Article
Environmental Sciences
Sarah A. Wegmueller, Philip A. Townsend
Summary: Severe forest disturbance events are on the rise due to climate change, leading forest managers to heavily rely on airborne surveys for mapping damage. Existing satellite-based systems may not meet the needs of managers, hence the continued use of airborne imaging. The Astrape system leverages high spatial and temporal resolution satellite imagery to reduce the need for ground data in mapping forest damage.
Article
Computer Science, Artificial Intelligence
Debasish Mishra, Utsav Awasthi, Krishna R. Pattipati, George M. Bollas
Summary: This article presents an unsupervised approach for estimating tool condition in precision machining processes using real-time sensory information. The proposed method utilizes distance metrics as health indicators of tool wear, achieving a high accuracy in classifying tool wear.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Geochemistry & Geophysics
Rene Steinmann, Leonard Seydoux, Eric Beauce, Michel Campillo
Summary: Researchers proposed a strategy to identify signals in continuous seismograms using deep scattering network and independent component analysis, successfully discovering new signal types in Turkish earthquake data. The method utilizes hierarchical clustering to extract waveform features and analyze seismic data effectively.
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2022)
Article
Engineering, Chemical
Javier Merrill-Cifuentes, Matthew J. Cracknell, Angela Escolme
Summary: The value of rock characterisation lies in its ability to describe the composition and texture, which can now be assessed through technological developments and modern image analysis techniques. This study proposes a workflow for the automated classification of rock textures using a novel textural feature extraction method, allowing for meaningful identification of different textural families in large drill-core hyperspectral imagery datasets.
MINERALS ENGINEERING
(2022)
Article
Forestry
Huiyi Su, Xiu Ma, Mingshi Li
Summary: This study developed a framework to extract fire footprints from MODIS-based burn products using the Jenks natural breaks classification method and the DBSCAN algorithm. The results showed that the model achieved an overall accuracy of 80% in spatial and temporal domains, making it an efficient tool for large-scale and long-term wildfire monitoring.
INTERNATIONAL JOURNAL OF WILDLAND FIRE
(2023)
Article
Engineering, Electrical & Electronic
Claudia Olivares-Cabello, David Chaparro, Merce Vall-llossera, Adriano Camps, Carlos Lopez-Martinez
Summary: This study analyzes the sensitivity of VOD at three frequencies (L-, C-, and X-bands) to different vegetation covers on a global scale. Results show that L-VOD is suitable for monitoring dense canopies, while X-, C-, and LCX-VOD are more sensitive to vegetation cover in savannahs, shrublands, and grasslands. The study also provides insights on the vegetation-frequency relationship and suggests suitable frequencies for vegetation monitoring.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Pharmacology & Pharmacy
Jing Cao, Jiao Gong, Xinhua Li, Zhaoxia Hu, Yingjun Xu, Hong Shi, Danyang Li, Guangjian Liu, Yusheng Jie, Bo Hu, Yutian Chong
Summary: Gastric cancer can be classified into three subtypes based on gene expression patterns and cell composition. Subtypes associated with high mortality exhibit specific gene expression and cell infiltration characteristics, while those with a better prognosis show different gene expression and cell infiltration features.
FRONTIERS IN PHARMACOLOGY
(2021)
Article
Automation & Control Systems
Jiao Zhu, Sugen Chen, Yufei Liu, Cong Hu
Summary: This study proposes a novel energy-based structural least squares twin support vector clustering algorithm (ESLSTWSVC), which improves clustering performance and efficiency by introducing within-class covariance matrix and solving system of linear equations.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2024)
Article
Transportation Science & Technology
Huanhuan Li, Jasmine Siu Lee Lam, Zaili Yang, Jingxian Liu, Ryan Wen Liu, Maohan Liang, Yan Li
Summary: This study develops an unsupervised methodology for feature extraction and knowledge discovery based on AIS data to support trajectory data mining and improve maritime traffic safety. The methodology includes trajectory compression, similarity measure, and trajectory clustering, effectively extracting vessel traffic behavior characteristics and navigation knowledge.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Environmental Sciences
Floris Hermanns, Felix Pohl, Corinna Rebmann, Gundula Schulz, Ulrike Werban, Angela Lausch
Summary: The study utilized unsupervised learning to analyze hyperspectral imagery for ecosystem monitoring and understanding grassland drought responses. The application of SiVM for grassland stress detection at the ecosystem canopy scale was successful, with carotenoid-related variables playing a significant role in the interannual stress model. The study highlights the potential of combining imaging spectrometry and unsupervised learning for vegetation stress monitoring and remote estimation of photosynthetic efficiency.
