STEM: spatial speech separation using twin-delayed DDPG reinforcement learning and expectation maximization حسب Muhammad Salman Khan (7202543)

Single channel speech denoising by DDPG reinforcement learning agent حسب Sania Gul (18272227)

"…The noisy speech is first converted from the time domain to the time–frequency (TF) domain by taking its short-time Fourier transform (STFT), and then two separate DDPG agents are trained on the magnitude and phase components of the STFT. The reward function used for training these agents is the relative perceptual quality score of speech. …"

Face Recognition in Uncontrolled Indoor Environment حسب Abuqaaud, Kamal Adel

احصل على النص الكامل

Motion Artifacts Correction From EEG and fNIRS Signals Using Novel Multiresolution Analysis حسب Md. Shafayet Hossain (16888833)

Rate Adaptation in Dynamic Adaptive Video Streaming Over HTTP حسب Abdelhafez, Nada

احصل على النص الكامل

Integrated Energy Optimization and Stability Control Using Deep Reinforcement Learning for an All-Wheel-Drive Electric Vehicle حسب Reza Jafari (3494018)

"…A tailored multi-term reward function is structured to penalize excessive yaw rate error, sideslip angle, tire slip deviations beyond peak grip regions, and power losses based on a realistic electric machine efficiency map. …"

StackDPPred: Multiclass prediction of defensin peptides using stacked ensemble learning with optimized features حسب Muhammad Arif (769250)

"…Next, principal component analysis (PCA) is used to select the best subset of attributes. …"

Exploring the Dynamic Interplay of Deleterious Variants on the RAF1–RAP1A Binding in Cancer: Conformational Analysis, Binding Free Energy, and Essential Dynamics حسب Abbas Khan (5141000)

"…Principal component analysis (PCA) and free energy landscape (FEL) evaluation further determined dynamical variations in the wild‐type and mutant complexes. …"

DeepRaman: Implementing surface-enhanced Raman scattering together with cutting-edge machine learning for the differentiation and classification of bacterial endotoxins حسب Samir Brahim, Belhaouari

"…Unlike standard machine learning approaches such as PCA, LDA, SVM, RF, GBM etc, DeepRaman functions independently, requiring no human interaction, and can be used to much smaller datasets than traditional CNNs. …"
احصل على النص الكامل
احصل على النص الكامل
احصل على النص الكامل