Matching Items (98)
Filtering by
- All Subjects: Computer Science
- Genre: Masters Thesis
- Creators: Doupe, Adam
- Creators: Bansal, Ajay
- Creators: Walker, Erin
Description
Lots of previous studies have analyzed human tutoring at great depths and have shown expert human tutors to produce effect sizes, which is twice of that produced by an intelligent tutoring system (ITS). However, there has been no consensus on which factor makes them so effective. It is important to know this, so that same phenomena can be replicated in an ITS in order to achieve the same level of proficiency as expert human tutors. Also, to the best of my knowledge no one has looked at student reactions when they are working with a computer based tutor. The answers to both these questions are needed in order to build a highly effective computer-based tutor. My research focuses on the second question. In the first phase of my thesis, I analyzed the behavior of students when they were working with a step-based tutor Andes, using verbal-protocol analysis. The accomplishment of doing this was that I got to know of some ways in which students use a step-based tutor which can pave way for the creation of more effective computer-based tutors. I found from the first phase of the research that students often keep trying to fix errors by guessing repeatedly instead of asking for help by clicking the hint button. This phenomenon is known as hint refusal. Surprisingly, a large portion of the student's foundering was due to hint refusal. The hypothesis tested in the second phase of the research is that hint refusal can be significantly reduced and learning can be significantly increased if Andes uses more unsolicited hints and meta hints. An unsolicited hint is a hint that is given without the student asking for one. A meta-hint is like an unsolicited hint in that it is given without the student asking for it, but it just prompts the student to click on the hint button. Two versions of Andes were compared: the original version and a new version that gave more unsolicited and meta-hints. During a two-hour experiment, there were large, statistically reliable differences in several performance measures suggesting that the new policy was more effective.
ContributorsRanganathan, Rajagopalan (Author) / VanLehn, Kurt (Thesis advisor) / Atkinson, Robert (Committee member) / Burleson, Winslow (Committee member) / Arizona State University (Publisher)
Created2011
Description
Strong communities are important for society. One of the most important community builders, making friends, is poorly supported online. Dating sites support it but in romantic contexts. Other major social networks seem not to encourage it because either their purpose isn't compatible with introducing strangers or the prevalent methods of introduction aren't effective enough to merit use over real word alternatives. This paper presents a novel digital social network emphasizing creating friendships. Research has shown video chat communication can reach in-person levels of trust; coupled with a game environment to ease the discomfort people often have interacting with strangers and a recommendation engine, Zazzer, the presented system, allows people to meet and get to know each other in a manner much more true to real life than traditional methods. Its network also allows players to continue to communicate afterwards. The evaluation looks at real world use, measuring the frequency with which players choose the video chat game versus alternative, more traditional methods of online introduction. It also looks at interactions after the initial meeting to discover how effective video chat games are in creating sticky social connections. After initial use it became apparent a critical mass of users would be necessary to draw strong conclusions, however the collected data seemed to give preliminary support to the idea that video chat games are more effective than traditional ways of meeting online in creating new relationships.
ContributorsSorensen, Asael (Author) / VanLehn, Kurt (Thesis advisor) / Liu, Huan (Committee member) / Burleson, Winslow (Committee member) / Arizona State University (Publisher)
Created2011
Description
There has been a lot of research in the field of artificial intelligence about thinking machines. Alan Turing proposed a test to observe a machine's intelligent behaviour with respect to natural language conversation. The Winograd schema challenge is suggested as an alternative, to the Turing test. It needs inferencing capabilities, reasoning abilities and background knowledge to get the answer right. It involves a coreference resolution task in which a machine is given a sentence containing a situation which involves two entities, one pronoun and some more information about the situation and the machine has to come up with the right resolution of a pronoun to one of the entities. The complexity of the task is increased with the fact that the Winograd sentences are not constrained by one domain or specific sentence structure and it also contains a lot of human proper names. This modification makes the task of association of entities, to one particular word in the sentence, to derive the answer, difficult. I have developed a pronoun resolver system for the confined domain Winograd sentences. I have developed a classifier or filter which takes input sentences and decides to accept or reject them based on a particular criteria. Once the sentence is accepted. I run parsers on it to obtain the detailed analysis. Furthermore I have developed four answering modules which use world knowledge and inferencing mechanisms to try and resolve the pronoun. The four techniques I use are : ConceptNet knowledgebase, Search engine pattern counts,Narrative event chains and sentiment analysis. I have developed a particular aggregation mechanism for the answers from these modules to arrive at a final answer. I have used caching technique for the association relations that I obtain for different modules, so as to boost the performance. I run my system on the standard ‘nyu dataset’ of Winograd sentences and questions. This dataset is then restricted, by my classifier, to 90 sentences. I evaluate my system on this 90 sentence dataset. When I compare my results against the state of the art system on the same dataset, I get nearly 4.5 % improvement in the restricted domain.
