Mühendislik Fakültesi / Faculty of Engineering

Permanent URI for this communityhttps://hdl.handle.net/11413/11

Browse

Now showing 1 - 20 of 78

Open Access
Akciğer Basınçlarının İnvasiv Olmayan Yöntemler ile Kestirilmesi Amacıyla Akciğer Basınçları Ve Akciğer Sesleri Arasındaki İlişkinin Modellenmesi
(TÜBİTAK EEEAG Proje, 2020) SAATÇI, ESRA; Öztürk, Ayşe Bilge; SAATÇI, ERTUĞRUL; Akan, aydın
Solunum fonksiyon testleri solunum hastalıklarının teshis ve tedavisinin izlenmesinde kullanılırlar. Hastane ortamında yapılan bu testler pahalı cihazlara ve hastalar tarafından yapılan çesitli solunum manevralarına ihtiyaç duyarlar. Bu projenin amacı klinikte kullanılan solunum fonksiyon testlerinin yerine basit yöntemler ile solunum parametrelerinin bulunmasıdır. Bu amacı gerçeklestirmek için akciger basınçlarının girisimsel olmayan yöntemler ile kestirilmesi gerekmektedir. Basit mikrofonlar ile ölçülen akciger seslerinin ve havayolu gaz akıs hızı, sıcaklıgı ve nemi gibi çesitli solunum sinyallerinin istatistiksel ve fraktal sinyal isleme yöntemleri ile islenmesi bu projede önerilen temel yöntemdir. Solunum parametrelerinin kestiriminde bazı sinyal isleme yaklasımları önerilmis olsa bile solunum sesleriyle beraber istatistiksel ve fraktal sinyal isleme yöntemleri kombinasyonunun kullanılması bu projenin yenilikçi kısmıdır. Yapılan analizler sonucunda derin ve normal solunumların birlikte kullanıldıgı bronsial solunum sesinden elde edilen Hurst üstelinin agız içi basıncının kestiriminde en basarılı sonuçları verdigi görülmüstür. Ayrıca viskoelastik modelin yardımıyla kestirilen akciger basınçlarının gücü en iyi spirometrik testlerde FEV1 ve FVC parametreleriyle IOS testinde R5 parametresi ile ilişkilidir.
Open Access
An Efficient Generation and Security Analysis of Substitution Box Using Fingerprint Patterns
(IEEE, 2020) ŞENGEL, ÖZNUR; Aydın, Muhammed Ali; Sertbaş, Ahmet
Information and its security have attracted the research community in recent years with increasing usage of mobile applications. Mobile devices have different security options in data transmission such as reading some biometric values. The keystone of the modern block and stream ciphers is the use of a substitution box (s-box) that obscures correlation between plaintext and ciphertext. In this study, we proposed a novel s-box generation algorithm by using the fingerprint pattern of the person who transfers information to the target. We generated several s-boxes by using bifurcation and ridge ending features of the fingerprint. Proposed s-boxes are compared with several known s-boxes over nonlinearity, bijectiveness, strict avalanche criterion, bit independence criterion, linear probability, and differential probability. Along with these properties, we analyzed confidence interval and randomness properties of new s-boxes as well. Also, the execution time of the proposed s-box generation algorithm is calculated and examined. The results of the cryptographic properties have shown that the proposed s-boxes by using ridge ending of the fingerprint performs better. The performances analysis show that the proposed s-box has satisfactory results according to the results of chaotic-based s-boxes. On the other hand, the fingerprint s-boxes are much better than the existing biometric s-boxes according to the s-box security metrics. The results have shown that the execution time of the proposed s-box generation algorithm is more minimum than the existing biometric s-box generation algorithms. Resulting from applying fingerprint biometric data to generate an s-box, such a successful algorithm is promising to be used in mobile devices.
