Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Artificial Intelligence and Robotics (248)
- Other Computer Sciences (125)
- Information Security (107)
- Databases and Information Systems (68)
- OS and Networks (38)
-
- Programming Languages and Compilers (22)
- Graphics and Human Computer Interfaces (20)
- Software Engineering (18)
- Systems Architecture (14)
- Theory and Algorithms (12)
- Data Science (7)
- Bioinformatics (4)
- Life Sciences (4)
- Arts and Humanities (1)
- Astrophysics and Astronomy (1)
- External Galaxies (1)
- Music (1)
- Numerical Analysis and Scientific Computing (1)
- Other Astrophysics and Astronomy (1)
- Other Music (1)
- Keyword
-
- Machine Learning (24)
- Machine learning (22)
- Deep Learning (16)
- Deep learning (13)
- CNNs (11)
-
- Natural Language Processing (9)
- Neural networks (8)
- SVM (8)
- CNN (7)
- Computer vision (6)
- Reinforcement Learning (6)
- BERT (5)
- Blockchain (5)
- Classification (5)
- Computer Vision (5)
- Twitter (5)
- Word2Vec (5)
- Community detection (4)
- Convolutional Neural Network (4)
- Convolutional Neural Networks (4)
- HMM (4)
- Logistic Regression (4)
- Malware (4)
- Malware classification (4)
- Malware detection (4)
- Reinforcement learning (4)
- Social networks (4)
- Visualization (4)
- Benchmarking (3)
- Bioinformatics (3)
Articles 541 - 570 of 859
Full-Text Articles in Computer Sciences
Text Summarization For Compressed Inverted Indexes And Snippets, Mangesh Dahale
Text Summarization For Compressed Inverted Indexes And Snippets, Mangesh Dahale
Master's Projects
Text summarization is a technique to generate a concise summary of
a larger text. In search engines, Text summarization can be used for
generating compressed descriptions of web pages. For indexing, these can
be used rather than whole pages when building inverted indexes. For query
results, summaries can be used for snippet generation. In this project, we
research on several techniques of text summarization. We evaluate these
techniques for quality of the generated summary and time required to
generate it. We implement the technique chosen from the evaluation in
Yioop, an open source, PHP-based search engine.
Incorporating Wordnet In An Information Retrieval System, Shailesh Padave
Incorporating Wordnet In An Information Retrieval System, Shailesh Padave
Master's Projects
Query expansion is a method of modifying an initial query to enhance retrieval performance in information retrieval operations [11] . There are alternate ways to expand a user input query such as finding synonyms of words, re-weighting the query, fixing spelling mistakes, etc. [11] . In this project, we created a query rewriting algorithm, which uses synonyms for a given word for query expansion. These synonyms were chosen using WordNet, a lexical database for English [16] [15] . Similarity ranking functions and a part-of- speech tagger were written to extract the essential data from WordNet output. Various experiments were carried …
A Tiered Approach To Detect Metamorphic Malware With Hidden Markov Models, Ashwin Kalbhor
A Tiered Approach To Detect Metamorphic Malware With Hidden Markov Models, Ashwin Kalbhor
Master's Projects
Work on the use of hidden Markov models (HMM) to detect viruses has been carried out previously with good results [2], but metamorphic viruses like MetaPHOR [27] and metamorphic worms like MWOR [3] have proven to be able to evade detection techniques based on HMMs. The dueling HMM approach looks to detect such viruses by training an HMM model for each of the metamorphic virus / worm families. The tests and the results from these have shown that this approach has been able to detect the metamorphic MetaPHOR virus with reasonable accuracy but with significantly more overhead. This paper presents …
Application Of Message Passing And Sinkhorn Balancing Algorithms For Probabilistic Graphical Models, Lakshmi Ananthagopal
Application Of Message Passing And Sinkhorn Balancing Algorithms For Probabilistic Graphical Models, Lakshmi Ananthagopal
Master's Projects
Probabilistic Graphical Models (PGMs) allow us to map real world scenarios to a
declarative representation and use it as a basis for predictive analysis. It is a framework that
allows us to express complex probability distributions in a simple way. PGMs can be applied to a
variety of scenarios wherein a model is built to reflect the conditional dependencies between
random variables and then used to simulate the interactions between them to draw conclusions.
