Optical Memory and Neural Networks, Год журнала: 2024, Номер 33(4), С. 429 - 446
Опубликована: Дек. 1, 2024
Язык: Английский
Optical Memory and Neural Networks, Год журнала: 2024, Номер 33(4), С. 429 - 446
Опубликована: Дек. 1, 2024
Язык: Английский
Peer-to-Peer Networking and Applications, Год журнала: 2025, Номер 18(2)
Опубликована: Янв. 28, 2025
Язык: Английский
Процитировано
0Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 147, С. 110343 - 110343
Опубликована: Фев. 26, 2025
Язык: Английский
Процитировано
0Journal of Hydroinformatics, Год журнала: 2024, Номер 26(6), С. 1313 - 1332
Опубликована: Май 23, 2024
ABSTRACT Multi-reservoir systems that have diverse and conflicting objectives are challenging to design due their uncertainties, non-linearities, dimensions conflicts. The operation of multi-reservoir is crucial increasing hydropower production. In this study, we investigated the application effectiveness new optimization algorithm MOAHA in multi-objective cascade reservoirs with objectives, it has been on a case-by-case basis Karun (Karun 3, 1, Masjed Soleyman Gotvand). suggested method (MOAHA) output other algorithms, MOALO, MOGWO NSGA-II, were compared evaluation criteria used select best performance. Additionally, employed powerful TOPSIS determine most suitable algorithm. considered restrictions also observed. results indicate MOAHA's proposed better than algorithms solving optimal reservoir utilization problems water resource systems. reduction evaporation (losses) from tank surface by 9% accompanied 15% increase energy MOAHA, scoring 0.90, deemed whereas MOGWO, score 0.10, regarded as least effective
Язык: Английский
Процитировано
4Applied Mathematical Modelling, Год журнала: 2025, Номер unknown, С. 116008 - 116008
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
0Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127660 - 127660
Опубликована: Апрель 1, 2025
Язык: Английский
Процитировано
0Journal of Machine and Computing, Год журнала: 2024, Номер unknown, С. 785 - 803
Опубликована: Июль 5, 2024
Network security is one of the key components cybersecurity anomaly intrusion detection, which responsible for identifying unusual behaviours or activities within a network that might indicate possible breaches threats. In this suggested detection system (IDS), traffic data continuously monitored via detection. The study makes utilising most recent datasets to spot behaviour in networks connected Internet Things, IoTID20 dataset, facilitate process. preprocessing stage involves painstaking steps smoothing, filtering, and cleaning data. Pine Cone Optimisation algorithm (PCOA), novel optimizer inspired by nature, introduced feature selection PCOA seeks increase effectiveness while drawing inspiration from various ways pine trees reproduce, such as pollination movement cones animals gravity. Moreover, IDS classified using Bidirectional Gated Recurrent Unit–Additive Attention Mechanism Based on Convolutional Neural Networks (CNN-BiGRU-AAM), use deep learning's capabilities efficient classification tasks. addition, work presents Botox Algorithm (BOA) hyperparameter tuning, modelled after way functions human anatomy. BOA uses human-based method adjust hyperparameters model attain best accuracy. results experiments show methodologies are effective improving systems, with maximum accuracy 99.45%.
Язык: Английский
Процитировано
0Ain Shams Engineering Journal, Год журнала: 2024, Номер 15(10), С. 102955 - 102955
Опубликована: Июль 14, 2024
Histopathology image analysis is paramount importance for accurate diagnosing diseases and gaining insight into tissue properties. The significant challenge of staining variability continues. This research work presents a new method that merges deep learning with Reinhardstain normalization, aiming to revolutionize histopathology analysis. multi-data stream attention-based generative adversarial network an innovative architecture designed enhance histopathological by integrating multiple data streams, attention mechanisms, networks improved feature extraction quality. Multi-data capitalizes on mechanisms process multi-modal efficiently, enhancing ensuring robust performance even in the presence variations. approach excels exact disease detection classification, emerging as invaluable tool both clinical diagnoses endeavors across diverse datasets. obtained accuracy proposed SCAN dataset 97.75%, BACH 99.50% Break His 99.66%. significantly advances analysis, offering diagnostic deeper insights networks. enhances extraction, quality, overall effectiveness medical
Язык: Английский
Процитировано
0Optical Memory and Neural Networks, Год журнала: 2024, Номер 33(4), С. 429 - 446
Опубликована: Дек. 1, 2024
Язык: Английский
Процитировано
0