Mühendislik Fakültesi / Faculty of Engineering

Permanent URI for this collectionhttps://hdl.handle.net/11727/1401

Browse

Now showing 1 - 20 of 540

Acoustic Scene Classification Using Spatial Pyramid Pooling With Convolutional Neural Networks
(2019) Basbug, Ahmet Melih; Sert, Mustafa; 0000-0002-7056-4245; AAB-8673-2019
Automatic understanding of audio events and acoustic scenes has been an active research topic for researchers from signal processing and machine learning communities. Recognition of acoustic scenes in the real life scenarios is a challenging task due to the diversity of environmental sounds and uncontrolled environments. Efficient methods and feature representations are needed to cope with these challenges. In this study, we address the acoustic scene classification of raw audio signal and propose a cascaded CNN architecture that uses spatial pyramid pooling (SPP, also referred to as spatial pyramid matching) method to aggregate local features coming from convolutional layers of the CNN. We use three well known audio features, namely MFCC, Mel Energy, and spectrogram to represent audio content and evaluate the effectiveness of our proposed CNN-SPP architecture on the DCASE 2018 acoustic scene performance dataset. Our results show that, the proposed CNN-SPP architecture with the spectrogram feature improves the classification accuracy.
An advanced human error assessment approach: HEART and AV-DEMATEL
(2019) Can, Guelin F.; Delice, Elif K.
Human error assessment and reduction technique (HEART) is one of the most commonly used human error assessment approaches which computes human error probability (HEP) to prioritize errors related to human actions. HEART is a powerful tool considering error producing conditions (EPCs) which increase the HEP for generalized task versions named as generic task types (GTTs). HEART can give a solution including prevention of human-related errors (HREs) and reduction of the HREs' impacts via implementing additional controls. However, it has many shortcomings for real-life error assessments. In this context, this study aims to improve effective usage of HEART through an advanced version of decision-making trial and evaluation laboratory (AV-DEMATEL). The reason to perform AV-DEMATEL is to show the complex effect relations between main tasks (MTs), subtasks (STs), and EPCs in a process. For this aim, an integrated effect relation matrix is proposed for DEMATEL and importance weights of MTs, STs, and EPCs are computed based on this matrix. In addition, not only HREs are considered but also machine-related errors (MREs) are taken into account to make error assessment for the process. The proposed approach also provides flexibility to categorize STs in different GTTs. Finally, a new term "process error probability" including HREs' probabilities and MREs' probabilities is recommended to compute error probability in an integrated manner for the process. To utilize the proposed approach, an example of a steam boiler daily control process is given.
An Advanced Stochastic Risk Assessment Approach Proposal Based on KEMIRA-M, QFD and Fine-Kinney Hybridization
(2021) Can, Gulin Feryal; Toktas, Pelin
In this study, an advanced stochastic risk assessment approach based on integration of advanced version of quality function deployment (AV-QFD) and Modified Kemeny Median Indicator Rank Accordance (KEMIRA-M) is proposed. It is aimed to perform a new criterion weighting procedure based on four different distributions as uniform, symmetric triangular, left asymmetric triangular, right asymmetric triangular distributions. The AV-QFD includes correlations between criteria (top roof of QFD), risk degrees (RDs) of risk types (RTs) (customer needs part of QFD), correlations between RTs and criteria sets (CSs) (in the middle of QFD) to obtain the criteria priorities. Correlations on the top roof of QFD comprises three types: correlations between criteria in the first CS, correlations between criteria in the second CS and correlations between criteria in both CSs. Additionally, Fine-Kinney method is performed in AV-QFD to compute RDs of RTs in the customer needs part. Then for each expert, the correlation-based importance degree (CBID) of each criterion is obtained to rank criteria for each CS. MATLAB code was performed to see the effect of different trial numbers and replications on risk assessment. It was observed that although uniform distribution provides the best value, the same alternative ranking was obtained for all distributions. In addition, right asymmetric triangular distribution converged to the best value rapidly in practice made in this study.
