Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Artificial Intelligence and Robotics (42)
- Data Science (16)
- Engineering (11)
- Other Computer Sciences (8)
- Computer Engineering (7)
-
- Life Sciences (7)
- Graphics and Human Computer Interfaces (6)
- Software Engineering (6)
- Information Security (5)
- Social and Behavioral Sciences (5)
- Agriculture (4)
- Cybersecurity (4)
- Databases and Information Systems (4)
- Medicine and Health Sciences (4)
- Systems Architecture (4)
- Theory and Algorithms (4)
- Communication (3)
- Numerical Analysis and Scientific Computing (3)
- Social Media (3)
- Statistics and Probability (3)
- Art and Design (2)
- Arts and Humanities (2)
- Bioinformatics (2)
- Business (2)
- Electrical and Computer Engineering (2)
- Law (2)
- OS and Networks (2)
- Robotics (2)
- Keyword
-
- Machine learning (45)
- Deep learning (42)
- Computer vision (18)
- Neural networks (10)
- Reinforcement learning (9)
-
- Security (8)
- Artificial intelligence (6)
- Big data (6)
- Combinatorial testing (6)
- Data mining (6)
- Fact-checking (6)
- Graph neural networks (6)
- Privacy (6)
- Robotics (6)
- Classification (5)
- Clustering (5)
- Convolutional neural networks (5)
- Crowdsourcing (5)
- Drug discovery (5)
- MapReduce (5)
- Misinformation (5)
- Semi-supervised learning (5)
- Transfer learning (5)
- Twitter (5)
- Analysis (4)
- Android (4)
- Cloud computing (4)
- Deep Learning (4)
- Graph mining (4)
- Malware (4)
- Publication Year
- Publication
-
- Computer Science and Engineering Theses - Archive (365)
- Computer Science and Engineering Dissertations - Archive (271)
- Computer Science and Engineering Dissertations (7)
- 2025 Spring Honors Capstone Projects - Archive (6)
- Computer Science and Engineering Datasets - Archive (3)
-
- 2024 Fall Honors Capstone Projects - Archive (2)
- Computer Science and Engineering Student Research - Archive (2)
- 2024 Spring Honors Capstone Projects - Archive (1)
- 2025 Fall Honors Capstones Projects - Archive (1)
- Agriculture (1)
- Agriculture - Archive (1)
- Electrical Engineering Theses - Archive (1)
- Event-Based Vision - Archive (1)
- Information Systems & Operations Management Dissertations - Archive (1)
- Management Dissertations (1)
- Mavs Open Press Open Educational Resources (1)
- Physics Dissertations - Archive (1)
- Publication Type
- File Type
Articles 181 - 210 of 666
Full-Text Articles in Computer Sciences
Feature Selection And Data Reconstruction Via Robust And Flexible Learning Models, Di Ming
Feature Selection And Data Reconstruction Via Robust And Flexible Learning Models, Di Ming
Computer Science and Engineering Dissertations - Archive
Feature selection and data reconstruction are very important topics in machine learning area. In today's big data environment, many data could have high dimensions and come with noise, corruption, etc. Thus, we develop robust and flexible learning models so as to select the relevant features from the high-dimensional data spaces and reconstruct the original clean data from the corrupted input data more efficiently and more effectively. To resolve the inflexibility of the widely used class-shared feature selection methods such as L21-norm, we derive LASSO from probabilistic selection on ridge regression which provides an independent point of view from the usual …
Deep Representation Learning On Giga-Pixel Whole Slide Images, Xinliang Zhu
Deep Representation Learning On Giga-Pixel Whole Slide Images, Xinliang Zhu
Computer Science and Engineering Dissertations - Archive
I present my work towards solving the fundamental, challenging and valuable problem for automatically processing the giga-pixel level whole slide pathology images (WSIs): the representation of them. Specifically, I target on solving the combinations of three critical aspects of the problem: (1) it's not engineering feasible to directly fit them into existing convolutional neural networks because they are too large; (2) pre-trained parameters from other domains may not be effectively transferred to pathology images, and (3) both the image samples and annotations for those images are rarely available. To evaluate the effectiveness of the developed methods, I mainly focus on …
Learning Transferable Meta-Policies For Hierarchical Task Decomposition And Planning Composition, Predrag Djurdjevic
Learning Transferable Meta-Policies For Hierarchical Task Decomposition And Planning Composition, Predrag Djurdjevic
Computer Science and Engineering Dissertations - Archive
In real world scenarios where situated agents are faced with dynamic, high-dimensional, partially observable environments with action and reward uncertainty, the traditional states space Reinforcement Learning (RL) becomes easily prohibitively large for policy learning. In such scenarios, addressing the curse of dimensionality and eventual transfer to closely related tasks is one of the principal challenges and motivations for Hierarchical Reinforcement Learning (HRL). The prime appeal of hierarchal and particularly recursive approaches is in effective factored state, transition and reward representations which abstract out aspects that are not relevant to subtasks and allow potential transfer of skills which represent solutions to …
