Digital Commons Network^™

Cross-Modal Food Retrieval: Learning A Joint Embedding Of Food Images And Recipes With Semantic Consistency And Attention Mechanism;, Hao Wang, Doyen Sahoo, Chenghao Liu, Ke Shu, Achananuparp Palakorn, Ee Peng Lim, Steven Hoi

Research Collection School Of Computing and Information Systems

Food retrieval is an important task to perform analysis of food-related information, where we are interested in retrieving relevant information about the queried food item such as ingredients, cooking instructions, etc. In this paper, we investigate cross-modal retrieval between food images and cooking recipes. The goal is to learn an embedding of images and recipes in a common feature space, such that the corresponding image-recipe embeddings lie close to one another. Two major challenges in addressing this problem are 1) large intra-variance and small inter-variance across cross-modal food data; and 2) difficulties in obtaining discriminative recipe representations. To address these …

Assessment And Diagnosis Of Human Colorectal And Ovarian Cancer Using Optical Imaging And Computer-Aided Diagnosis, Yifeng Zeng

McKelvey School of Engineering Graduate Student Theses & Dissertations

Tissue optical scattering has recently emerged as an important diagnosis parameter associated with early tumor development and progression. To characterize the differences between benign and malignant colorectal tissues, we have created an automated optical scattering coefficient mapping algorithm using an optical coherence tomography (OCT) system. A novel feature called the angular spectrum index quantifies the scattering coefficient distribution. In addition to scattering, subsurface morphological changes are also associated with the development of colorectal cancer. We have observed a specific mucosa structure indicating normal human colorectal tissue, and have developed a real-time pattern recognition neural network to localize this specific structure …

Zero-Bias Deep Learning Enabled Quick And Reliable Abnormality Detection In Iot, Yongxin Liu, Jian Wang, Jianqiang Li, Shuteng Niu, Houbing Song

Publications

Abnormality detection is essential to the performance of safety-critical and latency-constrained systems. However, as systems are becoming increasingly complicated with a large quantity of heterogeneous data, conventional statistical change point detection methods are becoming less effective and efficient. Although Deep Learning (DL) and Deep Neural Networks (DNNs) are increasingly employed to handle heterogeneous data, they still lack theoretic assurable performance and explainability. This paper integrates zero-bias DNN and Quickest Event Detection algorithms to provide a holistic framework for quick and reliable detection of both abnormalities and time-dependent abnormal events in Internet of Things (IoT).We first use the zero bias dense …

Deep Learning Based Sound Event Detection And Classification, Alireza Nasiri

Theses and Dissertations

Hearing sense has an important role in our daily lives. During the recent years, there has been many studies to transfer this capability to the computers. In this dissertation, we design and implement deep learning based algorithms to improve the ability of the computers in recognizing the different sound events.

In the first topic, we investigate sound event detection, which identifies the time boundaries of the sound events in addition to the type of the events. For sound event detection, we propose a new method, AudioMask, to benefit from the object-detection techniques in computer vision. In this method, we convert …

Pneumonia Radiograph Diagnosis Utilizing Deep Learning Network, Wesley O'Quinn

Honors College Theses

Pneumonia is a life-threatening respiratory disease caused by bacterial infection. The goal of this study is to develop an algorithm using Convolutional Neural Networks (CNNs) to detect visual signals for pneumonia in medical images and make a diagnosis. Although Pneumonia is prevalent, detection and diagnosis are challenging. The deep learning network AlexNet was utilized through transfer learning. A dataset consisting of 11,318 images was used for training, and a preliminary diagnosis accuracy of 72% was achieved.

Strategies In Botnet Detection And Privacy Preserving Machine Learning, Di Zhuang

USF Tampa Graduate Theses and Dissertations

Peer-to-peer (P2P) botnets have become one of the major threats in network security for serving as the infrastructure that responsible for various of cyber-crimes. Though a few existing work claimed to detect traditional botnets effectively, the problem of detecting P2P botnets involves more challenges. In this dissertation, we present two P2P botnet detection systems, PeerHunter and Enhanced PeerHunter. PeerHunter starts from a P2P hosts detection component. Then, it uses mutual contacts as the main feature to cluster bots into communities. Finally, it uses community behavior analysis to detect potential botnet communities and further identify bot candidates. Enhanced PeerHunter is an …

Exploring The Use Of Neural Transformers For Psycholinguistics, Antonio Laverghetta Jr.

