Digital Commons Network^™

Deep Learning Architectures For Heterogeneous Face Recognition, Seyed Mehdi Iranmanesh

Graduate Theses, Dissertations, and Problem Reports (ETD)

Face recognition has been one of the most challenging areas of research in biometrics and computer vision. Many face recognition algorithms are designed to address illumination and pose problems for visible face images. In recent years, there has been significant amount of research in Heterogeneous Face Recognition (HFR). The large modality gap between faces captured in different spectrum as well as lack of training data makes heterogeneous face recognition (HFR) quite a challenging problem. In this work, we present different deep learning frameworks to address the problem of matching non-visible face photos against a gallery of visible faces.

Algorithms for …

Vibro-Acoustic Codling Moth Larvae Infestation Detection In Apples, Chadwick A. Parrish

Theses and Dissertations--Electrical and Computer Engineering

Within recent years, the demand for organic produce has greatly increased due to many factors, including increasing knowledge about such things as dietary fiber and balanced gastrointestinal bacterial ecosystems. This increase in demand, coupled with the financial penalties for sending invasive species and pests across borders, presents a need for a scalable and accurate system to non-destructively detect infestation. The proposed work addresses this problem by testing the performance of a non-destructive vibro-acoustic method for detecting lava activity in apples. This involved 3 steps; design a mechanical data collection prototype for testing apples, a evaluate a set of features, and …

Emotional Body Language Synthesis For Humanoid Robots, Asimina Marmpena

School of Engineering, Computing and Mathematics Theses

In the next decade, societies will witness a rise in service robots deployed in social environments, such as schools, homes, or shops, where they will operate as assistants, public relation agents, or companions. People are expected to willingly engage and collaborate with these robots to accomplish positive outcomes. To facilitate collaboration, robots need to comply with the behavioural and social norms used by humans in their daily interactions. One such behavioural norm is the expression of emotion through body language. Previous work on emotional body language synthesis for humanoid robots has been mainly focused on hand-coded design methods, often employing …

Deep Learning For Crime Prediction, Nicholas Gacharich

Electronic Theses and Dissertations 2020 - Present

In this research, we propose to use deep learning to predict crimes in small neighborhoods (regions) of a city, by using historical crime data collected from the past. The motivation of crime predictions is that if we can predict the number crimes that will occur in a certain week then the city officials and law enforcement can prepare resources and manpower more effectively. Due to inherent connections between geographic regions and crime activities, the crime numbers in different regions (with respect to different time periods) are often correlated. Such correlation brings challenges and opportunities to employ deep learning to learn …

Developmental Neurorobotics Models Of Counting And Numerosity Judgment, Leszek Pecyna

School of Engineering, Computing and Mathematics Theses

This thesis presents novel developmental robotics models of number cognition which take into account the embodied basis of this process. The ability to perceive quantity is undoubtedly crucial for both humans and animals. Nowadays, automation is becoming increasingly important in society; it seems that the way, similar to humans, to perceive and process numbers is one of the pressing issues for the future of robotics. This is important in the context of proper interaction between robots and humans which requires machines - at least on some level - to understand complex/abstract words such as number names. This thesis takes into …

Just-In-Time Biomass Yield Estimation With Multi-Modal Data And Variable Patch Training Size, Patricia O'Byrne, Patrick Jackman Dr., Damon Dr. Berry Dr., Thomas Lee, Michael French, Robert J. Ross

Conference papers

The just-in-time estimation of farmland traits such as biomass yield can aid considerably in the optimisation of agricultural processes. Data in domains such as precision farming is however notoriously expensive to collect and deep learning driven modelling approaches need to maximise performance but also acknowledge this reality. In this paper we present a study in which a platform was deployed to collect data from a heterogeneous collection of sensor types including visual, NIR, and LiDAR sources to estimate key pastureland traits. In addition to introducing the study itself we address two key research questions. The first of these was the …

Pothole Detection Under Diverse Conditions Using Object Detection Model, Ibrahim Hassan Syed, Dympna O'Sullivan, Susan Mckeever