Semi-Supervised Deep Learning With Applications In Surgical Video Analysis And Bioinformatics, Sheng Wang
Semi-Supervised Deep Learning With Applications In Surgical Video Analysis And Bioinformatics, Sheng Wang
Computer Science and Engineering Dissertations - Archive
In the current era of big data, deep learning has been the state-of-the-art model for various applications. Image-based applications such as image classification, object detection, image segmentation, benefit most from deep learning networks. One reason for the successful applications of deep learning is that there are a large number of labeled training samples for the model to learn from. People are interested in reducing the cost of getting labeled training samples, and there are various research going on with unsupervised, semi-supervised, and self-supervised deep learning. The cost of health-related data is even higher. Labeling the surgical videos with tools being …
Efficient Network Design For High Dimensional Data, Xin Miao
Efficient Network Design For High Dimensional Data, Xin Miao
Computer Science and Engineering Dissertations - Archive
Due to the powerful feature representation capabilities, deep learning has became a powerful tool in the field of computer vision. Especially in the aspect of high-dimensional images, deep learning can achieve fast inference compared with most traditional methods. This paper focuses on how to design an efficient neural network and apply it to two high-dimensional images application, video facial landmarks detections and compressive imaging system. In this first part of this paper, we focus on landmarks detection for video facial images. Existing methods for facial landmarks detection mainly rely on cascaded regression. It is an indirect method and progressively estimates …
Learning Abstractions For Planning, Brian Charles Cook
Learning Abstractions For Planning, Brian Charles Cook
Computer Science and Engineering Dissertations - Archive
Planners for hard problems must exploit domain-specific structure to find solutions efficiently. Yet, hand-engineered solutions and optimizations are often expensive and difficult or impossible to adapt to other problems. This work applies automatic machine learning techniques to increase planner performance for specific problem domains and to learn useful abstract representations for planning. In particular, this dissertation develops methods to address important aspects of learning in planning in four different areas: State-of-the-art domain-independent classical planners utilize multiple search heuristics and decide how to allocate computational effort between heuristics prior to planning. This work presents a heuristic planning algorithm that uses a …
Special Topics In Natural Language Processing: Mwe Identification, Opinion Question Answering And Summarization, Aishwarya Ashok
Special Topics In Natural Language Processing: Mwe Identification, Opinion Question Answering And Summarization, Aishwarya Ashok
Computer Science and Engineering Dissertations - Archive
Natural Language Processing (NLP) is the use of computers for the analysis of text. The approaches used to solve problems in NLP has transitioned from human tagging to statistical methods and currently many of the approaches make use of techniques from Machine Learning (ML) and Artificial Intelligence (AI). Some of the text-based problems in NLP include question answering, summarization, and text-based recommendation systems. The amount of text data that is available is increasing by the day. With the growing size of text data, the research in NLP needs more sophisticated methods than traditional statistical methods. Current day approaches make use …
Parsing Code-Switched Taglish Language By Creating Constituents, Fadiah Qudah
Parsing Code-Switched Taglish Language By Creating Constituents, Fadiah Qudah
Computer Science and Engineering Theses - Archive
When extracting meaning from language, a common first step is to break down language into constituents, or words that work together as a unit. This task, known as parsing, typically follows a specific grammar in order decompose the language into its underlying structure composed of constituents. Difficulties with this grammar-based parsing occur, however, with real-world natural language due to its unstructured nature. Code-switching, the phenomenon of alternating between languages while communicating, further complicates this task by requiring us to parse based on two (or more) languages instead of one. In this thesis, a data-driven method to parse code-switched language into …
Approxml: Efficient Approximate Ad-Hoc Ml Models Through Materialization And Reuse, Faezeh Ghaderi
Approxml: Efficient Approximate Ad-Hoc Ml Models Through Materialization And Reuse, Faezeh Ghaderi
