Open Access. Powered by Scholars. Published by Universities.®
![Digital Commons Network](http://assets.bepress.com/20200205/img/dcn/DCsunburst.png)
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- University for Business and Technology in Kosovo (88)
- San Jose State University (85)
- Chulalongkorn University (65)
- Walden University (54)
- Nova Southeastern University (37)
-
- University of Central Florida (35)
- University of South Florida (27)
- Wright State University (26)
- California Polytechnic State University, San Luis Obispo (25)
- University of Massachusetts Amherst (25)
- University of Nevada, Las Vegas (22)
- Western University (22)
- Old Dominion University (21)
- Air Force Institute of Technology (20)
- Wayne State University (19)
- Florida Institute of Technology (18)
- University of Wisconsin Milwaukee (18)
- University of Mississippi (16)
- West Virginia University (16)
- University of Arkansas, Fayetteville (15)
- Washington University in St. Louis (15)
- Brigham Young University (14)
- New Jersey Institute of Technology (14)
- Portland State University (14)
- Singapore Management University (13)
- The University of Akron (13)
- University of Kentucky (13)
- University of South Carolina (13)
- Missouri University of Science and Technology (12)
- Dartmouth College (11)
- Keyword
-
- Machine learning (70)
- Machine Learning (47)
- Deep learning (43)
- Computer Science (35)
- Cybersecurity (26)
-
- Deep Learning (26)
- Department of Computer Science and Engineering (26)
- Computer science (17)
- Security (17)
- Computer vision (16)
- Artificial intelligence (14)
- Artificial Intelligence (13)
- Blockchain (13)
- Classification (12)
- Data mining (12)
- Center_CCR (11)
- Internet of Things (11)
- Natural language processing (11)
- Social media (11)
- Natural Language Processing (10)
- Computer Engineering (9)
- Information Technology (9)
- Privacy (9)
- Neural networks (8)
- CNNs (7)
- Data Mining (7)
- Information technology (7)
- Optimization (7)
- Reinforcement learning (7)
- Robotics (7)
- Publication
-
- Theses and Dissertations (186)
- Master's Projects (85)
- Electronic Theses and Dissertations (67)
- Chulalongkorn University Theses and Dissertations (Chula ETD) (65)
- Walden Dissertations and Doctoral Studies (54)
-
- CCE Theses and Dissertations (37)
- Doctoral Dissertations (32)
- USF Tampa Graduate Theses and Dissertations (27)
- Browse all Theses and Dissertations (26)
- Dissertations (24)
- Electronic Thesis and Dissertation Repository (22)
- UNLV Theses, Dissertations, Professional Papers, and Capstones (22)
- Master's Theses (21)
- Honors Theses (20)
- Graduate Theses, Dissertations, and Problem Reports (16)
- Wayne State University Dissertations (16)
- Dissertations and Theses (14)
- Dissertations and Theses Collection (Open Access) (13)
- McKelvey School of Engineering Theses & Dissertations (13)
- Williams Honors College, Honors Research Projects (13)
- Graduate Theses and Dissertations (11)
- Boise State University Theses and Dissertations (10)
- Masters Theses & Doctoral Dissertations (10)
- Theses and Dissertations--Computer Science (10)
- All Graduate Theses and Dissertations, Spring 1920 to Summer 2023 (9)
- Dartmouth College Undergraduate Theses (9)
- Dissertations, Theses, and Capstone Projects (8)
- Graduate Research Theses & Dissertations (8)
- ICT (8)
- Legacy Theses & Dissertations (2009 - 2024) (8)
Articles 31 - 60 of 1109
Full-Text Articles in Physical Sciences and Mathematics
Local Radiance, Scott Peter Britell
Local Radiance, Scott Peter Britell
Dissertations and Theses
Recent years have seen a proliferation of web applications based on content management systems (CMS). Using a CMS, non-technical content authors are able to define custom content types to support their needs. These content type names and the attribute names in each content type are typically domain-specific and meaningful to the content authors. The ability of a CMS to support a multitude of content types allows for endless creation and customization but also leads to a large amount of heterogeneity within a single application. While this meaningful heterogeneity is beneficial, it introduces the problem of how to write reusable functionality …
Grounding Size Predictions For Answer Set Programs, Nicholas Hippen
Grounding Size Predictions For Answer Set Programs, Nicholas Hippen
Student Work
Answer set programming is a declarative programming paradigm geared towards solving difficult combinatorial search problems. Logic programs under answer set semantics can typically be written in many different ways while still encoding the same problem. These different versions of the program may result in diverse performances. Unfortunately, it is not always easy to identify which version of the program performs the best, requiring expert knowledge on both answer set processing and the problem domain. More so, the best version to use may even vary depending on the problem instance. One measure that has been shown to correlate with performance is …
