Physical Sciences and Mathematics Commons^™

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. …

Ensemble Learning Of Multiview Cnn Models For Survival Time Prediction Of Braintumor Patients Using Multimodal Mri Scans, Abdela Ahmed Mossa, Ulus Çevi̇k

Turkish Journal of Electrical Engineering and Computer Sciences

Brain tumors have been one of the most common life-threatening diseases for all mankind. There have beenhuge efforts dedicated to the development of medical imaging techniques and radiomics to diagnose tumor patients quicklyand e?iciently. One of the main aims is to ensure that preoperative overall survival time (OS) prediction is accurate.Recently, deep learning (DL) algorithms, and particularly convolutional neural networks (CNNs) achieved promisingperformances in almost all computer vision fields. CNNs demand large training datasets and high computational costs.However, curating large annotated medical datasets are difficult and resource-intensive. The performances of singlelearners are also unsatisfactory for small datasets. Thus, this study …

Image Forgery Detection Based On Fusion Of Lightweight Deep Learning Models, Amit Doegar, Srinidhi Hiriyannaiah, Siddesh Gaddadevara Matt, Srinivasa Krishnarajanagar Gopaliyengar, Maitreyee Dutta

Turkish Journal of Electrical Engineering and Computer Sciences

Image forgery detection is one of the key challenges in various real time applications, social media and online information platforms. The conventional methods of detection based on the traces of image manipulations are limited to the scope of predefined assumptions like hand-crafted features, size and contrast. In this paper, we propose a fusion based decision approach for image forgery detection. The fusion of decision is based on the lightweight deep learning models namely SqueezeNet, MobileNetV2 and ShuffleNet. The fusion decision system is implemented in two phases. First, the pretrained weights of the lightweight deep learning models are used to evaluate …

Deep Learning For Turkish Makam Music Composition, İsmai̇l Hakki Parlak, Yalçin Çebi̇, Ci̇han Işikhan, Derya Bi̇rant

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, we introduce a new deep-learning-based system that can compose structured Turkish makam music (TMM) in the symbolic domain. Presented artificial TMM composer (ATMMC) takes eight initial notes from a human user and completes the rest of the piece. The backbone of the composer system consists of multilayered long short-term memory (LSTM) networks. ATMMC can create pieces in Hicaz and Nihavent makams in Şarkı form, which can be viewed and played with Mus2, a notation software for microtonal music. Statistical analysis shows that pieces composed by ATMMC are approximately 84% similar to training data. ATMMC is an open-source …

Predicting Carcass Cut Yields In Cattle From Digitalimages Using Artificial Intelligence, Darragh Matthews

Theses

Beef carcass classification in Europe is predicated on the EUROP grid for both fatness and conformation. Although this system performs well for grouping visually similar carcasses, it cannot be used to accurately predict meat yields from these groups, especially when considered on an individual cut level. Deep Learning (DL) has proven to be a successful tool for many image classification problems but has yet to be fully proven in a regression scenario using carcass images. Here we have trained DL models to predict carcass cut yields and compared predictions to more standard machine learning (ML) methods. Three approaches were undertaken …

A Multi-Resolution Graph Convolution Network For Contiguous Epitope Prediction, Lisa Oh

Dartmouth College Master’s Theses

Computational methods for predicting binding interfaces between antigens and antibodies (epitopes and paratopes) are faster and cheaper than traditional experimental structure determination methods. A sufficiently reliable computational predictor that could scale to large sets of available antibody sequence data could thus inform and expedite many biomedical pursuits, such as better understanding immune responses to vaccination and natural infection and developing better drugs and vaccines. However, current state-of-the-art predictors produce discontiguous predictions, e.g., predicting the epitope in many different spots on an antigen, even though in reality they typically comprise a single localized region. We seek to produce contiguous predicted epitopes, …

Accurate Diagnosis Of Colorectal Cancer Based On Histopathology Images Using Artificial Intelligence, K. S. Wang, G. Yu, C. Xu, X. H. Meng, J. Zhou, W. Zhou, Et. Al.

