3d Dental Biometrics: Automatic Pose-Invariant Dental Arch Extraction And Matching,
2021
Singapore Management University
3d Dental Biometrics: Automatic Pose-Invariant Dental Arch Extraction And Matching, Xin Zhong, Zhiyuan Zhang
Research Collection School Of Computing and Information Systems
A novel automatic pose-invariant dental arch extraction and matching framework is developed for 3D dental identification using laser-scanned dental plasters. In our previous attempt [1-5], 3D point-based algorithms have been developed and they have shown a few advantages over existing 2D dental identifications. This study is a continuous effort in developing arch-based algorithms to extract and match dental arch feature in an automatic and pose-invariant way. As best as we know, this is the first attempt at automatic dental arch extraction and matching for 3D dental identification. A Radial Ray Algorithm (RRA) is proposed by projecting dental arch shape from …
Converting Optical Videos To Infrared Videos Using Attention Gan And Its Impact On Target Detection And Classification Performance,
2021
Old Dominion University
Converting Optical Videos To Infrared Videos Using Attention Gan And Its Impact On Target Detection And Classification Performance, Mohammad Shahab Uddin, Reshad Hoque, Kazi Aminul Islam, Chiman Kwan, David Gribben, Jiang Li
Electrical & Computer Engineering Faculty Publications
To apply powerful deep-learning-based algorithms for object detection and classification in infrared videos, it is necessary to have more training data in order to build high-performance models. However, in many surveillance applications, one can have a lot more optical videos than infrared videos. This lack of IR video datasets can be mitigated if optical-to-infrared video conversion is possible. In this paper, we present a new approach for converting optical videos to infrared videos using deep learning. The basic idea is to focus on target areas using attention generative adversarial network (attention GAN), which will preserve the fidelity of target areas. …
The (Digital) Medium Of Mobility Is The Message: Examining The Influence Of E-Scooter Mobile App Perceptions On E-Scooter Use Intent,
2021
Singapore Management University
The (Digital) Medium Of Mobility Is The Message: Examining The Influence Of E-Scooter Mobile App Perceptions On E-Scooter Use Intent, Rabindra Ratan, Kelsey Earle, Sonny Rosenthal, Vivian Hsueh Hua Chen, Andrew Gambiro, Gerard Goggin, Hallam Stevens, Benjamin Li, Kwan Min Lee
Research Collection College of Integrative Studies
The present research examines how perceptions of e-scooter mobile apps (i.e., a communication technology) influence intent to use e-scooters (i.e., a transportation technology) while considering other perceptions specific to e-scooters (ease of use, usefulness, safety, environmental impact, and enjoyment), context of use (geographic landscape), and demographic factors (age and sex). Results suggest mobile app perceived ease of use is associated with e-scooter use intent and this effect is mediated by e-scooter perceived usefulness, even when controlling for e-scooter perceived ease of use as well as other influential elements of e-scooter use. In addition to illustrating the importance of user experiences …
Soda: An Open-Source Library For Visualizing Biological Sequence Annotation,
2021
The University Of Montana
Soda: An Open-Source Library For Visualizing Biological Sequence Annotation, Jack W. Roddy, Travis J. Wheeler
Graduate Student Theses, Dissertations, & Professional Papers
Genome annotation is the process of identifying and labeling known genetic sequences or features within a genome. Across the various subfields within modern molecular biology, there is a common need for the visualization of such annotations. Genomic data is often visualized on web browser platforms, providing users with easy access to visualization tools without the need for installing any software or, in many cases, underlying datasets. While there exists a broad range of web-based visualization tools, there is, to my knowledge, no lightweight, modern library tailored towards the visualization of genomic data. Instead, developers charged with the task of producing …
Facial Emotion Recognition With Noisy Multi-Task Annotations,
2021
Singapore Management University
Facial Emotion Recognition With Noisy Multi-Task Annotations, S. Zhang, Zhiwu Huang, D.P. Paudel, Gool L. Van
Research Collection School Of Computing and Information Systems