A Longitudinal Study Of Mammograms Utilizing The Automated Wavelet Transform Modulus Maxima Method, Brian C. Toner
A Longitudinal Study Of Mammograms Utilizing The Automated Wavelet Transform Modulus Maxima Method, Brian C. Toner
Electronic Theses and Dissertations
Breast cancer is a disease which predominatly affects women. About 1 in 8 women are diagnosed with breast cancer during their lifetime. Early detection is key to increasing the survival rate of breast cancer patients since the longer the tumor goes undetected, the more deadly it can become. The modern approach for diagnosing breast cancer relies on a combination of self-breast exams and mammography to detect the formation of tumors. However, this approach only accounts for tumors which are either detectable by touch or are large enough to be observed during a screening mammogram. For some individuals, by the time …
Image Encryption And Stegenography Based On Computational Single Pixel Imaging, Hossein Ghanbari Ghalehjoughi
Image Encryption And Stegenography Based On Computational Single Pixel Imaging, Hossein Ghanbari Ghalehjoughi
Theses and Dissertations
Multiple layers of information security are introduced based on computational ghost imaging (CGI). We show, in the first step, that it is possible to design a very reliable image encryption scheme using 3D computational ghost imaging with two single-pixel detectors sending data through two channels. Through the Normalized Root Mean Square scale, it is then shown that a further level of security can be achieved by merging data-carrying channels into one and using a coded order for their placement in the sequence of bucket data carried by the single channel. Yet another layer of security is introduced through hiding the …
Escape Puzzler, Shane Robertson
Escape Puzzler, Shane Robertson
Masters Theses & Doctoral Dissertations
This project is a systems design project. The goal of the project was to complete an online game for the purpose of entertaining an end-user. There is also additional research potential with analyzing the end-user behavior. This project showcases various skills learned at Dakota State University. This project required systems analysis, research of information technologies, database design, and project management.
About 50% of the planning phase was dedicated to scanning the IT industry for various technologies. We researched web hosting providers that would support the technologies we wanted to use. Also, a survey of available game engines was conducted. Additionally, …
A Machine Learning Assessment To Predict The Sediment Transport Rate Under Oscillating Sheet Flow Conditions, Huy Vu
Senior Honors Theses
The two-phase flow approach has been the conventional method designed to study the sediment transport rate. Due to the complexity of sediment transport, the precisely numerical models computed from that approach require initial assumptions and, as a result, may not yield accurate output for all conditions. This research work proposes that Machine Learning algorithms can be an alternative way to predict the processes of sediment transport in two-dimensional directions under oscillating sheet flow conditions, by utilizing the available dataset of the SedFoam multidimensional two-phase model. The assessment utilized linear regression and gradient boosting algorithm to analyze the lowest average mean …
Zhvillimi I Ueb Aplikacionit Për Menaxhimin E Qendrave Të Karrierës: Ubt Campus, Elhame Krasniqi
Zhvillimi I Ueb Aplikacionit Për Menaxhimin E Qendrave Të Karrierës: Ubt Campus, Elhame Krasniqi
Theses and Dissertations
Ueb aplikacionet janë bërë pjesë e rëndësishme e bizneseve dhe institucioneve në përgjithësi pasi janë duke mundësuar shkëmbim dhe menaxhim të informacionit nga të gjitha vendet ku do që ndodhemi, rëndësia e ueb aplikacioneve responsive është një mundësi e mirë për tu përshtatur pajisjeve të ndryshme. Qëllimi i këtij studimi është të ofrojmë njohuri shtesë rreth praktikimit të këtyre aplikacioneve nga institucionet e arsimit të lartë, më saktësisht se si këto ueb aplikacioneve do të mund t’iu ofrojnë studenteve një ambient më të mirë për komunikim me njeri tjetrin e deri tek menaxhimi më i mirë i qendrave të karrierës …
Dizajnimi I Web Faqës Së Shpedicionit “Vjosa”, Fitore Bajrami
Dizajnimi I Web Faqës Së Shpedicionit “Vjosa”, Fitore Bajrami
Theses and Dissertations
Në këtë temë diplome do të trajtohet krijimi dhe dizajnimi i një Web faqeje të Agjensionit Doganor (shpedicioni) “VJOSA”.
