Bilgisayar Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/203

Browse

Now showing 1 - 20 of 114

3-State Protein Secondary Structure Prediction based on SCOPe Classes
(INST TECNOLOGIA PARANARUA PROF ALGACYR MUNHOZ MADER 3775-CIC, 81350-010 CURITIBA-PARANA, BRAZIL, 2021) Atasever, Sema; Azgınoglu, Nuh; Erbay, Hasan; Aydın, Zafer; 0000-0002-2295-7917; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Atasever, Sema
Abstract Improving the accuracy of protein secondary structure prediction has been an important task in bioinformatics since it is not only the starting point in obtaining tertiary structure in hierarchical modeling but also enhances sequence analysis and sequence-structure threading to help determine structure and function. Herein we present a model based on DSPRED classifier, a hybrid method composed of dynamic Bayesian networks and a support vector machine to predict 3-state secondary structure information of proteins. We used the SCOPe (Structural Classification of Proteins-extended) database to train and test the model. The results show that DSPRED reached a Q3 accuracy rate of 82.36% when trained and tested using proteins from all SCOPe classes. We compared our method with the popular PSIPRED on the SCOPe test datasets and found that our method outperformed PSIPRED.
4D-QSAR investigation and pharmacophore identification of pyrrolo[2,1-c][1,4]benzodiazepines using electron conformational–genetic algorithm method
(Taylor and Francis Ltd., 2016) Özalp, A.; Yavuz, S.Ç.; Sabancı, N.; Çapur, F.; Kökbudak, Z.; Sarıpınar, E.; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Çopur, Fatih
In this paper, we present the results of pharmacophore identification and bioactivity prediction for pyrrolo[2,1-c][1,4]benzodiazepine derivatives using the electron conformational–genetic algorithm (EC–GA) method as 4D-QSAR analysis. Using the data obtained from quantum chemical calculations at PM3/HF level, the electron conformational matrices of congruity (ECMC) were constructed by EMRE software. The ECMC of the lowest energy conformer of the compound with the highest activity was chosen as the template and compared with the ECMCs of the lowest energy conformer of the other compounds within given tolerances to reveal the electron conformational submatrix of activity (ECSA, i.e. pharmacophore) by ECSP software. A descriptor pool was generated taking into account the obtained pharmacophore. To predict the theoretical activity and select the best subset of variables affecting bioactivities, the nonlinear least square regression method and genetic algorithm were performed. For four types of activity including the GI50, TGI, LC50 and IC50 of the pyrrolo[2,1-c][1,4] benzodiazepine series, the r2 train, r2 test and q2 values were 0.858, 0.810, 0.771; 0.853, 0.848, 0.787; 0.703, 0.787, 0.600; and 0.776, 0.722, 0.687, respectively.
Aguhyper: a hyperledger-based electronic health record management framework
(PEERJ INC, 2024) Dedeturk, Beyhan Adanur; Bakir-Gungor, Burcu; 0000-0003-4983-2417; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Dedeturk, Beyhan Adanur; Bakir-Gungor, Burcu
The increasing importance of healthcare records, particularly given the emergence of new diseases, emphasizes the need for secure electronic storage and dissemination. With these records dispersed across diverse healthcare entities, their physical maintenance proves to be excessively time-consuming. The prevalent management of electronic healthcare records (EHRs) presents inherent security vulnerabilities, including susceptibility to attacks and potential breaches orchestrated by malicious actors. To tackle these challenges, this article introduces AguHyper, a secure storage and sharing solution for EHRs built on a permissioned blockchain framework. AguHyper utilizes Hyperledger Fabric and the InterPlanetary Distributed File System (IPFS). Hyperledger Fabric establishes the blockchain network, while IPFS manages the off-chain storage of encrypted data, with hash values securely stored within the blockchain. Focusing on security, privacy, scalability, and data integrity, AguHyper’s decentralized architecture eliminates single points of failure and ensures transparency for all network participants. The study develops a prototype to address gaps identified in prior research, providing insights into blockchain technology applications in healthcare. Detailed analyses of system architecture, AguHyper’s implementation configurations, and performance assessments with diverse datasets are provided. The experimental setup incorporates CouchDB and the Raft consensus mechanism, enabling a thorough comparison of system performance against existing studies in terms of throughput and latency. This contributes significantly to a comprehensive evaluation of the proposed solution and offers a unique perspective on existing literature in the field.
