Article
Computer Science, Artificial Intelligence
Eva Blanco-Mallo, Laura Moran-Fernandez, Beatriz Remeseiro, Veronica Bolon-Canedo
Summary: This paper provides an overview of the use of distance measures in machine learning and data mining tasks. It examines the factors to consider when choosing the most appropriate measure and analyzes seven commonly used measures, exploring their properties and applications. The paper also conducts experiments to study their relationships, performance, and their performance in the presence of noise, as well as the execution time required by each measure.
PATTERN RECOGNITION
(2023)
Article
Microbiology
Yushu Shi, Liangliang Zhang, Christine B. Peterson, Kim-Anh Do, Robert R. Jenq
Summary: This study systematically compared beta diversity and clustering methods commonly used in microbiome analysis. The results showed that no single method consistently outperforms others across all datasets. A combined metric of BC and UU was proposed, which demonstrated high performance across all datasets.
Review
Multidisciplinary Sciences
Mahnoor Chaudhry, Imran Shafi, Mahnoor Mahnoor, Debora Libertad Ramirez Vargas, Ernesto Bautista Thompson, Imran Ashraf
Summary: This paper presents an overview of data mining and clustering, covering algorithmic methodologies, evaluation metrics, and proposed improvements. It emphasizes the importance of clustering as an active research area for identifying patterns, enhancing knowledge acquisition, and improving decision-making. The study aims to contribute to the knowledge base of data mining practitioners and researchers, facilitating informed decision-making and advancing the field.
Article
Ecology
Maria J. Guerrero, Carol L. Bedoya, Jose D. Lopez, Juan M. Daza, Claudia Isaza
Summary: We propose an unsupervised methodology for multi-species call recognition based on a clustering algorithm, which provides similar results to acoustic indices and can analyze the entire soundscape without the need for parameterization.
METHODS IN ECOLOGY AND EVOLUTION
(2023)
Article
Computer Science, Artificial Intelligence
Wenjie Zhu, Bo Peng
Summary: The paper proposes a novel unsupervised vehicle re-identification approach based on Manifold-based Aggregation Clustering (MAC) with an unknown number of clusters. The approach outperforms state-of-the-art unsupervised V-reID methods on VehicleID and Veri-776 benchmark datasets.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Economics
Antonis F. Lentzakis, Ravi Seshadri, Moshe Ben-Akiva
Summary: Congestion pricing is a standard approach to mitigate traffic congestion. The advancement of satellite technology has led to the interest in distance-based congestion pricing schemes, which eliminate the need for fixed infrastructure. Distance-based pricing has the potential to effectively manage traffic congestion.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2023)
Article
Genetics & Heredity
Charles W. Harrison, Qing He, Hsin-Hsiung Huang
Summary: Table Invitation Prior (TIP) is a prior used for Bayesian nonparametric clustering of gene expression data, automatically estimating the number of clusters based on pairwise distances without requiring analyst intervention.
Article
Computer Science, Artificial Intelligence
Huy Quang Ung, Cuong Tuan Nguyen, Khanh Minh Phan, Vu Tran Minh Khuong, Masaki Nakagawa
Summary: This paper proposes a bag-of-features for clustering online handwritten mathematical expressions and introduces a distance-based representation method to reduce dimensionality. Experimental results show that combining low-level and high-level features with DbR can improve performance and reduce marking cost.
PATTERN RECOGNITION LETTERS
(2021)
Article
Computer Science, Information Systems
Yiji Zhao, Youfang Lin, Zhihao Wu, Yang Wang, Haomin Wen
Summary: Dynamic networks are widely used in various scientific fields, but existing network distance measures are designed for static networks and ignore valuable context structure information. To address this issue, a context-aware distance paradigm is proposed, and a context-aware spectral distance is given as an instance. In node-aligned dynamic networks, the context helps the context-aware spectral distance outperform traditional spectral distance.
ACM TRANSACTIONS ON THE WEB
(2022)
Article
Automation & Control Systems
Nestor Rendon, Jhony H. Giraldo, Thierry Bouwmans, Susana Rodriguez-Buritica, Edison Ramirez, Claudia Isaza
Summary: Knowing the number of clusters in unsupervised learning is difficult, and current clustering internal validity indices (CIVIs) don't work well in all scenarios. To address this problem, a new Uncertainty Frechet (UF) CIVI is proposed, which assesses the certainty of a partition using uncertainty fingerprints and the Frechet distance between clusters. UF is integrated into a merging methodology that combines similar clusters, eliminating the need for iterative clustering algorithms. Extensive evaluations on synthetic and real datasets demonstrate the effectiveness of UF, obtaining high scores in different scenarios. The UF index is proven to be a valuable tool for researchers and practitioners working with highly uncertain data.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Ecology
Dena J. Clink, Holger Klinck
Summary: Passive acoustic monitoring (PAM) has the potential to improve the monitoring of vocal animals, but distinguishing between individuals remains a major challenge. This study tested three unsupervised clustering algorithms on Bornean gibbon female calls data and found that affinity propagation consistently outperformed the others. Unsupervised techniques could provide additional information regarding individual identity for PAM applications, with potential for broader use in studying individually distinct vocal animals.
METHODS IN ECOLOGY AND EVOLUTION
(2021)
Article
Computer Science, Information Systems
Mostafa Raeisi, Abu B. Sesay
Summary: In this paper, a new distance metric for the K-means clustering algorithm is proposed, which is useful for cases that require unequal size clusters. Mathematical and exhaustive search methods are used to establish its validity, and it is compared with five other distance metrics. Simulation results demonstrate the effectiveness of the proposed metric compared with others in one-dimensional and two-dimensional randomly generated datasets. Internal evaluation measures including Compactness, Sum of Squared Errors, and Silhouette measures are used to determine the proper number of clusters.
Article
Behavioral Sciences
Ananda Shikhara Bhat, Varun Aniruddha Sane, K. S. Seshadri, Anand Krishnan
Summary: The study found that two anuran species from different lineages modify their vocal sequence structure according to different contexts, suggesting that vocal sequences and context-dependent 'syntax' may be more common in anurans than previously thought.
Article
Behavioral Sciences
Ronald A. Fernandez-Gomez, Jorge E. Morales-Mavil, Laura T. Hernandez-Salazar, J. Roberto Sosa-Lopez
Summary: This study assessed the behavioural responses of olive sparrows to geographical variation in songs, revealing an asymmetrical response pattern and a correlation between response intensity and acoustic similarity. This suggests that males from different populations may use a similar mechanism to recognize signals and that song divergence could act as a premating barrier for some populations.
Article
Psychology, Clinical
Alex S. Cohen, Christopher R. Cox, Tovah Cowan, Michael D. Masucci, Thanh P. Le, Anna R. Docherty, Jeffrey S. Bedwell
Summary: This study utilized machine learning to optimize and validate predictive models of negative schizotypy, finding that accuracy was good and improved by considering sex and speaking task. The identified predictive features were not considered critical to the conceptual definitions of negative schizotypal traits. The implications for validating and implementing digital phenotyping to understand and quantify negative schizotypy were discussed.
CLINICAL PSYCHOLOGICAL SCIENCE
(2022)