The framework further provides many algorithms to analyze these models and extract
information.
One of the applications of PGMs is in solving mathematical puzzles such as …
Big Data Analysis Using Neuro-Fuzzy System, Amir Eibagi
Big Data Analysis Using Neuro-Fuzzy System, Amir Eibagi
Master's Projects
This project addresses big data classification using hybrid Intelligence
Classification System. Hybrid Intelligence classification system is a system that
combines at least two intelligent technologies. Specifically, the focus of this project is to
apply hybrid Neuro-Fuzzy system to the IBM Watson data and Innocentive
Trustworthiness challenge data for prediction and classification. Neural network are low-
level computational structure which has ability to learn and performs well on the raw
data. On the other hand, fuzzy logic deals with reasoning on higher level using If-then
rules and linguistic variables. So combining these two methods can provide us with a
very powerful …
Dart: Declaratively Rendering 2d Sketches In Canvas, Jesus Rocha
Dart: Declaratively Rendering 2d Sketches In Canvas, Jesus Rocha
Master's Projects
Dart is a recent programming language for the web browser. It features structured programming through traditional class-based syntax, metaprogramming via mirror-based reflection and scriptable rendering of 2D shapes with the Canvas API. This project explores Dart as a potential host for a domain-specific language (DSL) to produce figures, like those found in entry-level programming books. The goal is for instructors or book authors to generate figures such as the ones that appear in a typical CS1/CS2 text book. Figures from the book are analyzed and a library for rendering them declaratively is developed. Dart was able to provide a convenient …
Automatic Evaluation Of Python And C Programs With Codecheck, Kiet Nguyen
Automatic Evaluation Of Python And C Programs With Codecheck, Kiet Nguyen
Master's Projects
This project enhances the codecheck autograder by implementing automatic evaluation of C and Python programs. Two security approaches are implemented and analyzed in order to complete this goal. The first approach involves isolation by using virtualization and the second approach involves hardening of the host operating system. I describe both implementations and measure their performance levels to see which approach is more efficient.
Improving The Performance And Energy Efficiency For Mobile Cloud Computing, Seungbeom Ma
Improving The Performance And Energy Efficiency For Mobile Cloud Computing, Seungbeom Ma
Master's Projects
Based on the worldwide high-speed networks and advanced hardware (e.g., multiple cores mobile processor, and various sensors), mobile software industries enthusiastically release advanced mobile applications. These phenomena cause mobile devices to break down the limitation of time and place. Mobile cloud computing provides the most convenient communication and effective working environment to humans. However, the fundamental hardware has technical difficulties to keep up advanced technologies and applications in mobile devices, which means that there is a gap between available hardware resource and the demand of complex applications in mobile devices. The limited hardware decreases the quality of service. Mobile Cloud …
Opinion Mining On Twitter Data Stream To Give Companies An Up-To-Date Feedback On Their Free Products, Lokmanyathilak Govindan Sankar Selvan
Opinion Mining On Twitter Data Stream To Give Companies An Up-To-Date Feedback On Their Free Products, Lokmanyathilak Govindan Sankar Selvan
Master's Projects
There are lots of companies producing various products ranging from expensive to free products. There is no software product without any bug irrespective of their cost. The problem with this situation is that when people purchase a software product by paying money they are more concerned about its performance. People report to the companies if the product they purchased does not work as expected. It is not the same in the case of free products. People tend to switch to some other free product produced by different company which does the same job. The notion of this project is to …
Automating Nfc Message Sending For Good And Evil, Nikki Benecke Brandt
Automating Nfc Message Sending For Good And Evil, Nikki Benecke Brandt
Master's Projects
Near Field Communication (NFC) is an emerging proximity wireless technology used for triggering automatic interactions between mobile devices. In standard NFC usage, one message is sent per device contact, then the devices must be physically separated and brought together again. In this paper, we present a mechanism for automatically sending multiple messages without any need to physically decouple the devices. After an introduction to NFC and related security issues, we discuss the motivation for—and an implementation of—an automation framework for sending repeated NFC messages without any need for human interaction. Then we consider how such an automated mechanism can be …
Onecareer-A Visualization Approach To Job Search Process, Avinash Anantharamu
Onecareer-A Visualization Approach To Job Search Process, Avinash Anantharamu
Master's Projects
No abstract provided.
