최적화 할 수 있는 처리 기법을 제안한다. 제안 기법에서는 처리 효율을 위해서 IoT 데이터의 인덱스, 수집 위치(X와 Y축 좌표의 이진값), 그룹 인덱스, 타입, 종류 등을 QR 기반으로 임베디드 벡터화를 수행한다. 또한, IoT 데이터를 비대칭적으로 연계하 도록 IoT 데이터 수집 과정에서 로드밸런싱을 수행할 수 있도록 다양한 IoT 장치에서 생성한 데이터를 통합 관리한 다. 제안 기법은 비대칭적으로 IoT 데이터를 그룹화할 수 있도록 IoT 데이터를 해쉬기반으로 서로 직교화하도록 처리한다. 또한, IoT 데이터 종류 및 특성에 따라 주기적으로 생성 및 그룹화하기 때문에 IoT 데이터 간 간섭은 최소화할 수 있다. 향후 연구에서는 IoT 서비스를 제공하는 여러 환경에서 제안 기법을 비교 평가할 계획이다.

Recently, IoT-linked services have been used in various environments, and IoT and artificial intelligence technologies are being fused. However, since technologies that process IoT data stably are not fully supported, research is needed for this. In this paper, we propose a processing technique that can optimize IoT data after generating embedded vectors based on machine learning for IoT data. In the proposed technique, for processing efficiency, embedded vectorization is performed based on QR such as index of IoT data, collection location (binary values of X and Y axis coordinates), group index, type, and type. In addition, data generated by various IoT devices are integrated and managed so that load balancing can be performed in the IoT data collection process to asymmetrically link IoT data. The proposed technique processes IoT data to be orthogonalized based on hash so that IoT data can be asymmetrically grouped. In addition, interference between IoT data may be minimized because it is periodically generated and grouped according to IoT data types and characteristics. Future research plans to compare and evaluate proposed techniques in various environments that provide IoT services.

에지 네트워크 환경에서 IoT 장치가 다양하게 활용되면서 IoT 장치에서 수집되는 정보들을 여러 응용 분야에서 활용하는 연구들이 다양하게 진행되고 있다. 그러나, 네트워크 환경(간섭, 전파방해 등)에 따라 수집되는 IoT 데이터들 이 누락 또는 오류가 발생하는 상황이 빈번해지면서 정확한 IoT 데이터들을 바로 적용하기가 쉽지 않은 상황이다. 본 논문에서는 에지 네트워크 환경에서 수집되는 IoT 데이터들의 오류를 줄이기 위해서 IoT 데이터의 서명 값을 랜덤하게 생성하여 비트 형태로 보안 정보(Security Information, SI) 값만을 IoT 데이터들에 각각 할당함으로써 IoT 데이터의 신뢰성을 보장하는 관리 기법을 제안한다. 제안 기법은 IoT 장치로부터 수집되는 데이터들을 비대칭적으로 서로 연계 처리하도록 다중 해쉬 체인을 적용하여 IoT 데이터를 블록체인으로 묶는다. 이때, 블록 체인화된 IoT 데이터들은 딥 러닝 기반으로 상관관계 지수에 따라 가중치를 적용한 확률 함수를 사용한다. 또한, IoT 데이터의 무결성과 처리 비용 을 낮추기 위해서 제안 기법은 그룹화된 IoT 데이터를 n-계층 구조로 확장 운영 가능하다.

As IoT devices are used in various ways in an edge network environment, multiple studies are being conducted that utilizes the information collected from IoT devices in various applications. However, it is not easy to apply accurate IoT data immediately as IoT data collected according to network environment (interference, interference, etc.) are frequently missed or error occurs. In order to minimize mistakes in IoT data collected in an edge network environment, this paper proposes a management technique that ensures the reliability of IoT data by randomly generating signature values of IoT data and allocating only Security Information (SI) values to IoT data in bit form. The proposed technique binds IoT data into a blockchain by applying multiple hash chains to asymmetrically link and process data collected from IoT devices. In this case, the blockchainized IoT data uses a probability function to which a weight is applied according to a correlation index based on deep learning. In addition, the proposed technique can expand and operate grouped IoT data into an n-layer structure to lower the integrity and processing cost of IoT data.