Michigan Tech Publications, Part 1

Background: Accurate and robust pathological image analysis for colorectal cancer (CRC) diagnosis is time-consuming and knowledge-intensive, but is essential for CRC patients’ treatment. The current heavy workload of pathologists in clinics/hospitals may easily lead to unconscious misdiagnosis of CRC based on daily image analyses. Methods: Based on a state-of-the-art transfer-learned deep convolutional neural network in artificial intelligence (AI), we proposed a novel patch aggregation strategy for clinic CRC diagnosis using weakly labeled pathological whole-slide image (WSI) patches. This approach was trained and validated using an unprecedented and enormously large number of 170,099 patches, > 14,680 WSIs, from > 9631 subjects that covered …

Implementing A Neural Network For Supervised Learning With A Random Configuration Of Layers And Nodes, Kane A. Phillips

College of Graduate Studies: Theses & Dissertations

Deep learning has a substantial amount of real-life applications, making it an increasingly popular subset of artificial intelligence over the last decade. These applications come to fruition due to the tireless research and implementation of neural networks. This paper goes into detail on the implementation of supervised learning neural networks utilizing MATLAB, with the purpose being to generate a neural network based on specifications given by a user. Such specifications involve how many layers are in the network, and how many nodes are in each layer. The neural network is then trained based on known sample values of a function …

A Deep Learning Model To Predict Traumatic Brain Injury Severity And Outcome From Mr Images, Dacosta Yeboah, Hung Nguyen, Daniel B. Hier, Gayla R. Olbricht, Tayo Obafemi-Ajayi

Chemistry Faculty Research & Creative Works

For Many Neurological Disorders, Including Traumatic Brain Injury (TBI), Neuroimaging Information Plays a Crucial Role Determining Diagnosis and Prognosis. TBI is a Heterogeneous Disorder that Can Result in Lasting Physical, Emotional and Cognitive Impairments. Magnetic Resonance Imaging (MRI) is a Non-Invasive Technique that Uses Radio Waves to Reveal Fine Details of Brain Anatomy and Pathology. Although MRIs Are Interpreted by Radiologists, Advances Are Being Made in the Use of Deep Learning for MRI Interpretation. This Work Evaluates a Deep Learning Model based on a Residual Learning Convolutional Neural Network that Predicts TBI Severity from MR Images. the Model Achieved a …

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 …

Active Learning Strategy For Covid-19 Annotated Dataset, Amril Nazir, Ricky Maulana Fajri

All Works

The efficient diagnosis of COVID-19 plays a key role in preventing its spread. Recently, many artificial intelligence techniques, such as the deep neural network approach, have been implemented to help efficient diagnosis of COVID-19. However, the accurate performance of deep learning depends on the tuning of many hyperparameters and a large amount of labeled data. This COVID-19 data bottleneck also leads to insufficient human resources for data labeling, which presents a challenging obstacle. In this paper, a novel discriminative batch-mode active learning (DS3) is proposed to allow faster and more effective COVID-19 data annotation. The framework specifically designed to suit …

Variational Autoencoders And Wasserstein Generative Adversarial Networks For Improving The Anti-Money Laundering Process, Zhiyuan Chen, Waleed Soliman, Amril Nazir, Mohammad Shorfuzzaman

All Works

There has been much recent work on fraud and Anti Money Laundering (AML) detection using machine learning techniques. However, most algorithms are based on supervised techniques. Studies show that supervised techniques often have the limitation of not adapting well to new irregular fraud patterns when the dataset is highly imbalanced. Instead, unsupervised learning can have a better capability to find anomalous and irregular patterns in new transaction. Despite this, unsupervised techniques also have the disadvantage of not being able to give state-of-the-art detection results. We propose a suite of unsupervised and deep learning techniques to implement an anti-money laundering and …

Smart Scribbles For Image Matting, Yang Xin, Yu Qiao, Shaozhe Chen, Shengfeng He, Baocai Yin, Qiang Zhang, Xiaopeng Wei, Rynson W. H. Lau

Research Collection School Of Computing and Information Systems

Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles. Drawing a fine trimap requires a large amount of user effort, while using scribbles can hardly obtain satisfactory alpha mattes for non-professional users. Some recent deep learning-based matting networks rely on large-scale composite datasets for training to improve performance, resulting in the occasional appearance of obvious artifacts when processing natural images. In this article, we explore the intrinsic relationship between user input and alpha mattes and strike a balance between user effort and the quality of alpha mattes. In particular, we propose an …

Adaptive Physics-Based Non-Rigid Registration For Immersive Image-Guided Neuronavigation Systems, Fotis Drakopoulos, Christos Tsolakis, Angelos Angelopoulos, Yixun Liu, Chengjun Yao, Kyriaki Rafailia Kavazidi, Nikolaos Foroglou, Andrey Fedorov, Sarah Frisken, Ron Kikinis, Alexandra Golby, Nikos Chrisochoides