Improving The Efficiency Of Tesseract Ocr Engine, Sahil Badla
Improving The Efficiency Of Tesseract Ocr Engine, Sahil Badla
Master's Projects
This project investigates the principles of optical character recognition used in the Tesseract OCR engine and techniques to improve its efficiency and runtime. Optical character recognition (OCR) method has been used in converting printed text into editable text in various applications over a variety of devices such as Scanners, computers, tablets etc. But now Mobile is taking over the computer in all the domains but OCR still remains one not so conquered field. So programmers need to improve the efficiency of the OCR system to make it run properly on Mobile devices. This paper focuses on improving the Tesseract OCR …
Semantic Similarity Based Information Retrieval As Applied To Moocs, Krishna Nitin Tenali
Semantic Similarity Based Information Retrieval As Applied To Moocs, Krishna Nitin Tenali
Master's Projects
Over the last few years there has been a significant development in the e-learning industry that provides online courses to the public. Due to the drastic improvement in technology and the Internet, this form of education reaches many people across boundaries. There is vast set of courses currently provided by various sources, which range from the latest technologies in the field of computer science to any topic in history. Since the invention of e-learning, there has been constant improvement of user friendly tools to enhance the learning process. In the span of the last three years, many websites have come …
Attribute Selection Methods In Rough Set Theory, Xiaohan Li
Attribute Selection Methods In Rough Set Theory, Xiaohan Li
Master's Projects
Attribute selection for rough sets is an NP-hard problem, in which fast heuristic algorithms are needed to find reducts. In this project, two reduct methods for rough set were implemented: particle swarm optimization and Johnson’s method. Both algorithms were evaluated with five different benchmarks from the KEEL repository. The results obtained from both implementations were compared with results obtained by the ROSETTA software using the same benchmarks. The results show that the implementations achieve better correction rates than ROSETTA.
Analyzing Big Data With Decision Trees, Lok Kei Leong
Analyzing Big Data With Decision Trees, Lok Kei Leong
Master's Projects
ANALYZING BIG DATA WITH DECISION TREES
Improving Smart Grid Security Using Merkle Trees, Melesio Calderón Muñoz
Improving Smart Grid Security Using Merkle Trees, Melesio Calderón Muñoz
Master's Projects
Abstract—Presently nations worldwide are starting to convert their aging electrical power infrastructures into modern, dynamic power grids. Smart Grid offers much in the way of efficiencies and robustness to the electrical power grid, however its heavy reliance on communication networks will leave it more vulnerable to attack than present day grids. This paper looks at the threat to public key cryptography systems from a fully realized quantum computer and how this could impact the Smart Grid. We argue for the use of Merkle Trees in place of public key cryptography for authentication of devices in wireless mesh networks that are …
Hunting For Pirated Software Using Metamorphic Analysis, Hardikkumar Rana
Hunting For Pirated Software Using Metamorphic Analysis, Hardikkumar Rana
Master's Projects
In this paper, we consider the problem of detecting software that has been pirated and modified. We analyze a variety of detection techniques that have been previously studied in the context of malware detection. For each technique, we empirically determine the detection rate as a function of the degree of modification of the original code. We show that the code must be greatly modified before we fail to reliably distinguish it, and we show that our results offer a significant improvement over previous related work. Our approach can be applied retroactively to any existing software and hence, it is both …
Bayesian Classification Using Probabilistic Graphical Models, Mehal Patel
Bayesian Classification Using Probabilistic Graphical Models, Mehal Patel
Master's Projects
Bayesian Classifiers are used to classify unseen observations to one of the probable class category (also called class labels). Classification applications have one or more features and one or more class variables. Naïve Bayes Classifier is one of the simplest classifier used in practice. Though Naïve Bayes Classifier performs well in practice (in terms of its prediction accuracy), it assumes strong independence among features given class variable. Naïve Bayes assumption may reduce prediction accuracy when two or more features are dependent given class variable. In order to improve prediction accuracy, we can relax Naïve Bayes assumption and allow dependencies among …
