Waterloo Library Journal Publishing Service (University of Waterloo, Canada)
Not a member yet
2023 research outputs found
Sort by
Potential of cold spray technology for 3D printing of dense TiO2 green parts
No full textManufacturing ceramic parts, generally involves forming a green body and heating it to fuse the particles together, thereby densifying the part. Methods such as powder compaction in a die cavity using mechanical pressing, slip casting, and injection molding are widely employed in the industry for green body formation. However, these methods are costly, complex, and time-consuming. Recently, various 3D printing technologies have been adapted for manufacturing ceramic parts. These include slurry-based methods such as stereolithography and inkjet printing, powder-based systems like selective laser sintering/melting and binder jetting, and bulk solid-based methods such as laminated object manufacturing and fused deposition modeling. Regardless of the forming technology, the green density of the printed preform is a vital factor in achieving fully dense parts with high dimensional accuracy after firing. Among all these methods, injection molding achieves the highest green density, ranging from 75% to 85%, while 3D printing methods typically achieve green densities between 40% and 60%. Therefore, post-processing techniques such as cold isostatic pressing are often employed to enhance the density of parts up to 85%. In this research, we evaluate cold spray technology potential for 3D printing green TiO2 parts with exceptionally high green density. By leveraging the supersonic impact of TiO2 agglomerates, we demonstrate the ability to fabricate dense 3D structures with green densities ranging from 70% to 80%. Subsequent sintering further increases the density to well over 96.2%. This approach eliminates the need for powder modification, allowing as-received powders to be directly fed into the system for free-forming 3D printing, offering significant technical and cost advantages over conventional 3D printing techniques. These attributes can position cold spray as a promising manufacturing method in digital printing technologies
The Athenian Way: For Our Allies, Subjects and Neighbours: By: Pericles
No full textIn my years of service to the Athenian demos I have been asked by many men both worldly and intelligent how the Athenian system works, and why? Ironically, I must begin my explanation by discrediting myself in many people\u27s eyes. I am asked habitually “as Athens’ ruler why ….” and I am no such thing. Athens has no ruler, I am merely a citizen who has had the honour to serve as one of ten strategoi several times throughout my career. I know no offence is meant by these allegations, but still I must fervently diminish them. My fellow Athenians do not take kindly to such ambitions and I have no aspirations to be ostracized. Nonetheless, I will attempt to explain the ways of my people and justify my fondness for them
Enhancing Parkinson’s Disease Diagnosis through Synthetic Image Augmentation and Deep Learning Model Evaluation
No full textParkinson’s disease (PD) is a progressive neurodegenerative disorder that can be clinically diagnosed through various neuroimaging techniques. Single-photon emission computed tomography (SPECT) has proven to be an effective tool for the early detection of PD. Automatic detection of PD from SPECT images, using machine learning or deep learning models is crucial for providing faster, more accurate diagnoses, and facilitating early intervention. While large datasets of SPECT scans for PD are available, they are often highly imbalanced, which can significantly hinder the performance of deep learning models. In this paper, we explore how synthetic image generation can address the dataset imbalance problem and improve the accuracy of deep learning models. We evaluated the performance of several state-of-the-art pre-trained deep learning models, including Vision Transformer (ViT), VGG-16, EfficientNet, and a newly proposed hybrid model, Inception-VGG16. Experimental results demonstrate that augmenting the dataset with synthetic images significantly improves the performance of all models, with ViT achieving the highest test accuracy of 98\%. The proposed Inception-VGG16 model performed second best, achieving a test accuracy of 95\%. These results suggest that synthetic augmentation can enhance the performance of pre-trained models in detecting Parkinson\u27s disease, presenting a promising approach for enhancing automatic diagnostic tools. The implementation of this work is available at https://github.com/mosarrat28/Parkinsons_disease_detection_using_SPECT_image
Aligning Feature Distributions in VICReg Using Maximum Mean Discrepancy for Enhanced Manifold Awareness in Self-Supervised Representation Learning
No full textSelf-supervised learning (SSL) methods like VICReg
have shown considerable success in generating ro-
bust data representation by promoting invariance
across augmented views. However, VICReg’s focus
on pairwise alignment between augmentations lim-
its its capacity to ensure broader consistency across
entire batches of diverse transformations. In this