Alzheimer Disease Associated Loci: APOE Single Nucleotide Polymorphisms in Marmara Region
(MDPI, 2024) Ismail, Aya Badeea; Dundar, Mehmet Sait; Erguzeloglu, Cemre Ornek; Ergoren, Mahmut Cerkez; Alemdar, Adem; Ozemri Sag, Sebnem; Temel, Sehime Gulsun; 0000-0002-0336-4825; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Dundar, Mehmet Sait
Alzheimer’s disease (AD) is a major global health challenge, especially among individuals aged 65 or older. According to population health studies, Turkey has the highest AD prevalence in the Middle East and Europe. To accurately determine the frequencies of common and rare APOE single nucleotide polymorphisms (SNPs) in the Turkish population residing in the Marmara Region, we conducted a retrospective study analyzing APOE variants in 588 individuals referred to the Bursa Uludag University Genetic Diseases Evaluation Center. Molecular genotyping, clinical exome sequencing, bioinformatics analysis, and statistical evaluation were employed to identify APOE polymorphisms and assess their distribution. The study revealed the frequencies of APOE alleles as follows: ε4 at 9.94%, ε2 at 9.18%, and ε3 at 80.68%. The gender-based analysis in our study uncovered a tendency for females to exhibit a higher prevalence of mutant genotypes across various SNPs. The most prevalent haplotype observed was ε3/ε3, while rare APOE SNPs were also identified. These findings align with global observations, underscoring the significance of genetic diversity and gender-specific characteristics in comprehending health disparities and formulating preventive strategies.
AMP-GSM: Prediction of Antimicrobial Peptides via a Grouping–Scoring–Modeling Approach
(MDPI, 2023) Soylemez, Ummu Gulsum; Yousef, Malik; Bakir-Gungor, Burcu; 0000-0002-6602-772X; 0000-0002-2272-6270; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Soylemez, Ummu Gulsum; Bakir-Gungor, Burcu
Due to the increasing resistance of bacteria to antibiotics, scientists began seeking new solutions against this problem. One of the most promising solutions in this field are antimicrobial peptides (AMP). To identify antimicrobial peptides, and to aid the design and production of novel antimicrobial peptides, there is a growing interest in the development of computational prediction approaches, in parallel with the studies performing wet-lab experiments. The computational approaches aim to understand what controls antimicrobial activity from the perspective of machine learning, and to uncover the biological properties that define antimicrobial activity. Throughout this study, we aim to develop a novel prediction approach that can identify peptides with high antimicrobial activity against selected target bacteria. Along this line, we propose a novel method called AMP-GSM (antimicrobial peptide-grouping-scoring-modeling). AMP-GSM includes three main components: grouping, scoring, and modeling. The grouping component creates sub-datasets via placing the physicochemical, linguistic, sequence, and structure-based features into different groups. The scoring component gives a score for each group according to their ability to distinguish whether it is an antimicrobial peptide or not. As the final part of our method, the model built using the top-ranked groups is evaluated (modeling component). The method was tested for three AMP prediction datasets, and the prediction performance of AMP-GSM was comparatively evaluated with several feature selection methods and several classifiers. When we used 10 features (which are members of the physicochemical group), we obtained the highest area under curve (AUC) value for both the Gram-negative (99%) and Gram-positive (98%) datasets. AMP-GSM investigates the most significant feature groups that improve AMP prediction. A number of physico-chemical features from the AMP-GSM's final selection demonstrate how important these variables are in terms of defining peptide characteristics and how they should be taken into account when creating models to predict peptide activity.