Ag-Carried CMC/Functional Copolymer/ODA-Mt Wled-Treated NC And Their Responses to Brain Cancer Cells
(2018) Rzayev, Zakir M. O.; Bunyatova, Ulviye; Lovell, Jonathan F.; Shen, Weipeng; Thomay, Tim; Cartwright, Alexander; 0000-0002-9705-1722; 30184772; J-5194-2019
The subject of this work is synthesis and characterization of novel multifunctional nanocomposite (8/2A-NC) consisting (1) carboxymethyl cellulose (CMC) as a matrix biopolymer and poly (maleic acid-tilt-acrylic acid) as a reactive synthetic partner matrix polymer; (2) octadecyl amine montmorillonite (ODA-MMT) reactive organoclay provide intercalated silicate layers structures and aqueous colloidal dispersing medium, and MMT as carriers and targeting agents for anticancer agents in drug delivery systems, respectively. ODA as a intercalated surfactant finely dispersed 8/2A NC and its compatibility with matrix polymers via the interfacial polarization (complexing) and functionalization of matrix polymers by amine (ODA) and carboxylic acids from both the CMC and copolymer; (3) silver nanoparticles (AgNPs) as in-situ generated onto matrix polymers with unique nano-size and morphology parameters was synthesized. Important material science and bioengineering aspects of these investigations included (a) novel approach in synthetic pathways; (b) effects of physical and chemical structural rearrangements; (c) effects of Light Emitting Dioda (LED)-treatment on the FT-IR spectra, XRD reflection parameters, SEM-TEM morphology and nano-size and diameter distribution of AgNPs onto matrix polymers; (d) positive effect of LED-treatment of 8/2A nanocomposite and its response to the MIAPaCa-2 and U87 human brain cancer cell lines were evaluated. Novel 8/2A-NC multifunctional drug consisting unique positive, intercalating and encapsulated core-shell morphology structures, nano-size (5.6 run) and narrow diameter distribution (94%) of AgNPs onto matrix polymers [silver NPs (0.25%) in 8/2A NC (25%)] with highest volume of contact area compared with used cancer micro-cells show lowest cell viability as an excellent anticancer platform. 8/2A-NC is a novel multifunctional drug with intercalating and encapsulated core-shell morphology structures consisting of positively charged, non-randomly distributed AgNPs with a large contact area and low diameters (5-6 nm). The anticancer properties of (This factor is not conformed experimentally in work) this drug can be explained by the following structural factors: 8/2A-NC contains a combination of active sites from protonated hydroxyl, carboxyl and amine groups; Ag + -cations and ODA-MMT with high physical and chemical surface areas. We suggest this material be further explored for anti-cancer testing.
Aintshop Production Line Optimization Using Response Surface Methodology
(2007) Dengiz, Berna; Belgin, Onder; 0000-0001-6702-2608; K-1080-2019
This paper deals with the problem of determining the optimum number of workstations to be used in parallel and workers at some stations using simulation optimization approach in a paint shop line of an automotive factory in Ankara, Turkey. In the optimization stage of the study Response Surface Methodology (RSM) is used to find the optimum levels of considered factors. Simulation model and optimization stage integration is used both to analyse the performance of the current paint shop line and determine the optimum working conditions, respectively, with reduced cost, time and effort.
Airfoil-slat arrangement model design for wind turbines in fuzzy environment
(2020) Atalay, Kumru Didem; Dengiz, Berna; Yavuz, Tahir; Koc, Emre; Ic, Yusuf Tansel
In this study, a multi-element wind turbine blade that consists of NACA 6411 and NACA 4412 leading-edge slat design is investigated computationally. Optimum design parameters of the slatted wind turbine blade leading to maximum value of C-L/C-D related to the turbine power are obtained. In the optimization process, a new fuzzy logic linear programming methodology integrating with fuzzy linear regression and 2D CFD analysis is proposed. The aerodynamic characteristics of the slatted blade are computed by using Incompressible Navier-Stokes equations and k-omega turbulence modeling. Results are compared with the results of linear programming method and direct search optimization method. The computational results reveal that the proposed methodology for performance optimization is more effective than other methods to obtain high-performance value of the C-L/C-D. The maximum value of the C-L/C-D is obtained as 25.1 leading the maximum efficiency of 0.52.