Open Access
Analysis of a Prefabricated Vertical Drain (PVD) Soil Improvement Project
(Turkish Chamber Civil Engineers, 2022) MERT, AHMET CAN; AREL, ERSİN; ÖNALP, AKIN
A settlement analysis has been carried out for several sectors of a rail station yard improved with prefabricated vertical drains (PVD) in Istanbul, that exhibited prolonged consolidation beyond the predicted values in certain sectors of the treated zone. Final settlement and End of Primary (EOP) settlement times have been estimated theoretically as well as using the Asaoka graphical procedure. The compliance of settlement-time curves with in-situ measurements and Asaoka solution has been investigated. A geotechnical model was developed for finite element and three-dimensional consolidation analyses. The settlement curves obtained by varying horizontal-vertical permeability coefficient ratio (k(h)/k(v)) and in-situ measurements have been compared, and k(h)/k(v) values corresponding to 90% degree of consolidation has been computed for all sectors. The effect of drain spacing (S-drain) as well as drain length (L-drain) on the rate of consolidation have been evaluated for each sector, keeping the specified ratios constant. The times corresponding to 95% degree of consolidation (t(95)) have been calculated using the theoretical solution and compared to in-situ measurements. Calculated t(95)'s has also been compared to their estimated values by varying the spacing (S-drain) and the length (L-drain). Additionally, the required intervals of S-drain and L-drain have been obtained corresponding to the calculated t(95) times. The analyses suggest that the main reason for prolonged consolidation was the horizontal to vertical permeability coefficient ratio. According to the analysis results, PVD implementation was not efficient in clays having k(h)/k(v) of approximately unity. The main conclusion of this study was to discover the necessity for optimizing the variables in any such project. The efficacy of the works can be significantly enhanced if simultaneous evaluation of the parameters S-drain and L-drain and the permeability ratio k(h)/k(v) is carried out prior to field work. Otherwise, "accidents" may emerge as found out in this project.
Open Access
Analysis of Facial Emotion Expression in Eating Occasions Using Deep Learning
(Springer, 2023) ELİF, YILDIRIM; AKBULUT, FATMA PATLAR; Çatal, Çağatay
Eating is experienced as an emotional social activity in any culture. There are factors that influence the emotions felt during food consumption. The emotion felt while eating has a significant impact on our lives and affects different health conditions such as obesity. In addition, investigating the emotion during food consumption is considered a multidisciplinary problem ranging from neuroscience to anatomy. In this study, we focus on evaluating the emotional experience of different participants during eating activities and aim to analyze them automatically using deep learning models. We propose a facial expression-based prediction model to eliminate user bias in questionnaire-based assessment systems and to minimize false entries to the system. We measured the neural, behavioral, and physical manifestations of emotions with a mobile app and recognize emotional experiences from facial expressions. In this research, we used three different situations to test whether there could be any factor other than the food that could affect a person’s mood. We asked users to watch videos, listen to music or do nothing while eating. This way we found out that not only food but also external factors play a role in emotional change. We employed three Convolutional Neural Network (CNN) architectures, fine-tuned VGG16, and Deepface to recognize emotional responses during eating. The experimental results demonstrated that the fine-tuned VGG16 provides remarkable results with an overall accuracy of 77.68% for recognizing the four emotions. This system is an alternative to today’s survey-based restaurant and food evaluation systems.
Open Access
AT-ODTSA: A Dataset of Arabic Tweets for Open Domain Targeted Sentiment Analysis
(University of Bahrain, 2022) Sahmoud, Shaaban; Abudalfa, Shadi; ELMASRY, WİSAM
In the field of sentiment analysis, most of research has conducted experiments on datasets collected from Twitter for manipulating a specific language. Little number of datasets has been collected for detecting sentiments expressed in Arabic tweets. Moreover, very limited number of such datasets is suitable for conducting recent research directions such as target dependent sentiment analysis and open-domain targeted sentiment analysis. Thereby, there is a dire need for reliable datasets that are specifically acquired for open-domain targeted sentiment analysis with Arabic language. Therefore, in this paper, we introduce AT-ODTSA, a dataset of Arabic Tweets for Open-Domain Targeted Sentiment Analysis, which includes Arabic tweets along with labels that specify targets (topics) and sentiments (opinions) expressed in the collected tweets. To the best of our knowledge, our work presents the first dataset that manually annotated for applying Arabic open-domain targeted sentiment analysis. We also present a detailed statistical analysis of the dataset. The AT-ODTSA dataset is suitable for train numerous machine learning models such as a deep learning-based model. © 2022 University of Bahrain. All rights reserved.
