A self-imitation learning approach for scheduling evaporation and encapsulation stages of OLED display manufacturing systems DOI
Donghun Lee, In-Beom Park,

Kwanho Kim

и другие.

Robotics and Computer-Integrated Manufacturing, Год журнала: 2024, Номер 93, С. 102917 - 102917

Опубликована: Ноя. 30, 2024

Язык: Английский

Dt-Gwo: A Hybrid Decision Tree and Gwo-Based Algorithm for Multi-Objective Task Scheduling Optimization in Cloud Computing DOI

Mohaymen Selselejoo,

HamidReza Ahmadifar

Опубликована: Янв. 1, 2025

Cloud computing faces significant challenges in task management, particularly balancing server loads to avoid overloads or underloads while satisfying diverse quality requirements. The need manage multiple criteria adds further complexity this problem. Conversely, the heterogeneity of cloud resources often complicates management. To address this, paper proposes a hybrid model that integrates decision tree approach with Grey Wolf Optimization (GWO) algorithm for managing independent tasks. aims optimize makespan, reduce total cost, enhance resource utilization, and maintain load balance. In proposed model, tasks are first classified using tree, after which GWO processes selected efficient allocation. Simulations conducted CloudSim tool, assuming heterogeneous environment experiments consider various input scenarios, ranging from 200 3200 Compared standalone algorithm, DT-GWO achieves improvements at least 18.5% 3.4% average 12.7% all maintaining

Язык: Английский

Процитировано

0

BERT-DomainAFP: Antifreeze Protein Recognition and Classification Model Based on BERT and Structural Domain Annotation DOI Creative Commons

Shengzhen Chen,

Ping Zheng,

Lele Zheng

и другие.

iScience, Год журнала: 2025, Номер 28(4), С. 112077 - 112077

Опубликована: Март 6, 2025

Antifreeze proteins (AFPs) are crucial for organisms to adapt low temperatures, with applications in medicine, food storage, aquaculture, and agriculture. Accurate AFP identification is challenging due structural sequence diversity. To improve prediction classification, we propose BERT-DomainAFP, a deep learning model trained on the AntiFreezeDomains dataset created novel annotation strategy. The uses pre-trained ProteinBERT incorporates oversampling undersampling techniques handle unbalanced data, ensuring high predictive ability. BERT-DomainAFP achieves 98.48% accuracy, highest among existing models, can classify different types based domain features. This outperforms current tools, offering promising solution recognition classification research applications.

Язык: Английский

Процитировано

0

DT-GWO: A Hybrid Decision Tree and GWO-Based Algorithm for Multi-Objective Task Scheduling Optimization in Cloud Computing DOI

Mohaymen Selselejoo,

HamidReza Ahmadifar

Sustainable Computing Informatics and Systems, Год журнала: 2025, Номер 47, С. 101138 - 101138

Опубликована: Май 20, 2025

Язык: Английский

Процитировано

0

BERT-DomainAFP: Antifreeze Protein Recognition and Classification Model Based on BERT and Structural Domain Annotation DOI

Shengzhen Chen,

Ping Zheng,

Lele Zheng

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0

A self-imitation learning approach for scheduling evaporation and encapsulation stages of OLED display manufacturing systems DOI
Donghun Lee, In-Beom Park,

Kwanho Kim

и другие.

Robotics and Computer-Integrated Manufacturing, Год журнала: 2024, Номер 93, С. 102917 - 102917

Опубликована: Ноя. 30, 2024

Язык: Английский

Процитировано

0