Big Data Analytics Using Neural Networks, Chetan Sharma
Big Data Analytics Using Neural Networks, Chetan Sharma
Master's Projects
Machine learning is a branch of artificial intelligence in which the system is made to learn from data which can be used to make predictions, real world simulations, pattern recognitions and classifications of the input data. Among the various machine learning approaches in the sub-field of data classification, neural-network methods have been found to be an useful alternatives to the statistical techniques. An artificial neural network is a mathematical model, inspired by biological neural networks, are used for modeling complex relationships between inputs and outputs or to find patterns in data. The goal of the project is to construct a …
Metamorphic Detection Using Function Call Graph Analysis, Prasad Deshpande
Metamorphic Detection Using Function Call Graph Analysis, Prasad Deshpande
Master's Projects
Well-designed metamorphic malware can evade many commonly used malware detection techniques including signature scanning. In this research, we consider a score based on function call graph analysis. We test this score on several challenging classes of metamorphic malware and we show that the resulting detection rates yield an improvement over previous research.
Repetitive Component Based Motion Learning With Kinect, Govind Kalyankar
Repetitive Component Based Motion Learning With Kinect, Govind Kalyankar
Master's Projects
Today’s world wants quick, smart and cost effective solutions to their problems. People want to learn everything online. They are interested in learning new techniques and every kind of art in a limited amount of time because they are busy with their own work and have very short time to take in class instructor led training. This is an attempt to fulfill the same so that the people can easily learn and master a new kind of art by themselves by using Kinect. The focus of this project is to master Kung-Fu, an ancient form of Chinese Martial Arts. Kung-Fu …
Higher Order Pwm For Modeling Transcription Factor Binding Sites, Dhivya Srinivasan
Higher Order Pwm For Modeling Transcription Factor Binding Sites, Dhivya Srinivasan
Master's Projects
Traditional Position Weight Matrices (PWMs) that are used to model Transcription Factor Binding Sites (TFBS) assume independence among different positions in the binding site. In reality, this may not necessarily be the case. A better way to model TFBS is to consider the distribution of dinucleotides or trinucleotides instead of just mononucleotides, thus taking neighboring nucleotides into account. We can therefore, extend the single nucleotide PWM to a dinucleotide PWM or an even higher-order PWM to correctly estimate the dependencies among the nucleotides in a given sequence. The purpose of this project is to develop an algorithm to implement higher-order …
Hidden Markov Models For Malware Classification, Chinmayee Annachhatre
Hidden Markov Models For Malware Classification, Chinmayee Annachhatre
Master's Projects
Malware is a software which is developed for malicious intent. Malware is a rapidly evolving threat to the computing community. Although many techniques for malware classification have been proposed, there is still the lack of a comprehensible and useful taxonomy to classify malware samples. Previous research has shown that hidden Markov model (HMM) analysis is useful for detecting certain types of malware. In this research, we consider the related problem of malware classification based on HMMs. We train HMMs for a variety of malware generators and a variety of compilers. More than 9000 malware samples are then scored against each …
Access Control In A Social Networking Environment, Mallika Perepa
Access Control In A Social Networking Environment, Mallika Perepa
Master's Projects
Collecting users into groups is a common activity in social networking sites such as Facebook, Google groups, Yahoo groups and many other web applications. This project explores access control techniques for dynamically created groups. The starting point was Yioop [1], a PHP-based search engine. The ability to create social groups was added to Yioop. The Grouping feature is enhanced by adding additional features like: blogs and pages for each individual user and as well as for groups of users. Access control is provided to every group and each user within a group based on the ownership of the group or …
Compression-Based Analysis Of Metamorphic Malware, Jared Lee
Compression-Based Analysis Of Metamorphic Malware, Jared Lee
Master's Projects
