Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds

Atmosphere, Journal Year: 2024, Volume and Issue: 15(12), P. 1407 - 1407

Published: Nov. 22, 2024

Predicting streamflow is essential for managing water resources, especially in basins and watersheds where snowmelt plays a major role river discharge. This study evaluates the advanced deep learning models accurate monthly peak forecasting Gilgit River Basin. The utilized were LSTM, BiLSTM, GRU, CNN, their hybrid combinations (CNN-LSTM, CNN-BiLSTM, CNN-GRU, CNN-BiGRU). Our research measured model’s accuracy through root mean square error (RMSE), absolute (MAE), Nash–Sutcliffe efficiency (NSE), coefficient of determination (R2). findings indicated that models, CNN-BiGRU achieved much better performance than traditional like LSTM GRU. For instance, lowest RMSE (71.6 training 95.7 testing) highest R2 (0.962 0.929 testing). A novel aspect this was integration MODIS-derived snow-covered area (SCA) data, which enhanced model substantially. When SCA data included, CNN-BiLSTM improved from 83.6 to 71.6 during 108.6 testing. In prediction, outperformed other with (108.4), followed by (144.1). study’s results reinforce notion combining CNN’s spatial feature extraction capabilities temporal dependencies captured or GRU significantly enhances accuracy. demonstrated improvements prediction accuracy, extreme events, highlight potential these support more informed decision-making flood risk management allocation.

Language: Английский

---

BDCOA: Wavefront Aberration Compensation Using Improved Swarm Intelligence for FSO Communication

Photonics, Journal Year: 2024, Volume and Issue: 11(11), P. 1045 - 1045

Published: Nov. 7, 2024

Free Space Optical (FSO) communication is extensively utilized in the telecommunication industry for both ground and space wireless links, as well last-mile applications, a result of its lesser Bit Error Rate (BER), free spectrum, easy relocation. However, atmospheric turbulence, also known Wavefront Aberration (WA), considered serious issue because it causes higher BER affects coupling efficiency. In order to address this issue, Sensor-Less Adaptive Optics (SLAO) system developed FSO enhance performance. research, compensation WA SLAO obtained by proposing Brownian motion Directional mutation scheme-based Coati Optimization Algorithm, BDCOA. Here, BDCOA search an optimum control signal value actuators Deformable Mirror (DM). The incorporated directional are used avoid local efficiency while searching signal. Therefore, dynamic optimization DM using helps Thus, WAs compensated optical concentration enhanced FSO. metrics analyzing Root Mean Square (RMS), BER, efficiency, Strehl Ratio (SR). existing methods, such Simulated Annealing (SA) Stochastic Parallel Gradient Descent (SPGD), Advanced Multi-Feedback SPGD (AMFSPGD), Oppositional-Breeding Artificial Fish Swarm (OBAFS), evaluating performance RMS iterations 500 0.12, which less than that SA-SPGD OBAFS.

Language: Английский

---

Elymus Repens Optimization (ERO); A Novel Agricultural-Inspired Algorithm

Journal of Information Systems and Telecommunication (JIST), Journal Year: 2024, Volume and Issue: 12(47), P. 170 - 182

Published: Nov. 11, 2024

Language: Английский

---

The Challenge of Deep Learning for the Prevention and Automatic Diagnosis of Breast Cancer: A Systematic Review

Diagnostics, Journal Year: 2024, Volume and Issue: 14(24), P. 2896 - 2896

Published: Dec. 23, 2024

Objectives: This review aims to evaluate several convolutional neural network (CNN) models applied breast cancer detection, identify and categorize CNN variants in recent studies, analyze their specific strengths, limitations, challenges. Methods: Using PRISMA methodology, this examines studies that focus on deep learning techniques, specifically CNN, for detection. Inclusion criteria encompassed from the past five years, with duplicates those unrelated excluded. A total of 62 articles IEEE, SCOPUS, PubMed databases were analyzed, exploring architectures applicability detecting pathology. Results: The found advanced architecture greater depth exhibit high accuracy sensitivity image processing feature extraction integrate transfer proved particularly effective, allowing use pre-trained less training data required. However, challenges include need large, labeled datasets significant computational resources. Conclusions: CNNs represent a promising tool although future research should aim create are more resource-efficient maintain while reducing requirements, thus improving clinical applicability.

Language: Английский

---

WF-AlexNet:AlexNet with Automatically Optimized Hyperparameters for Weather Forecasting

NATURENGS MTU Journal of Engineering and Natural Sciences Malatya Turgut Ozal University, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 25, 2024

Image classification is a critical area of research with widespread applications across various disciplines, including computer vision, pattern recognition, and artificial intelligence. Despite the advancements in Convolutional Neural Networks (CNNs), which have revolutionized field by providing powerful tools for image classification, many studies encountered challenges achieving optimal performance. These often arise from complex nature CNN architectures multitude hyperparameters that require fine-tuning. Among models, AlexNet has been widely recognized its contributions to deep learning, yet there remains significant potential improvement through optimization hyperparameters. In this study, WF-AlexNET designed enhance performance architecture optimizing first convolutional layer using Equilibrium Optimization (EO) algorithm. The EO algorithm, was employed fine-tune filter size, number, stride, padding parameters, are crucial effective feature extraction. proposed method rigorously tested on multi-class weather dataset evaluate accuracy robustness. Experimental results demonstrate significantly outperforms standard model, 10.5% increase mean validation 6.51% test accuracy. Furthermore, approach compared against other prominent architectures, VGG-16, GoogleNet, ShuffleNet, MobileNet-V2, VGG-19. consistently exhibited superior multiple metrics, F1-score maximum accuracy, highlighting efficacy addressing associated hyperparameter CNNs.

Language: Английский

---