Article
Computer Science, Artificial Intelligence
Yongda Cai, Joshua Zhexue Huang, Jianfei Yin
Summary: This paper proposes a new method called adaptive k-nearest neighbors similarity graph (AKNNG) for constructing a better graph structure. By assigning different k values to different data points and automatically adjusting the k value based on the similarity graph, the AKNNG method improves clustering accuracies and reduces construction time.
Article
Computer Science, Artificial Intelligence
Yizhang Wang, Wei Pang, Zhixiang Jiao
Summary: Clustering based on Mutual K-nearest Neighbors (CMNN) is a classical method that groups data into clusters. However, it has limitations regarding the parameter k and misidentification of noise points. To address these issues, we propose an adaptive improved CMNN algorithm (AVCMNN) consisting of the improved CMNN algorithm (VCMNN) and the adaptive VCMNN algorithm (AVCMNN). The experimental results show that VCMNN and AVCMNN outperform other classical and state-of-the-art clustering algorithms.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Mohamed Abbas, Adel El-Zoghabi, Amin Shoukry
Summary: The novel clustering algorithm DenMune is able to handle clusters of arbitrary shapes, varying densities, and unbalanced data classes effectively. It is based on the mutual nearest neighbor principle and can stably detect and remove noise while detecting target clusters.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Wuning Tong, Yuping Wang, Delong Liu, Xiulin Guo
Summary: This paper presents a multi-center clustering algorithm based on mutual nearest neighbors, which can effectively cluster non-convex data sets without any parameters by adaptively finding center points and utilizing the role of multiple center points, and obtaining final clusters based on the degree of overlapping and distance.
INTEGRATED COMPUTER-AIDED ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Chaoyang Xu, Renjie Lin, Jinyu Cai, Shiping Wang
Summary: This paper proposes a new deep image clustering framework that combines contrastive learning with neighbor relation mining, achieving more semantic meaningful representations and accurate image clusters. The framework alternates between contrastive learning and neighbor relation mining to update the model.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Software Engineering
Tanghuai Fan, Zhanfeng Yao, Longzhe Han, Baohong Liu, Li Lv
Summary: The DPC algorithm performs poorly on complex data sets with large differences in density, flow pattern or cross-winding, and has relatively poor fault tolerance in sample allocation. This article proposes the DPC-KNNS algorithm to improve clustering performance on datasets with large density differences and complex patterns.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Muhammad Jamal Ahmed, Faisal Saeed, Anand Paul, Sadeeq Jan, Hyuncheol Seo
Summary: Researchers have proposed clustering approaches that combine traditional clustering methods with deep learning techniques to improve clustering performance. Spectral clustering has become popular due to its performance, with various techniques introduced to enhance its performance, such as constructing a similarity graph. Introducing the weighted k-nearest neighbors technique for constructing the similarity graph has shown promising results on both real and artificial datasets.
PEERJ COMPUTER SCIENCE
(2021)
Article
Geochemistry & Geophysics
J. M. Holmgren, G. Kwiatek, M. J. Werner
Summary: The rupture behavior of microseismicity in fluid-injection settings is influenced by pore pressure and shows a certain degree of predictability. Through the analysis of directivity patterns and focal mechanisms, this study identifies rupture planes and directions of 10 events recorded during the 2018 St1 Deep Heat geothermal project in Finland. Unlike previous studies, the events in this project exhibit varied rupture directions, with some rupturing towards, away from, or parallel to the injection well. These findings contribute to the understanding of rupture growth in pore-pressure dominated settings.
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2023)
Article
Computer Science, Artificial Intelligence
Xiaoning Yuan, Hang Yu, Jun Liang, Bing Xu
Summary: The density peaks clustering algorithm (DPC) has garnered attention for its ability to quickly find cluster centers, but its reliance on human experience for determining cutoff distances and selecting cluster centers can impact results. The KNN-ADPC algorithm addresses these issues by incorporating a clusters merging strategy and adopting K nearest neighbors to divide data points more effectively, resulting in higher accuracy compared to other clustering algorithms.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2021)
Article
Geochemistry & Geophysics
P. Roselli, L. Improta, G. Kwiatek, P. Martinez-Garzon, G. Saccorotti, A. M. Lombardi
Summary: We have conducted a fully unconstrained moment tensor inversion to study induced seismic events in the Val d'Agri basin, Southern Italy, which is a complex and high seismic hazard region. Through the analysis of seismic events recorded during daily injection tests in a disposal well, we found significant non-double-couple components in the computed moment tensors, which correlate with the well-head injection pressure. The rupture mechanism can be interpreted as the opening/closing of a fracture network inside a fault zone of a pre-existing thrust fault.
GEOPHYSICAL JOURNAL INTERNATIONAL
(2023)
Article
Multidisciplinary Sciences
Lan Ngoc Nguyen, Thanh-Hai Le, Linh Quy Nguyen, Van Quan Tran
Summary: This study establishes a machine learning model to predict the CT Index of asphalt concrete and compares the performance of three different machine learning methods. The results show that the Random Forest model is the most effective. The study also identifies the important factors that affect the variation of the CT Index.
Article
Geochemistry & Geophysics
Maria Kozlowska, Mateusz Jamroz, Dorota Olszewska
Summary: Mining-induced seismic events can lead to aftershocks, and studies have shown that events producing large aftershock sequences may share similar focal mechanisms and have larger ground effects, but there may be potential differences in stress drops. This highlights the importance of further analyzing the focal mechanisms of strong events and their relationship to the exploitation technique.