Recent work has presented a technique based on structural entropy measurement as an effective way to detect metamorphic malware. The technique uses two steps, file segmentation and sequence comparison, to calculate file similarity. In another previous work, it was observed that similar malware have similar measures of Kolmogorov complexity. A proposed method of estimating Kolmogorov complexity was to calculate the compression ratio of a given malware which could then be used to cluster the malicious software. Malware detection has also been attempted through the use of adaptive data compression and showed promising results. In this paper, we attempt to combine …
Determining Spread Of Diseases Using Social Networking Data, Jiten P. Oswal
Determining Spread Of Diseases Using Social Networking Data, Jiten P. Oswal
Master's Projects
“Hi, in a weeks, there will be high possibility you may get infected by flu. Please go to take a flu shot.” – This is a sample warning to some users in Twitter about the spreading of flu to people from specific location. Twitter may already be used to plan social lives, interact with celebrities and communicate with friends. But now data from the social networking sites could have a far more serious use like tracking diseases and learning about their spread. Using this kind of data, I will help Health Agencies to personalize the prediction and warn the general …
Pattern Discovery Of Sequential Symbolic Data Using Automata With An Application To Author Identification, Nikhil Kalantri
Pattern Discovery Of Sequential Symbolic Data Using Automata With An Application To Author Identification, Nikhil Kalantri
Master's Projects
Author Identification is the process of identifying a piece of text to ascertain if it has an inherent writing style or pattern based on a certain author. Almost all literary books can be accredited to a certain author since it has been signed. However, there also exist a plethora of unfinished books or manuscripts that could be attributed to a range of possible authors. For example, William Shakespeare has written many plays that have not been signed by him. In order to assess the importance of such texts that do not bear the authors signature, it could be vital to …
San José State University Building Editor, Viet Trinh
San José State University Building Editor, Viet Trinh
Master's Projects
The San José State University (SJSU) Building Editor is a graphic application that renders the SJSU architectures in a multidimensional space and simulates the flows of people evacuating in the buildings under different circumstances. For a given building, the goals of this application are to analyze a density of people on each floor, to predict bottlenecks in each structure, and to simulate an optimal evacuation plan in case of an emergency for selected SJSU buildings that are visualized in multidimensional models. This report describes in detail functionalities of the application, studies key points in its implementation, and analyzes the application’s …
Pattern Recognition Of Dna Sequences Using Automata With Application To Species Distinction, Parnika P. Achrekar
Pattern Recognition Of Dna Sequences Using Automata With Application To Species Distinction, Parnika P. Achrekar
Master's Projects
"Darwin wasn't just provocative in saying that we descend from the apes—he didn't go far enough, we are apes in every way, from our long arms and tailless bodies to our habits and temperament." said Frans de Waal, a primate scientist at Emory University in Atlanta, Georgia. 1.3 million Species have been named and analyzed by scientists. This project focuses on capturing various nucleotide sequences of various species and determining the similarity and differences between them. Finite state automata have been used to accomplish this. The automata for a DNA genome is created using Alergia algorithm and is used as …
Metamorphic Detection Using Singular Value Decomposition, Ranjith Kumar Jidigam
Metamorphic Detection Using Singular Value Decomposition, Ranjith Kumar Jidigam
Master's Projects
Metamorphic malware changes its internal structure with each infection, while maintaining its original functionality. Such malware can be difficult to detect using static techniques, since there may be no common signature across infections. In this research we apply a score based on Singular Value Decomposition (SVD) to the problem of metamorphic detection. SVD is a linear algebraic technique which is applicable to a wide range of problems, including facial recognition. Previous research has shown that a similar facial recognition technique yields good results when applied to metamorphic malware detection. We present experimental results and we analyze the effectiveness and efficiency …