Krijimi i Web faqes është bërë me gjuhët e shënjimit (markup language) siç janë HTML dhe JavaScript po ashtu edhe me programet e Adobe si Photoshop dhe Dreamweaver dhe duke i kushtuar shumë rëndësi dizajnit të Web-it.
Në kapitullin e fundit do të prezentojmë Web faqen e Shpedicionit Vjosa ku demonstrohen disa parime të cilat duhet t’i ketë nje web faqe për të tërhequr vizitorët siç janë: lehtësia për të naviguar, përmbajtja e mirë, informacione relevante dhe të sakta, funksione te …
Privatësia Ne Sistemet Rekomanduese, Krist Domgjoni
Privatësia Ne Sistemet Rekomanduese, Krist Domgjoni
Theses and Dissertations
Sistemet rekomanduese janë shumë të përdorshme në ditet e sotme. Ato përdoren në internet për të ndihmuar një shfrytëzues të gjej një produkt të deshiruar në kohë sa më të shpejtë. SR pothuajse gjenden në çdo faqe të internetit, sidomos në kompanitë e mëdha siç janë: Facebook, eBay, Amazon, NetFlix etj. Në raste konkrete këto sisteme ndihmojnë që përdoruesi të gjejë një libër, film, artikull, produkt me preferenca të tij, poashtu në rrjetet sociale përdoren për të takuar shokë që kanë interesa të njejta në fusha të ndryshme. Këto kompani I përdorin sistemet rekomanduese sepse sjellin përfitime marramendëse në kohë …
Efektet E Digjitalizimit Të Shërbimeve Publike Te Bizneset - Rast Studimi Komuna E Ferizajit, Ardit Mehmeti
Efektet E Digjitalizimit Të Shërbimeve Publike Te Bizneset - Rast Studimi Komuna E Ferizajit, Ardit Mehmeti
Theses and Dissertations
Zhvillimi dhe përdorimi i TIK-ut (Teknologjia e Informatave dhe Komunikimit) rezultoi me krijimin e Shoqërisë Informative, në epiqendrën e së cilës është roli i informatave në shoqërinë e sotme. Ky zhvillim aq i hovshëm ka ndikuar në masë të madhe edhe në marrëdhëniet në mes të institucioneve dhe komunitetit të biznesit. Biznesi elektronik është forma më bashkohore e organizimit e cila në masë të madhe varet nga përdorimi i teknologjisë informatike, përkatësisht përdorimi i këtyre aplikimeve, sistemeve apo platformave. TIK ka lehtësuar të bërit biznes duke zgjeruar me lehtë tregun, duke ulur kostot e shpenzimeve, kursimin e kohës, duke ngritur …
C# Implementimi I Capsule Network Në Detektimin E Objekteve Në Imazhe, Bashkim Salihu
C# Implementimi I Capsule Network Në Detektimin E Objekteve Në Imazhe, Bashkim Salihu
Theses and Dissertations
Rrjeti me kapsula apo CapsNet është një qasje e re dhe interesante për zgjidhjen e problemeve në Computer Vision. Me publikimet e fundit është vërtetuar se kjo qasje e re është e saktë në detektimin e objekteve edhe nëse ato objekte janë të shtrembëruara apo pamja është prej një këndi tjetër. Implementimi i CapsNet është realizuar në shumicën e gjuhëve programuese si Python, R, Java etj.