GEOPHYSICAL JOURNAL INTERNATIONAL
(2021)
Article
Biochemical Research Methods
Yijia Li, Jonathan Nguyen, David C. Anastasiu, Edgar A. Arriaga
Summary: We describe a method called Cosine-based Tanimoto similarity-refined graph for community detection using Leiden's algorithm (CosTaL) to analyze large-sized multidimensional single-cell datasets. CosTaL transforms high-dimensional feature cells into a weighted k-nearest-neighbor (kNN) graph, where cells are represented by vertices and edges represent the relatedness between cells. CosTaL achieves equivalent or higher effectiveness scores compared to other graph-based clustering methods on benchmark datasets, demonstrating its high efficiency for small datasets and acceptable scalability for large datasets.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Yuying Wang, Youlong Yang
Summary: IDDC is a novel clustering algorithm based on relative density, which can effectively identify clusters with different densities and performs better in dealing with data sets with uneven density distribution compared to existing algorithms.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Mathematics
Lili Wang, Sunit Mistry, Abdulkadir Abdulahi Hasan, Abdiaziz Omar Hassan, Yousuf Islam, Frimpong Atta Junior Osei
Summary: The study presents an architecture for a recommendation system that transforms user items into narrow categories. It focuses on identifying movies that a user will likely watch based on their favorite items. The system prioritizes the shortest connections between item correlations and utilizes various methods to reduce data sparsity. It also demonstrates the ability to provide moderate recommendations from diverse perspectives.
Review
Green & Sustainable Science & Technology
Emmanuel Gaucher, Martin Schoenball, Oliver Heidbach, Arno Zang, Peter A. Fokker, Jan-Diederik van Wees, Thomas Kohl
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2015)
Article
Engineering, Geological
David P. Sahara, Martin Schoenball, Eleni Gerolymatou, Thomas Kohl
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2017)
Article
Geochemistry & Geophysics
Martin Schoenball, William L. Ellsworth
SEISMOLOGICAL RESEARCH LETTERS
(2017)
Article
Geochemistry & Geophysics
Fred F. Pollitz, Charles Wicks, Martin Schoenball, William Ellsworth, Mark Murray
SEISMOLOGICAL RESEARCH LETTERS
(2017)
Article
Geochemistry & Geophysics
Martin Schoenball, Nicholas C. Davatzes
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2017)
Article
Geochemistry & Geophysics
Martin Schoenball, William L. Ellsworth
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2017)
Article
Engineering, Geological
D. P. Sahara, M. Schoenball, T. Kohl, B. I. R. Mueller
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2014)
Article
Engineering, Geological
M. Schoenball, D. P. Sahara, T. Kohl
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2014)
Article
Engineering, Geological
Sophie Marchand, Olivier Mersch, Michael Selzer, Fabian Nitschke, Martin Schoenball, Jean Schmittbuhl, Britta Nestler, Thomas Kohl
ROCK MECHANICS AND ROCK ENGINEERING
(2020)
Article
Geosciences, Multidisciplinary
Chengping Chai, Monica Maceira, Singanallur V. Venkatakrishnan, Martin Schoenball, Weiqiang Zhu, Gregory C. Beroza, Clifford Thurber, Hector J. Santos-Villalobos
GEOPHYSICAL RESEARCH LETTERS
(2020)
Article
Geosciences, Multidisciplinary
Y. Guglielmi, P. Cook, F. Soom, M. Schoenball, P. Dobson, T. Kneafsey
Summary: This study reveals the importance of considering monitoring zonal deformation in conjunction with pressure and flow to better manage the complex hydromechanical evolution of the growing fracture during water injections.
GEOPHYSICAL RESEARCH LETTERS
(2021)
Article
Geochemistry & Geophysics
Martin Schoenball, Jonathan B. Ajo-Franklin, Doug Blankenship, Chengping Chai, Aditya Chakravarty, Patrick Dobson, Chet Hopp, Timothy Kneafsey, Hunter A. Knox, Monica Maceira, Michelle C. Robertson, Parker Sprinkle, Christopher Strickland, Dennise Templeton, Paul C. Schwering, Craig Ulrich, Todd Wood
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2020)
Article
Geochemistry & Geophysics
Pengcheng Fu, Martin Schoenball, Jonathan B. Ajo-Franklin, Chengping Chai, Monica Maceira, Joseph P. Morris, Hui Wu, Hunter Knox, Paul C. Schwering, Mark D. White, Jeffrey A. Burghardt, Christopher E. Strickland, Timothy C. Johnson, Vince R. Vermeul, Parker Sprinkle, Benjamin Roberts, Craig Ulrich, Yves Guglielmi, Paul J. Cook, Patrick F. Dobson, Todd Wood, Luke P. Frash, Lianjie Huang, Mathew D. Ingraham, Joseph S. Pope, Megan M. Smith, Ghanashyam Neupane, Thomas W. Doe, William M. Roggenthen, Roland Horne, Ankush Singh, Mark D. Zoback, Herb Wang, Kate Condon, Ahmad Ghassemi, Hao Chen, Mark W. McClure, George Vandine, Douglas Blankenship, Timothy J. Kneafsey
Summary: This study analyzed data from hydraulic fracturing tests in an underground testbed to determine the characteristics and development process of fractures. It was found that hydraulic fractures could cross natural fractures and continue to propagate under continued stimulation, while mineral-filled natural fractures did not have a significant impact on hydraulic fracture propagation. The high-quality data sets allowed confident conclusions to be drawn, highlighting the advantages of intermediate-scale experiments in subsurface research.
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2021)
Article
Geochemistry & Geophysics
Keurfon Luu, Martin Schoenball, Curtis M. Oldenburg, Jonny Rutqvist
Summary: This study uses a coupled multiphase fluid flow and geomechanical simulator to model the fluid pressure and stress changes during CO2 injection, and investigates the impact of CO2 injection on faults in crystalline basement rock. The results show that considering poroelastic stress changes is crucial for accurately modeling the seismicity rate.
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2022)