Theses - Department of Computer Engineering
Faculty of Engineering
Collections in this community
Recent Submissions
-
Segmentation of satellite SAR images using squeeze and attention based deep networks
(Bilkent University, 2021-09)Automatic extraction of objects of interests from high-resolution satellite images has been an active research area. Numerous recent papers have investigated on various deep learning-based semantic segmentation techniques ... -
Personality-aware deception detection from behavioral cues
(Bilkent University, 2021-09)We encounter with deceptive behavior in our daily lives, almost everyday. Even the most reliable ones among us can sometimes be deceptive either deliberately or unintentionally. Since people are not successful at detecting ... -
Facial analysis of dyadic interactions using multiple instance learning
(Bilkent University, 2021-09)Interpretation of nonverbal behavior is vital for a reliable analysis of social interactions. To this end, we automatically analyze facial expressions of romantic couples during their dyadic interactions, for the first time ... -
Effective and explainable mechanisms for natural language interface in databases
(Bilkent University, 2021-09)Structured Query Language (SQL) is a commonly used tool to extract and present structured data stored in Relational Database Management Systems (RDBMSs), yet inherited complexities of SQL create barriers for naive users ... -
Analysis of scratch-pad memory-based processor architecture for graph applications
(Bilkent University, 2021-09)In graph analytic applications, main memory accesses prove to be a bottleneck as graphs have a poor spatial and temporal locality usage in the caches and higher memory hierarchy. Although this bottleneck is slightly ... -
An orthogonal layout algorithm for small compound graphs
(Bilkent University, 2021-09)Information visualization is the study of different approaches that aid in the visualization and examination of data. Among the broad variety of different op-tions and techniques available in this field is “Graph Drawing”, ... -
Serious game approach to introduce the code review practice
(Bilkent University, 2021-09)Code Review is an accepted and widely utilized software engineering practice that focuses on improving code via manual inspections. However, this practice is not addressed adequately in a typical software engineering ... -
Age and gender normalization in kinship verification
(Bilkent University, 2021-09)Kinship veri cation from facial images using deep learning is an interesting problem that is unsolved and gains growing attention of the research community. However, the most recent kinship veri cation systems su er from ... -
Spatio-temporal assessment of pain intensity through facial transformation-based representation learning
(Bilkent University, 2021-09)The nature of pain makes it di cult to assess due to its subjectivity and multidimensional characteristics that include intensity, duration, and location. However, the ability to assess pain in an objective and reliable ... -
Visuall: a quickly customizable library for jumpstarting visual graph analysis components
(Bilkent University, 2021-09)Graph visualization is an area of information visualization, where relational data is depicted in the form of nodes (objects) and edges (links). Many people or organizations utilize graph visualization for insightful ... -
Towards deeply intelligent interfaces in relational databases
(Bilkent University, 2021-08)Relational databases is one of the most popular and broadly utilized infrastruc-tures to store data in a structured fashion. In order to retrieve data, users have to phrase their information need in Structured Query Language ... -
Learning visual similarity for image retrieval with global descriptors and capsule networks
(Bilkent University, 2021-07)Finding matching images across large and unstructured datasets plays an im-portant role in many computer vision applications. With the emergence of deep learning-based solutions, various visual tasks such as image retrieval ... -
Genome reconstruction attacks on genomic data-sharing beacons
(Bilkent University, 2021-07)Sharing genome data in a privacy-preserving way stands as a major bottleneck in front of the scientific progress promised by the big data era in genomics. A community-driven protocol named genomic data-sharing beacon ... -
Polishing copy number variant calls on exome sequencing data VIA deep learning
(Bilkent University, 2021-07)Accurate and efficient detection of copy number variants (CNVs) is of critical importance due to their significant association with complex genetic diseases. Although algorithms that use whole genome sequencing (WGS) data ... -
Hypergraph partitioning and reordering for parallel sparse triangular solves and tensor decomposition
(Bilkent University, 2021-07)Several scientific and real-world problems require computations with sparse ma-trices, or more generally, sparse tensors which are multi-dimensional arrays. For sparse matrix computations, parallelization of sparse triangular ... -
Machine learning assisted intraoperative assessment of brain tumor margins using HRMAS NMR spectroscopy
(Bilkent University, 2021-07)Complete resection of the tumor is important for survival in glioma patients. Even if the gross total resection was achieved, left-over micro-scale tissue in the excision cavity risks recurrence. High Resolution Magic Angle ... -
A media caching approach utilizing social groups information in 5G edge networks
(Bilkent University, 2021-03)Increased demand for media content by mobile applications has imposed huge pressure on wireless cellular networks to deliver the content efficiently and ef-fectively. To keep up with this demand, mobile edge computing (MEC), ... -
Performance improvement on latency-bound parallel HPC applications by message sharing between processors
(Bilkent University, 2021-02)The performance of paralellized High Performance Computing (HPC) applica-tions is tied to the efficiency of the underlying processor-to-processor commu-nication. In latency-bound applications, the performance runs into ... -
General reuse-centric CNN accelerator
(Bilkent University, 2021-02)Reuse-centric CNN acceleration speeds up CNN inference by reusing computa-tions for similar neuron vectors in CNN’s input layer or activation maps. This new paradigm of optimizations is however largely limited by the ... -
PAMOGK-Web: a framework for cancer subtype identification using copy number variatıons
(Bilkent University, 2020-12)Detection of molecular sub-groups of cancer is important for developing cancer therapeutics and to understand the underlying causes of the molecular differences in these groups. The cancer sequencing projects made multi-omics ...
RSS 1.0