Human emotions can be inferred from facial expressions. However, the annotations of facial expressions are often highly noisy in common emotion coding models, including categorical and dimensional ones. To reduce human labelling effort on multi-task labels, we introduce a new problem of facial emotion recognition with noisy multitask annotations. For this new problem, we suggest a formulation from the point of joint distribution match view, which aims at learning more reliable correlations among raw facial images and multi-task labels, resulting in the reduction of noise influence. In our formulation, we exploit a new method to enable the emotion prediction and …
Towards Location-Independent Eyes-Free Text Entry,
2021
Michigan Technological University
Towards Location-Independent Eyes-Free Text Entry, Dylan C. Gaines
Dissertations, Master's Theses and Master's Reports
We propose an interface for eyes-free text entry using an ambiguous technique and conduct a preliminary user study. We find that user are able to enter text at 19.09 words per minute (WPM) with a 2.08% character error rate (CER) after eight hours of practice. We explore ways to optimize the ambiguous groupings to reduce the number of disambiguation errors, both with and without familiarity constraints. We find that it is feasible to reduce the number of ambiguous groups from six to four. Finally, we explore a technique for presenting word suggestions to users using simultaneous audio feedback. We find …
Light Field Compression And Manipulation Via Residual Convolutional Neural Network,
2021
Michigan Technological University
Light Field Compression And Manipulation Via Residual Convolutional Neural Network, Eisa Hedayati
Dissertations, Master's Theses and Master's Reports
Light field (LF) imaging has gained significant attention due to its recent success in microscopy, 3-dimensional (3D) displaying and rendering, augmented and virtual reality usage. Postprocessing of LF enables us to extract more information from a scene compared to traditional cameras. However, the use of LF is still a research novelty because of the current limitations in capturing high-resolution LF in all of its four dimensions. While researchers are actively improving methods of capturing high-resolution LF's, using simulation, it is possible to explore a high-quality captured LF's properties. The immediate concerns following the LF capture are its storage and processing …
Detecting Surface Interactions Via A Wearable Microphone To Improve Augmented Reality Text Entry,
2021
Michigan Technological University
Detecting Surface Interactions Via A Wearable Microphone To Improve Augmented Reality Text Entry, R. Habibi
Dissertations, Master's Theses and Master's Reports
This thesis investigates whether we can detect and distinguish between surface interaction events such as tapping or swiping using a wearable mic from a surface. Also, what are the advantages of new text entry methods such as tapping with two fingers simultaneously to enter capital letters and punctuation? For this purpose, we conducted a remote study to collect audio and video of three different ways people might interact with a surface. We also built a CNN classifier to detect taps. Our results show that we can detect and distinguish between surface interaction events such as tap or swipe via a …
Internet-Of-Things Devices In Support Of The Development Of Echoic Skills Among Children With Autism Spectrum Disorder,
2021
Old Dominion University
Internet-Of-Things Devices In Support Of The Development Of Echoic Skills Among Children With Autism Spectrum Disorder, Krzysztof J. Rechowicz, John B. Stull, Michelle M. Hascall, Saikou Y. Diallo, Kevin J. O'Brien
VMASC Publications
A significant therapeutic challenge for people with disabilities is the development of verbal and echoic skills. Digital voice assistants (DVAs), such as Amazon’s Alexa, provide networked intelligence to billions of Internet-of-Things devices and have the potential to offer opportunities to people, such as those diagnosed with autism spectrum disorder (ASD), to advance these necessary skills. Voice interfaces can enable children with ASD to practice such skills at home; however, it remains unclear whether DVAs can be as proficient as therapists in recognizing utterances by a developing speaker. We developed an Alexa-based skill called ASPECT to measure how well the DVA …
Natural User Interface Based American Sign Language Tutoring Program,
2021
The University of Akron
Natural User Interface Based American Sign Language Tutoring Program, Bryce J. Allen
Williams Honors College, Honors Research Projects
The COVID-19 pandemic has exposed a substantial shortcoming in the modern American educational system: there is a sufficient need for our educators to be trained in the practices required to provide an educational experience for their students that is as effective as in-person instruction. There exist already systems of online instruction for various academic subjects, such as math and the sciences. In the subject of linguistic studies, educational programs have been developed to evaluate student proficiency in both the written and spoken forms of the language in which they are studying. However, there exist few programs that can effectively provide …
