Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 11 of 11
Full-Text Articles in Physical Sciences and Mathematics
Survey On Deep Neural Networks In Speech And Vision Systems, M. Alam, Manar D. Samad, Lasitha Vidyaratne, Alexander Glandon, Khan M. Iftekharuddin
Survey On Deep Neural Networks In Speech And Vision Systems, M. Alam, Manar D. Samad, Lasitha Vidyaratne, Alexander Glandon, Khan M. Iftekharuddin
Computer Science Faculty Research
This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in speech and vision applications. Recent advances in deep artificial neural network algorithms and architectures have spurred rapid innovation and development of intelligent speech and vision systems. With availability of vast amounts of sensor data and cloud computing for processing and training of deep neural networks, and with increased sophistication in mobile and embedded technology, the next-generation intelligent systems are poised to revolutionize personal and commercial computing. This survey begins by providing background and evolution of some of the most successful deep learning models for intelligent …
Semiotic Aggregation In Deep Learning, Bogdan Muşat, Răzvan Andonie
Semiotic Aggregation In Deep Learning, Bogdan Muşat, Răzvan Andonie
All Faculty Scholarship for the College of the Sciences
Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of these layers from the perspective of semiotics, also known as the study of signs and sign-using behavior. In computational semiotics, this aggregation operation (known as superization) is accompanied by a decrease of spatial entropy: signs are aggregated into supersign. Using spatial entropy, we compute the information content of the saliency maps and study the superization processes which take place between successive layers of the network. In …
Visual Sentiment Analysis For Review Images With Item-Oriented And User-Oriented Cnn: Reproducibility Companion Paper, Quoc Tuan Truong, Hady W. Lauw, Martin Aumuller, Naoko Nitta
Visual Sentiment Analysis For Review Images With Item-Oriented And User-Oriented Cnn: Reproducibility Companion Paper, Quoc Tuan Truong, Hady W. Lauw, Martin Aumuller, Naoko Nitta
Research Collection School Of Computing and Information Systems
We revisit our contributions on visual sentiment analysis for online review images published at ACM Multimedia 2017, where we develop item-oriented and user-oriented convolutional neural networks that better capture the interaction of image features with specific expressions of users or items. In this work, we outline the experimental claims as well as describe the procedures to reproduce the results therein. In addition, we provide artifacts including data sets and code to replicate the experiments.
Real-Time Road Hazard Information System, Carlos Pena-Caballero, Dong-Chul Kim, Adolfo Gonzalez, Osvaldo Castellanos, Angel A. Cantu, Jungseok Ho
Real-Time Road Hazard Information System, Carlos Pena-Caballero, Dong-Chul Kim, Adolfo Gonzalez, Osvaldo Castellanos, Angel A. Cantu, Jungseok Ho
Computer Science Faculty Publications and Presentations
Infrastructure is a significant factor in economic growth for systems of government. In order to increase economic productivity, maintaining infrastructure quality is essential. One of the elements of infrastructure is roads. Roads are means which help local and national economies be more productive. Furthermore, road damage such as potholes, debris, or cracks is the cause of many on-road accidents that have cost the lives of many drivers. In this paper, we propose a system that uses Convolutional Neural Networks to detect road degradations without data pre-processing. We utilize the state-of-the-art object detection algorithm, YOLO detector for the system. First, we …
Machine Learning-Based Signal Degradation Models For Attenuated Underwater Optical Communication Oam Beams, Patrick L. Neary, Abbie T. Watnik, K. Peter Judd, James R. Lindle, Nicholas S. Flann
Machine Learning-Based Signal Degradation Models For Attenuated Underwater Optical Communication Oam Beams, Patrick L. Neary, Abbie T. Watnik, K. Peter Judd, James R. Lindle, Nicholas S. Flann
Computer Science Faculty and Staff Publications
Signal attenuation in underwater communications is a problem that degrades classification performance. Several novel CNN-based (SMART) models are developed to capture the physics of the attenuation process. One model is built and trained using automatic differentiation and another uses the radon cumulative distribution transform. These models are inserted in the classifier training pipeline. It is shown that including these attenuation models in classifier training significantly improves classification performance when the trained model is tested with environmentally attenuated images. The improved classification accuracy will be important in future OAM underwater optical communication applications.