Datasets

One of the most important tasks in road maintenance is the detection of potholes. This process is usually done through manual visual inspection, where certified engineers assess recorded images of pavements acquired using cameras or professional road assessment vehicles. Machine learning techniques are now being applied to this problem, with models trained to automatically identify road conditions. However, approaching this real-world problem with machine learning techniques presents the classic problem of how to produce generalizable models. Images and videos may be captured in different illumination conditions, with different camera types, camera angles and resolutions. In this paper we present our …

Deep Models For Improving The Performance And Reliability Of Person Recognition, Sobhan Soleymani

Graduate Theses, Dissertations, and Problem Reports (ETD)

Deep models have provided high accuracy for different applications such as person recognition, image segmentation, image captioning, scene description, and action recognition. In this dissertation, we study the deep learning models and their application in improving the performance and reliability of person recognition. This dissertation focuses on five aspects of person recognition: (1) multimodal person recognition, (2) quality-aware multi-sample person recognition, (3) text-independent speaker verification, (4) adversarial iris examples, and (5) morphed face images. First, we discuss the application of multimodal networks consisting of face, iris, fingerprint, and speech modalities in person recognition. We propose multi-stream convolutional neural network architectures …

Adversarial Reconstruction Loss For Domain Generalization, Bekkouch Imad Eddine Ibrahim, Dragos Constantin Nicolae, Adil Khan, S. M. Ahsan Kazmi, Asad Masood Khattak, Bulat Ibragimov

All Works

The biggest fear when deploying machine learning models to the real world is their ability to handle the new data. This problem is significant especially in medicine, where models trained on rich high-quality data extracted from large hospitals do not scale to small regional hospitals. One of the clinical challenges addressed in this work is magnetic resonance image generalization for improved visualization and diagnosis of hip abnormalities such as femoroacetabular impingement and dysplasia. Domain Generalization (DG) is a field in machine learning that tries to solve the model’s dependency on the training data by leveraging many related but different data …

Variational Inference For Morphological Modification To 3d Geometry : An Application To The Support Generation For Metal Additive Manufacturing, Mugdha Swanand Joshi

Masters Theses

"A key issue in metal additive manufacturing (AM) processes is the optimization of support geometry. Correct selection of support strategy can reduce build time, improve surface finish, reduce support removal time, and maximize build success. Strategies used to design support structure are time consuming and need skilled personnel. In this research we have deployed a deep generative model capable of making morphological modifications to the part. However, it is not similar to topology optimization where the aim is to reduce or eliminate support structure. The proposed model can make necessary changes to the part in order to transform it into …

Classification Of Skin Disease Using Deep Learning Neural Networks With Mobilenet V2 And Lstm, Parvathaneni N. Srinivasu, Jalluri G. Siva Sai, Muhammad F. Ijaz, Akash K. Bhoi, Wonjoon Kim, James J. Kang

Research outputs 2014 to 2021

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning-based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), …

Deep Reinforcement Learning Based Path-Planning For Multi-Agent Systems In Advection-Diffusion Field Reconstruction Tasks, Deepak Talwar

Master's Theses

Many environmental processes can be represented mathematically using spatial-temporal varying partial-differential equations. Timely estimation and prediction of processes such as wildfires is critical for disaster management response, but is difficult to accomplish without the availability of a dense network of stationary sensors. In this work, we propose a deep reinforcement learning-based real-time path-planning algorithm for mobile sensor networks traveling in a formation through a spatial-temporal varying advection-diffusion field for the task of field reconstruction. A deep Q-network (DQN) agent is trained on simulated advection-diffusion fields to direct the mobile sensor network to travel along information-rich trajectories. The field measurements made …

Data: The Good, The Bad And The Ethical, John D. Kelleher, Filipe Cabral Pinto, Luis M. Cortesao

Articles

It is often the case with new technologies that it is very hard to predict their long-term impacts and as a result, although new technology may be beneficial in the short term, it can still cause problems in the longer term. This is what happened with oil by-products in different areas: the use of plastic as a disposable material did not take into account the hundreds of years necessary for its decomposition and its related long-term environmental damage. Data is said to be the new oil. The message to be conveyed is associated with its intrinsic value. But as in …

