Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Big Data (2)
- Machine Learning (2)
- Optimization (2)
- Android applications (1)
- Co-evolution (1)
-
- Cultural Algorithm (1)
- Emergency Department (1)
- Feature Learning (1)
- Feature selection (1)
- GPU (1)
- Hadoop (1)
- High Performance Computing Cluster (1)
- ICD9 (1)
- Image Classification (1)
- K-Means (1)
- Multicore CPU (1)
- Object classification (1)
- Platform Comparison (1)
- RCHITECTURAL-LEVEL APPROACH (1)
- Representation learning (1)
- SECURITY VULNERABILITIES (1)
- Social Fabric (1)
- Software Engineering (1)
- Spark (1)
- Static Analysis (1)
- Triage (1)
Articles 1 - 11 of 11
Full-Text Articles in Physical Sciences and Mathematics
Comparison Of Lazy Controller And Constant Bandwidth Server For Temperature Control, Zhen Sun
Comparison Of Lazy Controller And Constant Bandwidth Server For Temperature Control, Zhen Sun
Wayne State University Theses
Temperature control plays an important role in building control systems; there are
numerous methods for controlling temperature. Recently, a popular controller is the
lazy controller which proposed by Truong et al. However, by applying lazy control, the
temperature is not stable since this controller simply lets temperature increase or decrease
until it reaches the upper or lower temperature thresholds. We seek a heater-control
schedule that can make room temperatures more stable. The Constant Bandwidth Server
(CBS) was developed to handle soft real-time tasks characterized by the execution time
and period. By employing the concepts of CBS, we can derive a …
Evaluation Of An Architectural-Level Approach For Finding Security Vulnerabilities, Mohammad Anamul Haque
Evaluation Of An Architectural-Level Approach For Finding Security Vulnerabilities, Mohammad Anamul Haque
Wayne State University Theses
The cost of security vulnerabilities of a software system is high. As a result,
many techniques have been developed to find the vulnerabilities at development time. Of particular interest are static analysis techniques that can consider all possible executions of a system. But, static analysis can suffer from a large number of false positives.
A recently developed approach, Scoria, is a semi-automated static analysis that requires security architects to annotate the code, typecheck the annotations, extract a hierarchical object graph and write constraints in order to find security vulnerabilities in a system.
This thesis evaluates Scoria on three systems (sizes …
Survival Analysis Approach For Early Prediction Of Student Dropout, Sattar Ameri
Survival Analysis Approach For Early Prediction Of Student Dropout, Sattar Ameri
Wayne State University Theses
Retention of students at colleges and universities has long been a concern for educators for many decades. The consequences of student attrition are significant for both students, academic staffs and the overall institution. Thus, increasing student retention is a long term goal of any academic institution. The most vulnerable students at all institutions of higher education are the freshman students, who are at the highest risk of dropping out at the beginning of their study. Consequently, the early identification of at-risk students is a crucial task that needs to be addressed precisely. In this thesis, we develop a framework for …
Performance Comparison Of Two Data Mining Algorithms On Big Data Platforms, Md Rajiur Rahman Raju
Performance Comparison Of Two Data Mining Algorithms On Big Data Platforms, Md Rajiur Rahman Raju
Wayne State University Theses
In this Big data era, the need for performing large-scale computations is evident. A better understanding of the most suitable platforms which can efficiently run these computations is needed. In this thesis, we attempt to compare four such big data platforms, namely Hadoop, Spark, GPU, and Multicore CPU. We compare these platforms using two prominent data mining algorithms, namely, K-means clustering and K-nearest neighbour classification and discuss specific implementation-level details. We provide several insights into the best possible implementations of these algorithms and systematically compare the benefits and drawbacks of each of these platforms. We conduct experiments by varying data …
Plus: A Unique Personalized Literature Recommender System, Jingwen Zhang
Plus: A Unique Personalized Literature Recommender System, Jingwen Zhang
Wayne State University Theses
There are massive research papers published from various of disciplines every year, and people who are engaged in scientific research usually have to spend a large amount of time on searching and finding the papers that they are interested in.