USF Tampa Graduate Theses and Dissertations

Deep learning has the potential to help solve numerous problems in cognitive science andeducation, by providing us a way to model the cognitive profiles of individual people. If this were possible, it would allow us to design targeted tests and suggest specific remediation based on each individual’s needs. On the flip side, employing techniques from psychology can give us insight into the underlying skillsets neural networks have acquired during training, addressing the interpretability concern. This thesis explores these ideas in the context of transformer language models, which have achieved state-of-the-art results on virtually every natural language processing (NLP) task. First, …

Node Classification On Relational Graphs Using Deep-Rgcns, Nagasai Chandra

Master's Theses

Knowledge Graphs are fascinating concepts in machine learning as they can hold usefully structured information in the form of entities and their relations. Despite the valuable applications of such graphs, most knowledge bases remain incomplete. This missing information harms downstream applications such as information retrieval and opens a window for research in statistical relational learning tasks such as node classification and link prediction. This work proposes a deep learning framework based on existing relational convolutional (R-GCN) layers to learn on highly multi-relational data characteristic of realistic knowledge graphs for node property classification tasks. We propose a deep and improved variant, …

Limitations Of Transformers On Clinical Text Classification, Shang Gao, Mohammed Alawad, Michael Todd Young, John Gounley, Noah Schaefferkoetter, Hong-Jun Yoon, Xiao-Cheng Wu, Eric B. Durbin, Jennifer Doherty, Antoinette Stroup, Linda Coyle, Georgia D. Tourassi

Kentucky Cancer Registry Faculty Publications

Bidirectional Encoder Representations from Transformers (BERT) and BERT-based approaches are the current state-of-the-art in many natural language processing (NLP) tasks; however, their application to document classification on long clinical texts is limited. In this work, we introduce four methods to scale BERT, which by default can only handle input sequences up to approximately 400 words long, to perform document classification on clinical texts several thousand words long. We compare these methods against two much simpler architectures -- a word-level convolutional neural network and a hierarchical self-attention network -- and show that BERT often cannot beat these simpler baselines when classifying …

Bibliometric Survey On Multipurpose Face Recognition System Using Deep Learning, Priyanka Tupe-Waghmare, Rahul Raghvendra Joshi Prof.

Library Philosophy and Practice (e-journal)

Face recognition is a new concept coming up lately and flourishing in the field of network access and multimedia information systems. Since humans are at the focus of attention in variety of applications containing videos, the concept of face recognition is rising in popularity. Several areas involving network security, retrieval and indexing of the content, and compression of videos gain a lot of benefit from the face recognition systems and related technology. Controlling the access of the networks with the help of facial recognition not only makes it difficult for the hackers to steal the information but also makes the …

Ft-Cnn: Algorithm-Based Fault Tolerance For Convolutional Neural Networks, Kai Zhao, Sheng Di, Sihuan Li, Xin Liang, For Full List Of Authors, See Publisher's Website.

Computer Science Faculty Research & Creative Works

Convolutional neural networks (CNNs) are becoming more and more important for solving challenging and critical problems in many fields. CNN inference applications have been deployed in safety-critical systems, which may suffer from soft errors caused by high-energy particles, high temperature, or abnormal voltage. Of critical importance is ensuring the stability of the CNN inference process against soft errors. Traditional fault tolerance methods are not suitable for CNN inference because error-correcting code is unable to protect computational components, instruction duplication techniques incur high overhead, and existing algorithm-based fault tolerance (ABFT) techniques cannot protect all convolution implementations. In this paper, we focus …