Computer Science Faculty Publications

Objective: In image-guided neurosurgery, co-registered preoperative anatomical, functional, and diffusion tensor imaging can be used to facilitate a safe resection of brain tumors in eloquent areas of the brain. However, the brain deforms during surgery, particularly in the presence of tumor resection. Non-Rigid Registration (NRR) of the preoperative image data can be used to create a registered image that captures the deformation in the intraoperative image while maintaining the quality of the preoperative image. Using clinical data, this paper reports the results of a comparison of the accuracy and performance among several non-rigid registration methods for handling brain deformation. A …

A Tool For Segmentation Of Secondary Structures In 3d Cryo-Em Density Map Components Using Deep Convolutional Neural Networks, Yongcheng Mu, Salim Sazzed, Maytha Alshammari, Jiangwen Sun, Jing He

Computer Science Faculty Publications

Although cryo-electron microscopy (cryo-EM) has been successfully used to derive atomic structures for many proteins, it is still challenging to derive atomic structures when the resolution of cryo-EM density maps is in the medium resolution range, such as 5–10 Å. Detection of protein secondary structures, such as helices and β-sheets, from cryo-EM density maps provides constraints for deriving atomic structures from such maps. As more deep learning methodologies are being developed for solving various molecular problems, effective tools are needed for users to access them. We have developed an effective software bundle, DeepSSETracer, for the detection of protein secondary structure …

Single And Differential Morph Attack Detection, Baaria Chaudhary

Graduate Theses, Dissertations, and Problem Reports (ETD)

Face recognition systems operate on the assumption that a person's face serves as the unique link to their identity. In this thesis, we explore the problem of morph attacks, which have become a viable threat to face verification scenarios precisely because of their inherent ability to break this unique link. A morph attack occurs when two people who share similar facial features morph their faces together such that the resulting face image is recognized as either of two contributing individuals. Morphs inherit enough visual features from both individuals that both humans and automatic algorithms confuse them. The contributions of this …

A Deep Machine Learning Approach For Predicting Freeway Work Zone Delay Using Big Data, Abdullah Shabarek

Dissertations

The introduction of deep learning and big data analytics may significantly elevate the performance of traffic speed prediction. Work zones become one of the most critical factors causing congestion impact, which reduces the mobility as well as traffic safety. A comprehensive literature review on existing work zone delay prediction models (i.e., parametric, simulation and non-parametric models) is conducted in this research. The research shows the limitations of each model. Moreover, most previous modeling approaches did not consider user delay for connected freeways when predicting traffic speed under work zone conditions. This research proposes Deep Artificial Neural Network (Deep ANN) and …

Addressing Ad-Blocking Challenges In Online Publishing: A Data Science Approach, Shuai Zhao

Dissertations

The revenue of online display advertising is expected to reach 389 billion U.S. dollars globally in 2021. However, the fast increase in ad-blocker usage impacts publishers' ad revenue and the ad-supported free web. Faced with this problem, many online publishers choose either to cooperate with ad-blocker software companies to show acceptable ads or to build a wall that requires users to whitelist (i.e., turn off ad-blockers) for content access. This dissertation aims to deepen the understanding of existing counter-ad-blocking strategies and further explore how to address ad-blocking challenges through a data science approach.

The dissertation starts with investigating and identifying …

Leveraging The Inductive Bias Of Large Language Models For Abstract Textual Reasoning, Christopher Michael Rytting

Theses and Dissertations

Large natural language models (such as GPT-2 or T5) demonstrate impressive abilities across a range of general NLP tasks. Here, we show that the knowledge embedded in such models provides a useful inductive bias, not just on traditional NLP tasks, but also in the nontraditional task of training a symbolic reasoning engine. We observe that these engines learn quickly and generalize in a natural way that reflects human intuition. For example, training such a system to model block-stacking might naturally generalize to stacking other types of objects because of structure in the real world that has been partially captured by …

2d-Att: Causal Inference For Mobile Game Organic Installs With 2-Dimensional Attentional Neural Network, Boxiang Dong, Hui Bill Li, Yang Ryan Wang, Rami Safadi

Department of Computer Science Faculty Scholarship and Creative Works

In the mobile gaming industry, organic installs refer to downloads that cannot be attributed to any advertising channel and thus do not introduce upfront user acquisition (UA) cost. Understanding the causal factors on organic installs is of vital importance for a game's ecosystem, as such knowledge can help bring in more organic users, who tend to be more loyal and active. A major challenge in discovering the causal effects is the potential temporal lag between an UA operation and the growth in organic installs. In this paper, we solve the problem by using a deep attentional neural network to analyze …

