Dear Students,
In the 2023-2024 Academic Year Fall Term, an introduction and information meeting will be held on 27.09.2023 at 10:00 at Room II-02, with our students who have newly registered and will enroll in the Medical Informatics and Bioinformatics Graduate programs.
We congratulate our students who have been accepted to the program and wish them success.
Multimedia Informatics Fall 2023-2024 Academic Year Orientation Meeting for our newly registered students will be held on 06.10.2023 at 12:00 pm at Room A-212. Welcome to our program!
Dear Students,
In the 2023-2024 Academic Year Fall Term, an introduction and information meeting will be held on 27.09.2023 at 10:00-11:00 at Neşe Yalabık Conference Hall, with our students who have newly registered and will enroll in the Information Systems Graduate programs. We congratulate our students who have been accepted to the program and wish them success.
We developed an efficient and scalable method for identification of signature sequences that can handle thousands of whole genomes for organisms with high mutation rates and genetic diversity. Thermodynamics is the main driving force in our method, which is tested on three highly divergent viruses. The oligonucleotides found can identify 99.9% of 1657 HCV genomes, 99.7% of 11838 HIV genomes, and 95.4% of 4016 Dengue genomes. We also show subspecies identification on genotypes 1-6 of HCV and genotypes 1-4 of the Dengue virus with >99.5% true positive and <0.05% false positive rate. None of the state-of-the-art methods achieve this performance.
Date: 11.09.2023 / 17:00 Place: A-212
With the help of large language models, prompt engineering enables easy access to vast knowledge for various applications. However, limited research has been done on multi-hop question answering using this approach. This thesis introduces a new semi-automatic prompting method for answering two-hop questions. The method involves creating a prompt with automatically selected examples by grouping answer-named entities from the training set and using a chain-of-thought principle. The results demonstrate comparable performance to fine-tuned models on the MuSiQue dataset. Ablation studies further validate the effectiveness of each component in the proposed method. The approach has the potential to be applied to more complex multi-hop question-answering systems while upholding performance on par with other state-of-the-art techniques.
Date: 07.09.2023/13:00 Place: A-212
Most of the variants in the genome are at the non-coding region. While variations in the coding region effect the protein, variations in non-coding region effect the regulatory mechanism. Therefore, observation of non-coding variations may ensure to identify variations that effect gene expression. eQTL is a popular method used for the purpose to determine the SNPs that effect the gene expression. We have implemented a python based, easy-to-use tool to understand the relationship between the somatic SNPs and gene expression based on eQTL analysis.
Date: 11.09.2023 / 14:00 Place: A-212
Crude oil prices are very volatile as they depend on many factors. Traders in this market, therefore need to constantly monitor different factors affecting the price, which can lead to information asymmetry for individual traders. Therefore, this thesis presents a comprehensive decision support system incorporating fundamental, technical, and sentiment analysis to support the decisions of crude oil traders.
Date: 06.09.2023 / 15:30 Place: A-212
Traditionally, football coaches make this decision by analyzing players' match and training performances and by analyzing the data of the opposing team. In this thesis, a new solution to the team selection problem is proposed with a data-driven approach by using the match data of the players and teams, grouping the players based on their positions and roles, considering the opposing team, tactical formation and environmental factors.
Date: 05.09.2023 / 13:00 Place: A-212
The study aimed to classify task difficulties using wavelet transform images of EEG signals and deep learning models. The EfficientNet-B0 model achieved the highest accuracy, but its performance varied significantly across individuals and task difficulties, indicating limited generalizability. The study suggests a need for further research to improve model generalizability, optimize performance, and validate the models on larger, more diverse datasets.
Date: 06.09.2023 Place: MODSIMMER Meeting Room
New technologies in distributed energy systems offer solutions for managing demand and generation variability in the grid. Trade between small grids allows cost reduction and system flexibility. This thesis proposes Multi-Agent Reinforcement Learning model for short-term energy trading among peers. It integrates short-term forecasts for load, generation, and price, leading to more accurate decision-making. Real-world data simulations demonstrate improved efficiency and stability compared to rule-based agents. This approach empowers prosumers to respond effectively to dynamic energy markets, enhancing grid reliability, energy efficiency, and sustainability.
Date: 07.09.2023 / 11:30 Place: -
©2017 METU Graduate School of Informatics. All rights reserved.
Design: CC-IG