Results 211 to 220 of about 638,433 (245)

n-Pipeline Log Anomaly Detection Drift Mitigation

2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW)
Hironori Washizaki, Scott Lupton
exaly   +2 more sources

Mitigating Drift in Time Series Data with Noise Augmentation

2019 International Conference on Computational Science and Computational Intelligence (CSCI), 2019
Machine leaning (ML) models must be accurate to produce quality AI solutions. There must be high accuracy in the data and with the model that is built using the data. Online machine learning algorithms fits naturally with use cases that involves time series data.
Tonya Fields, George Hsieh, Jules Chenou
openaire   +1 more source

Digital twins for mitigation of orchard spray drift

Acta Horticulturae
The annual sale of agricultural pesticides in Australia doubled from 2010 to 11 to 2021-22. While an analysis found that 73% of Australian crop production in 2015-16 relied on herbicides, fungicides and insecticides, a large proportion of pesticide applications miss the right targets and become “spray drift”.
Han, Liqi, Cao, J., Ibell, Paula T., Orr, Ryan, Abramson, D., Carr, D., Diczbalis, Yan, Innes, David J.   +7 more
openaire   +3 more sources

Gas sensor drift mitigation using classifier ensembles

Proceedings of the Fifth International Workshop on Knowledge Discovery from Sensor Data, 2011
Sensor drift remains to be one of the challenging problems in chemical sensing. To address this problem we collected an extensive data set for six different volatile organic compounds over a period of three years under tightly-controlled operating conditions using an array of 16 metal-oxide sensors. We then adopted a machine learning approach namely an
Alexander Vergara, Ramón Huerta, Tuba Ayhan, Margaret Ryan, Shankar Vembu, Margie Homer   +5 more
openaire   +1 more source

Detect, Adapt, Overcome: Mitigating Concept Drift in Federated Learning

2025 3rd International Conference on Federated Learning Technologies and Applications (FLTA)
Federated Learning (FL) is a distributed machine learning paradigm where a central server coordinates the training of a global model across multiple decentralized clients. Most FL algorithms assume stationary data-generating processes and neglect concept drift, i.e., the change of data distributions over time.
Rahman, Iftekhar, Manikku Badu, Nisal Hemadasa, Kaaser, Dominik, Murena, Pierre-Alexandre, Schulte, Stefan   +4 more
openaire   +1 more source

Efficiently Mitigating the Impact of Data Drift on Machine Learning Pipelines

Proceedings of the VLDB Endowment
Despite the increasing success of Machine Learning (ML) techniques in real-world applications, their maintenance over time remains challenging. In particular, the prediction accuracy of deployed ML models can suffer due to significant changes between training and serving data over time, known as data drift ...
Sijie Dong, Qitong Wang 0003, Soror Sahri, Themis Palpanas, Divesh Srivastava   +4 more
openaire   +2 more sources

Motion near frozen orbits as a means for mitigating satellite relative drift

Celestial Mechanics and Dynamical Astronomy, 2013
Generally, any initially-close satellites-chief and deputy-moving on orbits with slightly different orbital elements, will depart each other on locally unbounded relative trajectories. Thus, constraints on the initial conditions must be imposed to mitigate the chief-deputy mutual departure.
Gurfil, null, Lara, null, 0000-0001-7097-5602, 0000-0001-6754-916X   +3 more
openaire   +3 more sources

The need for nozzle emission spectra in drift mitigation

2000
Aerial application models, such as AgDRIFT®, rely on an accurate nozzle emission spectrum to quantify the effects of atomization on deposition and drift. In this paper we explore the consequences of approximating the droplet size distribution and the implications of the accuracy of that approximation for downwind drift and the setting of buffer zones.
Teske, Milton E., Hewitt, Andrew J., Esterly, David M., Valcore, David L.   +3 more
openaire   +1 more source

INS Drift Mitigation During DVL Outages

OCEANS 2021: San Diego – Porto, 2021
openaire   +1 more source

APPLICATION OF ALGORITHM LEARNING TO IDENTIFY AND MITIGATE CONCEPT DRIFT

2021
Data streams are becoming more numerous and complex, driven by an increased number of capable sensors. The complex, highly dimensional datasets created by these sensors contain information critical to our understanding of the battlefield situation. A significant change in the adversary's tactics, techniques, and procedures (TTPs) leads to a shift in ...
openaire   +1 more source