Open Access
Biosignals, Facial Expressions, and Speech as Measures of Workplace Stress: Workstress3d Dataset
(Elsevier, 2024) Doğan, Gülin; AKBULUT, FATMA PATLAR; Çatal, Çağatay
WorkStress3D is a comprehensive collection of multimodal data for the research of stress in the workplace. This dataset contains biosignals, facial expressions, and speech signals, making it an invaluable resource for stress analysis and related studies. The ecological validity of the dataset was ensured by the fact that the data were collected in actual workplace environments. The biosignal data contains measurements of electrodermal activity, blood volume pressure, and cutaneous temperature, among others. High-resolution video recordings were used to capture facial expressions, allowing for a comprehensive analysis of facial cues associated with tension. In order to capture vocal characteristics indicative of tension, speech signals were recorded. The dataset contains samples from both stress-free and stressful work situations, providing a proportionate representation of various stress levels. The dataset is accompanied by extensive metadata and annotations, which facilitate in-depth analysis and interpretation. WorkStress3D is a valuable resource for developing and evaluating stress detection models, examining the impact of work environments on stress levels, and exploring the potential of multimodal data fusion for stress analysis.
Open Access
Blockchain-Based KYC Model for Credit Allocation in Banking
(IEEE-Inst Electrical Electronics Engineers Inc., 2024) Karadağ, Bulut; Zaim, A. Halim; AKBULUT, AKHAN
The implementation of the Know Your Customer (KYC) strategy by banks within the financial sector enhances the operational efficiency of such establishments. The data gathered from the client during the KYC procedure may be applied to deter possible fraudulent activities, money laundering, and other criminal undertakings. The majority of financial institutions implement their own KYC procedures. Furthermore, a centralized system permits collaboration and operation execution by multiple financial institutions. Aside from these two scenarios, KYC processes can also be executed via a blockchain-based system. The blockchain's decentralized network would be highly transparent, facilitating the validation and verification of customer data in real-time for all relevant stakeholders. In addition, the immutability and cryptography of the blockchain ensure that client information is secure and immutable, thereby eradicating the risk of data breaches. Blockchain-based KYC can further improve the client experience by eliminating the requirement for redundant paperwork and document submissions. After banks grant consumers loans, a blockchain-based KYC system is proposed in this study to collect limit, risk, and collateral information from them. The approach built upon Ethereum grants financial institutions the ability to read and write financial data on the blockchain network. This KYC method establishes a transparent, dynamic, and expeditious framework among financial institutions. In addition, solutions are discussed for the Sybil attack, one of the most severe problems in such networks.
Open Access
Boosting the Visibility of Services in Microservice Architecture
(Springer, 2023) TOKMAK, AHMET VEDAT; AKBULUT, AKHAN; Çatal, Çağatay
Monolithic software architectures are no longer sufficient for the highly complex software-intensive systems, which modern society depends on. Service Oriented Architecture (SOA) surpassed monolithic architecture due to its reusability, platform independency, ease of maintenance, and scalability. Recent SOA implementations made use of cloud-native architectural approaches such as microservice architecture, which has resulted in a new challenge: the discovery difficulties of services. One way to dynamically discover and route traffic to service instances is to use a service discovery tool to locate the Internet Protocol (IP) address and port number of a microservice. In the event that replicated microservice instances are found to provide the same function, it is crucial to select the right microservice that provides the best overall experience for the end-user. Parameters including success rate, efficiency, delay time, and response time play a vital role in establishing a microservice's Quality of Service (QoS). These assessments can be performed by means of a live health-check service, or, alternatively, by making a prediction of the current state of affairs with the application of machine learning-based approaches. In this research, we evaluate the performance of several classification algorithms for estimating the quality of microservices using the QWS dataset containing traffic data of 2505 microservices. Our research also analyzed the boosting algorithms, namely Gradient Boost, XGBoost, LightGBM, and CatBoost to improve the overall performance. We utilized parameter optimization techniques, namely Grid Search, Random Search, Bayes Search, Halvin Grid Search, and Halvin Random Search to fine-tune the hyperparameters of our classifier models. Experimental results demonstrated that the CatBoost algorithm achieved the highest level of accuracy (90.42%) in predicting microservice quality.