Aligned Polyvinylpyrrolidone Nanofibers with Advanced Electrospinning for Biomedical Applications
(2018) Karayegen, Gokay; Kocum, I. Cengiz; Serdaroglu, Dilek Cokeliler; Dogan, Mustafa; 0000-0001-5215-8887; 30400080; I-4296-2019
BACKGROUND: Electrospinning is a highly effective method in order to generate nano-scaled fibers. In conventional electrospinning technique, geometry of nanofibers are mostly random due to the chaotic behavior of polymer jet. OBJECTIVE: Purpose of this study is to produce aligned nanofibers from PVP polymers with advanced electrospinning technique in order to be used in a potential novel sensor applications, tissue regeneration and engineering. METHODS: In this study, by using finite hollow cylinder focusing electrodes, an external electrostatic field is created. With these electrodes, it is aimed to decrease whipping instability of polymer jet. In addition, it is also investigated that the alignment ratio of nanofibers by using conductive parallel electrodes which placed through jet trajectory. RESULTS: In conclusion, with the effect of electrical field created by cylinder electrodes, radius of the fiber dispersion on the collector was able to be reduced and aligned nanofibers were successfully produced by using electrical field generated from the parallel plates. CONCLUSIONS: Radius of the fiber dispersion on the collector is 9.95 mm and fiber diameters varied between 800 nm and 3 mu m. Additionally, alignment ratio of the fibers is determined with ImageJ software. These alignment of nanofibers can be used in tissue engineering applications and sensor applications.
Analysis of Lack of Cohesion in Methods (LCOM): A Case Study
(2021) Haner Kirgil, Elif Nur; Ercelebi Ayyildiz, Tulin
As the need for software has increased, the maintainability of software has become an important issue and the need for the qualitative study of source codes has arisen. For this reason, we used software quality metrics to measure software quality. Moreover, for object-oriented software development projects, cohesion is an important factor. The main purpose of cohesion is to provide the rule that each class should serve a single purpose. Every class should have a single responsibility. In this study, types of Lack of Cohesion in Methods (LCOM) metrics were examined and compared using a sample Java code. As a result, it was observed that the LCOM5 metric gave the best result.
Analysis of post-graduate theses in Industrial Engineering area of Turkish Universities
(2020) Cetinkaya, Cihan; Uslu, Aysenur; Ozceylan, Eren; Hayirsoz, Kaan Mert
Today, engineers make efforts for post-graduate programs far more than before. The main reasons can be increasing awareness of firms about education, decreasing job opportunities for undergraduate degrees, the increasing demand for being an academician or scholarship opportunities by government. Some firms want their postgraduate student engineers to solve the firm's problems in their master or doctoral thesis as case studies. In this regard industrial engineering is a field that adjusts almost with every sector because of its multidisciplinary nature. Thus, there are many post-graduate theses written in this area. The aim of this paper is to analyze 2,122 postgraduate theses (master & doctoral) which are carried out in the department of industrial engineering in Turkish universities. The data is obtained from the website of Council of Higher Education of Turkey. The time period is determined as 2010-2017 and only the 1780 "permission" theses are analyzed in order to reach keywords for solution approaches and keywords analysis. Nine different indicators are used to analyze the thesis such as; university status, page numbers, language, keywords etc. As a result, this study shows how the theses are clustered according to different indicators and which topics are studied more frequently in recent years. The inference of the paper is important because the results give an insight about the road map of industrial engineering thesis completed in 56 different Turkish universities.
Analysis of the manufacturing flexibility parameters with effective performance metrics: a new interactive approach based on modified TOPSIS-Taguchi method
(2022) Ic, Yusuf Tansel; Sasmaz, Turgut; Yurdakul, Mustafa; Dengiz, Berna; 0000-0001-9274-7467; AGE-3003-2022
Flexibility is one of the most important strategy parameters to achieve a long-term successful performance for a manufacturing company. Studies in the literature aim to operate a manufacturing system at optimum levels of flexibility parameters under its own manufacturing environment. This study aims to present an interactive analysis framework based on TOPSIS and Taguchi parameter design principles for investigating the effects of different levels of flexibility parameters on the performance of a flexible manufacturing cell (FMC). The main performance metric used in this study is manufacturing lead time. Other important metrics to evaluate quality control and inspection policies are also investigated in this study. To conclude, a combined model of an interactive approach based on TOPSIS and Taguchi methods are used to assess the effectiveness of the flexibility parameters for a FMC.
Analysis of The Performance of A Solar Air Heater With Different Configurations: Effect of Fins And Turbulators
(2022) Erol, Ozgur
Solar air heaters are simple tools used to harvest the energy of the sun. The main objective of the solar air heater design is to get the highest thermal energy from the sun. In order to do this different kinds of fins and turbulators are placed in the flow channel of the solar air heater, which also affects the flow characteristic of the working fluid. In this study, the performance of two different configurations, a turbulator placed at the bottom of the channel and a longitudinal rectangular fin placed on the absorber plate, are investigated using different performance parameters. These parameters are the thermal efficiency, rational exergy management method (REMM) efficiency, flow work, and the temperature distribution on the absorber plate. According to the results, both of the test cases have nearly the same performance, which is higher than the flat solar air except the flow work. When the heat gain per unit flow work is investigated, it can be said that turbulator configuration is the best choice among the configurations that are investigated.
