A5075890706- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Sentiment Analysis and Opinion Mining
- Data Quality and Management
- Computational Drug Discovery Methods
- Hate Speech and Cyberbullying Detection
- IoT and Edge/Fog Computing
- Cloud Computing and Resource Management
- Web Data Mining and Analysis
- Blockchain Technology Applications and Security
- Advanced Text Analysis Techniques
- Industrial Vision Systems and Defect Detection
- Stock Market Forecasting Methods
- Pharmacogenetics and Drug Metabolism
- Digital Transformation in Industry
- Spam and Phishing Detection
- Biometric Identification and Security
- Graph Theory and Algorithms
- Privacy-Preserving Technologies in Data
- Cancer Diagnosis and Treatment
- Pharmacovigilance and Adverse Drug Reactions
- User Authentication and Security Systems
- Energy Load and Power Forecasting
- Misinformation and Its Impacts
- Digital Communication and Language
Yıldız Technical University
2021-2023
University of Southern Denmark
2023
Office of Management
2022
Shahid Chamran University of Ahvaz
2022
Bahçeşehir University
2016-2021
Cleveland Clinic
2014-2018
Kent State University
2014-2015
Although potential drug–drug interactions (PDDIs) are a significant source of preventable drug-related harm, there is currently no single complete PDDI information. In the current study, all publically available sources information that could be identified using comprehensive and broad search were combined into dataset. The dataset merged fourteen different including 5 clinically-oriented sources, 4 Natural Language Processing (NLP) Corpora, Bioinformatics/Pharmacovigilance sources. As...
This study investigates the usage of Emoji characters on social networks and effects in text mining sentiment analysis.As it provides live access to based public opinions, we chose Twitter as our information source analysis.We collected data for some global positive negative events analyze impact analysis.In analysis, noticed that utilization analysis results higher scores.Furthermore, observed appeared have overall sentiments opinions comparison opinions.
Traditional maintenance approaches often result in either premature replacement of machine parts or downtime production lines due to malfunctions. Consequently, these lead significant amount waste material, time and, ultimately, money. In this study, a learning-based predictive approach is proposed predict the Remaining Useful Life manufacturing. Using data collected from integrated IoT sensors real-world factory, we attempted address problem predicting potential equipment failures on...
Prognostication in cancer is challenging and inaccurate. C-Reactive Protein (CRP), a cheap sensitive marker of inflammation may help. This study investigated the relationship between CRP prognosis large cohort solid tumors with mixed diagnoses stages.Electronic medical records 4931 adults who attended Taussig Cancer Institute from 2006-2012 were reviewed. Demographic clinical characteristics recorded. Maximum (mCRP) was identified for each individual. analysed as time-dependent, continuous...
The Covid-19 pandemic has made individuals and organizations to rethink the way of handling identity verification credentials sharing particularly in quarantined situations. In this study, we investigate inefficiencies traditional systems, discuss how a proper implementation Blockchain technology would result safer, more secure, privacy respecting remote friendly systems. As result, propose based framework for digital verification, record attestation sharing, explain details with certain use...
To develop a novel pharmacovigilance inferential framework to infer mechanistic explanations for asserted drug-drug interactions (DDIs) and deduce potential DDIs.A mechanism-based DDI knowledge base was constructed by integrating from several existing sources at the pharmacokinetic, pharmacodynamic, pharmacogenetic, multipathway interaction levels. A query-based then created utilize this integrated in conjunction with 9 inference rules DDIs DDIs.The discovery demystification (D3) system...
The disruptive technology of blockchain can deliver secure solutions without the need for a central authority. In protocols, assets that belong to participant are controlled through private key an asymmetric pair is owned by participant. Although, this lets network participants have sovereignty on their assets, it comes with responsibility managing own keys. Currently, there exists two major bottlenecks in keys; $a)$ users don't efficient and way store keys, $b)$ no recovery mechanism case...