Open Access
A Broadband, Polarization Insensitive, Wide Incidence-Angle-Slotted Ring/Lumped Resistor-Based Metamaterial Absorber for K-u-Band Applications
(Istanbul University - Cerrahpaşa, 2021) AKŞİMŞEK, HÜSEYİN SİNAN
A broadband-slotted ring/lumped resistor-based metamaterial absorber (MA) is presented in this study for K-u-band microwave applications. Numerical results of the MA indicate that it can achieve a broadband absorption ratio of more than 85% in the frequency range of 12.4-17.6 GHz and has active polarization insensitivity and wide incidence-angle response over the entire operation band between 12.4-17.6 GHz. The designed MA is ultrathin around lambda/14.7 in terms of wavelength at its lowest operation frequency, corresponding to 1.7 mm. The proposed unit-cell structure of the MA is novel, consisting of a slotted ring with eight symmetrically-located lumped resistors, FR-4 material, and a metallic ground, which is compatible with low-cost PCB fabrication; therefore, the MA is suitable for practical microwave applications in the K-u-band.
Open Access
Bulanık CPM ile Doğrusal Programlama: İnşaat Endüstrisinde Bir Vaka Çalışması
(Süleyman Demirel Üniversitesi Mühendislik Fakültesi, 2022) Değirmenci, Güllü; UĞURAL, MEHMET NURETTİN
İnşaat sektöründe karmaşık projelerin planlanması ve kontrolü için Kritik Yol Metodunun (KYM), yaygın olarak kullanılan yararlı bir araç olduğu kanıtlanmıştır. Ancak, faaliyetlerin süresi net sayılarla temsil edildiğinden, kritik yol analizinde faaliyet sürelerini kesin olarak tahmin etmek zorlaşır. Buna ek olarak, vakaların çoğu, görev sürelerinin sübjektif olarak hesaplanmasını gerektirir ve bu da faaliyetlerin süresi hakkında belirsizliğe neden olur. Bu makale, bulanık kümelere dayalı bir yaklaşım önererek bu sorunları ele almaktadır. Bu çalışmanın amacı, bir inşaat projesinin kritik yolunu ve tamamlanma süresini hesaplamak için bulanık sayıların nasıl kullanılacağını göstermektir. Çalışma kapsamında proje faaliyetlerine üçgen bulanık süreler verilerek iki ayrı çözüm algoritması oluşturulmuştur. Örnek bir inşaat projesinin kritik yolu ve proje süresi ilk çözüm algoritmasında proje faaliyetlerine üçgen bulanık süreler atanarak ve doğrusal programlama modeli kullanılarak hesaplanırken, ikinci çözüm algoritmasında bulanık proje süresi ve kritik yol Alfa kesme yöntemi (α -Kesme Yöntemi) kullanılarak hesaplanmış ve daha sonra Centroid yöntemi (Alanların Merkezi Yöntemi) kullanılarak netleştirilmiştir. Bu proje için kritik yol ve tamamlanma süresi önceden bilindiğinden, iki çözüm algoritması karşılaştırılmıştır. Kritik yol yöntemi yerine Bulanık kritik yol yönteminin kullanılmasının bu çalışmanın önemini vurgulayacağı umulmaktadır.
Open Access
Calculation of Pile Capacity in Cohesionless Soil by CPT Considering Spatial Variability
(Çukurova Üniversitesi Mühendislik Fakültesi, 2021) MERT, AHMET CAN; YAZICI, GÖKHAN
The study aims to construct a framework for CPT based ultimate pile capacity calculation for cohesionless soils with random field theory. Cone tip resistance (qc) was taken as the spatially varying parameter with a constant mean and changing coefficients of variation. CPT profiles were simulated with random field generations, and the ultimate capacity of a single pile (Qu) was calculated with these simulations. The influence of spatial variation of qc on the variation of Qu was investigated. The proposed framework was finally verified by comparing the results of an actual CPT database and the simulated CPT profiles in the study. The results showed that the critical vertical scale of fluctuation for CPT-based pile capacity calculations was equal to one diameter of pile (dv=1D), and that the method effectively predicted the ultimate pile capacity through simulated CPT profiles with random field. The proposed method is especially recommended for cases where the uncertainty consideration is necessary, yet the site-specific data is limited. The study aims to contribute a simple framework to the methods of CPTbased pile capacity with unceratinty consideration. The propesed method aims to facilitate the pile design framework with limited available data.