ContributorsBudukh, Tejas Ulhas (Author) / Baral, Chitta (Thesis advisor) / VanLehn, Kurt (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Gathering and managing software requirements, known as Requirement Engineering (RE), is a significant and basic step during the Software Development Life Cycle (SDLC). Any error or defect during the RE step will propagate to further steps of SDLC and resolving it will be more costly than any defect in other steps. In order to produce better quality software, the requirements have to be free of any defects. Verification and Validation (V&V;) of requirements are performed to improve their quality, by performing the V&V; process on the Software Requirement Specification (SRS) document. V&V; of the software requirements focused to a specific domain helps in improving quality. A large database of software requirements from software projects of different domains is created. Software requirements from commercial applications are focus of this project; other domains embedded, mobile, E-commerce, etc. can be the focus of future efforts. The V&V; is done to inspect the requirements and improve the quality. Inspections are done to detect defects in the requirements and three approaches for inspection of software requirements are discussed; ad-hoc techniques, checklists, and scenario-based techniques. A more systematic domain-specific technique is presented for performing V&V; of requirements.
ContributorsChughtai, Rehman (Author) / Ghazarian, Arbi (Thesis advisor) / Bansal, Ajay (Committee member) / Millard, Bruce (Committee member) / Arizona State University (Publisher)
Created2012
Description
Building computational models of human problem solving has been a longstanding goal in Artificial Intelligence research. The theories of cognitive architectures addressed this issue by embedding models of problem solving within them. This thesis presents an extended account of human problem solving and describes its implementation within one such theory of cognitive architecture--ICARUS. The document begins by reviewing the standard theory of problem solving, along with how previous versions of ICARUS have incorporated and expanded on it. Next it discusses some limitations of the existing mechanism and proposes four extensions that eliminate these limitations, elaborate the framework along interesting dimensions, and bring it into closer alignment with human problem-solving abilities. After this, it presents evaluations on four domains that establish the benefits of these extensions. The results demonstrate the system's ability to solve problems in various domains and its generality. In closing, it outlines related work and notes promising directions for additional research.
ContributorsTrivedi, Nishant (Author) / Langley, Patrick W (Thesis advisor) / VanLehn, Kurt (Committee member) / Kambhampati, Subbarao (Committee member) / Arizona State University (Publisher)
Created2011
Description
One persisting problem in Massive Open Online Courses (MOOCs) is the issue of student dropout from these courses. The prediction of student dropout from MOOC courses can identify the factors responsible for such an event and it can further initiate intervention before such an event to increase student success in MOOC. There are different approaches and various features available for the prediction of student’s dropout in MOOC courses.In this research, the data derived from the self-paced math course ‘College Algebra and Problem Solving’ offered on the MOOC platform Open edX offered by Arizona State University (ASU) from 2016 to 2020 was considered. This research aims to predict the dropout of students from a MOOC course given a set of features engineered from the learning of students in a day. Machine Learning (ML) model used is Random Forest (RF) and this model is evaluated using the validation metrics like accuracy, precision, recall, F1-score, Area Under the Curve (AUC), Receiver Operating Characteristic (ROC) curve. The average rate of student learning progress was found to have more impact than other features. The model developed can predict the dropout or continuation of students on any given day in the MOOC course with an accuracy of 87.5%, AUC of 94.5%, precision of 88%, recall of 87.5%, and F1-score of 87.5% respectively. The contributing features and interactions were explained using Shapely values for the prediction of the model. The features engineered in this research are predictive of student dropout and could be used for similar courses to predict student dropout from the course. This model can also help in making interventions at a critical time to help students succeed in this MOOC course.
ContributorsDominic Ravichandran, Sheran Dass (Author) / Gary, Kevin (Thesis advisor) / Bansal, Ajay (Committee member) / Cunningham, James (Committee member) / Sannier, Adrian (Committee member) / Arizona State University (Publisher)
Created2021
Description
Honeypots – cyber deception technique used to lure attackers into a trap. They contain fake confidential information to make an attacker believe that their attack has been successful. One of the prerequisites for a honeypot to be effective is that it needs to be undetectable. Deploying sniffing and event logging tools alongside the honeypot also helps understand the mindset of the attacker after successful attacks. Is there any data that backs up the claim that honeypots are effective in real life scenarios? The answer is no.Game-theoretic models have been helpful to approximate attacker and defender actions in cyber security. However, in the past these models have relied on expert- created data. The goal of this research project is to determine the effectiveness of honeypots using real-world data. So, how to deploy effective honeypots? This is where honey-patches come into play. Honey-patches are software patches designed to hinder the attacker’s ability to determine whether an attack has been successful or not. When an attacker launches a successful attack on a software, the honey-patch transparently redirects the attacker into a honeypot. The honeypot contains fake information which makes the attacker believe they were successful while in reality they were not.