Purpose The purpose of this paper is to develop a model for autonomous cars establish trusted parties by combining distributed ledgers and self-driving in the traffic provide single version truth thus build public trust. Design/methodology/approach model, which authors call Witness Things, based on keeping decision logs vehicles through use vehicular networks vehicle-to-vehicle/vehicle-to-infrastructure (or vice versa) communications. provides helps enable vehicle industry, related...
Drug-drug interaction (DDI) is a vital problem that threatens people's health. However, the prediction of DDIs through in-vivo experiments not only extremely costly but also difficult as many serious side effects are hard to detect in and in-vitro settings. The aim this study was assess effectiveness similarity-based in-silico computational DDI approaches provide cost effective scalable solution predict potential DDIs.In study, widely known methods were utilized discover novel DDIs. More...
Despite the significant health impacts of adverse events associated with drug-drug interactions, no standard models exist for managing and sharing evidence describing potential interactions between medications. Minimal information have been used in other communities to establish community consensus around simple capable communicating useful information. This paper reports on a new minimal model interactions. A task force Semantic Web Health Care Life Sciences Community Group World-Wide...
The field of explainability in artificial intelligence (AI) has witnessed a growing number studies and increasing scholarly interest. However, the lack human-friendly individual interpretations explaining outcomes machine learning algorithms significantly hindered acceptance these methods by clinicians their research clinical practice. To address this issue, our study uses counterfactual explanations to explore applicability "what if?" scenarios medical research. Our aim is expand...
The structured data available in the semantic web have been rapidly increasing with contribution of linked open and other similar community initiatives recent years. Thus, searching processing large become more challenging. Building a summary graph can help reduce computational complexity query time searches by providing an intermediate index structure which contains entity type classes relations between them. In current study, we propose algorithm for discovering types entities RDF building...
The systems with a short window of opportunity for actions and decisions require developing solutions providing real-time streaming analytics. Real-time big data analytics is challenging task. In this paper, we propose architecture social network analysis. As case study, investigated the relation between public opinions on media about cryptocurrencies changes in their prices using lexicon-based sentiment analysis approaches goal assessing feasibility predicting cryptocurrencies. Two...
The problem of food image classification has become a prominent topic that attracts many researchers due to its multiple benefits and applications in various aspects life, from health marketing. Image rely heavily on recent advancements computer vision-based object recognition. In this paper, several deep transfer learning methods were investigated for classification. Furthermore, we applied data augmentation approach expand the Food-101 dataset. impact applying was evaluated using five...
Information searching techniques are rapidly developing as the World Wide Web (WWW) evolves. Along with development of information technologies, need for acquiring domain knowledge bases, accessing data sources and discovering insights increases. The advancements in discovery, management artificial intelligence require faster processing, storing more intelligent applications. This study provides an discovery integration approach linked open semantic web. Using semantics embedded ontologies,...
Bu çalışmanın amacı, Türkçe için kapsamlı yeni bir duygu kütüphanesi geliştirmektir. kütüphane ile sosyal medya paylaşımlarında etkili analizi çalışmalarının yapılmasına katkı sunmak hedeflenmektedir. çalışmada, varolan diğer kütüphanelerden bazıları incelenmiş olup bunları genişleten oluşturulmuştur. Daha önce yapılmış çalışmalara ek olarak kütüphaneye basit emoji karakterler ve puanlama altyapısı eklenmiştir. Geliştirilen Duygu Kütüphanesi'nin verimliliğini ölçmek Twitter'da belli...
The significant improvements in communication technologies revealed innovative online services.Time and location barriers have been eliminated customer satisfaction has gained importance.The most remarkable evolution is observed electronic commerce.Electronic commerce a widely accepted industry which provides an effective medium for both retailers customers, enabling to perform transactions through websites.The analysis of consumer preferences become key aspect this challenging...
With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating problems such as hatred, racism, and sexism. Detecting language use is crucial to prevent from being widely shared on media. However, accurate detection irony, implication, various forms hate speech media remains challenge. Natural language-based deep learning models require extensive training with large, comprehensive, labeled datasets....