Výsledky vyhledávání - "Ko, Jonghyeon"

Report

Knowledge-Driven Modulation of Neural Networks with Attention Mechanism for Next Activity Prediction

Autor: Donadello, Ivan, Ko, Jonghyeon, Maggi, Fabrizio Maria, Mendling, Jan, Riva, Francesco, Weidlich, Matthias

Predictive Process Monitoring (PPM) aims at leveraging historic process execution data to predict how ongoing executions will continue up to their completion. In recent years, PPM techniques for the prediction of the next activities have matured sign

Externí odkaz: http://arxiv.org/abs/2312.08847

Zobrazit plný text záznamu

Akademický článek

Combining blockchain and IoT for safe and transparent nuclear waste management: A prototype implementation

Autor: Yessenbayev, Olzhas, Nguyen, Dung Chi Duy, Jeong, Taeseok, Kang, Ki Joon, Kim, Hee Reyoung, Ko, Jonghyeon, Park, Jin-Young, Roh, Myung-Sub, Comuzzi, Marco

Publikováno v: In Journal of Industrial Information Integration May 2024 39

Zobrazit plný text záznamu

Report

Online anomaly detection using statistical leverage for streaming business process events

Autor: Ko, Jonghyeon, Comuzzi, Marco

While several techniques for detecting trace-level anomalies in event logs in offline settings have appeared recently in the literature, such techniques are currently lacking for online settings. Event log anomaly detection in online settings can be

Externí odkaz: http://arxiv.org/abs/2103.00831

Zobrazit plný text záznamu

Akademický článek

Optimizing Lane Departure Warning System towards AI-Centered Autonomous Vehicles.

Autor: Jeong, Siwoo¹ (AUTHOR) swj736@kiu.ac.kr, Ko, Jonghyeon² (AUTHOR) whd1gus2@jj.ac.kr, Lee, Sukki³ (AUTHOR) oksk@kict.re.kr, Kang, Jihoon⁴ (AUTHOR) jhkang57@inha.ac.kr, Kim, Yeni⁵ (AUTHOR) kimyeni8757@jj.ac.kr, Park, Soon Yong⁶ (AUTHOR) psy@sit.re.kr, Mun, Sungchul^2,5,7 (AUTHOR) psy@sit.re.kr

Publikováno v: Sensors (14248220). Apr2024, Vol. 24 Issue 8, p2505. 14p.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

An empirical investigation of different classifiers, encoding and ensemble schemes for next event prediction using business process event logs

Autor: Tama, Bayu Adhi, Comuzzi, Marco, Ko, Jonghyeon

There is a growing need for empirical benchmarks that support researchers and practitioners in selecting the best machine learning technique for given prediction tasks. In this paper, we consider the next event prediction task in business process pre

Externí odkaz: http://arxiv.org/abs/2008.10748

Zobrazit plný text záznamu