Results 21 to 30 of about 16,703 (255)

Human action recognition method based on multi-view semi-supervised ensemble learning

网络与信息安全学报, 2021
Mass labeled data are hard to get in mobile devices. Inadequate training leads to bad performance of classifiers in human action recognition. To tackle this problem, a multi-view semi-supervised ensemble learning method was proposed.
CHEN Shengnan, FAN Xinmin
doaj   +1 more source

Модель градієнтного бустінгу LightGBM

, 2023
У цій роботі ми досліджували метод легкого градієнтного бустінгу (LightGBM), що є швидким та ефективним ансамблевим методом ML, який використовує дерева рішень у ролі слабких учнів та має у своїй основі алгоритм градієнтного спуску.
Вербівська, Юлія
core  

基于机器学习技术的返乡发展人群预测模型研究与应用

Dianxin kexue
随着经济的发展和一线城市生活压力的增大，越来越多的人迁移城市以及返回家乡发展，为了高效服务用户和提升用户产品使用体验，提出基于LightGBM、CatBoost等算法来预测返乡发展人群，并进行了异构模型融合。通过模型对比，所提融合模型有更好的效果，可以为服务和产品提供依据，减少流失优化感知，提高市场保有率。
杜昭1, 谢国城2, 陈静旋2, 张伟斌1
doaj   +1 more source

The Application of LightGBM in Microsoft Malware Detection

Journal of Physics: Conference Series, 2020
Abstract The development of new technologies has caused computers one of the most popular electronic products. However, there is always a number of people who intend to take advantages of others through attacking others’ computers. To avoid property damage as much as possible, a precise and efficient detection is essential.
Qiangjian Pan, Weiliang Tang, Siyue Yao
openaire   +1 more source

Optimized LightGBM Power Fingerprint Identification Based on Entropy Features

, 2022
The huge amount of power fingerprint data often has the problem of unbalanced categories and is difficult to upload by the limited data transmission rate for IoT communications. An optimized LightGBM power fingerprint extraction and identification method
Shi, Jiancheng, Lin, Lin, Lin Lin, Na Zhang, Chen, Cheng, Jiancheng Shi, Zhang, Na, Jie Zhang, Cheng Chen, Zhang, Jie   +9 more
core   +1 more source

A comparative classification framework using PCA and modified PCA with ensemble and kernel-based learning models for mangrove feature analysis [PDF]

BIO Web of Conferences
Hyperspectral image (HSI) classification remains challenging due to high spectral dimensionality, redundancy among bands, and limited labeled samples, particularly in high–spatial-resolution agricultural and coastal environments.
Saha Chowdhury Arpita, De Mukhopadhyay Keya, Abhishek Kumar   +2 more
doaj   +1 more source

Machine learning-driven sedation-analgesia optimization in mechanically ventilated sepsis patients: a retrospective MIMIC-IV analysis

Frontiers in Pharmacology
BackgroundIn the intensive care unit (ICU), septic patients frequently require endotracheal intubation followed by invasive mechanical ventilation. Nonetheless, the optimal sedation-analgesia regimen for these critically ill patients remains undetermined.
Qinxue Hu, Tao Xu, Xiaolan Gao, Xianying Lei, Lirong Hu   +4 more
doaj   +1 more source

A Two‐Stage Questionnaire and Actigraphy Screening for iRBD in a Multicenter Retrospective Cohort

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Isolated rapid‐eye‐movement sleep behavior disorder is a prodromal marker of synucleinopathies. However, most cases remain undiagnosed due to the insufficient predictive value of questionnaires and limited access to confirmatory video‐polysomnography. We assessed a two‐stage screening strategy combining a brief questionnaire on rapid‐
Caleb A. Massimi, Giorgio Ricciardiello Mejia, Andre Metzger, Kang Hyun Ryu, Salonee Marwaha, Eva Grzegorczyk, Li Zhou, Eliana Jacobs, Boris Gilyadov, Claudia Kunney, Liqhwa Ncube, Ankit Parekh, Emmanuel Mignot, Fanny M. Elahi, Joseph Winer, Kathleen Poston, Andreas Brink‐Kjaer, Emmanuel H. During   +17 more
wiley   +1 more source

Optimized LightGBM Model for Predicting Total Cup Points of Arabica Coffee using Sensory Cupping Data

Jurnal Teknologi dan Manajemen Informatika
Evaluating coffee quality through sensory cupping is essential but inherently subjective, as scoring depends on the consistency and expertise of professional panelists.
Arya Rezagama Sudrajat, Ricardus Anggi Pramunendar, Mohammad Syaifur Rohman   +2 more
doaj   +1 more source

High‐Performance Transparent, Deformable, and Recoverable Biomimetic Stevia–PVA Hydrogel Triboelectric Nanogenerator with Machine Learning‐Assisted Motion Recognition

Advanced Materials, EarlyView.
A transparent, deformable stevia–PVA hydrogel triboelectric nanogenerator delivers significantly enhanced mechanical strength and electrical output through biomimetic hydrogen‐bonded networks. Coupled with machine learning–assisted signal recognition, the self‐powered hydrogel enables accurate human‐motion sensing for intelligent wearable and IoT ...
Thien Trung Luu, Bui Minh Quang, Toan Minh Pham, Jinsoo Kim, Kyungwho Choi, Dukhyun Choi   +5 more
wiley   +1 more source