Results 21 to 30 of about 2,134,531 (182)

Exploring the Applicability of Transfer Learning and Feature Engineering in Epilepsy Prediction Using Hybrid Transformer Model

IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023
Objective: Epilepsy prediction algorithms offer patients with drug-resistant epilepsy a way to reduce unintended harm from sudden seizures. The purpose of this study is to investigate the applicability of transfer learning (TL) technique and model inputs
Shuaicong Hu, Jian Liu, Rui Yang, Ya'Nan Wang, Aiguo Wang, Kuanzheng Li, Wenxin Liu, Cuiwei Yang   +7 more
doaj   +1 more source

Ontology Driven Feature Engineering for Opinion Mining

IEEE Access, 2019
In the process of knowledge discovery, the reliability of results depends upon the effectiveness of attributes selected for decision. The curse of dimensionality refers to the phenomenon in which the excessive number of dimensions affect the analysis. In
Shafaq Siddiqui, M. Abdul Rehman, Sher Muhammad Doudpota, Ahmad Waqas   +3 more
doaj   +1 more source

Flavor changes of Yunnan large-leaf cultivar white tea during different aging periods

Food Chemistry: X
Yunnan large-leaf white tea gains popularity for its unique flavor attributable to the local tea varieties and environments. But how aging crucially enhances its quality and flavor remains unclear. Here, flavor change and safety quality of “Qinghuan” (QH)
Caibi Zhou, Yongshi Chen, Mengling Chen, Mei Xu, Dongwei Zhao, Long Huang, Wenpin Chen   +6 more
doaj   +1 more source

DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

, 2017
Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods seem to have a strong bias towards low- or high-order interactions, or require expertise ...
Guo, Huifeng, He, Xiuqiang, Li, Zhenguo, Tang, Ruiming, Ye, Yunming   +4 more
core   +1 more source

Machine Learning Techniques for Stellar Light Curve Classification [PDF]

, 2018
We apply machine learning techniques in an attempt to predict and classify stellar properties from noisy and sparse time series data. We preprocessed over 94 GB of Kepler light curves from MAST to classify according to ten distinct physical properties ...
Hinners, Trisha, Tat, Kevin, Thorp, Rachel   +2 more
core   +2 more sources

Penerapan Feature Engineering dan Hyperparameter Tuning untuk Meningkatkan Akurasi Model Random Forest pada Klasifikasi Risiko Kredit

Jurnal Teknologi Informasi dan Ilmu Komputer
  Risiko kredit adalah hal yang penting untuk dianalisis di awal pengajuan kredit guna mengurangi nilai Non-Performing Loan (NPL) atau risiko gagal bayar.
Nadea Putri Nur Fauzi, Siti Khomsah, Aditya Dwi Putra Wicaksono   +2 more
doaj   +3 more sources

Towards correct-by-construction product variants of a software product line: GFML, a formal language for feature modules

, 2015
Software Product Line Engineering (SPLE) is a software engineering paradigm that focuses on reuse and variability. Although feature-oriented programming (FOP) can implement software product line efficiently, we still need a method to generate and prove ...
Dubois, Catherine, Levy, Nicole, Pham, Thi-Kim-Zung   +2 more
core   +2 more sources

Deep & Cross Network for Ad Click Predictions

, 2017
Feature engineering has been the key to the success of many prediction models. However, the process is non-trivial and often requires manual feature engineering or exhaustive searching.
Fu, Bin, Fu, Gang, Wang, Mingliang, Wang, Ruoxi   +3 more
core   +1 more source

Feature Engineering for Predictive Modeling using Reinforcement Learning

, 2017
Feature engineering is a crucial step in the process of predictive modeling. It involves the transformation of given feature space, typically using mathematical functions, with the objective of reducing the modeling error for a given target.
Khurana, Udayan, Samulowitz, Horst, Turaga, Deepak   +2 more
core   +1 more source

Feature engineering through two-level genetic algorithm

Machine Learning with Applications
Deep learning models are widely used for their high predictive performance, but often lack interpretability. Traditional machine learning methods, such as logistic regression and ensemble models, offer greater interpretability but typically have lower ...
Aditi Gulati, Armin Felahatpisheh, Camilo E. Valderrama   +2 more
doaj   +1 more source