Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
2 results
Search Results
Item Restricted Sketch compression(University of Surre, 2023-09) Alsadoun, Hadeel Mohammed; song, Yi-Zhe; Ashcroft, AlexanderIn the rapidly evolving field of digital art and animation, traditional sketching techniques often rely on pixel-based methods, leading to less meaningful representations. This dissertation aims to transform this paradigm by rigorously investigating the efficacy of autoencoders for vector sketch compression. We conducted experiments using two distinct neural network architectures: Long Short-Term Memory (LSTM) and Transformer-based autoencoders. The Transformer model, which has significantly impacted the field of sequence-to-sequence tasks, especially in natural language processing, serves as a focal point of our study. Our experiment aims to answer a compelling question: Can these impressive results be replicated in the domain of vector sketch compression? The answer is a resounding yes. The Transformer model not only excelled in reconstructing sketches but also simplified the strokes and enhanced the overall quality of the sketch, achieving an impressive 85.03% classification accuracy. The LSTM model, known for its ability to capture temporal dependencies, served as our baseline, achieving a classification accuracy of 56.139% on a pre-trained classifier. Our findings strongly advocate for the adoption of Transformer-based models in vector sketch compression, offering a more compact and semantically rich representation. The LSTM model’s respectable performance also suggests its potential utility in less complex scenarios. Overall, this study opens new avenues for research in digital art, particularly in optimizing Transformer architectures for sketch compression.12 0Item Restricted Deep Learning Techniques for Next Generation Wireless Networks(2023) Alawad, Mohamad Abdulaziz; Hamdi, KhairiMachine learning (ML) techniques have shown promising performance in solving different communication system issues. Recently, several deep learning-based end-to-end techniques have been implemented to optimize the transmitter, the channel, and the receiver blocks in one single process, thereby replacing the conventional communications system. In this thesis, we start exploring the research for the end-to-end wireless model where we used the autoencoder (AE) as a based communication system. We studied the performance of the AE with additive white Gaussian noise (AWGN) channel and compared it with the equivalent conventional communication system. Then for deep learning (DL), we introduce a DL-based detector, termed DL Index Modulation (DLIM), for IM-MIMO-OFDM using a deep neural network (DNN) in terms of error performance. Our initial results using the proposed DLIM can detect the transmitted symbols with performance comparable to near-optimal bit error rate (BER) with shorter runtime than the existing hand-crafted detectors. Next, for the Intelligent Reflecting Surfaces (IRS), we proposed an IRS-assisted end-to-end communication system that operates over AWGN channels, where the modulation and demodulation are performed by a DNN based on an AE architecture. Simulation results show the BER performance of our AE-based scheme achieves better performance gains than the existing classical IRS baseline and the AE hand-crafted baselines. Moreover, a new probabilistic model, based on the variational autoencoders (VAE), is proposed for short-packet wireless communication systems. Using this new approach, the information messages are represented by the so-called packet hot vectors (PHV), which are inferred by the VAE latent random variables (LRVs). Numerical results show that the proposed VAE, with a DL classifier, improved symbol error rate (SER) performance in comparison to the baseline schemes.10 0