Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
11 results
Search Results
Publication Metadata only Performance Comparison of Oral, Laryngeal and Thoracic Sounds in the Detection of COVID-19 by Employing Machine Learning Techniques(IEEE, 2022) Gozuacik, Necip; Serbes, Gorkem; Kara, Eyup; Atar, Eren; Sakar, C. Okan; Yener, H. Murat; Borekci, Sermin; Korkmazer, Bora; Karaali, Ridvan; Kara, Halide; Gulmez, Zuleyha; Cogen, Talha; Atas, Ahmet; Bahcesehir University; Yildiz Technical University; Istanbul University; Istanbul University - CerrahpasaCOVID-19 can directly or indirectly cause lung involvements by crossing the upper airways. It is essential to quickly detect the lung involvement condition and to follow up and treat these patients by early hospitalization. In recent COVID-19 diagnosis procedure, PCR testing is applied to the samples taken from the patients and a quarantine period is applied to the patient until the test results are received. As a complement to PCR tests and for faster diagnosis, thin-section lung computed tomography (CT) imaging is used in COVID-19 patients. In this study, it is aimed to develop a method that is as reliable as CT, and compared to CT, less risky, more accessible, and less costly for the diagnosis of COVID-19 disease. For this purpose, first speech and cough sounds from the oral, laryngeal and thoracic regions of COVID-19 patients and healthy individuals were obtained with the multi-channel voice recording system we proposed, the obtained data were processed with machine learning methods and their accuracies in COVID-19 diagnosis were presented comparatively. In our study, the best results were obtained with the features extracted from the cough sounds taken from the oral region.Publication Metadata only Design and analysis of a label-free water-soluble glucose sensor based on suspended hybrid plasmonic micro-ring resonator(IEEE, 2022) Moeinimaleki, Kaveh; Moeinimaleki, Babak; Zarean, Rana; Abedashtiani, Alireza; Karamzadeh, Saeid; Akdeniz University; Bahcesehir UniversityIn this paper, the design and analysis of a label-free water-soluble glucose sensor based on a suspended hybrid plasmonic micro-ring resonator with an external radius of 940 nm in the third telecommunication window to sense the concentration of water-soluble glucose is presented. The simulation results obtained using three-dimensional FDTD show that the sensitivity and the figure of merit values obtained for glucose measurements with concentrations of 0 to 50% in water solution are 218.5 (nm/RIU) and 16.11 (1/RIU), respectively. Comparing the results of the proposed sensor with the previous work, which has four times more footprint, shows that the structure's sensitivity has increased by 17 percent.Publication Metadata only Natural Language Processing-Based Product Category Classification Model for E-Commerce(IEEE, 2022) Koksal, Deniz; Alacan, M. Mert; Olgun, Ecesu; Sakar, C. Okan; Bahcesehir UniversityIn scope of the great dynamism that the world of e-commerce gained with the post-pandemic changes on customer behavior, extending the customer's time on site has become much more valuable. With regards to creating a better understanding of the online shopper's intent on site, an effective search engine is the best tool for improving the user experience. A useful search engine needs to produce fast results and do intent analysis of customers correctly to present successful recommendations. In this study, BERT, ELECTRA and RoBERTa which are language models that give successful results in similar problems and pre-training libraries in Turkish languages are used for developing text classification and customer intent analysis models based on e-commerce product categories. The results of these deep learning models, which were optimized using the product description and comment libraries of the selected e-commerce brand, are shared in a comparative way, and the results of our e-commerce end-user intent analysis model, which was tested on user search history, were detailed on the basis of product category. The developed model can be used for e-commerce product prioritization in Turkish language, as well as creating an infrastructure for the development of intent analysis models that are able to predict as far as the main product that the user wants to display in searches containing multiple products.Publication Metadata only A Scoring Method for Interpretability of Concepts in Convolutional Neural Networks(IEEE, 2022) Gurkan, Mustafa Kagan; Arica, Nafiz; Vural, Fato Yarman; Bahcesehir University; Middle East Technical UniversityIn this paper, we propose a scoring algorithm for measuring the interpretability of CNN models by focusing on the feature extraction operation at the convolutional layers. The proposed approach is based on the principal of concept analysis, for a predefined list of concepts. A map of the network is created based on its responsiveness against each concept. Once this map is ready, various images can be applied as inputs and they are matched with the concepts whose hidden nodes are highly activated. Finally, the evaluation algorithm kicks in to use these descriptions during the final prediction and provides human-understandable explanations.Publication Metadata only Performance Assessment of Physiotherapy and Rehabilitation Exercises with Deep Learning(IEEE, 2022) Aytutuldu, Ilhan; Aydin, Tarkan; Gebze Technical University; Bahcesehir UniversityPhysiotherapy and rehabilitation process is critical for patients in postoperative recovery or the treatment of a wide variety of musculoskeletal disorders. However, providing access to a clinician for each rehabilitation session is a heavy burden and high cost to individuals. Also, it is very important to remotely check whether the exercises are performed correctly, especially during periods of lock-down due to the current pandemic, to provide motivation in the rehabilitation progress of the patients and to ensure that the recommended exercises contribute to the treatment. In this study, deep learning-based performance assessment of rehabilitation exercises has been proposed by using RGB videos obtained with low cost