Image Spam Classification With Deep Neural Networks,
2020
San Jose State University
Image Spam Classification With Deep Neural Networks, Ajay Pal Singh, Katerina Potika
Faculty Publications, Computer Science
Image classification is a fundamental problem of computer vision and pattern recognition. We focus on images that contain spam. Spam is unwanted bulk content, and image spam is unwanted content embedded inside the images. Image spam potentially creates a threat to the credibility of any email-based communication system. While a lot of machine learning techniques are successful in detecting textual based spam, this is not the case for image spams, which can easily evade these textual-spam detection systems. In our work, we explore and evaluate four deep learning techniques that detect image spams. First, we train deep neural networks using …
Fractal And Edge-Based Techniques For Kidney Enhancement And Segmentation On Magnetic Resonance Images (Mri),
2020
Universiti Malaya
Fractal And Edge-Based Techniques For Kidney Enhancement And Segmentation On Magnetic Resonance Images (Mri), Alaá Rateb Mahmoud Al-Shamasneh
Student Works (2020-2029)
Recently, many rapid developments in digital medical imaging have made further contributions to healthcare systems. However, the segmentation of regions of interest in medical images plays a vital role in assisting doctors in their medical diagnoses and for the early detection of disease. Since health issues related to the kidneys are increasing exponentially, this thesis focused on developing methods for the segmentation of MRI images of the kidney. Kidney images frequently suffer from low contrast, low resolution and noise, and are blur. Hence, it is necessary to enhance the images in order to improve the segmentation. Therefore, the current thesis …
Responsive Web Design,
2020
CUNY New York City College of Technology
Responsive Web Design, Ashley Varon, David Karlins
Publications and Research
Responsive web design is one of the most important topics in web. It can be one of the main reasons a website can be costing a business clients, and creating an effect on a business. The rise in popularity of mobile phones and tablets makes it crucial for a website to be designed to respond and adjust to different viewports. This project will research how important responsive web design is in 2020 and the positive or negative impacts it may have on the users, customers, and businesses. Companies must consider text size, layout, navigation, image sizes, and testing when designing …
Envrment: Investigating Experience In A Virtual User-Composed Environment,
2020
California Polytechnic State University, San Luis Obispo
Envrment: Investigating Experience In A Virtual User-Composed Environment, Matthew Key
Master's Theses
Virtual Reality is a technology that has long held society's interest, but has only recently began to reach a critical mass of everyday consumers. The idea of modern VR can be traced back decades, but because of the limitations of the technology (both hardware and software), we are only now exploring its potential. At present, VR can be used for tele-surgery, PTSD therapy, social training, professional meetings, conferences, and much more. It is no longer just an expensive gimmick to go on a momentary field trip; it is a tool, and as with the automobile, personal computer, and smartphone, it …
A Study Of Multi-Task And Region-Wise Deep Learning For Food Ingredient Recognition,
2020
Fudan University
A Study Of Multi-Task And Region-Wise Deep Learning For Food Ingredient Recognition, Jingjing Chen, Bin Zhu, Chong-Wah Ngo, Tat-Seng Chua, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
Food recognition has captured numerous research attention for its importance for health-related applications. The existing approaches mostly focus on the categorization of food according to dish names, while ignoring the underlying ingredient composition. In reality, two dishes with the same name do not necessarily share the exact list of ingredients. Therefore, the dishes under the same food category are not mandatorily equal in nutrition content. Nevertheless, due to limited datasets available with ingredient labels, the problem of ingredient recognition is often overlooked. Furthermore, as the number of ingredients is expected to be much less than the number of food categories, …
Generating Concept Based Api Element Comparison Using A Knowledge Graph,
2020
Singapore Management University