After conducting a series of experiments and analyzing the results, there is a clear indication that honey-patches are not the perfect application security solution having both pros and cons.
ContributorsChauhan, Purv Rakeshkumar (Author) / Doupe, Adam (Thesis advisor) / Bao, Youzhi (Committee member) / Wang, Ruoyu (Committee member) / Arizona State University (Publisher)
Created2022
Description
A significant proportion of medical errors exist in crucial medical information, and most stem from misinterpreting non-standardized clinical notes. Clinical Skills exam offered by the United States Medical Licensing Examination (USMLE) was put in place to certify patient note-taking skills before medical students joined professional practices, offering the first line of defense in protecting patients from medical errors. Nonetheless, the exams were discontinued in 2021 following high costs and resource usage in scoring the exams. This thesis compares four transformer-based models, namely BERT (Bidirectional Encoder Representations from Transformers) Base Uncased, Emilyalsentzer Bio_ClinicalBERT, RoBERTa (Robustly Optimized BERT Pre-Training Approach), and DeBERTa (Decoding-enhanced BERT with disentangled attention), with the goal to map free text in patient notes to clinical concepts present in the exam rubric. The impact of context-specific embeddings on BERT was also studied to determine the need for a clinical BERT in Clinical Skills exam. This thesis proposes the use of DeBERTa as a backbone model in patient note scoring for the USMLE Clinical Skills exam after comparing it with three other transformer models. Disentangled attention and enhanced mask decoder integrated into DeBERTa were credited for the high performance of DeBERTa as compared to the other models. Besides, the effect of meta pseudo labeling was also investigated in this thesis, which in turn, further enhanced DeBERTa’s performance.
ContributorsGanesh, Jay (Author) / Bansal, Ajay (Thesis advisor) / Mehlhase, Alexandra (Committee member) / Findler, Michael (Committee member) / Arizona State University (Publisher)
Created2022
Description
The rise in popularity of applications and services that charge for access to proprietary trained models has led to increased interest in the robustness of these models and the security of the environments in which inference is conducted. State-of-the-art attacks extract models and generate adversarial examples by inferring relationships between a model’s input and output. Popular variants of these attacks have been shown to be deterred by countermeasures that poison predicted class distributions and mask class boundary gradients. Neural networks are also vulnerable to timing side-channel attacks. This work builds on top of Subneural, an attack framework that uses floating point timing side channels to extract neural structures. Novel applications of addition timing side channels are introduced, allowing the signs and arrangements of leaked parameters to be discerned more efficiently. Addition timing is also used to leak network biases, making the framework applicable to a wider range of targets. The enhanced framework is shown to be effective against models protected by prediction poisoning and gradient masking adversarial countermeasures and to be competitive with adaptive black box adversarial attacks against stateful defenses. Mitigations necessary to protect against floating-point timing side-channel attacks are also presented.
ContributorsVipat, Gaurav (Author) / Shoshitaishvili, Yan (Thesis advisor) / Doupe, Adam (Committee member) / Srivastava, Siddharth (Committee member) / Arizona State University (Publisher)
Created2023
Description
Open Information Extraction (OIE) is a subset of Natural Language Processing (NLP) that constitutes the processing of natural language into structured and machine-readable data. This thesis uses data in Resource Description Framework (RDF) triple format that comprises of a subject, predicate, and object. The extraction of RDF triples from natural language is an essential step towards importing data into web ontologies as part of the linked open data cloud on the Semantic web. There have been a number of related techniques for extraction of triples from plain natural language text including but not limited to ClausIE, OLLIE, Reverb, and DeepEx. This proposed study aims to reduce the dependency on conventional machine learning models since they require training datasets, and the models are not easily customizable or explainable. By leveraging a context-free grammar (CFG) based model, this thesis aims to address some of these issues while minimizing the trade-offs on performance and accuracy. Furthermore, a deep-dive is conducted to analyze the strengths and limitations of the proposed approach.
ContributorsSingh, Varun (Author) / Bansal, Srividya (Thesis advisor) / Bansal, Ajay (Committee member) / Mehlhase, Alexandra (Committee member) / Arizona State University (Publisher)
Created2023