영상 감시 시스템은 다양한 실외 환경에서 실시간으로 수집되는 다채널 영상을 처리해야 하며, 저시정 환 경에서는 영상 품질이 급격히 저하되는 문제가 발생한다. 이를 해결하기 위한 인공지능(AI) 기반 영상 복원 기술 은 고품질 영상 복원을 가능하게 하지만, 높은 연산 자원 요구로 인해 모든 채널에 일괄 적용하기에는 실시간성 확보가 어렵다. 본 논문에서는 복원 기능을 채널별로 선택적으로 적용할 수 있는 선택적 제어 구조(Selective Control Architecture)를 제안하고, 온 디바이스 환경에서 구현된 시스템의 자원 효율성과 실시간 처리 성능을 실 험적으로 분석하였다. 실험 결과, 복원 기능의 적용 채널 수에 따라 GPU 사용률과 영상 출력 속도가 크게 달라지 는 것을 확인하였으며, 선택적 제어 구조가 자원 최적화와 시스템 안정성 확보에 효과적임을 입증하였다. 본 연구 는 AI 영상 복원 기술의 실시간 시스템 통합에 있어 유연하고 실용적인 구조 설계 방안을 제시하며, 향후 모델 경량화 및 병렬 처리 구조 확장을 통한 시스템 고도화를 계획하고 있다.

Video surveillance systems must process multi-channel real-time streams in various outdoor environments, where image quality often deteriorates under low-visibility conditions such as fog or haze. While AI-based video restoration techniques have shown promise in recovering high-quality images, their high computational demands make it difficult to apply them uniformly across all channels in real-time systems. This paper proposes a Selective Control Architecture that enables channel-wise activation of AI restoration functions. The system was implemented in an on-device environment using a CPU with integrated GPU, and its performance was evaluated by measuring GPU usage and frame rate under varying numbers of active restoration channels. The experimental results demonstrate that GPU load and processing speed significantly change depending on the number of channels using AI restoration, and that the proposed architecture effectively optimizes resource usage while maintaining system stability. This study provides a practical system-level solution for integrating AI-based restoration into surveillance platforms, and future work will focus on model compression and parallel processing to enhance real-time performance and scalability.

도로 교통 상황을 감시하고 교통 정보를 추출하는 현재의 기술은 고가이며 설치하기가 어려운 하드웨어에 의존하고 있다. 비디오 카메라와 컴퓨터 비죤 기술의 이용은 기존의 방법의 새로운 대안이 될 수 있다. 비디오 카메라를 이용한 교통 정보 추출은 최근의 교통 운영 시스템의 중요한 열쇠이다. 본 논문에서는 비디오 카메라를 이용한 영상처리 기술을 적용하여 교통 정보를 추출하는 방법을 제안하였다. 제안된 방법에서는 주변 환경에서 여러 가지 잡음으로 인한 오 인식을 제거하기 위하여 적응적 배경영상 갱신 방법을 사용하였다. 또한 교통정보 추출 방법에서는 거리 값을 정의하여 검색구간을 통과하는 차량의 점유율을 통해 교통변수를 구하고, 이를 이용하여 8개의 교통상태를 정의하여 교통량을 측정하였다. 제안된 방법은 도심의 교통상황 데이터를 이용하여 실험하였다.

Current techniques for road-traffic monitoring rely on sensors which have limited capabilities, are costly and disruptive to install. The use of video cameras coupled with computer vision techniques offers an attractive alternative to current sensors. Video based traffic monitoring systems are now being considered key points of advanced traffic management systems. In this paper, we propose the new method which extract the traffic information using video camera. The proposed method uses an adaptive updating scheme for background in order to reduce the false alarm rate due to various noises in images. also, the proposed extraction method of traffic information calculates the traffic volume ratio of vehicles passing through predefined detection area, which is defined by the length of profile occupied by cars over that of overall detection area. Then the ratio is used to define 8 different states of traffic and to interpret the state of vehicle flows. The proposed method is verified by an experiment using CCTV traffic data from urban area.

