• Geomechanics and Engineering
• /
• 제36권5호
• /
• pp.441-453
• /
• 2024

Sinkhole subsidence and collapse is a common geohazard often formed in karst areas such as the state of Florida, United States of America. To predict the sinkhole occurrence, we need to understand the formation mechanism of sinkhole and its karst hydrogeology. For this purpose, investigating the factors affecting sinkholes is an essential and important step. The main objectives of the presenting study are (1) the development of a machine learning (ML)-based model, namely C5.0 decision tree (C5.0 DT), for the prediction of sinkhole susceptibility, which accounts for sinkhole/subsidence inventory and sinkhole contributing factors (e.g., geological/hydrogeological) and (2) the construction of a regional-scale sinkhole susceptibility map. The study area is east central Florida (ECF) where a cover-collapse type is commonly reported. The C5.0 DT algorithm was used to account for twelve (12) identified hydrogeological factors. In this study, a total of 1,113 sinkholes in ECF were identified and the dataset was then randomly divided into 70% and 30% subsets for training and testing, respectively. The performance of the sinkhole susceptibility model was evaluated using a receiver operating characteristic (ROC) curve, particularly the area under the curve (AUC). The C5.0 model showed a high prediction accuracy of 83.52%. It is concluded that a decision tree is a promising tool and classifier for spatial prediction of karst sinkholes and subsidence in the ECF area.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2007년도 추계학술대회 및 정기총회
• /
• pp.377-382
• /
• 2007

Mobile ad hoc network(MANET) is a kind of wireless network which has no infrastructure. Each component node of MANET can move freely and communicate based on wireless peer to peer mode. Because of its vulnerable routing protocols, MANET is exposed to many kinds of attacks. A sinkhole attack is one of the representative attacks in MANET caused by attempts to draw all network traffic to a sinkhole node. This paper focuses on the sinkhole problem on Dynamic Source Routing(DSR) protocol in MANET. To detect the sinkhole node, we extract several useful sinkhole indicators through analyzing the sinkhole problem, then propose an efficient detection method based on an incremental learning algorithm. The simulation results show that the proposed method is effective and reliable for detecting sinkhole intrusion.

• 한국지형학회지
• /
• 제24권4호
• /
• pp.75-89
• /
• 2017

Sinkholes are key karst landforms that primarily evolve through the dissolution of limestone, and it posing a significant threat to roads, buildings, and other man-made structures. This study aims to analyze the area susceptible to sinkhole development using GIS and to identify potential danger area from sinkholes. Eight sinkhole related factors (slope angle, distance to caves, distance to faults, bedrock lithology, soil depth, drainage class, distance to mines, and distance to traffic routes) were constructed as spatial databases with sinkhole inventory. Based on the spatial database, sinkhole susceptibility maps were produced using nearest neighbor distance and frequency ratio models. The maps were verified with prediction rate curve and area under curve. The result indicates that the nearest neighbor distance and frequency ratio models predicted 95.3% and 94.4% of possible sinkhole locations respectively. Furthermore, to identify potential sinkhole danger area, the susceptibility map was compared with population distribution and land use map. It has been found that very highly susceptible areas are along Osipcheon and southeast southwest part of Hajang-myeon and south part of Gagok-myeon of Samcheok-si. Among those areas, it has been identified that potential sinkhole danger areas are Gyo-dong, Seongnae-dong, Jeongna-dong, Namyang-dong and Dogye-eup. These results can be useful in the aspects of land use planning and hazard prevention and management.

• 한국정보기술학회논문지
• /
• 제17권6호
• /
• pp.17-25
• /
• 2019

최근 자주 발생하는 싱크 홀(sinkhole)을 정확하게 발견하고 추적하는 것은 사람 및 재산 피해를 예방하기 위해서 매우 중요하다. 그 동안 싱크 홀을 검출하기 위한 방안들이 많이 제안되었지만 지하 깊은 곳에서 발생하는 싱크 홀에 대한 검출은 완전히 해결되지 않고 있다. 또한 실시간으로 싱크 홀을 감지하고 실시간으로 경고를 발생하는 시스템은 아직 안정화되지 않은 상태이다. 본 연구는 딥 러닝과 데이터 결합에 의해 싱크 홀을 실시간으로 검출하기 위한 연구이며, 제안하는 알고리즘은 크게 바이너리 분할(binrary segmentation), 싱크 홀분류(sinkhole classification) 및 싱크 홀 추적(sinkhole tracking)의 세 가지 주요 부분으로 구성된다. 실험 결과 싱크 홀이 실시간으로 데이터 세트에서 추적 될 수 있음을 보여주었다. 따라서 본 연구에서 제안된 시스템은 싱크 홀을 탐지하기 위해서 실제로 적용될 수 있음을 보여준다.

• 로봇학회논문지
• /
• 제15권4호
• /
• pp.341-349
• /
• 2020

Recently, interest in ground subsidence in urban areas has increased after a large sinkhole occurred near the high-story building area in Jamsil, Seoul, Korea, in 2014. If a massive sinkhole occurs in an urban area, it is crucial to assess its risk rapidly. Access to humans for on-site safety diagnosis may be difficult because of the additional risk of collapse in the disaster area. Generally, inspection using drones equipped with high-speed lidar sensors can be utilized. However, if the sinkhole is created vertically to a depth of 100 m, similar to the sinkhole in Guatemala, the drone cannot be applied because of the wireless communication limit and turbulence inside the sinkhole. In this study, a three-dimensional (3D) scanning system was fabricated and operated using a towed cable in a massive vertical sinkhole to a depth of 200 m. A high-speed lidar sensor was used to obtain a continuous cross-sectional shape at a certain depth. An inertial-measuring unit was applied to compensate for the error owing to the rotation and pendulum movement of the measuring unit. A reconstruction algorithm, including the compensation scheme, was developed. In a vertical hole with a depth of 180 m in the mining area, the fabricated system was applied to scan 0-165 m depth. The reconstructed shape was depicted in a 3D graph.

