Proceedings Paper
Computer Science, Artificial Intelligence
Zichong Wang, Nripsuta Saxena, Tongjia Yu, Sneha Karki, Tyler Zetty, Israat Haque, Shan Zhou, Dukka Kc, Ian Stockwell, Xuyu Wang, Albert Bifet, Wenbin Zhang
Summary: Bias in machine learning has been a focus, but most research has focused on addressing bias in offline settings. This study focuses on the challenges of achieving fairness in biased data streams in the online setting, and presents a novel fair rebalancing approach and a unified performance-fairness metric for evaluation.
PROCEEDINGS OF THE 6TH ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, FACCT 2023
(2023)
Article
Biology
Cengiz Kaya, Tomas N. Generalovic, Gunilla Stahls, Martin Hauser, Ana C. Samayoa, Carlos G. Nunes-Silva, Heather Roxburgh, Jens Wohlfahrt, Ebenezer A. Ewusie, Marc Kenis, Yupa Hanboonsong, Jesus Orozco, Nancy Carrejo, Satoshi Nakamura, Laura Gasco, Santos Rojo, Chrysantus M. Tanga, Rudolf Meier, Clint Rhode, Christine J. Picard, Chris D. Jiggins, Florian Leiber, Jeffery K. Tomberlin, Martin Hasselmann, Wolf U. Blanckenhorn, Martin Kapun, Christoph Sandrock
Summary: The study provides the first comprehensive genetic characterization of black soldier fly populations, revealing 16 well-distinguished genetic clusters with significant global population structure. It highlights the dynamic population genetic history and ongoing domestication of black soldier flies, with implications for future research on this emerging insect-livestock model.
Article
Computer Science, Artificial Intelligence
Yiliao Song, Jie Lu, Haiyan Lu, Guangquan Zhang
Summary: This article introduces the problems of concept drift and temporal dependency, proposes a novel drift adaptation regression (DAR) framework to address both issues, and demonstrates its performance through experimentation.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Elif Selen Baburoglu, Alptekin Durmusoglu, Turkay Dereli
Summary: This study focuses on addressing concept drift during online learning through a large-scale comparison of drift detectors and classifiers to determine the most efficient matched pairs for improving model accuracy. The results indicate that the most effective pairs primarily include the HDDMA, RDDM, WSTD, and FHDDM detectors, which vary depending on the dataset type and size.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Physics, Particles & Fields
Orhan Donmez
Summary: This paper investigates the numerical simulation of Bondi-Hoyle accretion around a non-rotating black hole in a novel four-dimensional Einstein-Gauss-Bonnet gravity. The study focuses on the effects of the Gauss-Bonnet coupling constant alpha on the accreted matter and shock cones created in the downstream region. Increases in alpha lead to violent oscillations inside the shock cone and an increase in accretion efficiency.
EUROPEAN PHYSICAL JOURNAL C
(2021)
Article
Engineering, Marine
Han Li, Qiaogao Huang, Guang Pan, Xinguo Dong, Fuzheng Li
Summary: This study investigated the effects of oblique flow on an underwater propulsor through numerical calculations, showing significant force fluctuations and complex vortex evolution in drifts. The duct experienced the largest force change, with flow separation observed at high drifts.
Article
Computer Science, Information Systems
Rodrigo Amador Coelho, Luiz Carlos Bambirra Torres, Cristiano Leite de Castro
Summary: Online learning faces challenges in monitoring and detecting changes in data distribution over time, which affect the performance of the learning algorithm. This study proposes a novel detection method that analyzes the occupied space by the data and detects drifts by checking the relevance of data assigned to different classes. The evaluation on benchmark problems demonstrates that our method competes effectively with existing drift detectors on synthetic and real-world datasets.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Vinicius M. A. Souza, Antonio R. S. Parmezan, Farhan A. Chowdhury, Abdullah Mueen
Summary: This paper introduces an unsupervised and model-independent concept drift detector suitable for high-speed and high-dimensional data streams. The proposed method allows faster processing of datasets with a large number of examples and dimensions, achieving better performance in classification problems for different types of drifts. The experimental evaluation demonstrates the method's versatility in multiple domains, including entomology, medicine, and transportation systems.
KNOWLEDGE AND INFORMATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Joanna Komorniczak, Pawel Ksieniewicz
Summary: This publication introduces the Complexity Drift Detector (C2D), a method for detecting concept shifts in data streams based on classification task complexity measures. The method is agnostic to the recognition quality of the base classifier and can be applied to tasks where detection of classification task complexity change is expected. The publication includes experiments analyzing the influence of hyperparameters and a comparative experiment comparing the proposed algorithm with state-of-the-art solutions.