Analysis of the Robustness of the Operational Performance Using a Combined Model of the Design of Experiment and Goal Programming Approaches for a Flexible Manufacturing Cell
(2023) Ic, Yusuf Tansel; Yurdakul, Mustafa; Dengiz, Berna; Sasmaz, Turgut
A combined model of a 2(k) design of experiment (DOE) and goal programming (GP) approaches is presented to determine optimum levels of input variables and analyze their robustness for a multiobjective performance of a flexible manufacturing cell (FMC) in this study. Two main performance metrics, namely, manufacturing lead time (MLT) and surface roughness (SR), are considered performance outputs for the FMC. Machine sequence, robot speed, tool type, and material type are selected as the four input variables on the input side of the proposed model. The study shows that even with a limited number of experiments, one can determine optimum input levels for the multiobjective performance of the FMC and determine their robustness.
An Analysis Tool that Detects The Code Caves in Specified Sizes for Portable Executable Files
(2022) Ugurlu, Guney; Acici, Koray; 0000-0002-3821-6419; HDM-9910-2022
Code caves represent sequential null bytes in portable executable files and are particularly used in reverse engineering. With the help of code caves, the execution flow of the program can be changed, and different codes can be injected into the compiled programs. In the sections in the PE files, it is determined manually whether there is a code cave suitable for the size of the code to be injected. This paper presents the analysis tool named CodeCaveFinder. It finds in detail whether the code caves of the user desired size are in the sections of the PE file. As a result of tests, it has been proven that CodeCaveFinder gives accurate and reliable results.
Anomaly Detection in Smart Home Environments using Convolutional Neural Network
(2021) Ercan, Naci Mert; Sert, Mustafa
The use of smart devices in home environments has been increasing in recent years. The wireless connection of these devices to the internet enables smart homes to be built with less cost and hence, recognition of activities in home environments and the detection of possible anomalies in activities is important for several applications. In this study, we propose a new method based on the changepoint representation of sensor data and variable-length windowing for the recognition of abnormal activities. We present comparative analyses with different representations to demonstrate the efficacy of the proposed scheme. Our results on the WSU performance dataset show that, the use of variable-length windowing improves the anomaly detection performance in comparison to fixed-length windowing.
Antenna-Type Radiofrequency Generator in Nanoparticle-Mediated Hyperthermia
(2016) Nasseri, B.; Yilmaz, M.; Turk, M.; Kocum, I. C.; Piskin, E.
Induction of hyperthermia using nanoparticles with specific magnetic, electrical, acoustic, optical or thermal properties is a potential alternative to conventional thermal ablation in cancer therapy. In this study, for the first time we employed an antenna-type radiofrequency (RF) generator as the energy source and as a proof of concept the effects of nanoparticles of varying structures and sizes, such as super-paramagnetic iron oxide nanoparticles (SPIONs), gold-coated superparamagnetic iron oxide nanoparticles (Au@SPIONs), spherical gold nanoparticles (AuNPs), and gold nanorods (AuNRs) on RF hyperthermia were examined to determine hyperthermia efficiency of the antenna-type RF generator. In preliminary experiments, RF was applied at varying powers to various nanoparticle solutions. In all cases, temperature rises due to exposure of RF radiation to nanoparticles were captured by using an infrared thermal camera. This procedure was applied to in vitro tests of fibroblast (L-929) and breast cancer (MCF-7) cell lines. Cell viability, apoptosis and necrosis were evaluated in both cell lines to comprehensively determine cell toxicity. Due to their particle size and chemical nature, SPIONs, in the case of highest RF power and nanoparticle concentration, resulted in the lowest cell viability and highest levels of apoptosis and necrosis.
