Theses - Department of Computer Engineering
Faculty of Engineering
Collections in this community
Recent Submissions
-
Towards unifiying mobility datasets
(Bilkent University, 2019-12)With the proliferation of smart phones integrated with positioning systems and the increasing penetration of Internet-of-Things (IoT) in our daily lives, mobility data has become widely available. A vast variety of mobile ... -
High level synthesis based FPGA implementation of Matricized Tensor Times Khatri-Rao Product to accelerate canonical polyadic decomposition
(Bilkent University, 2019-10)Tensor factorization has many applications such as network anomaly detection, structural damage detection and music genre classification. Most time consuming part of the CPD-ALS based tensor factorization is the Matricized ... -
Deepside: predicting drug side effects with deep learning
(Bilkent University, 2019-10)Drug failures due to unforeseen adverse effects at clinical trials pose health risks for the participants and cause substantial financial losses. Side effect prediction algorithms, on the other hand, have the potential ... -
Paralog-specific gene copy number discovery within segmental duplications
(Bilkent University, 2019-10)With the advancing technology in genome sequencing and analysis, it has become evident that the structural variations are the main source of alteration in human genome. Despite their signi cance in understanding disease ... -
Breakpoint refinement of genomic structural variation using split read analysis
(Bilkent University, 2019-10)Genomic variations that vary from single nucleotide polymorphisms (SNPs), small INDELs to structural variations (SVs) are discovered to have significant phenotypic effects on individuals. Among these genomic variations, ... -
On-the-fly ensemble classifier pruning in evolving data streams
(Bilkent University, 2019-09)Ensemble pruning is the process of selecting a subset of component classifiers from an ensemble which performs at least as well as the original ensemble while reducing storage and computational costs. Ensemble pruning ... -
Discovering regulatory non-coding RNA interactions
(Bilkent University, 2019-09)The vast majority of eukaryotic transcriptomes comprise noncoding RNAs (ncRNAs) which are not translated into proteins. Despite the accumulating evidence on the functional roles of ncRNAs, we are still far from understanding ... -
Hybrid fog-cloud based data distribution for internet of things applications
(Bilkent University, 2019-09)Technological advancements keep making machines, devices, and appliances faster, more capable, and more connected to each other. The network of all interconnected smart devices is called Internet of Things (IoT). It is ... -
A cryptocurrency incentivized voluntary grid computing platform for DNA read alignment
(Bilkent University, 2019-09)The main computational bottleneck of High Throughput Sequencing (HTS) data analysis is to map the reads to a reference genome, for which clusters are typically used. However, building clusters large enough to handle ... -
Semantic validation of biological maps in SBGN
(Bilkent University, 2019-09)Graph visualization is a research field where relational information is graphically represented in the form of graphs or networks. It is applicable in numerous areas from computer network systems, to biology, to software ... -
Coloring for distributed-memory-parallel Gauss-Seidel algorithm
(Bilkent University, 2019-09)Gauss-Seidel is a well-known iterative method for solving linear system of equations. The computations performed on Gauss-Seidel sweeps are sequential in nature since each component of new iterations depends on previously ... -
Learning efficient visual embedding models under data constraints
(Bilkent University, 2019-09)Deep learning models require large-scale datasets to learn rich sets of low and mid-level patterns and high-level semantics. Therefore, given a high-capacity neural network, one way to improve the performance of a model ... -
Partitioning models for scaling distributed graph computations
(Bilkent University, 2019-09)The focus of this thesis is intelligent partitioning models and methods for scaling the performance of parallel graph computations on distributed-memory systems. Distributed databases utilize graph partitioning to provide ... -
Conversational agent expressing ocean personality and emotions using laban movement analysis and nonverbal communication cues
(Bilkent University, 2019-08)Conversational human characters are heavily used in computer animation to convey various messages. Appearance, movement and voice of such characters in uence their perceived personality. Analyzing different channels of ... -
Fast and efficient model parallelism for deep convolutional neural networks
(Bilkent University, 2019-08)Convolutional Neural Networks (CNNs) have become very popular and successful in recent years. Increasing the depth and number of parameters of CNNs has crucial importance on this success. However, it is hard to t deep ... -
Analyzing the effect of kinship for re-identification attacks in genomic data sharing beacons
(Bilkent University, 2019-08)Genomic data contains sensitive information about an individual. Family members' genome sequence can be re-constructed with high confidence or individuals' may face discrimination because of predisposition of a disease ... -
Parafac-spark: parallel tensor decompositions on spark
(Bilkent University, 2019-08)Tensors are higher order matrices, widely used in many data science applications and scienti c disciplines. The Canonical Polyadic Decomposition (also known as CPD/PARAFAC) is a widely adopted tensor factorization to ... -
Diverse SNP selection for epistasis test prioritization
(Bilkent University, 2019-08)Genome-wide association studies explain a fraction of the underlying heritability of genetic diseases. Epistatic interactions between two or more loci help closing the gap and identifying those complex interactions ... -
Boosting fully convolutional networks for gland instance segmentation in histopathological images
(Bilkent University, 2019-08)In the current literature, fully convolutional neural networks (FCNs) are the most preferred architectures for dense prediction tasks, including gland segmentation. However, a signi cant challenge is to adequately train ... -
Source-to-source transformation based methodology for graph-parallel FPGA accelerators
(Bilkent University, 2019-08)Graph applications are becoming more and more important with their widespread usage and the amounts of data they deal with. Biological and social web graphs are well-known examples which show the importance of efficient ...