Methods For Generative Adversarial Output Enhancement, Michael B. Brodie

Theses and Dissertations

Generative Adversarial Networks (GAN) learn to synthesize novel samples for a given data distribution. While GANs can train on diverse data of various modalities, the most successful use cases to date apply GANs to computer vision tasks. Despite significant advances in training algorithms and network architectures, GANs still struggle to consistently generate high-quality outputs after training. We present a series of papers that improve GAN output inference qualitatively and quantitatively. The first chapter, Alpha Model Domination, addresses a related subfield of Multiple Choice Learning, which -- like GANs -- aims to generate diverse sets of outputs. The next chapter, CoachGAN, …

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

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 …

Trace: A Differentiable Approach To Line-Level Stroke Recovery For Offline Handwritten Text, Taylor Neil Archibald

Theses and Dissertations

Stroke order and velocity are helpful features in the fields of signature verification, handwriting recognition, and handwriting synthesis. Recovering these features from offline handwritten text is a challenging and well-studied problem. We propose a new model called TRACE (Trajectory Recovery by an Adaptively-trained Convolutional Encoder). TRACE is a differentiable approach using a convolutional recurrent neural network (CRNN) to infer temporal stroke information from long lines of offline handwritten text with many characters. TRACE is perhaps the first system to be trained end-to-end on entire lines of text of arbitrary width and does not require the use of dynamic exemplars. Moreover, …

Road Map Generation And Feature Extraction Algorithms From Gps Trajectories And Trajectories Data Warehousing, Tariq Alsahfi

Computer Science and Engineering Dissertations - Archive

Advanced technologies in location acquisition allow us to track the movement of moving objects (people, planes, vehicles, animals, ships, ..) in geographical space. These technologies generate a vast amount of trajectory data (TD). Several applica- tions in different fields can utilize such trajectory data, for example, traffic control management, social behavior analysis, wildlife migrations and movements, ship tra- jectories, shoppers behavior in a mall, facial nerve trajectory, location-based services (LBS) and many others. Fortunately, there are now many trajectory data sets avail- able that collected from moving objects such as cars with enabled GPS devices. Two main challenges arise when …

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, …

Language-Driven Region Pointer Advancement For Controllable Image Captioning, Annika Lindh, Robert J. Ross, John D. Kelleher

Conference papers

Controllable Image Captioning is a recent sub-field in the multi-modal task of Image Captioning wherein constraints are placed on which regions in an image should be described in the generated natural language caption. This puts a stronger focus on producing more detailed descriptions, and opens the door for more end-user control over results. A vital component of the Controllable Image Captioning architecture is the mechanism that decides the timing of attending to each region through the advancement of a region pointer. In this paper, we propose a novel method for predicting the timing of region pointer advancement by treating the …

Deep Learning-Based, Passive Fault Tolerant Control Facilitated By A Taxonomy Of Cyber-Attack Effects, Dean C. Wardell

Theses and Dissertations

In the interest of improving the resilience of cyber-physical control systems to better operate in the presence of various cyber-attacks and/or faults, this dissertation presents a novel controller design based on deep-learning networks. This research lays out a controller design that does not rely on fault or cyber-attack detection. Being passive, the controller’s routine operating process is to take in data from the various components of the physical system, holistically assess the state of the physical system using deep-learning networks and decide the subsequent round of commands from the controller. This use of deep-learning methods in passive fault tolerant control …

Acquisition, Processing, And Analysis Of Video, Audio And Meteorological Data In Multi-Sensor Electronic Beehive Monitoring, Sarbajit Mukherjee

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

In recent years, a widespread decline has been seen in honey bee population and this is widely attributed to colony collapse disorder. Hence, it is of utmost importance that a system is designed to gather relevant information. This will allow for a deeper understanding of the possible reasons behind the above phenomenon to aid in the design of suitable countermeasures.

Electronic Beehive Monitoring is one such way of gathering critical information regarding a colony’s health and behavior without invasive beehive inspections. In this dissertation, we have presented an electronic beehive monitoring system called BeePi that can be placed on top …

A Hybrid Approach For Detecting Prerequisite Relations In Multi-Modal Food Recipes, Liangming Pan, Jingjing Chen, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Modeling the structure of culinary recipes is the core of recipe representation learning. Current approaches mostly focus on extracting the workflow graph from recipes based on text descriptions. Process images, which constitute an important part of cooking recipes, has rarely been investigated in recipe structure modeling. We study this recipe structure problem from a multi-modal learning perspective, by proposing a prerequisite tree to represent recipes with cooking images at a step-level granularity. We propose a simple-yet-effective two-stage framework to automatically construct the prerequisite tree for a recipe by (1) utilizing a trained classifier to detect pairwise prerequisite relations that fuses …