Computer Science and Engineering Theses - Archive
Machine Learning (ML) has become an essential tool in answering complex predictive analytic queries. Model building for large scale datasets is one of the most time-consuming parts of the data science pipeline. Often data scientists are willing to sacrifice some accuracy in order to speed up this process during the exploratory phase. In this report, we aim to demonstrate ApproxML, a system that efficiently constructs approximate ML models for new queries from previously constructed ML models using the concepts of model materialization and reuse. ApproxML supports a wide variety of ML models such as generalized linear models for supervised learning …
Detect Traffic Signs From Large Street View Images With Deep Learning, Zhifei Deng
Detect Traffic Signs From Large Street View Images With Deep Learning, Zhifei Deng
Computer Science and Engineering Theses - Archive
Autonomous driving is about to shaping the future of our life. Self-driving vehicles produced by Waymo or many other companies have demonstrated excellent driving capabilities on the road. However, accidents still happen. Correctly recognising the traffic signs, such as stop signs, is critical for a self-driving vehicle. Failing to recognise the traffic signs could lead to fatal accidents. Meanwhile, computer vision technology has made huge progress since the advent of deep learning, for example, image classification, object detection, and instance segmentation. Efforts have been made in developing faster and more accurate object detection methods. Faster R-CNN stands out as one …
Social Media Text Analysis Using Multi-Kernel Convolutional Neural Network, Anna Philips
Social Media Text Analysis Using Multi-Kernel Convolutional Neural Network, Anna Philips
Computer Science and Engineering Theses - Archive
Transportation planners and ride hailing platforms such as Uber and Lyft use their riders feedback to assess their services and monitor customer satisfaction. Social media websites such as Facebook, Instagram, LinkedIn and in particular Twitter provides a large dataset of micro-texts by users who regularly post to their social media accounts about their grievances with their ride experience. This data is often unorganized and intractable to process because of it’s extremely large size which is continuously increasing daily. In this project, we collected ride hailing service relevant text data from Twitter around New York and developed a novel Convolutional Neural …
Distributed Deep Neural Networks Training For Brain Imaging Applications, Sudheer Raja
Distributed Deep Neural Networks Training For Brain Imaging Applications, Sudheer Raja
Computer Science and Engineering Theses - Archive
Over the recent years, Deep Neural Networks (DNNs) have surpassed human-level intelligence in recognizing and interpreting complex patterns in data. Ever since the ImageNet competition in 2012, Deep Learning (DL) has become a promising approach for solving numerous problems in the field of Computer Science. However, the neuroscience community is not able to utilize the DL algorithms effectively because the brain imaging datasets are huge in terms of size, and the current sequential training techniques do not scale up well for such big datasets. Without the proper amount of training data, training DNN models to competitive accuracies is quite challenging. …
Comprehensive Study Of Generative Methods On Drug Discovery, Siyu Xiu
Comprehensive Study Of Generative Methods On Drug Discovery, Siyu Xiu
Computer Science and Engineering Theses - Archive
Observing the recent success of the deep learning (DL) technology in multiple life-changing application areas, e.g., autonomous driving, image/video search and discovery, natural language processing, etc., many new opportunities have presented themselves. One of the biggest ones lies in applying DL in accelerating the drug discovery, where millions of human lives could potentially be saved. However, applying DL into the drug discovery task turns out to be non-trivial. The most successful DL methods take fix-sized tensors/matrices, e.g., images, or sequences of tokens, e.g., sentences with variant numbers of words, as their inputs. However, none of these registers with the inputs …
Deduplication-Aware Page Cache In Linux Kernel For Improved Read Performance, Venkata Satya Ravi Kiran Boggavarapu
Deduplication-Aware Page Cache In Linux Kernel For Improved Read Performance, Venkata Satya Ravi Kiran Boggavarapu
Computer Science and Engineering Theses - Archive
The amount of data being produced and consumed is increasing every day. As a result, there can be a large amount of redundant data in the storage system. Storing and accessing these duplicate data unnecessarily consumes disk space and I/O bandwidth. Deduplication techniques are widely deployed to remove the redundancy. In particular, the deduplication solutions that work at the block level are proven to be effective. These solutions aim to effectively use disk space and write bandwidth by avoiding duplicate data writes to the storage. However, such a design might not help in improving the read performance, which is critical …