Article
Engineering, Chemical
Mohamad Farhat, Philippe Nerisson, Laurent Cantrel, Maxime Chinaud, Olivier Vauquelin
Summary: Pool scrubbing has the potential to reduce the release of fission products, particularly aerosols, into the environment. However, there is a lack of systematic analysis on this phenomenon under different hydrodynamic conditions. Experimental work was conducted to investigate the effects of flow regimes and injection parameters on decontamination efficiency.
CHEMICAL ENGINEERING RESEARCH & DESIGN
(2023)
Article
Computer Science, Artificial Intelligence
Gavin Alberghini, Sylvio Barbon, Alberto Cano
Summary: This paper introduces a novel ensemble method AESAKNNS for multi-label drifting streams, which adapts to concept drift by training base classifiers on different subspaces and monitoring drift occurrences. Experimental results support the better performance of AESAKNNS compared to other classifiers in diverse multi-label datasets.
Article
Computer Science, Artificial Intelligence
Omer Gozuacik, Fazli Can
Summary: Data stream mining has become a crucial research area in the past decade due to the increasing volume of nonstationary data streams generated from various domains. Concept drift, the phenomenon of evolving data characteristics over time, poses a significant challenge as it renders models obsolete. To address this issue, drift detectors like OCDD can be run alongside classification models to adapt to changes in data distribution, leading to improved predictive performance on both real-world and synthetic datasets.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Engineering, Marine
Jorgen Fredsoe
Summary: This paper presents a simple model of the turbulent wave boundary layer with circular orbital motion formed by the waves, showing that the wall friction is larger in this flow compared to a similar 2D case. It is also demonstrated that for the case of weak current super-posed on the waves, the flow resistance increases by around 30-55% for a circular orbit compared to a straight motion back and forth.
Article
Computer Science, Artificial Intelligence
Alessio Bernardo, Emanuele Della Valle
Summary: This paper investigates binary classification in the presence of concept drift by rebalancing imbalanced data streams. The authors propose a pipeline based on C-SMOTE, which is combined with SML classification algorithms. Through experiments on synthetic and real data streams, the paper provides statistical evidence that using C-SMOTE pipelines can improve the performance of minority classes without significantly affecting the majority class performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Automation & Control Systems
Xiaokang Wang, Huiwen Wang, Dexiang Wu
Summary: This study proposes an online dynamic feature weighting algorithm to monitor feature drift in data streams. The algorithm detects changes in class relevance of features based on the log-likelihood divergence score, and it has been shown to improve the accuracy rates of Nearest Neighbor and Naive Bayes classifiers on both synthetic and real-world datasets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Ecology
Jonathan T. Fingerut, Dina M. Fonseca, James R. Thomson, David D. Hart
FRESHWATER SCIENCE
(2015)
Article
Ecology
Jonathan T. Fingerut, Dina M. Fonseca, James R. Thomson, David D. Hart
FRESHWATER SCIENCE
(2015)
Review
Ecology
Richard K. Zimmer, Jonathan T. Fingerut, Cheryl Ann Zimmer
Article
Ecology
Jonathan T. Fingerut, D. D. Hart, J. R. Thomson
FRESHWATER BIOLOGY
(2011)
Article
Parasitology
Jessica Oates, Jonathan Fingerut
JOURNAL OF PARASITOLOGY
(2011)
Article
Zoology
David M. Kays, Jonathan Fingerut, Scott P. McRobert
RUSSIAN JOURNAL OF HERPETOLOGY
(2019)
Meeting Abstract
Cell Biology
M. A. Levine, M. L. Chien-Hale, M. Chenworth, R. M. Lewinsohn, J. J. Hofmann, J. T. Fingerut, S. P. McRobert, R. E. Hoang
MOLECULAR BIOLOGY OF THE CELL
(2017)
Article
Zoology
Nelson A. Melendez, Brian Zarate, Jonathan Fingerut, Scott P. McRobert
HERPETOLOGICAL CONSERVATION AND BIOLOGY
(2017)
Article
Zoology
Michelle T. Brannin, Mary Kate O'Donnell, Jonathan Fingerut
INTEGRATIVE ZOOLOGY
(2014)
Meeting Abstract
Zoology
J. Fingerut, L. Schamel, A. Faugno, M. Mestrinaro, P. Habdas
INTEGRATIVE AND COMPARATIVE BIOLOGY
(2009)
Article
Ecology
Jonathan T. Fingerut, David D. Hart, James N. McNair
Article
Ecology
JR Thomson, BD Clark, JT Fingerut, DD Hart
Article
Biology
JT Fingerut, CA Zimmer, RK Zimmer
BIOLOGICAL BULLETIN
(2003)
Article
Ecology
JT Fingerut, CA Zimmer, RK Zimmer