Analyzing lifetime of energy harvesting wireless multimedia sensor nodes in industrial environments
(Elsevier, 2018) Tekin, Nazli; Erdem, H.Emre; Gungor, V.Cagri; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü;
Recently, there has been a great demand for multimedia communication using Wireless Multimedia Sensor Networks (WMSNs) in industrial environments thanks to their low cost, flexibility, and rapid deployment. However, WMSNs face a major challenge of limited lifetime due to their limited battery capacity. Compared to regular data transmission, multimedia data transmission causes higher energy consumption because of larger data sizes leading to faster depletion of sensor node's batteries. The objective of this paper is to analytically quantify the impact of different energy harvesting methods based on vibration, indoor solar, and temperature difference as well as Fast-Zonal DCT and BinDCT based image compression methods on the lifetime of Telos and Mica2 sensor nodes deployed in indoor industrial environment. Performance results show that energy harvesting and image compression techniques improve lifetime of Mica2 and Telos motes by 51.8% and 25.8%, respectively when used with proper power management methods.
Application of Biological Domain Knowledge Based Feature Selection on Gene Expression Data
(MDPIST ALBAN-ANLAGE 66, CH-4052 BASEL, SWITZERLAND, 2021) Yousef, Malik; Kumar, Abhishek; Bakir-Gungor, Burcu; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Bakir-Gungor, Burcu
In the last two decades, there have been massive advancements in high throughput technologies, which resulted in the exponential growth of public repositories of gene expression datasets for various phenotypes. It is possible to unravel biomarkers by comparing the gene expression levels under different conditions, such as disease vs. control, treated vs. not treated, drug A vs. drug B, etc. This problem refers to a well-studied problem in the machine learning domain, i.e., the feature selection problem. In biological data analysis, most of the computational feature selection methodologies were taken from other fields, without considering the nature of the biological data. Thus, integrative approaches that utilize the biological knowledge while performing feature selection are necessary for this kind of data. The main idea behind the integrative gene selection process is to generate a ranked list of genes considering both the statistical metrics that are applied to the gene expression data, and the biological background information which is provided as external datasets. One of the main goals of this review is to explore the existing methods that integrate different types of information in order to improve the identification of the biomolecular signatures of diseases and the discovery of new potential targets for treatment. These integrative approaches are expected to aid the prediction, diagnosis, and treatment of diseases, as well as to enlighten us on disease state dynamics, mechanisms of their onset and progression. The integration of various types of biological information will necessitate the development of novel techniques for integration and data analysis. Another aim of this review is to boost the bioinformatics community to develop new approaches for searching and determining significant groups/clusters of features based on one or more biological grouping functions.
Artificial cells: A potentially groundbreaking field of research and therapy
(Sciendo, 2024) Dundar, Mehmet Sait; Yildirim, A. Baki; Yildirim, Duygu T.; Akalin, Hilal; Dundar, Munis; 0000-0002-0336-4825; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Dundar, Mehmet Sait
Artificial cells are synthetic constructs that mimic the architecture and functions of biological cells. Artificial cells are designed to replicate the fundamental principles of biological systems while also have the ability to exhibit novel features and functionalities that have not been achieved before. Mainly, Artificial cells are made up of a basic structure like a cell membrane, nucleus, cytoplasm and cellular organelles. Nanotechnology has been used to make substances that possess accurate performance in these structures. There are many roles that artificial cells can play such as drug delivery, bio-sensors, medical applications and energy storage. An additional prominent facet of this technology is interaction with biological systems. The possibility of synthetic cells being compatible with living organisms opens up the potential for interfering with specific biological activities. This element is one of the key areas of research in medicine, aimed at developing novel therapies and comprehending life processes. Nevertheless, artificial cell technology is not exempt from ethical and safety concerns. The interplay between these structures and biological systems may give rise to questions regarding their controllability and safety. Hence, the pursuit of artificial cell research seeks to reconcile ethical and safety concerns with the potential advantages of this technology
An asymptotic-numerical hybrid method for singularly perturbed system of two-point reaction-diffusion boundary-value problems
(SCIENTIFIC TECHNICAL RESEARCH COUNCIL TURKEY-TUBITAK, ATATURK BULVARI NO 221, KAVAKLIDERE, TR-06100 ANKARA, TURKEY, 2019) Cengizci, Suleyman; Natesan, Srinivasan; Atay, Mehmet Tank; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü;
This article focuses on the numerical approximate solution of singularly perturbed systems of second-order reaction-diffusion two-point boundary-value problems for ordinary differential equations. To handle these types of problems, a numerical-asymptotic hybrid method has been used. In this hybrid approach, an efficient asymptotic method, the so-called successive complementary expansion method (SCEM) is employed first, and then a numerical method based on finite differences is applied to approximate the solution of corresponding singularly perturbed reaction-diffusion systems. Two illustrative examples are provided to demonstrate the efficiency, robustness, and easy applicability of the present method with convergence properties.