Use Of Word Embedding To Generate Similar Words And Misspellings For Training Purpose In Chatbot Development, Sanjay Thapa
Use Of Word Embedding To Generate Similar Words And Misspellings For Training Purpose In Chatbot Development, Sanjay Thapa
Computer Science and Engineering Theses - Archive
The advancement in the field of Natural Language Processing and Machine Learning has played a significant role in the huge improvement of conversational Artificial Intelligence (AI). The use of text-based conversation AI such as chatbots have increased significantly for the everyday purpose to communicate with real people for a variety of tasks. Chatbots are deployed in almost all popular messaging platforms and channels. The rise of chatbot development frameworks based on machine learning is helping to deploy chatbot easily and promptly. These chatbot development frameworks use machine learning and natural language understanding (NLU) to understand users' messages and intents and …
Hiding In Plain Sight? The Impact Of Face Recognition Services On Privacy, James Richard Ortega
Hiding In Plain Sight? The Impact Of Face Recognition Services On Privacy, James Richard Ortega
Computer Science and Engineering Theses - Archive
The public at large is increasingly concerned with privacy online. While the focus is on the data privately collected by platforms, there are also privacy concerns in the realm of public data. Seemingly innocuous information shared in public, on online platforms, can be pieced together to detrimentally affect one's privacy in unexpected ways. On YouTube there exists a rich public dataset for adversaries to analyze for the purposes of breaching privacy; particularly due to the intersection of location and facial data. The goal of this work is to characterize the privacy risks that exists on YouTube, and explore the viability …
Using Property-Based Testing, Weighted Grammar-Based Generators, And A Consensus Oracle To Test Browser Rendering Engines And To Reproduce Minimized Versions Of Existing Test Cases, Joel David Martin
Computer Science and Engineering Theses - Archive
Verifying that a web browser rendering engine correctly renders all valid web pages is challenging due to the size of the input space (valid web pages), the difficulty of determining correct rendering for any given web page (the test oracle problem), and the degree to which normal variation in browser rendering behavior can obscure other differences (fonts, bor- ders, input controls, etc). These challenges lead to manual human involvement during the testing process. We propose a new Property-Based Testing (PBT) approach that addresses these challenges in order to enable automated web browser render testing. Our approach is composed of the …
The Impact Of Toxic Replies On Twitter Conversations, Nazanin Salehabadi
The Impact Of Toxic Replies On Twitter Conversations, Nazanin Salehabadi
Computer Science and Engineering Theses - Archive
Social media has become an empowering agent for individual voices and freedom of expression. Yet, it can also serve as a breeding ground for hate speech. According to a Pew Research Center study, 41% of Americans have been personally subjected to harassing behavior online, 66% have witnessed these behaviors directed at others, and 18% have been subjected to particularly severe forms of harassment online, such as physical threats, harassment over a sustained period, sexual harassment, or stalking. Recently, many research studies have tried to understand online hate speech and its implications, focusing on detecting and characterizing hate speech. One limitation …
Performance Modeling And Resource Provisioning For Data-Intensive Applications, Zhongwei Li
Performance Modeling And Resource Provisioning For Data-Intensive Applications, Zhongwei Li
Computer Science and Engineering Theses - Archive
Performance evaluation and resource provisioning are two most critical factors to be considered for designers of distributed systems at modern warehouse data centers. The ever-increasing volumes of data in recent years have pushed many businesses to move their computing tasks to the Cloud, which offers many benefits including the low system management and maintenance costs and better scalability. As a result, most recent prominently emerging workloads are data-intensive, calling for scaling out the workload to a large number of servers for parallel processing. Questions can be asked as what factors impact the system scaling performance, and how to efficiently schedule …
Learning Robot Manipulation Tasks Via Observation, Michail Theofanidis
Learning Robot Manipulation Tasks Via Observation, Michail Theofanidis
Computer Science and Engineering Dissertations - Archive