Speech Enhancement Using Speech Synthesis Techniques, Soumi Maiti

Dissertations, Theses, and Capstone Projects

Traditional speech enhancement systems reduce noise by modifying the noisy signal to make it more like a clean signal, which suffers from two problems: under-suppression of noise and over-suppression of speech. These problems create distortions in enhanced speech and hurt the quality of the enhanced signal. We propose to utilize speech synthesis techniques for a higher quality speech enhancement system. Synthesizing clean speech based on the noisy signal could produce outputs that are both noise-free and high quality. We first show that we can replace the noisy speech with its clean resynthesis from a previously recorded clean speech dictionary from …

Source Localization With Machine Learning, Arjun Gupta

Electrical and Computer Engineering ETDs

Source localization with sensor arrays have found applications across domains beginning with radar and sonar, astronomy, acoustics, bio-medical devices and more recently in autonomous cars and adaptive communication systems. The knowledge of the spatial spectrum not only provide information about the source and interference but also assists in increasing signal integrity and avoid interference. This provides an added degree of freedom in the form of spatial diversity. This research investigates spatial spectrum estimation of waveforms from the signals sampled by arbitrarily distributed sensors. Conventional high resolution algorithms such as root-MuSiC fails to perform accurate source localization due to the reliance …

The U-Net-Based Active Learning Framework For Enhancing Cancer Immunotherapy, Vishwanshi Joshi

Theses, Dissertations and Capstones

Breast cancer is the most common cancer in the world. According to the U.S. Breast Cancer Statistics, about 281,000 new cases of invasive breast cancer are expected to be diagnosed in 2021 (Smith et al., 2019). The death rate of breast cancer is higher than any other cancer type. Early detection and treatment of breast cancer have been challenging over the last few decades. Meanwhile, deep learning algorithms using Convolutional Neural Networks to segment images have achieved considerable success in recent years. These algorithms have continued to assist in exploring the quantitative measurement of cancer cells in the tumor microenvironment. …

Artificial Intelligence Aided Receiver Design For Wireless Communication Systems, Wenjie Xu

Theses, Dissertations and Capstones

Physical layer (PHY) design in the wireless communication field realizes gratifying achievements in the past few decades, especially in the emerging cellular communication systems starting from the first generation to the fifth generation (5G). With the gradual increase in technical requirements of large data processing and end-to-end system optimization, introducing artificial intelligence (AI) in PHY design has cautiously become a trend. A deep neural network (DNN), one of the population techniques of AI, enables the utilization of its ‘learnable’ feature to handle big data and establish a global system model. In this thesis, we exploited this characteristic of DNN as …

Performance Of Deep Learning Synthetic Cts For Mr-Only Brain Radiation Therapy, Xiaoning Liu, Hajar Emami, Siamak P. Nejad-Davarani, Eric Morris, Lonni Schultz, Ming Dong, Carri K. Glide-Hurst

Public Health Sciences Articles

PURPOSE: To evaluate the dosimetric and image-guided radiation therapy (IGRT) performance of a novel generative adversarial network (GAN) generated synthetic CT (synCT) in the brain and compare its performance for clinical use including conventional brain radiotherapy, cranial stereotactic radiosurgery (SRS), planar, and volumetric IGRT.

METHODS AND MATERIALS: SynCT images for 12 brain cancer patients (6 SRS, 6 conventional) were generated from T1-weighted postgadolinium magnetic resonance (MR) images by applying a GAN model with a residual network (ResNet) generator and a convolutional neural network (CNN) with 5 convolutional layers as the discriminator that classified input images as real or synthetic. Following …

Computational Intelligent Impact Force Modeling And Monitoring In Hislo Conditions For Maximizing Surface Mining Efficiency, Safety, And Health, Danish Ali

Doctoral Dissertations

"Shovel-truck systems are the most widely employed excavation and material handling systems for surface mining operations. During this process, a high-impact shovel loading operation (HISLO) produces large forces that cause extreme whole body vibrations (WBV) that can severely affect the safety and health of haul truck operators. Previously developed solutions have failed to produce satisfactory results as the vibrations at the truck operator seat still exceed the “Extremely Uncomfortable Limits”. This study was a novel effort in developing deep learning-based solution to the HISLO problem.