Big Data acquired by Internet of Things-enabled industrial multichannel wireless sensors networks for active monitoring and control in the smart grid Industry 4.0
(ELSEVIERRADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS, 2021) Faheem, Muhammad; Fizza, Ghulam; Ashraf, Muhammad Waqar; Butt, Rizwan Aslam; Ngadi, Md. Asri; Gungor, Vehbi Cagri; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Faheem, Muhammad; Gungor, Vehbi Cagri
Smart Grid Industry 4.0 (SGI4.0) defines a new paradigm to provide high-quality electricity at a low cost by reacting quickly and effectively to changing energy demands in the highly volatile global markets. However, in SGI4.0, the reliable and efficient gathering and transmission of the observed information from the Internet of Things (IoT)-enabled Cyberphysical systems, such as sensors located in remote places to the control center is the biggest challenge for the Industrial Multichannel Wireless Sensors Networks (IMWSNs). This is due to the harsh nature of the smart grid environment that causes high noise, signal fading, multipath effects, heat, and electromagnetic interference, which reduces the transmission quality and trigger errors in the IMWSNs. Thus, an efficient monitoring and real-time control of unexpected changes in the power generation and distribution processes is essential to guarantee the quality of service (QoS) re-quirements in the smart grid. In this context, this paper de-scribes the dataset contains measurements acquired by the IMWSNs during events monitoring and control in the smart grid. This work provides an updated detail comparison of our proposed work, including channel detection, channel assign-ment, and packets forwarding algorithms, collectively called CARP [1] with existing G-RPL [2] and EQSHC [3] schemes in the smart grid. The experimental outcomes show that the dataset and is useful for the design, development, testing, and validation of algorithms for real-time events monitoring and control applications in the smart grid. (C) 2021 The Authors. Published by Elsevier Inc.
Big datasets of optical-wireless cyber-physical systems for optimizing manufacturing services in the internet of things-enabled industry 4.0
(ELSEVIER, 2022) Faheem, Muhammad; Butt, Rizwan Aslam; 0000-0003-4628-4486; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Faheem, Muhammad
The Industry 4.0 revolution is aimed to optimize the prod- uct design according to the customers’ demand, quality re- quirements and economic feasibility. Industry 4.0 employs advanced two-way communication technologies for optimiz- ing the manufacturing process to increase the sales of the products and revenues to cope the existing global economy issues. In Industry 4.0, big data obtained from the Internet of Things (IoT)-enabled industrial Cyber-Physical Systems (CPS) plays an important role in enhancing the system service per- formance to boost the productivity with enhanced quality of customer experience. This paper presents the big datasets obtained from the Internet of things (IoT)-enabled Optical- Wireless Sensor Networks (OWSNs) for optimizing service systems’ performance in the electronics manufacturing In- dustry 4.0. The updated raw and analyzed big datasets of our published work [3] contain five values namely, data de- livery, latency, congestion, throughput, and packet error rate in OWSNs. The obtained dataset are useful for optimizing the service system performance in the electronics manufacturing Industry 4.0.