Open Access
Characterization of Site Amplification by a Parametric Study
(Taylor & Francis Inc., 2023) FERCAN, NAZİFE ÖZGE; Şafak, Erdal; Ansal, Atilla
The reliability of Vs30 and the performance of alternative time averaged shear wave velocities (Vsz) and shear wave travel times (Ttz) at various depths, z, were investigated for the estimation of site amplification and fundamental frequency (f0) characterization by considering the linear and nonlinear soil behavior. The study revealed that alternative parameters performed better than Vs30 and the best performing z parameters changed by switching from convex to concave theoretical profiles and by increasing ground motions. For a practical usage in site investigations, guidelines to estimate nonlinear soil amplification factor and fundamental frequency from the linear ones were presented.
Open Access
A Clustering Approach for Intrusion Detection with Big Data Processing on Parallel Computing Platform
(Bajece (İstanbul Teknik Üniversitesi), 2019) REİS, B.; KAYA, S. B.; ŞAHİNGÖZ, ÖZGÜR KORAY
In recent years there is a growing number of attacks in the computer networks. Therefore, the use of a prevention mechanism is an inevitable need for security admins. Although firewalls are preferred as the first layer of protection, it is not sufficient for preventing lots of the attacks, especially from the insider attacks. Intrusion Detection Systems (IDSs) have emerged as an effective solution to these types of attacks. For increasing the efficiency of the IDS system, a dynamic solution, which can adapt itself and can detect new types of intrusions with a dynamic structure by the use of learning algorithms is mostly preferred. In previous years, some machine learning approaches are implemented in lots of IDSs. In the current position of artificial intelligence, most of the learning systems are transferred with the use of Deep Learning approaches due to its flexibility and the use of Big Data with high accuracy. In this paper, we propose a clustered approach to detect the intrusions in a network. Firstly, the system is trained with Deep Neural Network on a Big Data set by accelerating its performance with the use of CUDA architecture. Experimental results show that the proposed system has a very good accuracy rate and low runtime duration with the use of this parallel computation architecture. Additionally, the proposed system needs a relatively small duration for training the system.
Open Access
A Comparative Assessment of Five Different Distributions Based on Five Different Optimization Methods for Modeling Wind Speed Distribution
(Gazi University, 2023) Wadi, Mohammed; ELMASRY, WİSAM
Determining wind regime distribution patterns is essential for many reasons; modelling wind power potential is one of the most crucial. In that regard, Weibull, Gamma, and Rayleigh functions are the most widely used distributions for describing wind speed distribution. However, they could not be the best for describing all wind systems. Also, estimation methods play a significant role in deciding which distribution can achieve the best matching. Consequently, alternative distributions and estimation methods are required to be studied. An extensive analysis of five different distributions to describe the wind speeds distribution, namely Rayleigh, Weibull, Inverse Gaussian, Burr Type XII, and Generalized Pareto, are introduced in this study. Further, five metaheuristic optimization methods, Grasshopper Optimization Algorithm, Grey Wolf Optimization, Moth-Flame Optimization, Salp Swarm Algorithm, and Whale Optimization Algorithm, are employed to specify the optimum parameters per distribution. Five error criteria and seven statistical descriptors are utilized to compare the good-of-fitness of the introduced distributions. Therefore, this paper provides different important methods to estimate the wind potential at any site..