The coexistence of humans and robots has been the aspiration of many scientific endeavors in the past century. Most anthropomorphic or industrial robots are highly articulated and complex machines, which are designed to carry out tasks that often involve the manipulation of physical objects. Traditionally, robots learn how to perform such tasks with the aid of a human programmer or operator. In this regard, the human acts as a teacher who provides a demonstration of a task. From the data of the demonstration, the robot must learn a state-action mapping that accomplishes the task. This state-action mapping is often addressed …
Feature Extraction In Noise-Diverse Environments For Human Activities Recognition Using Wi-Fi, Sheheryar Arshad
Feature Extraction In Noise-Diverse Environments For Human Activities Recognition Using Wi-Fi, Sheheryar Arshad
Computer Science and Engineering Dissertations - Archive
With the rapid development of 802.11 standard and Internet of Things (IoT) applications, Wi-Fi (IEEE 802.11) has emerged as the most widely used wireless communication technology. Wi-Fi based sensing has found widespread use cases involving activity recognition, indoor localization, design of smart spaces and in healthcare applications. This dissertation presents the study of human activities’ sensing and recognition using channel state information (CSI) of Wi-Fi. We highlight the limitations of existing methods and consequently design the frameworks for collecting stable CSI and monitoring different indoor and outdoor environments for human activities. Specifically, this dissertation provide means to define and extract …
Using Property-Based Testing, Weighted Grammar-Based Generators, And A Consensus Oracle To Test Browser Rendering Engines And To Reproduce Minimized Versions Of Existing Test Cases, Joel David Martin
Computer Science and Engineering Dissertations - Archive
Verifying that a web browser rendering engine correctly renders all valid web pages is challenging due to the size of the input space (valid web pages), the difficulty of determining correct rendering for any given web page (the test oracle problem), and the degree to which normal variation in browser rendering behavior can obscure other differences (fonts, bor- ders, input controls, etc). These challenges lead to manual human involvement during the testing process. We propose a new Property-Based Testing (PBT) approach that addresses these challenges in order to enable automated web browser render testing. Our approach is composed of the …
Towards Location Free Movement Recognition With Channel State Information, Chunhai Feng
Towards Location Free Movement Recognition With Channel State Information, Chunhai Feng
Computer Science and Engineering Dissertations - Archive
Channel state information based movement recognition has gathered immense attention over recent years. Different from traditional systems which usually require wearable sensors or surveillance cameras, many existing works achieved desirable performance with only wireless signals in various applications, including healthcare, security and Internet of Things, with different machine learning algorithms. However, it still remains many challenges to be solved. Particularly, the location dependent nature of channel state information is one of the most significant challenges remaining. Firstly, many previous researchers deploy and evaluate their systems with employing machine learning or deep neural networks. Because of the aforementioned challenge, the models …
Spatial Similarity Measures With Applications To Map Integration And Improving Accuracy Of Map Data Sets, Mousa Alhajlah Almotairi
Spatial Similarity Measures With Applications To Map Integration And Improving Accuracy Of Map Data Sets, Mousa Alhajlah Almotairi
Computer Science and Engineering Dissertations - Archive
These days we live in a digital era where most societies rely on applications that depend on digital data. One popular type of digital data that is the basis many of applications is spatial data. Road network maps are one of the spatial data sets that are available for many important applications. However, acquisition of Road Network maps is an expensive task in terms of cost and time, not to mention the maintenance and the updating costs on these spatial data sets. In addition, each Road network map is captured for specific applications such as: road navigation, topographic cartography for …
Automated Testing Of A Commercial Cyber-Physical System Development Tool Chain, Shafiul Azam Chowdhury
Automated Testing Of A Commercial Cyber-Physical System Development Tool Chain, Shafiul Azam Chowdhury
Computer Science and Engineering Dissertations - Archive
Rigorous validation of commercial cyber-physical system (CPS) tool chains (e.g., MATLAB/Simulink) through automated testing is of utmost importance since tool-chain generated artifacts are often deployed in safety-critical embedded hardware. Although automated differential testing through random program generation and equivalence modulo input (EMI)-based mutation has been well studied for procedural compiler testing, applying these techniques for Simulink, the widely used commercial CPS development tool pose unique challenges, which we explore in this series of work for the very first time. To better understand real-world CPS modeling and to automatically generate Simulink models similar to those crafted by engineers and researchers, we …