Blockchain for genomics and healthcare: a literature review, current status, classification and open issues
(PEERJ INC341-345 OLD ST, THIRD FLR, LONDON EC1V 9LL, ENGLAND, 2021) Dedeturk, Beyhan Adanur; Soran, Ahmet; Bakir Gungor, Burcu; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Dedeturk, Beyhan Adanur; Soran, Ahmet; Bakir Gungor, Burcu
The tremendous boost in the next generation sequencing technologies and in the "omics"technologies resulted in the generation of hundreds of gigabytes of data per day. Nowadays, via integrating -omics data with other data types, such as imaging and electronic health record (EHR) data, panomics studies attempt to identify novel and potentially actionable biomarkers for personalized medicine applications. In this respect, for the accurate analysis of -omics data and EHR, there is a need to establish secure and robust pipelines that take the ethical aspects into consideration, regulate privacy and ownership issues, and data sharing. These days, blockchain technology has picked up significant attention in diverse fields, including genomics, since it offers a new solution for these problems from a different perspective. Blockchain is an immutable transaction ledger, which offers secure and distributed system without a central authority. Within the system, each transaction can be expressed with cryptographically signed blocks, and the verification of transactions is performed by the users of the network. In this review, firstly, we aim to highlight the challenges of EHR and genomic data sharing. Secondly, we attempt to answer "Why"or "Why not"the blockchain technology is suitable for genomics and healthcare applications in detail. Thirdly, we elucidate the general blockchain structure based on the Ethereum, which is a more suitable technology for the genomic data sharing platforms. Fourthly, we review current blockchain-based EHR and genomic data sharing platforms, evaluate the advantages and disadvantages of these applications, and classify these applications using different metrics. Finally, we conclude by discussing the open issues and introducing our suggestion on the topic. In summary, to facilitate the diagnosis, monitoring and therapy of diseases with the effective analysis of -omics data with other available data types, through this review, we put forward the possible implications of the blockchain technology to life sciences and healthcare.
BLSTM based night-time wildfire detection from video
(Public Library of Science, 2022) Agirman, Ahmet K; Tasdemir, Kasim; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Ağırman, Ahmet K.; Taşdemir, Kasım
Distinguishing fire from non-fire objects in night videos is problematic if only spatial features are to be used. Those features are highly disrupted under low-lit environments because of several factors, such as the dynamic range limitations of the cameras. This makes the analysis of temporal behavior of night-time fire indispensable for classification. To this end, a BLSTM based night-time wildfire event detection from a video algorithm is proposed. It is shown in the experiments that the proposed algorithm attains 95.15% of accuracy when tested against a wide variety of actual recordings of night-time wildfire incidents and 23.7 ms per frame detection time. Moreover, to pave the way for more targeted solutions to this challenging problem, experiment-based thorough investigations of possible sources of incorrect predictions and discussion of the unique nature of night-time wildfire videos are presented in the paper.
Cascade Control of Magnetic Levitation with Sliding Modes
(E D P SCIENCES, 17 AVE DU HOGGAR PARC D ACTIVITES COUTABOEUF BP 112, F-91944 CEDEX A, FRANCE, 2016) Eroglu, Yakup; Ablay, Gunyaz; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü;
The effectiveness and applicability of magnetic levitation systems need precise feedback control designs. A cascade control approach consisting of sliding mode control plus sliding mode control (SMC plus SMC) is designed to solve position control problem and to provide a high control performance and robustness to the magnetic levitation plant. It is shown that the SMC plus SMC cascade controller is able to eliminate the effects of the inductance related uncertainties of the electromagnetic coil of the plant and achieve a robust and precise position control. Experimental and numerical results are provided to validate the effectiveness and feasibility of the method.
Common miRNA signatures in a group of rare neuromuscular disorders
(WILEY, 111 RIVER ST, HOBOKEN 07030-5774, NJ USA, 2018) Aksu, E.; Akkaya-Ulum, Y. Z.; Balci-Peynircioglu, B.; Dayangac-Erden, D.; Yuzbasioglu, A.; Bakir-Gungor, B.; Talim, B.; Balci-Hayta, B.; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü;
Neuromuscular disorders (NMD) are heterogeneous group ofgenetic diseases that encompasses many different syndromes anddiseases that either directly or indirectly impairs the function ofskeletal muscle. However, there are currently no effective andcommon therapeutic approaches to prevent or delay the progres-sion of these diseases. Recent studies revealed important regula-tory roles for small noncoding RNAs, called microRNAs(miRNAs), in skeletal muscle function under physiological andpathological conditions. In this study, we aim to identify com-mon miRNA signatures associated with etiopathogenesis of dif-ferent neuromuscular diseases (Duchenne Muscular Dystrophy,Megaconial Congenital Muscular Dystrophy (CMD), UllrichCMD and alpha-dystroglycanopathy), each caused by mutationsin different nuclear genes encoding proteins with distinct roles.For this purpose, skeletal muscle biopsies from selected NMDspresenting mitochondrial damage (n=12, 3 from each group)and control individuals (n=3) were analyzed by using Affyme-trix GeneChip miRNA 4.0 Array. To identify differentiallyexpressed miRNAs in patients, raw data was analyzed by twodifferent programs, MeV-SAM and Affymetrix TAC. Differen-tially expressed miRNAs whose expression were found to be sta-tistically significant by both programs (miRNAs that showed anincrease/decrease by 2 fold in patient samples compared to thecontrol group) were identified as candidates. We then identifiedpotential target genes of these candidate miRNAs by using miR-Walk and classified them by using GENE ONTOLOGY-PANTHER databases. Our results revealed that 17 miRNAswere differentially expressed in patients and 5 of these miRNAsare likely involved in skeletal muscle differentiation. Our com-monality approach will provide contribution to the literature byidentifying common potential therapeutic targets and/orbiomarkers related to different rare NMDs.