Segmentation Method For Face Modelling In Thermal Images, Albar Albar, Hendrick Hendrick, Rahmat Hidayat

Knowledge Engineering and Data Science

Face detection is mostly applied in RGB images. The object detection usually applied the Deep Learning method for model creation. One method face spoofing is by using a thermal camera. The famous object detection methods are Yolo, Fast Region Based Convolutional Neural Networks (RCNN), Faster RCNN, SSD, and Mask RCNN. We proposed a segmentation Mask RCNN method to create a face model from thermal images. This model was able to locate the face area in images. The dataset was established using 1600 images. The images were created from direct capturing and collecting from the online dataset. The Mask RCNN was …

Convolutional Neural Network On Tanned And Synthetic Leather Textures, Faadihilah Ahnaf Faiz, Ahmad Azhari

Knowledge Engineering and Data Science

Tanned leather is an output from complex processes called tanning. Leather tanning is an important step that used to protect the fiber or protein structure of animal’s skin. Another reason of tanning process is to prevent the animal’s skin from any defect or rot. After the tanning is complete, the leather can be applied to produce a wide variety of leather products. Thus, the leather prices usually more expensive because it takes longer time in process. Another way to get cheaper price is make non-animal leather that usually known as synthetic or imitation leather. The purpose of this paper is …

A Deep Learning Framework Supporting Model Ownership Protection And Traitor Tracing, Guowen Xu, Hongwei Li, Yuan Zhang, Xiaodong Lin, Robert H. Deng, Xuemin (Sherman) Shen

Research Collection School Of Computing and Information Systems

Cloud-based deep learning (DL) solutions have been widely used in applications ranging from image recognition to speech recognition. Meanwhile, as commercial software and services, such solutions have raised the need for intellectual property rights protection of the underlying DL models. Watermarking is the mainstream of existing solutions to address this concern, by primarily embedding pre-defined secrets in a model's training process. However, existing efforts almost exclusively focus on detecting whether a target model is pirated, without considering traitor tracing. In this paper, we present SecureMark_DL, which enables a model owner to embed a unique fingerprint for every customer within parameters …

Integrating Deep Learning And Augmented Reality To Enhance Situational Awareness In Firefighting Environments, Manish Bhattarai

Electrical and Computer Engineering ETDs

We present a new four-pronged approach to build firefighter's situational awareness for the first time in the literature. We construct a series of deep learning frameworks built on top of one another to enhance the safety, efficiency, and successful completion of rescue missions conducted by firefighters in emergency first response settings. First, we used a deep Convolutional Neural Network (CNN) system to classify and identify objects of interest from thermal imagery in real-time. Next, we extended this CNN framework for object detection, tracking, segmentation with a Mask RCNN framework, and scene description with a multimodal natural language processing(NLP) framework. Third, …

A Bibliometric Survey Of Smart Wearable In The Health Insurance Industry, Apeksha Shah, Swati Ahirrao, Shraddha Phansalkar, Ketan Kotecha

Library Philosophy and Practice (e-journal)

Smart wearables help real-time and remote monitoring of health data for effective diagnostic and preventive health care services. Wearable devices have the ability to track and monitor healthcare vitals such as heart rate, physical activities, BMI (Body Mass Index), blood pressure, and keeps an individual notified about the health status. Artificial Intelligence-enabled wearables show an ability to transform the health insurance sector. This would not only enable self-management of individual health but also help them focus from treatments to the preventions of health hazards. With this customer-centric approach to health care, it will enable the insurance companies to track the …

Low-Shot Deep Learning Of Diabetic Retinopathy With Potential Applications To Address Artificial Intelligence Bias In Retinal Diagnostics And Rare Ophthalmic Diseases, Philippe Burlina, William Paul, Philip Mathew, Neil Joshi, Katia D Pacheco, Neil M Bressler

Faculty, Staff and Students Publications

IMPORTANCE: Recent studies have demonstrated the successful application of artificial intelligence (AI) for automated retinal disease diagnostics but have not addressed a fundamental challenge for deep learning systems: the current need for large, criterion standard-annotated retinal data sets for training. Low-shot learning algorithms, aiming to learn from a relatively low number of training data, may be beneficial for clinical situations involving rare retinal diseases or when addressing potential bias resulting from data that may not adequately represent certain groups for training, such as individuals older than 85 years.

