Articles

Permanent URI for this collectionhttps://ds.uofallujah.edu.iq/handle/123456789/48

Explore Our Articles

Dive into a collection of insightful articles covering a wide range of topics, from academic research to thought-provoking ideas and innovative solutions. Our curated content is designed to inform, inspire, and engage readers from all walks of life.

Whether you're seeking in-depth analyses, practical tips, or the latest trends, our articles provide valuable perspectives and knowledge to keep you informed and connected.

Start exploring and discover content that broadens your horizons and fuels your curiosity.

News

Latest News

University Hosts Annual Research Conference

March 2025

The University of Fallujah recently hosted its annual research conference, bringing together scholars, students, and industry experts to discuss the latest developments in science and technology.

New Digital Repository Launched

November 15, 2024

We are excited to announce the launch of the Digital Repository, providing open access to the university's academic and research materials for global audiences.

New University of Fallujah System Released

November 15, 2024

The University of Fallujah has launched a new system to enhance administrative processes and improve student services. This system aims to streamline academic records, facilitate communication, and provide a user-friendly platform for students, faculty, and staff.

Stay up-to-date with more news:

Browse

Filters

2020 - 20253

Settings

Start date: 2020

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
    (Corinel University, 2021-01-28) Li Yuan; Yunpeng Chen
    Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and then applies multiple Transformer layers to model their global relation for classification. However, ViT achieves inferior performance to CNNs when trained from scratch on a midsize dataset like ImageNet. We find it is because: 1) the simple tokenization of input images fails to model the important local structure such as edges and lines among neighboring pixels, leading to low training sample efficiency; 2) the redundant attention backbone design of ViT leads to limited feature richness for fixed computation budgets and limited training samples. To overcome such limitations, we propose a new Tokens-To-Token Vision Transformer (T2T-ViT), which incorporates 1) a layer-wise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study. Notably, T2T-ViT reduces the parameter count and MACs of vanilla ViT by half, while achieving more than 3.0\% improvement when trained from scratch on ImageNet. It also outperforms ResNets and achieves comparable performance with MobileNets by directly training on ImageNet. For example, T2T-ViT with comparable size to ResNet50 (21.5M parameters) can achieve 83.3\% top1 accuracy in image resolution 384×384 on ImageNet. (Code: this https URL)
  • No Thumbnail Available
    Item
    Layoutlm: Pre-training of text and layout for document image understanding
    (ACM, 2020-08-20) Lei Cui; second author
    Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while neglecting layout and style information that is vital for document image understanding. In this paper, we propose the LayoutLM to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned documents. Furthermore, we also leverage image features to incorporate words’ visual information into LayoutLM. To the best of our knowledge, this is the first time that text and layout are jointly learned in a single framework for documentlevel pre-training. It achieves new state-of-the-art results in several downstream tasks, including form understanding (from 70.72 to 79.27), receipt understanding (from 94.02 to 95.24) and document image classification (from 93.07 to 94.42). The code and pre-trained LayoutLM models are publicly available at https://aka.ms/layoutlm
  • No Thumbnail Available
    Item
    Porous hydroxyapatite-chitosan scaffolds for tissue engineering: experimental characterization and molecular dynamics simulation
    (Springer, 2025-01-07) Yasouj, University; Yasouj
    In recent years, hydroxyapatite (HA) scaffolds have been widely used in bone tissue engineering as a result of their superior properties. However, the compressive strength and toughness of HA was low. In this study, natural chitosan (CS) binder was extracted from honey bees and HA was extracted from cortical bovine bone. CS and HA were mixed with different ratios; 1/6, 1/8, and 1/10. After sintering and removing CS, porous HA scaffolds were synthesized with different porosities, and their biocompatibility and mechanical properties were evaluated. The samples were characterized using Fourier transform infrared spectroscopy (FTIR), scanning electron microscopy (SEM), Brunauer-Emmett-Teller (BET), X-ray diffraction (XRD), and atomic force microscopy (AFM). SEM results revealed that the pores are worm-shaped in all three samples. Furthermore, the porosities and roughness of CS/HA:1/6 were higher than the other two samples. However, the toughness and compressive strength of this sample were lower than other samples. The bioactivity of the scaffolds was evaluated by immersion in a simulated body fluid (SBF) at 37 °C for 28 days. Biocompatibility of the samples was performed by cell culture with human osteoblast cells for 7 days. The results showed that more porosity leads to higher biocompatibility, although the mechanical properties decreased with increasing porosity. Furthermore, the structural and physical properties of HA-CS simulated by molecular dynamics simulation (MD). The simulated HA-CS revealed that the simulated glass transition temperature (Tg) is reliable and well consistent with the experiment values. Experimental and simulated studies revealed that CS/HA:1/10 is a promising combination for tissue engineering applications.

© 2025 University of Fallujah. All rights reserved.