PGPınar Güner

Pınar Güner

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Pınar Güner has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Enhancing clinical gait abnormality analysis with multimodal deep learning

    by Pınar Güner Şahan, Erva Alacan, Suhap Şahin

    Advances in computer vision have produced promising results in gait analysis, which plays an important role in clinical diagnosis. These technologies enable early and objective detection of diseases by identifying changes in individual walking patterns. This study investigates multimodal clinical gait abnormality detection on the Gait Abnormality Video Dataset (GAVD) by combining appearance features and skeleton-based structural motion features. SlowFast was used to extract spatiotemporal appearance representations from RGB videos, while ST-GCN was used to model skeleton joint sequences. The extracted features were combined using late fusion and classified with an MLP classifier. The proposed framework was evaluated on the GAVD dataset using 5-fold stratified cross-validation. The results show that skeleton-based representations carry a substantial part of the discriminative signal, while RGB features provide complementary information when extracted by a sufficiently strong video backbone. The proposed SlowFast + ST-GCN model achieved a recall of 0.947, an F1-score of 0.910, and an AUC of 0.783. Under the abnormal-only test protocol, the same model achieved 95.0% accuracy. Ablation experiments showed that concatenation was the most effective fusion strategy, while frozen feature extraction with MLP classification provided the best generalization among the evaluated training strategies. Comparisons with GAVD-adapted multimodal baselines further showed that different modality combinations offer different strengths. Overall, this study provides a systematic multimodal evaluation on GAVD and shows that RGB + skeleton fusion is useful for abnormal gait detection.

  • Open Access

    A Comprehensive Vision-Based Gait Data Collection Framework with a Systematic Multi-Camera Placement Strategy

    by Pınar Güner Şahan, Ilgar Akkaya, İbRahim Şahan, Suhap Şahin

    Systematic collection of gait data directly affects the reliability of gait analysis. Therefore, the first step that should be given importance in gait analysis is to ensure that the data collected is of high quality and reliable. Optimising and standardising the data collection process is a critical requirement that increases the success of the analysis. This study proposes a systematic multi-camera placement strategy and data processing process to collect gait data in real time with RGB cameras for gait recognition and analysis applications. The proposed method provides an end-to-end framework from the physical setup of the data collection environment to the data processing steps. The camera placement strategy aims to maximise the visibility of all body parts by capturing the participant’s body from different directions during walking. The results of three different methods used for silhouette extraction from the acquired videos were compared. Furthermore, a video-based approach was used to calculate participants’ walking speeds. Theoretical and practical information provided regarding the data collection and analysis process is detailed to guide future studies. In this respect, the paper is aimed to be a guiding study for researchers working in the related field.

  • Open Access

    A survey of appearance-based approaches for human gait recognition: techniques, challenges, and future directions

    by Pınar Güner Şahan, Suhap Şahin, Fidan Kaya Gülağız

    Gait recognition has become an important biometric feature for human identification, in addition to data such as face, iris, and fingerprint. The goal of human gait recognition is to identify people based on walking images. Artificial intelligence technologies have revolutionized the field of gait recognition by enabling computers to automatically learn and extract intricate patterns. These techniques examine video recordings to determine key features in an individual's gait, and these features are used to identify the person. This paper examines the existing appearance-based gait recognition methods that have been published in recent years. The primary objective of this paper is to provide an informative survey of the state-of-the-art in appearance-based gait recognition techniques, highlighting their applications, strengths, and limitations. Through our analysis, we aim to highlight the significant advance that has been made in this field, draw attention to the challenges that have been faced, and identify areas of prospective future research and advances in technology. Furthermore, we comprehensively examine common datasets used in gait recognition research. By analyzing the latest developments in appearance-based gait recognition, our study aims to be a helpful resource for researchers, providing an extensive overview of current methods and guiding future attempts in this dynamic field.


  • Open Access

    Analysis of under-five mortality by diseases in countries with different levels of development: a comparative analysis

    by Muhammed Sütçü, Pınar Güner, Nur Şebnem Ersöz

    Objectives: The right to health is critical for children because they are sensitive beings who are more susceptible to disease and health problems. It would be beneficial to compare child mortality rates in countries with different levels of development and to conduct studies to address them by taking into account their causes. This study aims to analyze the situation of developed, developing and least developed countries in terms of causes under-5 child mortality (U5CM) determined by World Health Organization and to identify the similarities or differences of under-five mortality. Methods: Child mortality rates per 1,000 live births between 2000 and 2017 years in between different age groups (0-27 days and 1-59 months) by causes (disease-specific) were obtained from World Health Organization for a total 15 countries including developed, developing and least developed countries. Regression analysis was performed to identify which causes have more impact on child mortality. In addition, the relationship between diseases was calculated using Euclidean distance, and diseases were clustered using k-means clustering algorithm for each country. Results: As a result of mathematical and statistical analysis, it was seen that causes of child mortality have a significant relation with the development level of country where a child was born. Conclusions: It has been observed that the causes of child mortality in countries with different levels of development vary depending on different factors such as geographical conditions, air quality population and access to medicine.


