A5091723521- Internet Traffic Analysis and Secure E-voting
- Network Security and Intrusion Detection
- Spam and Phishing Detection
- Digital Media Forensic Detection
- Misinformation and Its Impacts
- Advanced Malware Detection Techniques
- AI in cancer detection
- Complexity and Algorithms in Graphs
- IoT and Edge/Fog Computing
- Advanced Steganography and Watermarking Techniques
- Text and Document Classification Technologies
- Adversarial Robustness in Machine Learning
- Galaxies: Formation, Evolution, Phenomena
- Computational Geometry and Mesh Generation
- Software Engineering Research
- Mobile Ad Hoc Networks
- Cancer Genomics and Diagnostics
- Anomaly Detection Techniques and Applications
- Opportunistic and Delay-Tolerant Networks
- Brain Tumor Detection and Classification
- Web Data Mining and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Radio Astronomy Observations and Technology
- Astronomy and Astrophysical Research
- Explainable Artificial Intelligence (XAI)
Siemens Healthcare (Germany)
2024-2025
Eastern Michigan University
2021-2024
Southern Illinois University Carbondale
2024
Jordan University of Science and Technology
2012-2024
University of Illinois Urbana-Champaign
2024
Purdue University Fort Wayne
2024
Hashemite University
2024
Geneva College
2024
University of Geneva
2023
University of Technology Sydney
2023
Abstract This work introduces a predictive Length of Stay (LOS) framework for lung cancer patients using machine learning (ML) models. The proposed to deal with imbalanced datasets classification-based approaches electronic healthcare records (EHR). We have utilized supervised ML methods predict inpatients LOS during ICU hospitalization the MIMIC-III dataset. Random Forest (RF) Model outperformed other models and achieved predicted results three phases. With clinical significance features...
<abstract><p>This study explores the use of Generative artificial intelligence (GenAI) tool ChatGPT in higher education. Amidst potential benefits and risk misuse, this research investigates tool's role as a classroom aid its impact on learning outcomes experiences. Three case studies involving undergraduate postgraduate ICT students were conducted. Findings revealed positive perception useful enjoyable resource. Most indicated willingness to such AI tools future. Additionally,...
Abstract We investigate the impact and mitigation of extragalactic foregrounds for cosmic microwave background (CMB) lensing power spectrum analysis Atacama Cosmology Telescope (ACT) data release 6 (DR6) data. Two independent sky simulations are used to test a range strategies. demonstrate that finding then subtracting point sources, models clusters, using profile bias-hardened estimator together reduce fractional biases well below statistical uncertainties, with inferred amplitude, A lens ,...
The fast growth of technology in online communication and social media platforms alleviated numerous difficulties during the COVID-19 epidemic. However, it was utilized to propagate falsehoods misleading information about disease vaccination. In this study, we investigate ability deep neural networks, namely, Long Short-Term Memory (LSTM), Bi-directional LSTM, Convolutional Neural Network (CNN), a hybrid CNN LSTM automatically classify identify fake news content related pandemic posted on...
Predicting Cardiovascular Length of stay based hospitalization at the time patients' admitting to coronary care unit (CCU) or (cardiac intensive units CICU) is deemed as a challenging task hospital management systems globally. Recently, few studies examined length (LOS) predictive analytics for cardiovascular inpatients in ICU. However, there are almost scarcely real attempts utilized machine learning models predict likelihood heart failure patients ICU hospitalization. This paper introduces...
To adapt to the rapidly increasing vulnerabilities in software products and cyber threats that exploit them, security professionals are actively working with developers produce more secure systems. In development, agile methods increasingly adopted critical projects where risks prominent challenges. This adoption stems from fact highly iterative support delivering services smaller batches which allows seamlessly integrate development activities methodologies. addition, nature of encourages...
Air pollution has detrimental impacts on our physical health and the quality of living environment, particularly in smart cities. Monitoring predicting air is crucial to empower individuals make informed decisions that protect their health. Predicting accurately plays an important effective action plan mitigate create healthier more sustainable environments. This can be achieved by relying Quality Index, one most reliable indicators for pollutant concentration levels certain study provides a...
The development of Generative AI Large Language Models (LLMs) raised the alarm regarding identifying content produced through generative or humans. In one case, issues arise when students heavily rely on such tools in a manner that can affect their writing coding skills. Other plagiarism also apply. This study aims to support efforts detect and identify textual generated using LLM tools. We hypothesize LLMs-generated text is detectable by machine learning (ML), investigate ML models...
This study seeks to enhance academic integrity by providing tools detect AI-generated content in student work using advanced technologies. The findings promote transparency and accountability, helping educators maintain ethical standards supporting the responsible integration of AI education. A key contribution this is generation CyberHumanAI dataset, which has 1000 observations, 500 are written humans other produced ChatGPT. We evaluate various machine learning (ML) deep (DL) algorithms on...
Medical diagnosis via image processing and machine learning is considered one of the most important issues artificial intelligence systems. In this paper, we present a approach to detect whether an MRI brain contains tumor or not. The results show that such very promising.
Cyberattacks have increased in tandem with the exponential expansion of computer networks and network applications throughout world. In this study, we evaluate compare four features selection methods, seven classical machine learning algorithms, deep algorithm on one million random instances CSE-CIC-IDS2018 big data set for intrusions. The dataset was preprocessed cleaned all algorithms were trained original values features. feature methods highlighted importance related to forwarding...
CMB lensing maps probe the mass distribution in projection out to high redshifts, but significant sensitivity low-redshift structure remains. In this paper we discuss a method remove contributions from by subtracting suitably scaled galaxy density maps, nulling low redshift with model-insensitive procedure that is similar delensing. This results high-$z$-only map can provide of growth at uniquely redshifts: if systematics be controlled, forecast CMB-S4 combined Rubin-LSST-like survey...
With the rapid growth of data exfiltration carried out by cyber attacks, Covert Timing Channels (CTC) have become an imminent network security risk that continues to grow in both sophistication and utilization. These types channels utilize inter-arrival times steal sensitive from targeted networks. CTC detection relies increasingly on machine learning techniques, which statistical-based metrics separate malicious (covert) traffic flows legitimate (overt) ones. However, given efforts attacks...
Covert timing channels are an important alternative for transmitting information in the world of Internet Things (IoT). In covert data encoded inter-arrival times between consecutive packets based on modifying transmission time legitimate traffic. Typically, modification takes place by delaying transmitted sender side. A key aspect is to find threshold packet delay that can accurately distinguish traffic from Based we assess level dangerous security threats or quality transferred sensitive...
Social media sites are considered one of the most important sources data in many fields, such as health, education, and politics. While surveys provide explicit answers to specific questions, posts social have same implicitly occurring text. This research aims develop a method for extracting implicit from large tweet collections, demonstrate this an concern: problem heart attacks. The approach is collect tweets containing “heart attack” then select those ones with useful information....
In the era of digital healthcare, biomedical data sharing is paramount importance for advancement research and personalised healthcare. However, such while preserving user privacy ensuring security poses significant challenges. This paper introduces BioChainReward (BCR), a blockchain-based framework designed to address these concerns. BCR offers enhanced security, privacy, incentivisation in applications. Its architecture consists four distinct layers: data, blockchain, smart contract,...