Think2act: Using Multimodal Data To Assess Human Cognitive And Physical Performance, Maher Abujelala
Think2act: Using Multimodal Data To Assess Human Cognitive And Physical Performance, Maher Abujelala
Computer Science and Engineering Dissertations - Archive
As computers become more advanced, affordable, and smaller in size, we start to use them in almost every aspect of our daily life. Nowadays, the use of computers is not just limited to accomplish work-related tasks. Instead, we use computers for education, entertainment, healthcare, and in many other areas to facilitate our daily life activities. From here, the Human-Computer Interaction (HCI) field emerged. HCI is a multidisciplinary field of study that focuses on utilizing computers and technology to interact with humans, improve their quality of life, and enhance their performance. The rapid advancements in other related research fields, such as …
Deep Representation Learning For Clustering And Domain Adaptation, Mohsen Kheirandishfard
Deep Representation Learning For Clustering And Domain Adaptation, Mohsen Kheirandishfard
Computer Science and Engineering Dissertations - Archive
Representation learning is a fundamental task in the area of machine learning which can significantly influence the performance of the algorithms used in various applications. The main goal of this task is to capture the relationships between the input data and learn feature representations that contain the most useful information of the original data. Such representations can be further leveraged in many machine learning applications such as clustering, natural language analysis, recommender systems, etc. In this dissertation, we first present a theoretical framework for solving a broad class of non-convex optimization problems. The proposed method is applicable to various tasks …
Performance Modeling And Resource Provisioning For Data-Intensive Applications, Zhongwei Li
Performance Modeling And Resource Provisioning For Data-Intensive Applications, Zhongwei Li
Computer Science and Engineering Dissertations - Archive
Performance evaluation and resource provisioning are two most critical factors to be considered for designers of distributed systems at modern warehouse data centers. The ever-increasing volumes of data in recent years have pushed many businesses to move their computing tasks to the Cloud, which offers many benefits including the low system management and maintenance costs and better scalability. As a result, most recent prominently emerging workloads are data-intensive, calling for scaling out the workload to a large number of servers for parallel processing. Questions can be asked as what factors impact the system scaling performance, and how to efficiently schedule …
Voice Controlled Accessibility And Testing Tool (Vcat), Nagendra Prasad Kasaghatta Ramachandra
Voice Controlled Accessibility And Testing Tool (Vcat), Nagendra Prasad Kasaghatta Ramachandra
Computer Science and Engineering Theses - Archive
Most current browser-based web applications and software engineering tools, such as test generators and management tools, are not accessible to users who cannot use a traditional input device, such as a mouse and/or a keyboard. To address this shortcoming, this research leverages recent speech-recognition advances to create a chrome browser extension that interprets voice inputs as web browser commands and executes those commands within the browser. As a result, the Voice Controlled Accessibility and Testing tool (VCAT) leverages the Chrome browser to achieve higher accessibility, with the capability to perform webpage navigation using voice commands. The tool is also capable …
Characterizing And Optimizing The Performance Of Virtualized Network Systems In The Cloud, Kun Suo
Characterizing And Optimizing The Performance Of Virtualized Network Systems In The Cloud, Kun Suo
Computer Science and Engineering Dissertations - Archive
To leverage the elastic resource allocation of cloud computing and enhance the service availability and productivity, numerous applications and businesses have been moved from the traditional data centers into the cloud during the past decade. Despite the benefits introduced by virtualization, such as high resource utilization, flexible resource management and operation cost reduction, it also incurs additional overhead, scheduling delays as well as semantic gaps among hardware, operating system and applications. These issues can cause non-negligible impact to the performance and quality-of-service (QoS) of the cloud applications, especially for I/O-intensive services. Meanwhile, the increasing scale and complexity of the cloud …