Në këtë temë është bërë implementimi në C# duke përdorur Microsoft Cognitive Toolkit (CNTK), si vegël per krijimin e modelit dhe trajnimin e tij. Rezultatet e fituara pas implementimit na tregojnë se implementimi në …
Arkitektura E Mikroshërbimeve Duke Perdorur .Net Core Dhe Reactjs, Gurakuq Krasniqi
Arkitektura E Mikroshërbimeve Duke Perdorur .Net Core Dhe Reactjs, Gurakuq Krasniqi
Theses and Dissertations
Në këtë punim diplome do të trajtohet implementimi i arkitekturës së mikroshërbimeve duke përdorur teknologjitë më bashkëkohore si .NET Core dhe React duke u bazuar në sistemin për menaxhimin e temës së diplomës. Mënyra e dizajnimit të arkitekturës softuerike ka evoluar që nga fillimi i përdorimit e deri në ditët e sotme dhe si rezultat i evoluconit kemi dizajne të ndryshme, ku secila nga to përdoret varësisht nga specifikat e sistemit dhe kërkesat që ato i përshtaten në mënyrën më efektive. Qëllimi kryesor i këtij punimi të diplomës është shtjellimi i realizimit dhe implementimit të sistemit për menaxhimin e temave …
Analiza E “Student Response System” Dhe Impakti I Tyre Në Ngritjen E Ndërveprimit Brenda Klasës, Kimete Haxhiu
Analiza E “Student Response System” Dhe Impakti I Tyre Në Ngritjen E Ndërveprimit Brenda Klasës, Kimete Haxhiu
Theses and Dissertations
Involvimi i teknologjisë po bëhet një komponentë thelbësore e klasës moderne dhe studentët kanë nevojë për mjete të tilla për të rritur interaktivitetin dhe të nxënit e tyre. Student Response Systems apo SRS, kujdesen pikërisht për këtë nevojë dhe përfaqësojnë disa nga teknologjitë më të mira dhe më të reja të arsimit që gjenden sot. Student Response System lejon mësimdhënësit të parashtrojnë pyetje ose të trajtojnë një problem në klasë, ku përmes tyre studentët japin përgjigjet e tyre në një pajisje dhe menjëherë grumbullohen përgjigjet e tyre për mësimdhënësin. Kjo ofron një mbështetje për procesin mësimor, duke marrë parasyshë që …
Zhvillimi I Sistemit Për Monitorim Të Ardhjes Dhe Largimit Nga Puna - Bazuar Në Java Sockets, Redon Bejtullahu
Zhvillimi I Sistemit Për Monitorim Të Ardhjes Dhe Largimit Nga Puna - Bazuar Në Java Sockets, Redon Bejtullahu
Theses and Dissertations
Sistemet për monitorimin e ardhjes dhe largimit nga puna bëjnë monitorimin e saktë dhe preciz të kohës së qëndrimit në orar të punës. Sistemet mund të gjenerojnë statistika komplekse rreth monitorimit të aktivitetit të punëtorit. Fokusi i zhvillimit të një sistemi të tillë është kontrolli i vijueshmërisë së punëtorëve në punë duke përfshirë largimet e hershme nga puna dhe tej zgjatjet e pauzave. Sistemi i monitorimit është i ndarë në dy pjesë atë administrative dhe pjesa raportuese, pjesa administrative kontrollon të gjithë sistemin dhe është përgjegjëse për monitorimin e tij, ndërsa pjesa raportuese përbëhet nga pajisja e cila bartet nga …
Employing Earth Observations And Artificial Intelligence To Address Key Global Environmental Challenges In Service Of The Sdgs, Wenzhao Li
Computational and Data Sciences (PhD) Dissertations
Earth Observation (EO) data provides the capability to integrate data from multiple sources and helps to produce more relevant, frequent, and accurate information about complex processes. EO, empowered by methodologies from Artificial Intelligence (AI), supports various aspects of the UN’s Sustainable Development Goals (SDGs). This dissertation presents author’s major studies using EO to fill in knowledge gaps and develop methodologies and cloud-based applications in selected SDGs, including SDG 6 (Clean Water and Sanitation), SDG 11 (Sustainable Cities and Communities), SDG 14 (Life below Water) and SDG 15 (Life on Land). For SDG 6, the study focuses on spatiotemporal water recharge …
Benchmarking Applicability Of Cryptographic Wireless Communication Over Arduino Platforms, Carolina Vázquez Torres
Benchmarking Applicability Of Cryptographic Wireless Communication Over Arduino Platforms, Carolina Vázquez Torres
University Honors Program Senior Projects
The spaces around us are becoming equipped with devices and appliances that collect data from their surroundings and react accordingly to provide smarter networks where they are interconnected and able to communicate with one another. These smart networks of devices and appliances along with the applications that utilize them build smart spaces known as Internet of Things (IoT). With the on growing popularity of such smart devices (e.g., smart cars, watches, home-security systems) and IoT, the need for securing these environments increases. The smart devices around us can collect private and personal information, and the challenge lies in maintaining the …
Cloud Based Iot Architecture, Nathan Roehl
Cloud Based Iot Architecture, Nathan Roehl
Theses and Dissertations
The Internet of Things (IoT) and cloud computing have grown in popularity over the past decade as the internet becomes faster and more ubiquitous. Cloud platforms are well suited to handle IoT systems as they are accessible and resilient, and they provide a scalable solution to store and analyze large amounts of IoT data. IoT applications are complex software systems and software developers need to have a thorough understanding of the capabilities, limitations, architecture, and design patterns of cloud platforms and cloud-based IoT tools to build an efficient, maintainable, and customizable IoT application. As the IoT landscape is constantly changing, …
Social Groups Characterization And Dynamics: A Network Science Approach, Josemar Faustino Da Cruz
Social Groups Characterization And Dynamics: A Network Science Approach, Josemar Faustino Da Cruz
Theses and Dissertations
Over the course of our lives, we tend to transition through many social groups. From an early age, our first social group is our family, then we have our schoolmates, later in life, our coworkers, and likely another family. As we move from one group to another, we embed ourselves in the dynamics of social groups’ losses and gains of new members. These dynamics are a complex system of interactions, which at scale, form the structural basis of our societies. In many years of sociological research, the details of social group interactions remained poorly understood. Certainly, not because of lack …