OBJECTIVE: To evaluate whether low-shot deep learning methods are beneficial when using …

Meta-Rcnn: Meta Learning For Few-Shot Object Detection, Xiongwei Wu, Doyen Sahoo, Steven Hoi

Research Collection School Of Computing and Information Systems

Despite significant advances in deep learning based object detection in recent years, training effective detectors in a small data regime remains an open challenge. This is very important since labelling training data for object detection is often very expensive and time-consuming. In this paper, we investigate the problem of few-shot object detection, where a detector has access to only limited amounts of annotated data. Based on the meta-learning principle, we propose a new meta-learning framework for object detection named "Meta-RCNN", which learns the ability to perform few-shot detection via meta-learning. Specifically, Meta-RCNN learns an object detector in an episodic learning …

Tag: Automated Image Captioning, Nathan Funckes

McNair Scholars Manuscripts

Many websites remain non-ADA compliant, containing images which lack accompanying textual descriptions. This leaves sight-impaired individuals unable to fully enjoy the rich wonders of the web. To address this inequity, our research aims to create an autonomous system capable of generating semantically accurate descriptions of images. This problem involves two tasks: recognizing an image and linguistically describing it. Our solution uses state-of-the-art deep learning: employing a convolutional neural network that "learns" to understand images and extracts their salient features, and a recurrent neural network that learns to generate structured, coherent sentences. These two networks are merged to create a single …

Zero-Bias Deep Learning For Accurate Identification Of Internet Of Things (Iot) Devices, Yongxin Liu, Houbing Song, Thomas Yang, Jian Wang, Jianqiang Li, Shuteng Niu, Zhong Ming

Publications

The Internet of Things (IoT) provides applications and services that would otherwise not be possible. However, the open nature of IoT makes it vulnerable to cybersecurity threats. Especially, identity spoofing attacks, where an adversary passively listens to the existing radio communications and then mimic the identity of legitimate devices to conduct malicious activities. Existing solutions employ cryptographic signatures to verify the trustworthiness of received information. In prevalent IoT, secret keys for cryptography can potentially be disclosed and disable the verification mechanism. Noncryptographic device verification is needed to ensure trustworthy IoT. In this article, we propose an enhanced deep learning framework …

A Study Of Information Bots And Knowledge Bots, Amartya Hatua

Dissertations

In this dissertation, a study of different aspects of information bots and knowledge bots is done. The research contributes to a better understanding of the various characteristics of information bots as well as the different patterns and factors responsible for the information diffusion in a social network. This research also shows how these factors can be used to predict information diffusion for a particular topic in a social network. The second part of the research is focused on strategies for improving the knowledge base of knowledge bots, where two different approaches are studied. In the first approach, knowledge is transferred …

Machine Learning Approaches For Improving Prediction Performance Of Structure-Activity Relationship Models, Gabriel Idakwo

Dissertations

In silico bioactivity prediction studies are designed to complement in vivo and in vitro efforts to assess the activity and properties of small molecules. In silico methods such as Quantitative Structure-Activity/Property Relationship (QSAR) are used to correlate the structure of a molecule to its biological property in drug design and toxicological studies. In this body of work, I started with two in-depth reviews into the application of machine learning based approaches and feature reduction methods to QSAR, and then investigated solutions to three common challenges faced in machine learning based QSAR studies.