paper, we enhance VICReg by integrating a Maxi-
mum Mean Discrepancy (MMD) term, which aligns
feature distributions across the entire batch in a
Reproducing Kernel Hilbert Space (RKHS), thereby
promoting batch-level invariance. By enforcing a
unified feature distribution across a batch, MMD
enables the model to capture higher-order depen-
dencies and reduce variability among augmented
views. We have evaluated our approach on MNIST,
CIFAR-10, and STL-10, where the results demon-
strate improved representation quality, as evidenced
by clustering accuracy and linear classification per-
formance. The results highlight the effectiveness of
incorporating MMD term into VICReg in enhancing
the representation quality
Leveraging Player Tracking for Event Detection in Ice Hockey
No full textFaceoffs are pivotal events in hockey, marking
strategic resets in gameplay that influence team
positioning and puck possession. Detecting these
events in video data can provide valuable insights
for coaches and analysts, enabling the study of
player formations and strategies around these critical
moments. This work presents a novel framework
for detecting ice hockey faceoffs. Our approach
processes overhead video sequences using
a multi-stage pipeline, incorporating object detection
and segmentation to track player trajectories
across frames. We employ state of the art detectors
and tracking tools, enabling tracking and trajectory
analysis for each player. Additionally, preprocessed
sequences are used to better ensure accurate
player tracking. We demonstrate the framework’s
effectiveness in automatically identifying faceoffs,
with promising results that suggest its potential for
broader applications in sports analytics. By enhancing
the visibility of faceoffs and player interactions
in hockey, this work contributes toward automated
sports analytics, providing a robust tool for studying
patterns and tactics in high-paced, dynamic sports
environments
Passive Video liveness detection using Vision Transformer
No full textThis paper presents a passive video liveness detection system designed to enhance security in online authentication and authorization services. As traditional authentication methods are increasingly susceptible to spoofing attacks using static images, videos, or deepfake technology, there is a growing need for advanced biometric solutions. The proposed system applies computer vision and machine learning techniques to accurately distinguish between live users and fraudulent attempts in real-time, without requiring active user interaction
Estimating the fundamental value of sports clubs and stadia: Application to Panathinaikos FC and Leoforos
No full textWe propose a fundamental valuation model for sports clubs and stadia using discounted (adjusted) revenues. We argue that a sports club is a “quasi firm” that aims to balance budgets, achieve an efficient allocation of financial resources, and maximize revenues. Under this objective the sports club’s welfare and value are maximized. Then we offer a method for estimating the value of a sports club’s stadium. The proposed valuation model can be useful during acquisition negotiations or for assessing managerial performance. Combining the proposed model with stochastic Monte Carlo simulations, we estimate the brand-name value and the club’s total value of the football team of Panathinaikos, as well as the value of its iconic home ground, Apostolos Nikolaidis Stadium (known as Leoforos) located in the heart of Athens at Alexandra’s Avenu
6. Digital Receptacle
No full textThis is a prose poem about some of my lived experiences of feminism
Crossing the Border: Indigenous Solidarity and Sovereignty within International Repatriations
No full textThe relationships between museums and the Indigenous Peoples of Turtle Island have changed monumentally over the last 20 years. Repatriation has gone from a contested topic to a reality of museum–Indigenous relationships. Despite the legitimization of repatriation, there still exist numerous obstacles for Indigenous people seeking the return of their sacred and cultural objects. One unique challenge is that of international repatriation. The international borders that we take for granted today arose out of settler politics and have no basis within Indigenous history. The United States (US)–Canada border inadvertently separated and split numerous Indigenous nations, significantly contributing to cultural fracturing and weakening. Museum collections of Indigenous material culture are nationally isolated, despite containing large collections from Indigenous groups outside their borders. This necessitates an original approach to repatriation that is not covered in national policy or legislation. International repatriation requires a high level of cooperation between Indigenous groups, giving nations split by the border a chance to reconnect and form a united front in order to achieve their objectives. Although the imposition of nation–state borders created many barriers for Indigenous Peoples, cross–border repatriation offers unique opportunities to assert Indigenous solidarity, sovereignty, and healing