Incorporating Word Order Explicitly In Glove Word Embedding, Brandon Cox
Incorporating Word Order Explicitly In Glove Word Embedding, Brandon Cox
Computer Science and Computer Engineering Undergraduate Honors Theses
Word embedding is the process of representing words from a corpus of text as real number vectors. These vectors are often derived from frequency statistics from the source corpus. In the GloVe model as proposed by Pennington et al., these vectors are generated using a word-word cooccurrence matrix. However, the GloVe model fails to explicitly take into account the order in which words appear within the contexts of other words. In this paper, multiple methods of incorporating word order in GloVe word embeddings are proposed. The most successful method involves directly concatenating several word vector matrices for each position in …
Informing Field Management Decisions To Enhance Alfalfa Seed Production Using Remote Sensing, Thomas V. Van Der Weide
Informing Field Management Decisions To Enhance Alfalfa Seed Production Using Remote Sensing, Thomas V. Van Der Weide
Boise State University Theses and Dissertations
The development rate of alfalfa seed crop depends on both environmental conditions and management decisions. Crop management decisions, such as determining when to release pollinators to optimize pollination, can be informed by the identification of plant development stages from remote sensing data. I first identify what electromagnetic wavelengths are sensitive to alfalfa plant development stages using hyperspectral data. A Random Forest regression is used to determine the best Vegetation Index (VI) to monitor how much of the plant is covered in flower. The results indicate that Blue, Green, and Near-Infrared are the important electromagnetic wavelengths for the VI. Imagery collected …
Multilingual Information Retrieval: A Representation Building Perspective, Ion Madrazo
Multilingual Information Retrieval: A Representation Building Perspective, Ion Madrazo
Boise State University Theses and Dissertations
Information Retrieval (IR) has changed the way we access digital resources and satisfy our daily information needs. Popular IR tools like Search Engines, Recommendation Systems, and Automatic Question Answering sites, act as a deterrent for information overload while fostering (at least in theory) the democratization of access to resources. Yet, in their majority, IR tools are built with a traditional user in mind. This causes users who deviate from the norm, e.g., users with low educational background, visually-impaired users, or users who speak different languages, to be undeserved and thus struggle to find the information they require. In this manuscript, …
Falcon: Framework For Anomaly Detection In Industrial Control Systems, Subin Sapkota
Falcon: Framework For Anomaly Detection In Industrial Control Systems, Subin Sapkota
Boise State University Theses and Dissertations
Industrial Control Systems (ICS) are used to control physical processes in the nation's critical infrastructures. They are composed of subsystems that control physical processes by analyzing the information received from the sensors. Based on the state of the process, the controller issues control commands to the actuators. These systems are utilized in a wide variety of operations such as water treatment plants, power, and manufacturing, etc. While the safety and security of these systems are of high concern, recent reports have shown an increase in targeted attacks that are aimed at manipulating the physical processes to cause catastrophic consequences. This …
When Keystroke Meets Password: Attacks And Defenses, Ximing Liu
When Keystroke Meets Password: Attacks And Defenses, Ximing Liu
Dissertations and Theses Collection (Open Access)
Password is a prevalent means used for user authentication in pervasive computing environments since it is simple to be deployed and convenient to use. However, the use of password has intrinsic problems due to the involvement of keystroke. Keystroke behaviors may emit various side-channel information, including timing, acoustic, and visual information, which can be easily collected by an adversary and leveraged for the keystroke inference. On the other hand, those keystroke-related information can also be used to protect a user's credentials via two-factor authentication and biometrics authentication schemes. This dissertation focuses on investigating the PIN inference due to the side-channel …
Multimodal Mobile Sensing Systems For Physiological And Psychological Assessment, Nguyen Phan Sinh Huynh
Multimodal Mobile Sensing Systems For Physiological And Psychological Assessment, Nguyen Phan Sinh Huynh
Dissertations and Theses Collection (Open Access)
Sensing systems for monitoring physiological and psychological states have been studied extensively in both academic and industry research for different applications across various domains. However, most of the studies have been done in the lab environment with controlled and complicated sensor setup, which is only suitable for serious healthcare applications in which the obtrusiveness and immobility can be compromised in a trade-off for accurate clinical screening or diagnosing. The recent substantial development of mobile devices with embedded miniaturized sensors are now allowing new opportunities to adapt and develop such sensing systems in the mobile context. The ability to sense physiological …
An Implementation Of Fully Convolutional Network For Surface Mesh Segmentation, Taiyu Zhang
An Implementation Of Fully Convolutional Network For Surface Mesh Segmentation, Taiyu Zhang
Theses and Dissertations
This thesis presents an implementation of a 3-Dimensional triangular surface mesh segmentation architecture named Shape Fully Convolutional Network, which is proposed by Pengyu Wang and Yuan Gan in 2018. They designed a deep neural network that has a similar architecture as the Fully Convolutional Network, which provides a good segmentation result for 2D images, on 3D triangular surface meshes. In their implementation, 3D surface meshes are represented as graph structures to feed the network. There are three main barriers when applying the Fully Convolutional Network to graph-based data structures.