Antibody Immobilization Techniques in Mass Sensitive Immunosensor: Enhanced Sensitivity through Limited Mass Load
(2022) Kirali, Kubra; Brimo, Nura; Serdaroglu, Dilek Cokeliler; https://orcid.org/0000-0002-3053-2169; https://orcid.org/0000-0002-9604-263X; https://orcid.org/0000-0001-8645-9047
Background: Biosensors are analytical devices that include a sample-delivery approach between a biological recognition element and a transducer required to convert the physicochemical change produced from the interaction of biological molecule-receptor interaction into a signal. The immunosensor is a special type of biosensor that includes an antibody as a biorecognition element to detect analytes as antigens. In mass sensitive sensors, antigen-antibody interactions can be specified by measuring the frequency change and the most commonly knowns are the surface acoustic wave, bulk acoustic wave, quartz crystal microbalance and microcantilevers. Methods: Different methods for antibody immobilization, including functionalization of the transducer surface with specific groups, have been reported for antibody immobilization. This stage affects the limit of detection and overall performance. In this review, perspectives on immobilization strategies of mass sensitive immunosensors according to transducer types will be presented. The choice of immobilization methods and their impact on performance in terms of capture molecule loading, orientation and signal improvement will also be discussed. Results: One of the most critical points during the configuration of the biorecognition layer is to improve the sensitivity. Therefore, we initially focused on comparisons of the antibody immobilization strategies in the biorecognition layer in terms of mass load level and high sensitivity. Conclusion: The lack of significant data on the mass accumulations up to the functionalization and antibody immobilization steps, which are the basis of immusensor production, has been identified. However, mass sensitive immunosensors have the potential to become more common and effective analytical devices for many application areas.
Application of Cellular Manufacturing and Simulation Approaches for Performance Improvement in an Aerospace Company's Manufacturing Activities
(2019) Ic, Yusuf Tansel; Yurdakul, Mustafa; Gulsen, Mehmet; Dalcan, Gizem; Kirdar, Didem; Kale, Meric; Altinkaya, Zeynep; Aktas, Dogukan; https://orcid.org/0000-0001-9274-7467; AGE-3003-2022
This paper presents performance improvement studies performed in manufacturing activities of an aerospace company. Cellular Manufacturing (CM) and simulation approaches are used to improve performance in the factory of the company. In the application of CM, reorganization of machines in the machining section as manufacturing cells is performed by using Rank Order Clustering (ROC) algorithm and Hollier method. The performance improvement provided by CM application is measured in terms of the total material handling distances travelled by the parts. On the other hand, a simulation model in SIMAN is developed for panel production section of the factory. Based on the performance outputs of the simulation model, various recommendations are proposed in the operation rules and numbers of resources in the panel production section. The results show that both approaches provide considerable performance improvement in the manufacturing activities of the factory.
Applications of Deep Learning Techniques to Wood Anomaly Detection
(2022) Celik, Yaren; Guney, Selda; Dengiz, Berna; Xu, J; Altiparmak, F.; Hassan, MHA; Marquez, FPG
Wood products and structures have an important place in today's industry. They are widely used in many fields. However, there are various difficulties in production systems where wood raw material is under many processes. Some difficulty and complexity of production processes result in high variability of raw materials such as a wide range of visible structural defects that must be checked by specialists on line or of line. These issues are not only difficult and biased in manual processes, but also less effective and misleading. To overcome the drawbacks of the manual quality control processes, machine vision-based inspection systems are in great of interest recently for quality control applications. In this study, the wood anomaly has been detected by using deep learning. As it will be a distinction-based method on image processing, the Convolution Neural Network (CNN), which is one of the most suitable methods, has been used for anomaly detection. In addition, it will be tried to obtain the most suitable one among different CNN architectures such as ShuffleNet, AlexNet, GoogleNet for the problem. MobileNet, SqueezeNet, GoogleNet, ShuffleNet among considered methods show promising results in classifying normal and abnormal wood products.
Approximation by statistical convergence with respect to power series methods
(2022) Bayram, Nilay Sahin; Yildiz, Sevda
In the present work, using statistical convergence with respect to power series methods, we obtain various Korovkin-type approximation theorems for linear operators defined on derivatives of functions. Then we give an example satisfying our approximation theorem. We study certain rate of convergence related to this method. In the final section we summarize these results to emphasize the importance of the study.
Approximation Properties of King Type -Bernstein Operators
(2019) Dalmanoglu, Ozge; Orkcu, Mediha
The present paper deals mainly with a King type modification of -Bernstein operators. By improving the conditions given in Mursaleen et al. (On (p, q)-analogue of Bernstein operators. Appl Math Comput 266:874-882, 2015a), we investigate the Korovkin type approximation of both -Bernstein and King type -Bernstein operators. We also prove that the error estimation of King type of the operator is better than that of the classical one whenever 0 <= x <= 1/3.