off-the-shelf cameras instead of high-cost, hard-to-reach depth cameras or wearable contact sensors. The proposed deep learning (DL) network models, PtConvNet, PtHybNet and PtBiLSTM, utilize three dimensional (3D) skeletal joint positions of patients extracted from exercise videos. Performance scores given by the physiotherapists have been used as the ground-truth in the training of the framework. We showed that the performance estimates of the learning models reliably follow the actual values and that the DL models confirm the ability to evaluate rehabilitation exercises.Publication Metadata only Microservice Interaction Prediction in Communication Platform as a Service(IEEE, 2022) Aktas, Kemal; Kilinc, H. Hakan; Arica, Nafiz; Bahcesehir UniversityIn telecommunication platforms, it is necessary to monitor the system, take quick action against possible and observed errors, and ensure the continuous operability of the system. However, debugging and problem addressing processes can take a long time in microservice architecture-based platforms with high number of users and heavy traffic. This difficulty arises from the necessity of detecting microservice interactions. In the first phase of this study, it has been observed that providing microservice flows and interactions saves operational teams a significant time during the debugging process. In this scope, different machine learning-based models that predict microservice interactions have been developed and performances are compared. In these models, log patterns are extracted on microservice log data and the interaction map of the mentioned microservice is created by estimating the previous and next microservices that the current microservice interacts with at a certain moment. In the experiments on microservice logs working with the basic call scenario, successful estimation results were obtained that could contribute positively to the debugging process.Publication Metadata only A Wearable Circularly Polarized Antenna for 5G Applications(IEEE, 2022) Ibrahim, Assim; Tetik, Evrim; Karamzadeh, Saeid; Bahcesehir University; Istanbul Arel University5G technology for health care is a considerable demand nowadays due to the revolution in IoT devices. A dual-band antenna on a Rogers RT/duroid 5880 substrate with a dielectric constant of 2.2 and thickness of 0.508 mm, is presented for 3.4 GHz and 5.85GHz frequency bands. The top layer of the proposed antenna consists of a square part that includes an inductive meander line. It is connected to an I-shape, which is merged with reversed L-shaped, the higher resonant frequency excited at 3.4 GHz. In the bottom layer, after the reflector is made, the inductive meander line is created and connected to a reversed U-shape. The proposed antenna of size 19 x 12 mm(2) reveals to perform well for frequencies between 3.37 and 3.47 GHz. It has an axial ratio less than 3dBi and a peak gain of 1.7 dBi that increases after adding a multi-layer of a human hand up to 8 dBi.Publication Metadata only A Compact Low SAR Value Circularly Polarized Wearable Antenna Design for 5G Applications(IEEE, 2022) Gokdemir, Melih; Saeidi, Tale; Karamzadeh, Saeid; Akleman, Funda; Istanbul Technical University; Bahcesehir UniversityIn this study, a wideband wearable antenna is proposed for 5G and IoT applications. The presented circularly polarized coplanar waveguide antenna has a compact size (16mm x 21.5mm). The other result of the novel design which makes this antenna one of the best choices for wearable applications is its low SAR values. These values are 0.0846 and 0.0497 W/kg for mass densities of 1g and 10g, respectively.Publication Metadata only Metamaterial-Based Circularly Polarized Wearable Antenna for ISM and 5G Communications(IEEE, 2022) Saeidi, Tale; Gokdemir, Melih; Karamzadeh, Saeid; Bahcesehir University; Istanbul Technical UniversityA multiband, small, high gain, low specific absorption rate (SAR), and circularly polarized (CP) textile wearable antenna is designed on a layer of denim (epsilon(r) = 1.3, h = 0.787 mm) substrate. The antenna is comprised of a rectangular patch that feeds through an inset transmission line and four tilted periodic slots to enhance the bandwidth (BW) and achieve circular polarization. A layer of fleece fabric (epsilon(r) = 1.04, h = 3 mm) attached to a layer of full ShieldIt to create maximum directivity and minimize SAR value. Then, the antenna is loaded with six arrays of Split Ring Resonator (SRR) on the same antenna layer to enhance the BW that had been reduced after adding the second layer. The antenna works for both ISM and 5G communication systems as it operates at 2.35-2.45 GHz and 3.3-3.9 GHz, respectively. It has the maximum directive gain of 8.52 dBi, acceptable SAR values for both standards with total dimensions of 54 x 56 mm(2). In addition, the antenna's CP is examined, showing AR values of < 3 dB at the working BW with a decent agreement between the simulation and measurement outcomes.Publication Metadata only Sales Forecasting of a Hypermarket: Case Study in Baghdad Using Machine Learning(IEEE, 2022) Anwer, Musaab Osamah; Akyuz, Siireyya; Bahcesehir University; Bahcesehir UniversityMachine learning is a multidisciplinary field that has become one of the most crucial data analysis tools. It supports researchers in understanding their data in a more accurate and reliable. Moreover, analyzing market needs is important to companies and manufacturers for developing their business. Sales forecasting is considered a powerful aspect of understanding market needs. Achieving such a process can be performed using some machine learning algorithms. In this paper, we use five wellknown algorithms for sales forecasting, namely, Multivariate Adaptive Regression Splines (MARS), Long Short-Term Memory Network (LSTM), Seasonal Auto-Regressive Integrated Moving Average (SARIMA), ARIMA, and Recurrent Neural Network (RNN). These algorithms were applied to a real sales dataset of one of the malls from 2016 to 2021. The results of the five algorithms were benchmarked with each other in terms of the adjusted r square. According to the results, the SARIMAX algorithm outperformed the other algorithms.