This research study developed a rigorous mathematical model and a 3D virtual simulation model to …

Sensor Data Based Adaptive Models For Assembly Worker Training In Cyber Manufacturing, Md. Al-Amin

Doctoral Dissertations

“Production innovations are occurring faster than ever leading conventional production systems towards cyber manufacturing. Manufacturing workers thus need to frequently learn new methods and skills. In fast-changing, largely uncertain production systems, manufacturers with the ability to comprehend workers’ behavior and assess their operational performance in near real-time will achieve better performance than peers. Recognizing worker actions in near real-time while performing the assembly can serve this purpose. However, reliably recognizing the assembly actions performed by the workers is challenging, because the actions for assembly are complex and workers are not only heterogeneous but sensitive to the variation of the work …

Cascaded Deep Learning Network For Postearthquake Bridge Serviceability Assessment, Youjeong Jang

Electronic Theses and Dissertations

Damages assessment of bridges is important to derive immediate response after severe events to decide serviceability. Especially, past earthquakes have proven the vulnerability of bridges with insufficient detailing. Due to lack of a national and unified post-earthquake inspection procedure for bridges, conventional damage assessments are performed by sending professional personnel to the onsite, detecting visually and measuring the damage state. To get accurate and fast damage result of bridge condition is important to save not only lives but also costs.
There have been studies using image processing techniques to assess damage of bridge column without sending individual to onsite. Convolutional …

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), …

Scaling Up Exact Neural Network Compression By Relu Stability, Thiago Serra, Xin Yu, Abhinav Kumar, Srikumar Ramalingam

Faculty Conference Papers and Presentations

We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable. However, current approaches to determine the stability of neurons with Rectified Linear Unit (ReLU) activations require solving or finding a good approximation to multiple discrete optimization problems. In this work, we introduce an algorithm based on solving a single optimization problem to identify all stable neurons. Our approach is on median 183 times faster than the state-of-art method on CIFAR-10, which allows us to explore exact compression on deeper (5 x 100) and wider …

High Level Learning Using The Temporal Features Of Human Demonstrated Sequential Tasks, Madison Brandywine Clark-Turner

Doctoral Dissertations

Modelling human-led demonstrations of high-level sequential tasks is fundamental to a number of practical inference applications including vision-based policy learning and activity recognition. Demonstrations of these tasks are captured as videos with long durations and similar spatial contents. Learning from this data is challenging since inference cannot be conducted solely on spatial feature presence and must instead consider how spatial features play out across time. To be successful these temporal representations must generalize to variations in the duration of activities and be able to capture relationships between events expressed across the scale of an entire video.

Contemporary deep learning architectures …

Multi-Stream Longitudinal Data Analysis Using Deep Learning, Sajjad Fouladvand

Theses and Dissertations--Computer Science

Longitudinal healthcare data encompasses all tasks where patients information are collected at multiple follow-up times. Analyzing this data is critical in addressing many real world problems in healthcare such as disease prediction and prevention. In this thesis, technical challenges in analyzing longitudinal administrative claims data are addressed and novel deep learning based models are proposed for multi-stream data analysis and disease prediction tasks. These algorithms and frameworks are assessed mainly on substance use disorders prediction tasks and specifically designed to tackled these disorders. Substance use disorder is a public health crisis costing the US an estimated $740 billion annually in …

Affordance Learning For Visual-Semantic Perception, Chau Nguyen Duc Minh

Theses: Doctorates and Masters

Affordance Learning is linked to the study of interactions between robots and objects, including how robots perceive objects by scene understanding. This area has been popular in the Psychology, which has recently come to influence Computer Vision. In this way, Computer Vision has borrowed the concept of affordance from Psychology in order to develop Visual-Semantic recognition systems, and to develop the capabilities of robots to interact with objects, in particular. However, existing systems of Affordance Learning are still limited to detecting and segmenting object affordances, which is called Affordance Segmentation. Further, these systems are not designed to develop specific abilities …

