Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
5 results
Search Results
Article Citation - WoS: 7Citation - Scopus: 8The Determination of Distinctive Single Nucleotide Polymorphism Sets for the Diagnosis of Behcet's Disease(IEEE Computer Soc, 2022-05-01) Isik, Yunus Emre; Gormez, Yasin; Aydin, Zafer; Bakir-Gungor, BurcuBehcet's Disease (BD) is a multi-system inflammatory disorder in which the etiology remains unclear. The most probable hypothesis is that genetic tendency and environmental factors play roles in the development of BD. In order to find the essential reasons, genetic changes on thousands of genes should be analyzed. Besides, there is a need for extra analysis to find out which genetic factor affects the disease. Machine learning approaches have high potential for extracting the knowledge from genomics and selecting the representative Single Nucleotide Polymorphisms (SNPs) as the most effective features for the clinical diagnosis process. In this study, we have attempted to identify representative SNPs using feature selection methods, incorporating biological information and aimed to develop a machine-learning model for diagnosing Behcet's disease. By combining biological information and machine learning classifiers, up to 99.64 percent accuracy of disease prediction is achieved using only 13,611 out of 311,459 SNPs. In addition, we revealed the SNPs that are most distinctive by performing repeated feature selection in cross-validation experiments.Article Citation - WoS: 2Citation - Scopus: 2Machine-Generated Hierarchical Structure of Human Activities to Reveal How Machines Think(IEEE-Inst Electrical Electronics Engineers Inc, 2021) Altin, Mahsun; Gursoy, Furkan; Xu, LinaDeep-learning based computer vision models have proved themselves to be ground-breaking approaches to human activity recognition (HAR). However, most existing works are dedicated to improve the prediction accuracy through either creating new model architectures, increasing model complexity, or refining model parameters by training on larger datasets. Here, we propose an alternative idea, differing from existing work, to increase model accuracy and also to shape model predictions to align with human understandings through automatically creating higher-level summarizing labels for similar groups of human activities. First, we argue the importance and feasibility of constructing a hierarchical labeling system for human activity recognition. Then, we utilize the predictions of a black box HAR model to identify similarities between different activities. Finally, we tailor hierarchical clustering methods to automatically generate hierarchical trees of activities and conduct experiments. In this system, the activity labels on the same level will have a designed magnitude of accuracy and reflect a specific amount of activity details. This strategy enables a trade-off between the extent of the details in the recognized activity and the user privacy by masking some sensitive predictions; and also provides possibilities for the use of formerly prohibited invasive models in privacy-concerned scenarios. Since the hierarchy is generated from the machine's perspective, the predictions at the upper levels provide better accuracy, which is especially useful when there are too detailed labels in the training set that are rather trivial to the final prediction goal. Moreover, the analysis of the structure of these trees can reveal the biases in the prediction model and guide future data collection strategies.Article Impact of Input Sequence Types on Healthcare Intrusion Prediction Models(IEEE-Inst Electrical Electronics Engineers Inc, 2025) Yusof, Mohammad Hafiz Mohd; Balfaqih, Mohammed; Khan, Md Munir Hayet; Almohammedi, Akram A.; Balfagih, ZainPrediction models are vital for sensing zero-day and even n-day cyberattacks, particularly in healthcare infrastructure. Most existing research focuses on developing classifiers also known as IDS to enhance detection and accuracy. However, predictive intrusion models for healthcare remain underexplored, with limited studies investigating the comparative performance of univariate and multivariate inputs against single-step and multi-step outputs in time series models. This study aims to address these gaps by evaluating the accuracy and error performance of selected predictive models across various input and output configurations. The methodology involves transforming input data sequences into univariate l* n and multivariate m * n formats, establishing single-step and multi-step splitting functions, and evaluating these configurations using the benchmark CIRA-CIC-DoHBrw-2020 dataset. Algorithms including Bidirectional LSTM, Stacked LSTM, Vanilla LSTM, Transformer Encoder-Decoder, Vector Output LSTM (GRU core), and CNN were applied, with results visualized to assess performance. The findings reveal that the Multivariate LSTM model, when trained on a sequence of multivariate inputs, demonstrates superior predictive performance, achieving low MAE error rates of 0.4% for single-step predictions and 0.1% for multi-step predictions. Additionally, GRU and Transformer models exhibit heightened sensitivity to specific input sequence configurations. In conclusion, our study demonstrates that Transformer Encoder-Decoder based prediction models exhibit exceptional prediction performance. This effectiveness is attributed to their ability to capture contextual and critical information from input sequences. These findings provide valuable insights for designing advanced intrusion prediction models, paving the way for improved prediction capabilities in future systems.Article Citation - WoS: 4Citation - Scopus: 7IGPRED-Multitask: A Deep Learning Model to Predict Protein Secondary Structure, Torsion Angles and Solvent Accessibility(IEEE Computer Soc, 2023-03-01) Gormez, Yasin; Aydin, ZaferProtein secondary structure, solvent accessibility and torsion angle predictions are preliminary steps to predict 3D structure of a protein. Deep learning approaches have achieved significant improvements in predicting various features of protein structure. In this study, IGPRED-Multitask, a deep learning model with multi task learning architecture based on deep inception network, graph convolutional network and a bidirectional long short-term memory is proposed. Moreover, hyper-parameters of the model are fine-tuned using Bayesian optimization, which is faster and more effective than grid search. The same benchmark test data sets as in the OPUS-TASS paper including TEST2016, TEST2018, CASP12, CASP13, CASPFM, HARD68, CAMEO93, CAMEO93_HARD, as well as the train and validation sets, are used for fair comparison with the literature. Statistically significant improvements are observed in secondary structure prediction on 4 datasets, in phi angle prediction on 2 datasets and in psi angel prediction on 3 datasets compared to the state-of-the-art methods. For solvent accessibility prediction, TEST2016 and TEST2018 datasets are used only to assess the performance of the proposed model.Article Citation - WoS: 26Citation - Scopus: 27ATOM: AI-Powered Sustainable Resource Management for Serverless Edge Computing Environments(IEEE-Inst Electrical Electronics Engineers Inc, 2024-11) Golec, Muhammed; Gill, Sukhpal Singh; Cuadrado, Felix; Parlikad, Ajith Kumar; Xu, Minxian; Wu, Huaming; Uhlig, SteveServerless edge computing decreases unnecessary resource usage on end devices with limited processing power and storage capacity. Despite its benefits, serverless edge computing's zero scalability is the major source of the cold start delay, which is yet unsolved. This latency is unacceptable for time-sensitive Internet of Things (IoT) applications like autonomous cars. Most existing approaches need containers to idle and use extra computing resources. Edge devices have fewer resources than cloud-based systems, requiring new sustainable solutions. Therefore, we propose an AI-powered, sustainable resource management framework called ATOM for serverless edge computing. ATOM utilizes a deep reinforcement learning model to predict exactly when cold start latency will happen. We create a cold start dataset using a heart disease risk scenario and deploy using Google Cloud Functions. To demonstrate the superiority of ATOM, its performance is compared with two different baselines, which use the warm-start containers and a two-layer adaptive approach. The experimental results showed that although the ATOM required more calculation time of 118.76 seconds, it performed better in predicting cold start than baseline models with an RMSE ratio of 148.76. Additionally, the energy consumption and CO2 emission amount of these models are evaluated and compared for the training and prediction phases.