Open Access
Comparative Economic and Experimental Assessment of Air Source Heat Pump and Gas-Fired Boiler: A Case Study from Turkey
(MDPI, 2022) KUL, ÖNDER; UĞURAL, MEHMET NURETTİN
Since sustainability has become a major concern in the construction industry, making economically efficient investment decisions in energy conservation are needed to minimize energy consumption for space heating and cooling. Although Air-Source Heat Pump (ASHP) systems are used to meet buildings' heating and cooling demands worldwide, high initial setup costs limit the widespread use of these systems. This paper presents comparative assessment of ASHP system versus conventional gas-fired boiler system for a real commercial building with a floor area of 2500 m(2) in Istanbul, Turkey. The key performance variable, Coefficient of Performance (COP), of the ASHP system was experimentally evaluated. The experimental results revealed that the system's COP ranged from 3.22 to 4.32, while the outside temperature ranged from 4.8 to 18.6 degrees C and the supply water temperature ranged from 32.2 to 36.2 degrees C. Moreover, the economic analysis results showed that despite the high initial cost, ASHP systems are cost competitive against gas-fired boiler in Turkey. ASHP system could reduce the present value of total Life-Cycle Cost (LCC) by up to 26.4% (47,865 USD) compared to the conventional gas-fired boiler system because it can dramatically reduce the energy consumption per year.
Open Access
Deep Learning-Based Defect Prediction for Mobile Applications
(MPDI, 2022) JORAYEVA, MANZURA; AKBULUT, AKHAN; Çatal, Çağatay; Mishra, Alok
Smartphones have enabled the widespread use of mobile applications. However, there are unrecognized defects of mobile applications that can affect businesses due to a negative user experience. To avoid this, the defects of applications should be detected and removed before release. This study aims to develop a defect prediction model for mobile applications. We performed cross-project and within-project experiments and also used deep learning algorithms, such as convolutional neural networks (CNN) and long short term memory (LSTM) to develop a defect prediction model for Android-based applications. Based on our within-project experimental results, the CNN-based model provides the best performance for mobile application defect prediction with a 0.933 average area under ROC curve (AUC) value. For cross-project mobile application defect prediction, there is still room for improvement when deep learning algorithms are preferred.
Open Access
Deep Learning-Based User Experience Evaluation in Distance Learning
(Springer, 2023) SADIGOV, RAHIM; YILDIRIM, ELİF; KOCAÇINAR, BÜŞRA; AKBULUT, FATMA PATLAR; Çatal, Çağatay
The Covid-19 pandemic caused uncertainties in many different organizations, institutions gained experience in remote working and showed that high-quality distance education is a crucial component in higher education. The main concern in higher education is the impact of distance education on the quality of learning during such a pandemic. Although this type of education may be considered effective and beneficial at first glance, its effectiveness highly depends on a variety of factors such as the availability of online resources and individuals' financial situations. In this study, the effectiveness of e-learning during the Covid-19 pandemic is evaluated using posted tweets, sentiment analysis, and topic modeling techniques. More than 160,000 tweets, addressing conditions related to the major change in the education system, were gathered from Twitter social network and deep learning-based sentiment analysis models and topic models based on latent dirichlet allocation (LDA) algorithm were developed and analyzed. Long short term memory-based sentiment analysis model using word2vec embedding was used to evaluate the opinions of Twitter users during distance education and also, a topic model using the LDA algorithm was built to identify the discussed topics in Twitter. The conducted experiments demonstrate the proposed model achieved an overall accuracy of 76%. Our findings also reveal that the Covid-19 pandemic has negative effects on individuals 54.5% of tweets were associated with negative emotions whereas this was relatively low on emotion reports in the YouGov survey and gender-rescaled emotion scores on Twitter. In parallel, we discuss the impact of the pandemic on education and how users' emotions altered due to the catastrophic changes allied to the education system based on the proposed machine learning-based models.