최근 ICT분야가 다양한 환경에서 사용되면서 지속가능한 농업 환경에서는 ICT 기술들을 활용하여 농작물 별 병충해 분석, 농작물 수확시 로봇 사용, 빅 데이터로 인한 예측 등이 가능해졌다. 그러나, 지속 가능한 농업 환경 에서는 자원의 고갈, 농업 인구 감소, 빈곤 증가, 환경 파괴 등을 해결하기 위한 노력이 꾸준히 요구되고 있다. 본 연구에서는 지속 가능한 농업 환경 기반의 농작물의 생산 비용 감소 및 효율성을 증가하기 위한 인공지능 기반 빅 데이터 처리 기법을 제안한다. 제안 기법은 AI를 결합한 농작물의 빅 데이터를 처리함으로써 데이터의 보안성과 신뢰성을 강화하고, 더 나은 의사 결정과 비즈니스 가치 추출이 가능하다. 이는 다양한 산업과 분야에서 혁신적인 변화를 이끌어내고, 데이터 중심의 비즈니스 모델의 발전을 촉진할 수 있다. 실험과정에서 제안 기법은 다량의 데 이터가 생성되나, 일일이 정답을 태깅하기 힘든 농장 현장에서, 소량의 데이터에 대해서만 정확한 정답을 부여하고, 정답이 부여되지 않은 다량의 데이터와 함께 학습하여, 다량의 정답 데이터로 학습했을 때와 유사한 성능(오차 율:0.05 이내)이 나타났다.

Recently, as the ICT field has been used in various environments, it has become possible to analyze pests by crops, use robots when harvesting crops, and predict by big data by utilizing ICT technologies in a sustainable agricultural environment. However, in a sustainable agricultural environment, efforts to solve resource depletion, agricultural population decline, poverty increase, and environmental destruction are constantly being demanded. This paper proposes an artificial intelligence-based big data processing analysis method to reduce the production cost and increase the efficiency of crops based on a sustainable agricultural environment. The proposed technique strengthens the security and reliability of data by processing big data of crops combined with AI, and enables better decision-making and business value extraction. It can lead to innovative changes in various industries and fields and promote the development of data-oriented business models. During the experiment, the proposed technique gave an accurate answer to only a small amount of data, and at a farm site where it is difficult to tag the correct answer one by one, the performance similar to that of learning with a large amount of correct answer data (with an error rate within 0.05) was found.

본 논문에서는 단일 센서와 공간집속 신호처리 기술로 시간 역전과 인버스 필터링을 이용하여 등방성 평판에 서 충격 위치를 결정할 수 있는 탐상법을 다루었다. 유한 평면에서 굽힘 파의 운동 방정식을 유도하여, 그 식을 통해 얻어진 데이터를 기반으로 해석적인 시뮬레이션을 통해 시간 역전과 인버스 필터링의 시간 집속 효과를 확 인하고 충격 위치와 그 주변에서 신호의 공간 집속 효과를 관찰하고 충격 위치 결정에 영향을 미칠 수 있는 인자 들(총 수신시간, 샘플링 주파수)에 대해 살펴보았다. 그리고 충격원의 위치에 따른 2차원 결과를 제시하고, 실제 충격 위치를 정확하게 결정할 수 있음을 확인하였다. 여기서 제안한 방법은 기존의 충격 위치 결정법에 비해 많 은 장점을 갖고 있다. 첫 번째로 단일 센서를 사용하는 것과 시험체의 형상과 물성을 몰라도 된다는 점이다. 또한 판 에서와 같이 분산성에 의한 다중모드 파동이 발생하는 경우에도 특정 모드나 주파수에 의존할 필요가 없다.

본 논문에서는 단일 센서와 공간집속 신호처리 기술로 시간 역전과 인버스 필터링을 이용하여 이방성 평판에 서 충격 위치를 결정할 수 있는 탐상법을 다루었다. 유한 평면에서 굽힘 파의 운동 방정식을 유도하여, 그 식을 통해 얻어진 데이터를 기반으로 해석적인 시뮬레이션을 통해 시간 역전과 인버스 필터링의 시간 집속 효과를 확 인하고 충격 위치와 그 주변에서 신호의 공간 집속 효과를 관찰하고 충격 위치 결정에 영향을 미칠 수 있는 인자 들(총 수신시간, 샘플링 주파수)에 대해 살펴보았다. 그리고 충격원의 위치에 따른 2차원 결과를 제시하고, 실제 충격 위치를 정확하게 결정할 수 있음을 확인하였다. 여기서 제안한 방법은 기존의 충격 위치 결정법에 비해 많은 장점을 갖고 있다. 첫 번째로 단일 센서를 사용하는 것과 시험체의 형상과 물성을 몰라도 된다는 점이다. 또한 판 에서와 같이 분산성에 의한 다중모드 파동이 발생하는 경우에도 특정 모드나 주파수에 의존할 필요가 없다.