A New Distributed Anomaly Detection Approach For Log Ids Management Based Ondeep Learning, Murat Koca, Muhammed Ali̇ Aydin, Ahmet Sertbaş, Abdül Hali̇m Zai̇m

Turkish Journal of Electrical Engineering and Computer Sciences

Today, with the rapid increase of data, the security of big data has become more important than ever for managers. However, traditional infrastructure systems cannot cope with increasingly big data that is created like an avalanche. In addition, as the existing database systems increase licensing costs per transaction, organizations using information technologies are shifting to free and open source solutions. For this reason, we propose an anomaly attack detection model on Apache Hadoop distributed file system (HDFS), which stands out in open source big data analytics, and Apache Spark, which stands out with its speed performance in analysis to reduce …

Improving A Network Intrusion Detection System’S Efficiency Using Model-Based Data Augmentation, Vinicius Waterkemper Lodetti

Dissertations

A network intrusion detection system (NIDS) is one important element to mitigate cybersecurity risks, the NIDS allow for detecting anomalies in a network which may be a cyberattack to a corporate network environment. A NIDS can be seen as a classification problem where the ultimate goal is to distinguish between malicious traffic among a majority of benign traffic. Researches on NIDS are often performed using outdated datasets that don’t represent the actual cyberspace. Datasets such as the CICIDS2018 address this gap by being generated from attacks and an infrastructure that reflects an up-to-date scenario.

A problem may arise when machine …

Improving Space Efficiency Of Deep Neural Networks, Aliakbar Panahi

Theses and Dissertations

Language models employ a very large number of trainable parameters. Despite being highly overparameterized, these networks often achieve good out-of-sample test performance on the original task and easily fine-tune to related tasks. Recent observations involving, for example, intrinsic dimension of the objective landscape and the lottery ticket hypothesis, indicate that often training actively involves only a small fraction of the parameter space. Thus, a question remains how large a parameter space needs to be in the first place — the evidence from recent work on model compression, parameter sharing, factorized representations, and knowledge distillation increasingly shows that models can be …

Visualization For Solving Non-Image Problems And Saliency Mapping, Divya Chandrika Kalla

All Master's Theses

High-dimensional data play an important role in knowledge discovery and data science. Integration of visualization, visual analytics, machine learning (ML), and data mining (DM) are the key aspects of data science research for high-dimensional data. This thesis is to explore the efficiency of a new algorithm to convert non-images data into raster images by visualizing data using heatmap in the collocated paired coordinates (CPC). These images are called the CPC-R images and the algorithm that produces them is called the CPC-R algorithm. Powerful deep learning methods open an opportunity to solve non-image ML/DM problems by transforming non-image ML problems into …

On Studying Distributed Machine Learning, Simeon Eberz

Senior Honors Theses

The Internet of Things (IoT) is utilizing Deep Learning (DL) for applications such as voice or image recognition. Processing data for DL directly on IoT edge devices reduces latency and increases privacy. To overcome the resource constraints of IoT edge devices, the computation for DL inference is distributed between a cluster of several devices. This paper explores DL, IoT networks, and a novel framework for distributed processing of DL in IoT clusters. The aim is to facilitate and simplify deployment, testing, and study of a distributed DL system, even without physical devices. The contributions of this paper are a deployment …

Multi-Branch Gabor Wavelet Layers For Pedestrian Attribute Recognition, Imran N. Junejo

All Works

CCBYNCND Surveillance cameras are everywhere, keeping an eye on pedestrians as they navigate through a scene. With this context, our paper addresses the problem of pedestrian attribute recognition (PAR). This problem entails recognizing attributes such as age-group, clothing style, accessories, footwear style etc. This is a multi-label problem and challenging even for human observers. The problem has rightly attracted attention recently from the computer vision community. In this paper, we adopt trainable Gabor wavelets (TGW) layers and use it with a convolution neural network (CNN). Whereas other researchers are using fixed Gabor filters with the CNN, the proposed layers are …