  • Open Access

    Topological feature generation for link prediction in biological networks

    by Mustafa Temiz, Burcu Bakir-Gungor, Pınar Güner Şahan, Mustafa Coskun

    Graph or network embedding is a powerful method for extracting missing or potential information from interactions between nodes in biological networks. Graph embedding methods learn representations of nodes and interactions in a graph with low-dimensional vectors, which facilitates research to predict potential interactions in networks. However, most graph embedding methods suffer from high computational costs in the form of high computational complexity of the embedding methods and learning times of the classifier, as well as the high dimensionality of complex biological networks. To address these challenges, in this study, we use the Chopper algorithm as an alternative approach to graph embedding, which accelerates the iterative processes and thus reduces the running time of the iterative algorithms for three different (nervous system, blood, heart) undirected protein-protein interaction (PPI) networks. Due to the high dimensionality of the matrix obtained after the embedding process, the data are transformed into a smaller representation by applying feature regularization techniques. We evaluated the performance of the proposed method by comparing it with state-of-the-art methods. Extensive experiments demonstrate that the proposed approach reduces the learning time of the classifier and performs better in link prediction. We have also shown that the proposed embedding method is faster than state-of-the-art methods on three different PPI datasets.

  • Open Access

    COMPARATIVE PERFORMANCE ANALYSIS OF ARIMA, PROPHET AND HOLT-WINTERS FORECASTING METHODS ON EUROPEAN COVID-19 DATA

    by Nur Şebnem Ersöz, Pınar Güner, Ayhan Akbaş, Burcu Baki̇r-Gungor

    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 attempted to understand and predict the spread of COVID-19 so that governments may make sufficient arrangements in hospitals and reduce the mortality rate. This research article presents a comparative performance analysis of ARIMA, Prophet and Holt-Winters 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.


  • Open Access

    Developing a label propagation approach for cancer subtype identification problem

    by Pınar Güner, Burcu Bakir-Gungor, Mustafa Coşkun

    Cancer is a disease in which abnormal cells grow uncontrollably and invade other tissues. Several types of cancer have various subtypes with different clinical and biological implications. Based on these differences, treatment methods need to be customized. The identification of distinct cancer subtypes is an important problem in bioinformatics, since it can guide future precision medicine applications. In order to design targeted treatments, bioinformatics methods attempt to discover common molecular pathology of different cancer subtypes. Along this line, several computational methods have been proposed to discover cancer subtypes or to stratify cancer into informative subtypes. However, existing works do not consider the sparseness of data (genes having low degrees) and result in an ill-conditioned solution. To address this shortcoming, in this paper, we propose an alternative unsupervised method to stratify cancer patients into subtypes using applied numerical algebra techniques. More specifically, we applied a label propagation-based approach to stratify somatic mutation profiles of colon, head and neck, uterine, bladder, and breast tumors. We evaluated the performance of our method by comparing it to the baseline methods. Extensive experiments demonstrate that our approach highly renders tumor classification tasks by largely outperforming the state-of-the-art unsupervised and supervised approaches.

  • Performance Evaluations of Active Subnetwork Search Methods in Protein-Protein Interaction Networks

    by Pınar Güner, Burcu Bakır-Güngör

    Protein-protein interaction networks are mathematical representations of the physical contacts between proteins in the cell. A group of interconnected proteins in a protein-protein interaction network that contains most of the disease associated proteins and some interacting other proteins is called an active subnetwork. Active subnetwork search is important to understand mechanisms underlying diseases. Active subnetworks are used to discover disease related regulatory pathways, functional modules and to classify diseases. In the literature there are many methods to search for active subnetworks. The purpose of this study is to compare the performance of different subnetwork identification methods. By using the Rheumatoid Arthritis dataset, the performances of greedy approach, genetic algorithm, simulated annealing algorithm, prize collecting steiner forest and game theory based subnetwork search methods are compared.