A Robust Structured Tracker Using Local Deep Features, Mohammadreza Javanmardi, Amir Hossein Farzaneh, Xiaojun Qi
A Robust Structured Tracker Using Local Deep Features, Mohammadreza Javanmardi, Amir Hossein Farzaneh, Xiaojun Qi
Computer Science Faculty and Staff Publications
Deep features extracted from convolutional neural networks have been recently utilized in visual tracking to obtain a generic and semantic representation of target candidates. In this paper, we propose a robust structured tracker using local deep features (STLDF). This tracker exploits the deep features of local patches inside target candidates and sparsely represents them by a set of templates in the particle filter framework. The proposed STLDF utilizes a new optimization model, which employs a group-sparsity regularization term to adopt local and spatial information of the target candidates and attain the spatial layout structure among them. To solve the optimization …
Weighted Random Search For Cnn Hyperparameter Optimization, Rǎzvan Andonie, Adrian-Cǎtǎlin Florea
Weighted Random Search For Cnn Hyperparameter Optimization, Rǎzvan Andonie, Adrian-Cǎtǎlin Florea
All Faculty Scholarship for the College of the Sciences
Nearly all model algorithms used in machine learning use two different sets of parameters: the training parameters and the meta-parameters (hyperparameters). While the training parameters are learned during the training phase, the values of the hyperparameters have to be specified before learning starts. For a given dataset, we would like to find the optimal combination of hyperparameter values, in a reasonable amount of time. This is a challenging task because of its computational complexity. In previous work, we introduced the Weighted Random Search (WRS) method, a combination of Random Search (RS) and probabilistic greedy heuristic. In the current paper, we …
Learning In The Machine: To Share Or Not To Share?, Jordan Ott, Erik Linstead, Nicholas Lahaye, Pierre Baldi
Learning In The Machine: To Share Or Not To Share?, Jordan Ott, Erik Linstead, Nicholas Lahaye, Pierre Baldi
Engineering Faculty Articles and Research
Weight-sharing is one of the pillars behind Convolutional Neural Networks and their successes. However, in physical neural systems such as the brain, weight-sharing is implausible. This discrepancy raises the fundamental question of whether weight-sharing is necessary. If so, to which degree of precision? If not, what are the alternatives? The goal of this study is to investigate these questions, primarily through simulations where the weight-sharing assumption is relaxed. Taking inspiration from neural circuitry, we explore the use of Free Convolutional Networks and neurons with variable connection patterns. Using Free Convolutional Networks, we show that while weight-sharing is a pragmatic optimization …
Graph Classification With Kernels, Embeddings And Convolutional Neural Networks, Monica Golahalli Seenappa, Katerina Potika, Petros Potikas
Graph Classification With Kernels, Embeddings And Convolutional Neural Networks, Monica Golahalli Seenappa, Katerina Potika, Petros Potikas
Faculty Publications, Computer Science
In the graph classification problem, given is a family of graphs and a group of different categories, and we aim to classify all the graphs (of the family) into the given categories. Earlier approaches, such as graph kernels and graph embedding techniques have focused on extracting certain features by processing the entire graph. However, real world graphs are complex and noisy and these traditional approaches are computationally intensive. With the introduction of the deep learning framework, there have been numerous attempts to create more efficient classification approaches. We modify a kernel graph convolutional neural network approach, that extracts subgraphs (patches) …
Underwater Gesture Recognition Using Classical Computer Vision And Deep Learning Techniques, Mygel Andrei M. Martija, Jakov Ivan S. Dumbrique, Prospero C. Naval Jr.
Underwater Gesture Recognition Using Classical Computer Vision And Deep Learning Techniques, Mygel Andrei M. Martija, Jakov Ivan S. Dumbrique, Prospero C. Naval Jr.
Mathematics Faculty Publications
Underwater Gesture Recognition is a challenging task since conditions which are normally not an issue in gesture recognition on land must be considered. Such issues include low visibility, low contrast, and unequal spectral propagation. In this work, we explore the underwater gesture recognition problem by taking on the recently released Cognitive Autonomous Diving Buddy Underwater Gestures dataset. The contributions of this paper are as follows: (1) Use traditional computer vision techniques along with classical machine learning to perform gesture recognition on the CADDY dataset; (2) Apply deep learning using a convolutional neural network to solve the same problem; (3) Perform …
Quantifying Seagrass Distribution In Coastal Water With Deep Learning Models, Daniel Perez, Kazi Islam, Victoria Hill, Richard Zimmerman, Blake Schaeffer, Yuzhong Shen, Jiang Li
Quantifying Seagrass Distribution In Coastal Water With Deep Learning Models, Daniel Perez, Kazi Islam, Victoria Hill, Richard Zimmerman, Blake Schaeffer, Yuzhong Shen, Jiang Li
OES Faculty Publications
Coastal ecosystems are critically affected by seagrass, both economically and ecologically. However, reliable seagrass distribution information is lacking in nearly all parts of the world because of the excessive costs associated with its assessment. In this paper, we develop two deep learning models for automatic seagrass distribution quantification based on 8-band satellite imagery. Specifically, we implemented a deep capsule network (DCN) and a deep convolutional neural network (CNN) to assess seagrass distribution through regression. The DCN model first determines whether seagrass is presented in the image through classification. Second, if seagrass is presented in the image, it quantifies the seagrass …