- Security in Wireless Sensor Networks
- Mobile Ad Hoc Networks
- Advanced Authentication Protocols Security
- Advanced Text Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Opportunistic and Delay-Tolerant Networks
- Topic Modeling
- Energy Efficient Wireless Sensor Networks
- Recommender Systems and Techniques
- Vehicular Ad Hoc Networks (VANETs)
- Complex Network Analysis Techniques
- Text and Document Classification Technologies
- Cloud Computing and Resource Management
- Anomaly Detection Techniques and Applications
- Cooperative Communication and Network Coding
- User Authentication and Security Systems
- Wireless Networks and Protocols
- Neural Networks and Applications
- Imbalanced Data Classification Techniques
- Caching and Content Delivery
- AI in cancer detection
- Network Security and Intrusion Detection
- Advanced Graph Neural Networks
- Renal Transplantation Outcomes and Treatments
- Radiomics and Machine Learning in Medical Imaging
Urmia University
2016-2025
Maersk (Denmark)
2024-2025
University of Southern Denmark
2024-2025
University of Kurdistan
2021
Islamic Azad University of Urmia
2021
University College of Azarabadegan
2010-2011
Indian Institute of Technology Delhi
2005
Summary Security indices are the main tools for evaluation of status financial markets. Moreover, a part economy any country is constituted investment in stock Therefore, investors could maximize return if it becomes possible to predict future trend market with appropriate methods. The nonlinearity and nonstationarity series make their prediction complicated. This study seeks evaluate power machine‐learning models market. data used this include daily close price iShares MSCI United Kingdom...
Ovarian cancer is the fifth leading cause of mortality among women in United States. also known as forgotten or silent disease. The survival ovarian patients depends on several factors, including treatment process and prognosis.The patients' dataset compiled from Surveillance, Epidemiology, End Results (SEER) database. With help a clinician, curated, most relevant features are selected. Pearson's second coefficient skewness test used to evaluate dataset. Pearson correlation investigate...
Recommendation systems are an important and undeniable part of modern applications. Recommending items users to the that likely buy or interact with them is a solution for AI-based In this article, novel architecture used utilization pre-trained knowledge graph embeddings different approaches. The proposed consists several stages have various advantages. first step method, from data created, since multi-hop neighbors in address ambiguity redundancy problems. Then representation learning...
Abstract Background In May 2022, the World Health Organization (WHO) European Region announced an atypical Monkeypox epidemic in response to reports of numerous cases some member countries unrelated those where illness is endemic. This issue has raised concerns about widespread nature this disease around world. The experience with Coronavirus Disease 2019 (COVID-19) increased awareness pandemics among researchers and health authorities. Methods Deep Neural Networks (DNNs) have shown...
Abstract In this study, we utilized data from the Surveillance, Epidemiology, and End Results (SEER) database to predict glioblastoma patients’ survival outcomes. To assess dataset skewness detect feature importance, applied Pearson's second coefficient test of Ordinary Least Squares method, respectively. Using two sampling strategies, holdout five-fold cross-validation, developed five machine learning (ML) models alongside a feed-forward deep neural network (DNN) for multiclass...
Abstract One of the main benefits unsupervised learning is that there no need for labelled data. As a method this category, latent Dirichlet allocation (LDA) estimates semantic relations between words text effectively and can play an important role in solving various issues, including emotional analysis combination with other parameters. In study, three novel topic models called date sentiment LDA (DSLDA), author–date (ADSLDA), pack–author–date (PADSLDA) are proposed. The proposed extend...
Abstract Artificial bee colony (ABC) optimization and imperialist competitive algorithm (ICA) are two famous metaheuristic methods. In ABC, exploration is good because each moves toward random neighbors in the first second phases. exploitation poor it does not try to examine a promising region of search space carefully see if contains local minimum. this study, ICA considered improve ABC exploitation, novel swarm-based hybrid methods called ABC–ICA ABC–ICA1 proposed, which combine...
The main objective of this paper project was to create a state-of-the-art face identification technique that can handle the various difficulties caused by changes in illumination, occlusions, and facial emotions. Face detection is cornerstone computer vision, facilitating diverse applications ranging from surveillance systems human-computer interaction. Throughout paper, comprehensive exploration advancing methodologies has been undertaken, culminating developing evaluating novel approach....
License plate recognition is an essential part of contemporary surveillance systems since it helpful in many applications, including parking management, vehicle access control, traffic and law enforcement. This project aims to provide a robust dependable method for detecting license plates that will outperform existing approaches accuracy dependability. observation uses technology address challenging troubles related recognition. Our methodology primarily based on the Faster R-CNN structure,...
Positive-unlabeled (PU) learning is a problem which uses semi-supervised method for learning. In PU problem, the aim to build an accurate binary classifier without need collect negative examples training. Two-step approach solution that consists of tow steps: (1) Identifying set reliable documents. (2) Building iteratively. this paper we evaluate five combinations techniques two-step strategy. We found using Rocchio in step 1 and Expectation-Maximization 2 most effective combination our experiments.
Topic Modeling encompasses a set of techniques for text clustering and tag recommendation with significant advantages such as unsupervised learning. Based on Latent Dirichlet Allocation (LDA) topic modeling, every single word is related to topics different weight. The weights are furt her estimated in order determine the semantic relation between words rest documents. Apparently chief drawback modeling techniques, specifically LDA, lies their incapability short texts which neglected. This...
Security and privacy are two main concerns in the critical applications Internet of Things environments. Long Range Wide Area Network (LoRaWAN) is a protocol, which effectively allows long-range communication for battery-constrained end devices IoT environments, it accepted used by individuals industry. In order to facilitate use this technology gain trust users, necessary assure security information collected devices. The user authentication key establishment protocols very paramount...
Limitation in the number of characters microblogging systems, such as Twitter, forces users to use various terms for same meaning, object, or concept. Sometimes term is used a shorter form (e.g. #friend and #frnd) tweet. This problem makes finding similarities between tags their corresponding tweets harder. The classical text mining methods cannot be efficiently short tweets. Thus similarity subsequently tag recommendation, one problems social networks, needs new method with higher...
Certificate authorities (CAs) are the main components of PKI that enable us for providing basic security services in wired networks and Internet. But, we cannot use centralized CAs, mobile ad hoc (MANETs). So, many efforts have been made to adapt CA special characteristics MANETs new concepts such as distributed CAs (DCAs) proposed distribute functionality between MANET nodes. In this article, study various DCA schemes then classify these according their internal structures techniques....
Grid computing is a promising technology for future platforms and expected to provide easier access remote computational resources that are usually locally limited. Scheduling one of the active research topics in grid environments. The goal task scheduling achieve high system throughput allocate various applications. complexity problem increases with size becomes highly difficult solve effectively. Many different methods have been proposed this problem. Some these based on heuristic...
Computer-Aided diagnosis of Solitary Pulmonary Nodules using the method X-ray CT images is early detection lung cancer. In this study, a computer-aided system for pulmonary nodules on scan based support vector machine classifier provided solitary nodules. So at first step, by data mining techniques, volume are reduced. Then divided area chest, suspicious identified and eventually detected. comparison with threshold-based methods, to classify more accurately describes areas lungs. false...