A Comparative Analysis of Convolutional Neural Network Architectures for Binary Image Classification: A Case Study in Skin Cancer Detection
(Giresun Üniversitesi, 2024) Korkut, Şerife Gül; Kocabaş, Hatice; Kurban, Rifat; 0009-0007-1398-0924; 0009-0003-1760-0555; 0000-0002-0277-2210; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Korkut, Şerife Gül; Kocabaş, Hatice; Kurban, Rifat
In this study, a comprehensive comparative analysis of Convolutional Neural Network (CNN) architectures for binary image classification is presented with a particular focus on the benefits of transfer learning. The performance and accuracy of prominent CNN models, including MobileNetV3, VGG19, ResNet50, and EfficientNetB0, in classifying skin cancer from binary images are evaluated. Using a pre-trained approach, the impact of transfer learning on the effectiveness of these architectures and identify their strengths and weaknesses within the context of binary image classification are investigated. This paper aims to provide valuable insights for selecting the optimal CNN architecture and leveraging transfer learning to achieve superior performance in binary image classification applications, particularly those related to medical image analysis.
Comparative analysis of machine learning approaches for predicting respiratory virus infection and symptom severity
(PEERJ INC, 2023) Aydin, Zafer; Isik, Yunus Emre; 0000-0001-7686-6298; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Aydin, Zafer
Respiratory diseases are among the major health problems causing a burden on hospitals. Diagnosis of infection and rapid prediction of severity without time-consuming clinical tests could be beneficial in preventing the spread and progression of the disease, especially in countries where health systems remain incapable. Personalized medicine studies involving statistics and computer technologies could help to address this need. In addition to individual studies, competitions are also held such as Dialogue for Reverse Engineering Assessment and Methods (DREAM) challenge which is a community-driven organization with a mission to research biology, bioinformatics, and biomedicine. One of these competitions was the Respiratory Viral DREAM Challenge, which aimed to develop early predictive biomarkers for respiratory virus infections. These efforts are promising, however, the prediction performance of the computational methods developed for detecting respiratory diseases still has room for improvement. In this study, we focused on improving the performance of predicting the infection and symptom severity of individuals infected with various respiratory viruses using gene expression data collected before and after exposure. The publicly available gene expression dataset in the Gene Expression Omnibus, named GSE73072, containing samples exposed to four respiratory viruses (H1N1, H3N2, human rhinovirus (HRV), and respiratory syncytial virus (RSV)) was used as input data. Various preprocessing methods and machine learning algorithms were implemented and compared to achieve the best prediction performance. The experimental results showed that the proposed approaches obtained a prediction performance of 0.9746 area under the precision-recall curve (AUPRC) for infection (i.e., shedding) prediction (SC-1), 0.9182 AUPRC for symptom class prediction (SC-2), and 0.6733 Pearson correlation for symptom score prediction (SC-3) by outperforming the best leaderboard scores of Respiratory Viral DREAM Challenge (a 4.48% improvement for SC-1, a 13.68% improvement for SC-2, and a 13.98% improvement for SC-3). Additionally, over-representation analysis (ORA), which is a statistical method for objectively determining whether certain genes are more prevalent in pre-defined sets such as pathways, was applied using the most significant genes selected by feature selection methods. The results show that pathways associated with the ‘adaptive immune system’ and ‘immune disease’ are strongly linked to pre-infection and symptom development. These findings contribute to our knowledge about predicting respiratory infections and are expected to facilitate the development of future studies that concentrate on predicting not only infections but also the associated symptoms.