Generating Concept Based Api Element Comparison Using A Knowledge Graph, Yang Liu, Mingwei Liu, Xin Peng, Christoph Treude, Zhenchang Xing, Xiaoxin Zhang
Research Collection School Of Computing and Information Systems
Recommender systems are a valuable tool for software engineers. For example, they can provide developers with a ranked list of files likely to contain a bug, or multiple auto-complete suggestions for a given method stub. However, the way these recommender systems interact with developers is often rudimentary—a long list of recommendations only ranked by the model’s confidence. In this vision paper, we lay out our research agenda for re-imagining how recommender systems for software engineering communicate their insights to developers. When issuing recommendations, our aim is to recommend diverse rather than redundant solutions and present them in ways that highlight …
Sharper Generalisation Bounds For Pairwise Learning,
2020
Singapore Management University
Sharper Generalisation Bounds For Pairwise Learning, Yunwen Lei, Antoine Ledent, Marius Kloft
Research Collection School Of Computing and Information Systems
Pairwise learning refers to learning tasks with loss functions depending on a pair of training examples, which includes ranking and metric learning as specific examples. Recently, there has been an increasing amount of attention on the generalization analysis of pairwise learning to understand its practical behavior. However, the existing stability analysis provides suboptimal high-probability generalization bounds. In this paper, we provide a refined stability analysis by developing generalization bounds which can be √nn-times faster than the existing results, where nn is the sample size. This implies excess risk bounds of the order O(n−1/2) (up to a logarithmic factor) for both …
Argumentation Stance Polarity And Intensity Prediction And Its Application For Argumentation Polarization Modeling And Diverse Social Connection Recommendation,
2020
University of Arkansas, Fayetteville
Argumentation Stance Polarity And Intensity Prediction And Its Application For Argumentation Polarization Modeling And Diverse Social Connection Recommendation, Joseph Winstead Sirrianni
Graduate Theses and Dissertations
Cyber argumentation platforms implement theoretical argumentation structures that promote higher quality argumentation and allow for informative analysis of the discussions. Dr. Liu’s research group has designed and implemented a unique platform called the Intelligent Cyber Argumentation System (ICAS). ICAS structures its discussions into a weighted cyber argumentation graph, which describes the relationships between the different users, their posts in a discussion, the discussion topic, and the various subtopics in a discussion. This platform is unique as it encodes online discussions into weighted cyber argumentation graphs based on the user’s stances toward one another’s arguments and ideas. The resulting weighted cyber …
Improving Gan Training With Probability Ratio Clipping And Sample Reweighting,
2020
Singapore Management University
Improving Gan Training With Probability Ratio Clipping And Sample Reweighting, Yue Wu, Pan Zhou, Andrew Wilson Gordon, Eric Xing, Zhiting Hu
Research Collection School Of Computing and Information Systems
Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation. To solve this issue, we propose a new variational GAN training framework which enjoys superior training stability. Our approach is inspired by a connection of GANs and reinforcement learning under a variational perspective. The connection leads to (1) probability ratio clipping that regularizes generator training to prevent excessively large updates, and (2) a sample re-weighting mechanism that improves discriminator training by downplaying bad-quality fake samples. Moreover, our variational GAN framework can provably …
Energy-Efficient Communications In Wireless Powered Cognitive Radio Networks Based On Game Theory,
2020
Universiti Malaya
Energy-Efficient Communications In Wireless Powered Cognitive Radio Networks Based On Game Theory, Fadhil Mukhlif Aswad Al-Obaidy
Student Works (2020-2029)
There are challenging and prevalent problems related to spectrum resources with the interference of battery-based devices in future wireless networks. To address such challenges, this thesis proposes a theoretical framework for designing and analyzing the distributed power control algorithms in modern 5G cognitive networks. Previous experiments have shown that game theory tools can be used as a suitable and efficient technique to build scalable, balanced, and energy efficient for the distributed power control schemes in order to use it practically in battery-based devices in wireless networks. In reality, the power control issue is constructed as a non-cooperative game for which …