• First, the pooling operation is much harder to apply to …
Deep Reinforcement Learning Pairs Trading, Andrew Brim
Deep Reinforcement Learning Pairs Trading, Andrew Brim
All Graduate Plan B and other Reports, Spring 1920 to Spring 2023
This research applies a deep reinforcement learning technique, Deep Q-network, to a stock market pairs trading strategy for profit. Artificial intelligent methods have long since been applied to optimize trading strategies. This work trains and tests a DQN to trade co-integrated stock market prices, in a pairs trading strategy. The results demonstrate the DQN is able to consistently produce positive returns when executing a pairs trading strategy.
Plug-And-Play Web Services, Arihant Jain
Plug-And-Play Web Services, Arihant Jain
All Graduate Theses and Dissertations, Spring 1920 to Summer 2023
The goal of this research is to make it easier to design and create web services for relational databases. A web service is a software service for providing data over computer networks. Web services provide data endpoints for many web applications. We adopt a plug-and-play approach for web service creation whereby a designer constructs a “plug,” which is a simple specification of the output produced by the service. If the plug can be “played” on the database then the web service is generated. Our plug-and-play approach has three advantages. First, a plug is portable. You can take the plug …
Temporal Json, Aayush Goyal
Temporal Json, Aayush Goyal
All Graduate Theses and Dissertations, Spring 1920 to Summer 2023
JavaScript Object Notation (JSON) is a format for representing data. In this thesis we show how to capture the history of changes to a JSON document. Capturing the history is important in many applications, where not only the current version of a document is required, but all the previous versions. Conceptually the history can be thought of as a sequence of non-temporal JSON documents, one for each instant of time. Each document in the sequence is called a snapshot. Since changes to a document are few and infrequent, the sequence of snapshots largely duplicates a document across many time instants, …
Sentiment Analysis, Quantification, And Shift Detection, Kevin Labille
Sentiment Analysis, Quantification, And Shift Detection, Kevin Labille
Graduate Theses and Dissertations
This dissertation focuses on event detection within streams of Tweets based on sentiment quantification. Sentiment quantification extends sentiment analysis, the analysis of the sentiment of individual documents, to analyze the sentiment of an aggregated collection of documents. Although the former has been widely researched, the latter has drawn less attention but offers greater potential to enhance current business intelligence systems. Indeed, knowing the proportion of positive and negative Tweets is much more valuable than knowing which individual Tweets are positive or negative. We also extend our sentiment quantification research to analyze the evolution of sentiment over time to automatically detect …
Hybrid Recommender Systems Via Spectral Learning And A Random Forest, Alyssa Williams
Hybrid Recommender Systems Via Spectral Learning And A Random Forest, Alyssa Williams
Electronic Theses and Dissertations
We demonstrate spectral learning can be combined with a random forest classifier to produce a hybrid recommender system capable of incorporating meta information. Spectral learning is supervised learning in which data is in the form of one or more networks. Responses are predicted from features obtained from the eigenvector decomposition of matrix representations of the networks. Spectral learning is based on the highest weight eigenvectors of natural Markov chain representations. A random forest is an ensemble technique for supervised learning whose internal predictive model can be interpreted as a nearest neighbor network. A hybrid recommender can be constructed by first …