A Comparative Analysis of Passenger Flow Forecasting in Trams Using Machine Learning Algorithms
(Bitlis Eren Üniversitesi, 2024) Adanur Dedeturk, Beyhan; Dedeturk, Bilgi Kağan; Akbas, Ayhan; 0000-0003-4983-2417; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Adanur Dedeturk, Beyhan
Forecasting tram passenger flow is an important part of the intelligent transportation system since it helps with resource allocation, network design, and frequency setting. Due to varying destinations and departure times, it is difficult to notice large fluctuations, non-linearity, and periodicity of tram passenger flows. In this paper, the first-order difference technique is used to eliminate seasonal structure from the time series data and the performance of different machine learning algorithms on passenger flow forecasting in trams is evaluated. Furthermore, the impact of the Covid-19 pandemic on forecasting success is examined. For this purpose, the tram data of Kayseri Transportation Inc. for the years 2018-2021 are used. Different estimation models including Linear Regression, Support Vector Regression, Random Forest, Artificial Neural Network, Convolutional Neural Network, and LongTerm Short Memory are applied and the time series forecasting performances of the models are evaluated with MAPE and R2 metrics.
COMPARATIVE PERFORMANCE ANALYSIS OF ARIMA, PROPHET AND HOLT-WINTERS FORECASTING METHODS ON EUROPEAN COVID-19 DATA
(Kerim ÇETİNKAYA, 2022) Ersöz, Nur Şebnem; Güner Şahan, Pınar; Akbas, Ayhan; Bakır Güngör, Burcu; 0000-0003-3343-9936; 0000-0001-5979-0375; 0000-0002-6425-104X; 0000-0002-2272-6270; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Ersöz, Nur Şebnem; Güner Şahan, Pınar; Akbas, Ayhan; Bakır Güngör, Burcu
COVID-19 is the most common infectious disease of the last few years and has caused an outbreak all around the world. The mortality rate, which was earlier in the hundreds, increased to thousands and then to millions. Since January 2020, several scientists have attempted to understand and predict the spread of COVID-19 so that governments may make sufficient arrangements in hospitals and reduce the number of deaths. This research article presents a comparative performance analysis of ARIMA, Prophet and HoltWinters Exponential Smoothing forecasting methods to make predictions for the COVID-19 disease epidemiology in Europe. The dataset has been collected from the World Health Organization (WHO) and includes the COVID-19 case data of European countries, which is categorized by WHO between the years of 2020 and 2022. The results indicate that Holt-Winters Exponential Smoothing method (RMSE: 0.2080, MAE: 0.1747) outperforms ARIMA and Prophet forecasting methods.
Consensus embedding for multiple networks: Computation and applications
(CAMBRIDGE UNIV PRESS32 AVENUE OF THE AMERICAS, NEW YORK, NY 10013-2473, 2022) Li, Mengzhen; Coskun, Mustafa; Koyuturk, Mehmet; 0000-0002-2266-4313; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Coşkun, Mustafa
Machine learning applications on large-scale network-structured data commonly encode network information in the form of node embeddings. Network embedding algorithms map the nodes into a lowdimensional space such that the nodes that are “similar” with respect to network topology are also close to each other in the embedding space. Real-world networks often have multiple versions or can be “multiplex” with multiple types of edges with different semantics. For such networks, computation of Consensus Embeddings based on the node embeddings of individual versions can be useful for various reasons, including privacy, efficiency, and effectiveness of analyses. Here, we systematically investigate the performance of three dimensionality reduction methods in computing consensus embeddings on networks with multiple versions: singular value decomposition, variational auto-encoders, and canonical correlation analysis (CCA). Our results show that (i) CCA outperforms other dimensionality reduction methods in computing concensus embeddings, (ii) in the context of link prediction, consensus embeddings can be used to make predictions with accuracy close to that provided by embeddings of integrated networks, and (iii) consensus embeddings can be used to improve the efficiency of combinatorial link prediction queries on multiple networks by multiple orders of magnitude

Browse

Browsing Bilgisayar Mühendisliği Bölümü Koleksiyonu by Access Right "info:eu-repo/semantics/openAccess"