First, to improve the prediction accuracy of learning …

Rethinking Pruning For Accelerating Deep Inference At The Edge, Dawei Gao, Xiaoxi He, Zimu Zhou, Yongxin Tong, Ke Xu, Lothar Thiele

Research Collection School Of Computing and Information Systems

There is a growing trend to deploy deep neural networks at the edge for high-accuracy, real-time data mining and user interaction. Applications such as speech recognition and language understanding often apply a deep neural network to encode an input sequence and then use a decoder to generate the output sequence. A promising technique to accelerate these applications on resource-constrained devices is network pruning, which compresses the size of the deep neural network without severe drop in inference accuracy. However, we observe that although existing network pruning algorithms prove effective to speed up the prior deep neural network, they lead to …

Numerical Approximations Of Phase Field Equations With Physics Informed Neural Networks, Colby Wight

All Graduate Plan B and other Reports, Spring 1920 to Spring 2023

Designing numerical algorithms for solving partial differential equations (PDEs) is one of the major research branches in applied and computational mathematics. Recently there has been some seminal work on solving PDEs using the deep neural networks. In particular, the Physics Informed Neural Network (PINN) has been shown to be effective in solving some classical partial differential equations. However, we find that this method is not sufficient in solving all types of equations and falls short in solving phase-field equations. In this thesis, we propose various techniques that add to the power of these networks. Mainly, we propose to embrace the …

An End-To-End Trainable Method For Generating And Detecting Fiducial Markers, J. Brennan Peace

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Existing fiducial markers are designed for efficient detection and decoding. The methods are computationally efficient and capable of demonstrating impressive results, however, the markers are not explicitly designed to stand out in natural environments and their robustness is difficult to infer from relatively limited analysis. Worsening performance in challenging image capture scenarios - such as poorly exposed images, motion blur, and off-axis viewing - sheds light on their limitations. The method introduced in this work is an end-to-end trainable method for designing fiducial markers and a complimentary detector. By introducing back-propagatable marker augmentation and superimposition into training, the method learns …

Understanding Spatial Language In Radiology: Representation Framework, Annotation, And Spatial Relation Extraction From Chest X-Ray Reports Using Deep Learning, Surabhi Datta, Yuqi Si, Laritza Rodriguez, Sonya E Shooshan, Dina Demner-Fushman, Kirk Roberts

Faculty, Staff and Student Publications

Radiology reports contain a radiologist's interpretations of images, and these images frequently describe spatial relations. Important radiographic findings are mostly described in reference to an anatomical location through spatial prepositions. Such spatial relationships are also linked to various differential diagnoses and often described through uncertainty phrases. Structured representation of this clinically significant spatial information has the potential to be used in a variety of downstream clinical informatics applications. Our focus is to extract these spatial representations from the reports. For this, we first define a representation framework based on the Spatial Role Labeling (SpRL) scheme, which we refer to as …

Inter-Slice Compression And Reconstruction Of Glioma Magnetic Resonance Imaging (Mri) Data Using Encoder-Decoder Neural Networks, Gavin Michael Karr

Graduate Theses - Electrical and Computer Engineering

Magnetic Resonance Imaging (MRI) scans of patients with brain tumors are an important source of pre-surgical medical information. These three-dimensional image volumes can be represented as a stack of two-dimensional image slices. The objective of this thesis is to compress the size of these image volumes by removing the odd-numbered slices and reconstruct the image volume using an encoder-decoder convolutional neural network. This neural network architecture is based on a modified form of the U-net segmentation network, which has been adjusted to allow for multiple image inputs and to support a network capable of generating new image slices. A novel …

Deep Learning For Real-World Object Detection, Xiongwei Wu

Dissertations and Theses Collection (Open Access)

Despite achieving significant progresses, most existing detectors are designed to detect objects in academic contexts but consider little in real-world scenarios. In real-world applications, the scale variance of objects can be significantly higher than objects in academic contexts; In addition, existing methods are designed for achieving localization with relatively low precision, however more precise localization is demanded in real-world scenarios; Existing methods are optimized with huge amount of annotated data, but in certain real-world scenarios, only a few samples are available. In this dissertation, we aim to explore novel techniques to address these research challenges to make object detection algorithms …