Article
Computer Science, Information Systems
M. Tanveer, Tarun Gupta, Miten Shah
Summary: This article introduces a new clustering algorithm pinTSVC to address the issues of noise sensitivity and re-sampling instability, by incorporating the pinball loss function for enhanced stability and performance in noise-corrupted datasets.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2021)
Article
Geosciences, Multidisciplinary
Prahlada V. Mittal, Rishabh Bafna, Ankush Mittal
Summary: Population-based damage assessment is crucial for timely aid in natural hazards. This study proposes an unsupervised density-based clustering algorithm to automatically form spatial groups of affected regions and assign labels based on the degree of damage. The algorithm selects the optimal number of clusters based on the spatial distribution of data and works well with any shape of the hazard-affected region. The framework accurately identifies regions and performs well on evaluation metrics.
Article
Computer Science, Theory & Methods
Lingxi Liu, Giovanni Delnevo, Silvia Mirri
Summary: In this paper, the hierarchical clustering algorithm (HCA) is proposed as an alternative machine learning approach to process the large hyperspectral imaging (HSI) datasets in the field of cultural heritage (CH). HCA, by forming an agglomerative hierarchical tree, maximizes the information to be extracted from the high-dimensional spectral dataset. The application of HCA in CH successfully segmented the degradation areas with distinctive characteristics.
JOURNAL OF BIG DATA
(2023)
Article
Computer Science, Artificial Intelligence
Yan Bai, Ce Wang, Yihang Lou, Jun Liu, Ling-Yu Duan
Summary: The paper introduces a novel learnable HCC clustering scheme by GCNs to generate more reliable pseudo labels, which learns the complicated cluster structure by hierarchically estimating connectivity and uses a new relation feature for handling intra-person variations.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Construction & Building Technology
Xing Li, Xudong Chen, Andrey P. Jivkov, Jiang Hu
Summary: In this study, the fracture process of hydraulic concrete was analyzed using acoustic emission data, revealing three distinct stages of fracture and characterizing different failure modes through specific parameters. Hierarchical clustering analysis and a support vector machine model successfully quantified the degree of damage in the concrete. Therefore, combining acoustic emission and machine learning offers an effective method for damage assessment.
STRUCTURAL CONTROL & HEALTH MONITORING
(2022)
Article
Environmental Sciences
Julius Y. Anchang, Lara Prihodko, Armel T. Kaptue, Christopher W. Ross, Wenjie Ji, Sanath S. Kumar, Brianna Lind, Mamadou A. Sarr, Abdoul A. Diouf, Niall P. Hanan
Article
Ecology
Wenjie Ji, Niall P. Hanan, Dawn M. Browning, H. Curtis Monger, Debra P. C. Peters, Brandon T. Bestelmeyer, Steve R. Archer, C. Wade Ross, Brianna M. Lind, Julius Anchang, Sanath S. Kumar, Lara Prihodko
Correction
Multidisciplinary Sciences
C. Wade Ross, Lara Prihodko, Julius Anchang, Sanath Kumar, Wenjie Ji, Niall P. Hanan
Article
Environmental Sciences
Sanath Sathyachandran Kumar, Niall P. Hanan, Lara Prihodko, Julius Anchang, C. Wade Ross, Wenjie Ji, Brianna M. Lind
Article
Environmental Sciences
Kaboro Samasse, Niall P. Hanan, Julius Y. Anchang, Yacouba Diallo
Article
Multidisciplinary Sciences
S. S. Kumar, L. Prihodko, B. M. Lind, J. Anchang, W. Ji, C. W. Ross, M. N. Kahiu, N. M. Velpuri, N. P. Hanan
SCIENTIFIC REPORTS
(2020)
Editorial Material
Multidisciplinary Sciences
Niall P. Hanan, Julius Y. Anchang
Article
Soil Science
Colby Brungard, Travis Nauman, Mike Duniway, Kari Veblen, Kyle Nehring, David White, Shawn Salley, Julius Anchang
Summary: Regional-specific models and ensemble models of regional models are approximately as accurate as global models in predicting soil depth classes, but result in lower uncertainty.
Article
Environmental Sciences
Julius Y. Anchang, Lara Prihodko, Wenjie Ji, Sanath S. Kumar, C. Wade Ross, Qiuyan Yu, Brianna Lind, Mamadou A. Sarr, Abdoul A. Diouf, Niall P. Hanan
FRONTIERS IN ENVIRONMENTAL SCIENCE
(2020)
Article
Environmental Studies
Michael Acheampong, Qiuyan Yu, Lucy Deba Enomah, Julius Anchang, Michael Eduful
Article
Area Studies
Ambe J. Njoh, Erick O. Ananga, Julius Y. Anchang, Elizabeth M. N. Ayuk-Etang, Fenda A. Akiwumi
JOURNAL OF ASIAN AND AFRICAN STUDIES
(2017)
Article
Development Studies
Erick O. Ananga, Ambe J. Njoh, Julius Y. Anchang, Fenda A. Akiwumi
COMMUNITY DEVELOPMENT JOURNAL
(2017)