Open Access
Derin Öğrenme Yöntemleri ile Borsada Fiyat Tahmini
(Bitlis Eren Üniversitesi Rektörlüğü, 2020) Şişmanoğlu, Gözde; Koçer, Furkan; Önde, Mehmet ali; ŞAHİNGÖZ, ÖZGÜR KORAY
Son yıllarda, bilgisayarların donanımındaki teknolojik gelişmeler ve makine öğrenme tekniklerindeki gelişmeler nedeniyle, "Büyük Veri" ve "Paralel İşleme" kullanımı olmak üzere problem çözmek için iki artan yaklaşım vardır. Özellikle GPU'lar gibi çok çekirdekli bilgi işlem aygıtlarında paralel olarak gerçekleştirilebilen Derin Öğrenme algoritmalarının ortaya çıkmasıyla, bu yaklaşımlarla birçok gerçek dünya problemleri çözülebilmektedir. Derin öğrenme modelleri eğitildikleri veri ile sınıflandırma, regresyon analizi ve zaman serilerinde tahmin gibi uygulamalarda büyük başarılar göstermektedir. Bu modellerin finansal piyasadaki en aktif uygulama alanlarından biri özellikle borsada işlem gören hisse senetlerinin tahmini işlemleridir. Bu alanda amaç, pazardaki değişim süreci hakkındaki hisse senedinin önceki günlük verilerine bakarak kısa veya uzun vadeli gelecekteki değerini tahmin etmeye çalışmaktır. Bu çalışmada, LSTM, GRU ve BLSTM isimli 3 farklı derin öğrenme modeli kullanılarak bir hisse senedi tahmin sistemi geliştirilip, kullanılan modeller arasında karşılaştırmalı bir analiz yapıldı. Spekülatif hareketlerden uzak olması için veri seti olarak 1968'den 2018'e kadar olan New York Borsası'ndan hisse senedinin zaman serisi değerlerini kullanıldı. Spesifik olarakta IBM hisse senedi ile test çalışmaları yapıldı. Deneysel sonuçlar BLSTM modelinin 5 günlük girdi verileriyle eğitilmesi ile %63,54 lük bir yönsel doğruluk değerine ulaşıldığını göstermektedir.
Open Access
Design and Implementation of a Deep Learning-Empowered m-Health Application
(Springer, 2023) AKBULUT, AKHAN; DESOUKI, SARA; ABDELKHALIQ, SARA; KHANTOMANI, LAYAL; Çatal, Çağatay
Many people are unaware of the severity of melanoma disease even though such a disease can be fatal if not treated early. This research aims to facilitate the diagnosis of melanoma disease in people using a mobile health application because some people do not prefer to visit a dermatologist due to several concerns such as feeling uncomfortable by exposing their bodies. As such, a skincare application was developed so that a user can easily analyze a mole at any part of the body and get the diagnosis results quickly. In the first phase, the corresponding image is extracted and sent to a web service. Later, the web service classifies using the pre-trained model built based on a deep learning algorithm. The final phase displays the confidence rates on the mobile application. The proposed model utilizes the Convolutional Neural Network and provides 84% accuracy and 72% precision. The results demonstrate that the proposed model and the corresponding mobile application provide remarkable results for addressing the specified health problem.
Open Access
Design of 24-28 GHz band 5G Antenna Based on Symmetrically Located Circular Gaps
(Osman Sağdıç, 2020) ÖZPINAR, HÜRREM; AKŞİMŞEK, HÜSEYİN SİNAN
5G (fifth generation) cellular system is expected to work in a wide frequency range to meet the demand for mobile services and applications. Antennas will be addressed to the future 5G applications should pose superior characteristics, such as high gain and ultra-large bandwidth response by considering atmospheric absorption/free-space path loss on planned millimeter-wave frequency range of 5G communications. Therefore, antenna design for the future 5G applications is a challenging process. In this article we present a high-gain, broadband mm-Wave antenna based on a circular patch structure with a ground plane and resonator gaps. The designed antenna is analyzed using a widely used full-wave electromagnetic solver. The major antenna figure-of-merits including reflection coefficient, VSWR (voltage-standing wave ratio), antenna patterns in E- and H-planes, surface current distribution, antenna directivity and maximum gain, are obtained. The simulation results show that the gapped circular patch based design has the S11 response less than −10 dB in the frequency range of 21.6-28.8 GHz, which includes 24-28 GHz band of 5G cellular systems. Moreover, it is observed that the symmetrically located circular gaps on both top and bottom layers decrease the side lobe level under −10 dB value, and enhance the gain. We attribute the improvement in the antenna performance to the created current regions due to gaps hosting large vortex current distributions. With 10 mm × 13mm surface area, the proposed antenna demonstrates the peak gain of 9.44 dBi and the radiation efficiency of over 85%. High gain and compact size make this antenna suitable for coming 5G devices.