Results 21 to 30 of about 50,820 (258)

Time Series Forecasting With Volatility Activation Function

IEEE Access, 2022
Time series forecasting is the method of predicting future values of a model by reviewing its past data. Various models like traditional approaches, statistical methods, moving average, ARIMA, RNN’s, or XGBoost may also be applied.
Furkan Kayim, Atinc Yilmaz
doaj   +1 more source

Robust Multi-Dimensional Time Series Forecasting

Entropy
Large-scale and high-dimensional time series data are widely generated in modern applications such as intelligent transportation and environmental monitoring. However, such data contains much noise, outliers, and missing values due to interference during
Chen Shen, Yong He, Jin Qin
doaj   +1 more source

Personalized Zebrafish Models for Fusion‐Positive Pediatric Sarcomas

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Clinical sequencing efforts have revolutionized our approaches to categorizing pediatric cancers in real time. This has dramatically improved our ability to profile pediatric tumors, identify actionable vulnerabilities, and influence clinical care.
Lisa H. Hall, Emma N. Harrison, Genevieve C. Kendall   +2 more
wiley   +1 more source

HUTFormer: Hierarchical U-Net transformer for long-term traffic forecasting

Communications in Transportation Research
Traffic forecasting, which aims to predict traffic conditions based on historical observations, has been an enduring research topic and is widely recognized as an essential component of intelligent transportation.
Zezhi Shao, Fei Wang, Tao Sun, Chengqing Yu, Yuchen Fang, Guangyin Jin, Zhulin An, Yang Liu, Xiaobo Qu, Yongjun Xu   +9 more
doaj   +1 more source

Time Series Forecastability Measures

CoRR
This paper proposes using two metrics to quantify the forecastability of time series prior to model development: the spectral predictability score and the largest Lyapunov exponent. Unlike traditional model evaluation metrics, these measures assess the inherent forecastability characteristics of the data before any forecast attempts.
Rui Wang, Steven Klee, Alexis Roos
openaire   +2 more sources

The Role of “Adult‐Onset” Cancer Predisposition Genes in Pediatric Cancer: A Comprehensive Review

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Current literature estimates that 10% of pediatric cancers are caused by pathogenic or likely pathogenic (P/LP) germline variants in cancer predisposition genes (CPGs). Variants in CPGs thought to increase cancer risk exclusively during adulthood are referred to as “adult‐onset” CPGs (aoCPGs).
Maria Rozo, Miriam A. Bornhorst, Angela J. Waanders, Sara Zarnegar‐Lumley, Ashwin Lakshman Koppayi, Lucy A. Godley   +5 more
wiley   +1 more source

Performative Time-Series Forecasting

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2
Time-series forecasting is a critical challenge in various domains and has witnessed substantial progress in recent years. Many real-life scenarios, such as public health, economics, and social applications, involve feedback loops where predictions can influence the predicted outcome, subsequently altering the target variable's distribution.
Zhiyuan Zhao, Haoxin Liu, Alexander Rodríguez, B. Aditya Prakash   +3 more
openaire   +2 more sources

Re‐Irradiation in Pediatric Diffuse Midline Glioma: A Multi‐Institutional Retrospective Study

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Background Children with recurrent diffuse midline gliomas (DMGs) have limited therapeutic options at recurrence. Re‐irradiation (RT2) may be used at progression, but with uncertainty about the benefit. Methods We conducted a multi‐institutional retrospective study of children aged < 18 with DMG treated at three centers (Toronto, Canada ...
Ajay Thomas Alex, Sean P. Hassan, Helen Benghiat, Liam Herbert, Jennifer Adamski, Shivani Bailey, Claire Esler, Louise Brookes, Molly Bamber, Grace Koudou, Karen Waite, Julie Bennett, Anirban Das, Derek S. Tsang   +13 more
wiley   +1 more source

Fuzzy Supervised Multi-Period Time Series Forecasting

Cybernetics and Information Technologies, 2019
The goal of this paper is to propose a new method for fuzzy forecasting of time series with supervised learning and k-order fuzzy relationships. In the training phase based on k previous historical periods, a multidimensional matrix of fuzzy dependencies
Ilieva Galina
doaj   +1 more source

Recent Advances in Energy Time Series Forecasting

Energies, 2017
This editorial summarizes the performance of the special issue entitled Energy Time Series Forecasting, which was published in MDPI’s Energies journal. The special issue took place in 2016 and accepted a total of 21 papers from twelve different countries.
Francisco Martínez-Álvarez, Alicia Troncoso, José C. Riquelme   +2 more
doaj   +1 more source