In this thesis, we illustrated a unique personalized literature recommender system (PLUS) which was proposed to predict users' personal research interests and recommend the latest papers to them as much as possible. The system shows advantages in four aspects: (1) it takes multiple sources that could reflect a user's personal research interest as the input; (2) it prevents the recommendations …
Effective Auto Encoder For Unsupervised Sparse Representation, Faria Mahnaz
Effective Auto Encoder For Unsupervised Sparse Representation, Faria Mahnaz
Wayne State University Theses
High dimensionality and the sheer size of unlabeled data available today demand
new development in unsupervised learning of sparse representation. Despite of recent
advances in representation learning, most of the current methods are limited when
dealing with large scale unlabeled data. In this study, we propose a new unsupervised
method that is able to learn sparse representation from unlabeled data efficiently. We
derive a closed-form solution based on the sequential minimal optimization (SMO)
for training an auto encoder-decoder module, which efficiently extracts sparse and
compact features from any data set with various size. The inference process in the
proposed learning …
Unsupervised Learning And Image Classification In High Performance Computing Cluster, Itauma Itauma
Unsupervised Learning And Image Classification In High Performance Computing Cluster, Itauma Itauma
Wayne State University Theses
Feature learning and object classification in machine learning have become very active research areas in recent decades. Identifying good features has various benefits for object classification in respect to reducing the computational cost and increasing the classification accuracy. In addition, many research studies have focused on the use of Graphics Processing Units (GPUs) to improve the training time for machine learning algorithms. In this study, the use of an alternative platform, called High Performance Computing Cluster (HPCC), to handle unsupervised feature learning, image and speech classification and improve the computational cost is proposed.
HPCC is a Big Data processing and …
Quantitative And Qualitative Evaluation Of Metrics On Object Graphs Extracted By Abstract Interpretation, Sumukhi Chandrashekar
Quantitative And Qualitative Evaluation Of Metrics On Object Graphs Extracted By Abstract Interpretation, Sumukhi Chandrashekar
Wayne State University Theses
Evaluating programming-language based techniques is crucial to judge their usefulness in practice but requires a careful selection of systems on
which to evaluate the technique. Since it is particularly hard to evaluate a heavyweight technique, such as one that requires adding annotations
to the code or rewriting the system in a radically different language, it is common to use a lightweight proxy to predict the technique's usefulness
for a system. But the reliability of such a proxy is unclear.
We propose a principled data-driven approach to derive a lightweight proxy for a heavyweight technique that requires adding annotations to the …
Bayesian Approach For Early Stage Event Prediction In Survival Data, Mahtab Jahanbani Fard
Bayesian Approach For Early Stage Event Prediction In Survival Data, Mahtab Jahanbani Fard
Wayne State University Theses
Predicting event occurrence at an early stage in longitudinal studies is an important and challenging problem which has high practical value. As opposed to the standard classification and regression problems where a domain expert can provide the labels for the data in a reasonably short period of time, training data in such longitudinal studies must be obtained only by waiting for the occurrence of sufficient number of events. On the other hand, survival analysis aims at finding the underlying distribution for data that measure the length of time until the occurrence of an event. However, it cannot give an answer …
Predictive Analytics For Disease Condition Of Patients In Emergency Department, Azade Tabaie
Predictive Analytics For Disease Condition Of Patients In Emergency Department, Azade Tabaie
Wayne State University Theses
Emergency Departments (EDs) in hospitals are experiencing severe crowding and prolonged patient waiting times. The reported crowding in hospitals shows patients in hospital hallways, long waiting times and full occupancy of ED beds. ED crowding has several potential unfavorable effects including patients and staff frustration, lower patient satisfaction and poor health outcomes. The primary motivations behind this study are shortening the patients’ waiting time and improving patient satisfaction and level of care.
The very initial interaction between clinicians and a patient is recorded on nurse triage notes which contain details of the reason for patient’s visit including specific symptoms and …
The Impact Of Increased Optimization Problem Dimensionality On Cultural Algorithm Performance, Yang Yang
The Impact Of Increased Optimization Problem Dimensionality On Cultural Algorithm Performance, Yang Yang
Wayne State University Theses
ABSTRACT
The Impact of Increased Optimization Problem Dimensionality on
Cultural Algorithm Performance
by
Yang Yang
August 2015
Advisor: Dr. Robert Reynolds
Major: Computer Science
Degree: Master of Science
In this thesis, we investigate the performance of Cultural Algorithms when dealing with the increasing dimensionality of optimization problems. The research is based on previous cultural algorithm approaches with the Cultural Algorithms Toolkit, CAT 2.0, which supports a variety of co-evolutionary features at both the knowledge and population levels. In this project, the system was applied to the solution of 60 randomly generated problems that ranged from 2-dimensional to 5-dimensional problem spaces. …