• 디지털산업정보학회논문지
• /
• 제6권3호
• /
• pp.31-36
• /
• 2010

In this paper, We propose a transaction signing-based authentication scheme for protecting sinkhole attacks in wireless sensor networks. Sinkhole attack makes packets that flow network pass through attacker. So, Sinkhole attack can be extended to various kind of attacks such as denial of service attacks, selective delivery or data tamper etc. We analyze sinkhole attack methods in directed diffusion based wireless sensor networks. For the purpose of response to attack method, Transaction signing-based authentication scheme is proposed. This scheme can work for those sensor networks which use directed diffusion based wireless sensor networks. The validity of proposed scheme is provided by BAN logic.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.203-216
• /
• 2019

The nature of wireless transmission has made wireless sensor networks defenseless against various attacks. This paper presents warning message counter method (WMC) to detect blackhole attack, grayhole attack and sinkhole attack in wireless sensor networks. The objective of these attackers are, to draw the nearby network traffic by false routing information and disrupt the network operation through dropping all the received packets (blackhole attack), selectively dropping the received packets (grayhole and sinkhole attack) and modifying the content of the packet (sinkhole attack). We have also attempted light weighted symmetric key cryptography to find data modification by the sinkhole node. Simulation results shows that, WMC detects sinkhole attack, blackhole attack and grayhole attack with less false positive 8% and less false negative 6%.

• 한국지능시스템학회논문지
• /
• 제26권4호
• /
• pp.267-272
• /
• 2016

무선 센서 네트워크는 제약적인 하드웨어 자원과 무선 통신의 특징으로 인해 외부 침입에 취약하다. 따라서 공격자는 네트워크에 침입하여 싱크홀 공격을 시도할 수 있다. 이러한 싱크홀 공격을 방지하기 위해서 INSENS가 제안되었다. INSENS는 세 개의 대칭키를 사용하여 싱크홀 공격을 방지한다. 하지만 INSENS는 노드의 훼손을 고려하지 않기 때문에 훼손된 노드를 통해 싱크홀 공격이 다시 발생한다. 본 논문에서는 훼손된 노드를 통해 발생하는 싱크홀 공격을 이웃 노드들의 상태 정보를 사용하여 방지하는 기법을 제안한다. 제안 기법은 i) 공격을 안전하게 방지하여 네트워크의 신뢰성을 향상하고, ii) 에너지 소비 절감을 목표로 한다. 실험 결과 제안기법은 보고서의 신뢰성을 평균 71.50% 향상하고 에너지 소비를 평균 19.90% 절감한다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제14권9호
• /
• pp.901-905
• /
• 2008

본 논문에서는 무선 센서 네트워크 환성에서 싱크홀 공격을 탐지할 수 있는 방안을 제시한다. 싱크홀 공격은 네트워크를 흐르는 패킷들이 공격자를 통과하도록 하는 공격이다. 따라서 이는 다양한 공격으로 확장될 수 있다. 본 논문에서는 링크 품질 지표에 기반한 라우팅을 수행하는 네트워크에서 싱크홀 공격 방법들을 분석하고 각 공격방법에 따라 공격을 탐지하기 위한 방안들을 제시한다. 제안하는 싱크홀 공격 탐지 방법은 링크 품질 지표에 기반한 동적 라우팅 프로토콜을 사용하는 모든 센서 네트워크에 적용할 수 있으며 소수의 공격 탐지 노드를 사용하여 싱크홀 공격의 탐지가 가능함을 알 수 있다.

• 동굴
• /
• 제34권35호
• /
• pp.78-104
• /
• 1993

Analysis of one sinkhole, the Dodgeville sinkhole, developed in Ordovician dolostones in the Driftless Area of Wisconsin in the Upper Midwest'd Driftless Area reveals homogenous clayey sediment fills reflecting a range of dissolutional processes during the Quaternary or Pre-Quaternary. Granulometric analysis, graphical moments statistics, carbonate minerals, ana sand grain lithology were used to differentiate sinkhole sediment sources and modes of accumulation. Sediments in the dolostone sinkholes developed by dissolution. Sediments contain two major types of sediments : residual redish clay( autogenic sediments) and aeolian silt (allogenic sediments). The massive clay is generated from the weathered dolostone bedrocks as a in situ materials. The loessial silt is mostly derived from transportation of the surrounding surface materials, with some evidences of penetrated deposition. Unlike the collapsed sandstone sinkholes (Oh et al., 1993), dolostone sinkholes reveal homogenous, autogenic clay materials, and a geochemical composition indicative of in situ autogenic karstification. Dolostone sinkhole si1ts (26.9%) and sands (34.9%) are derived from weathered Plattevi1le-Galena dolostones, and contain high carbonate(37.5%), chert (57.2%) and lead ore (3%). Graphical moments statistics for sorting, skewness, and kurtosis indicate that sand grains from dolostones were derived entirely from local bedrock by in situ dissolution. Upper sinkhole sediments are pedagogically very young as carbonate is unleashed. Materials of the sinkhole sediment are definitely inherited from internal dolostones by dissolution and weathering, because not only a granulomatric comparison of dolostone and sandstone sediments demonstrates that they have heterogeneous paticle size distributions, but also 1ithologic analyses displays they differ completely.