Browsing by Author "Hançerliogullari, A."

Now showing 1 - 5 of 5

An Approach based on Convolutional Neural Network and ACO-PSO for Colon Cancer Disease Diagnosis
(2024.01.01) Mohamed, A.A.A.; Ghadami, R.; Hançerliogullari, A.; Rahebi, J.
The diagnosis of colon cancer has evolved into a global preoccupation, reflecting its profound impact on public health and healthcare systems worldwide. In this study, the diagnosis of colon cancer is performed using convolutional neural networks (CNN) and metaheuristic methods. Various CNN architectures, including GoogLeNet and ResNet-50, were employed to extract features related to colon disease. However, inaccuracies were introduced in both feature extraction and data classification due to the abundance of features. To address this issue, feature reduction techniques were implemented using combined Ant Colony Optimization (ACO) and particle swarm optimization (PSO). Superior convergence speed in optimizing the fitness function was observed in the case of ACO-PSO. With ResNet-50 producing 2048 features and GoogLeNet generating 1024 features, the reduction of feature dimensions proved to be crucial in identifying the most informative elements. Encouraging results were obtained in the evaluation of metrics, including sensitivity, specificity, accuracy, and F1 score, which were found to be 99.50%, 99.93%, 99.97%, and 99.97%, respectively.
Colon Cancer Disease Diagnosis Based on Convolutional Neural Network and Fishier Mantis Optimizer
(2024.01.01) Mohamed, A.A.A.; Hançerliogullari, A.; Rahebi, J.; Rezaeizadeh, R.; Lopez-Guede, J.M.
Colon cancer is a prevalent and potentially fatal disease that demands early and accurate diagnosis for effective treatment. Traditional diagnostic approaches for colon cancer often face limitations in accuracy and efficiency, leading to challenges in early detection and treatment. In response to these challenges, this paper introduces an innovative method that leverages artificial intelligence, specifically convolutional neural network (CNN) and Fishier Mantis Optimizer, for the automated detection of colon cancer. The utilization of deep learning techniques, specifically CNN, enables the extraction of intricate features from medical imaging data, providing a robust and efficient diagnostic model. Additionally, the Fishier Mantis Optimizer, a bio-inspired optimization algorithm inspired by the hunting behavior of the mantis shrimp, is employed to fine-tune the parameters of the CNN, enhancing its convergence speed and performance. This hybrid approach aims to address the limitations of traditional diagnostic methods by leveraging the strengths of both deep learning and nature-inspired optimization to enhance the accuracy and effectiveness of colon cancer diagnosis. The proposed method was evaluated on a comprehensive dataset comprising colon cancer images, and the results demonstrate its superiority over traditional diagnostic approaches. The CNN-Fishier Mantis Optimizer model exhibited high sensitivity, specificity, and overall accuracy in distinguishing between cancer and non-cancer colon tissues. The integration of bio-inspired optimization algorithms with deep learning techniques not only contributes to the advancement of computer-aided diagnostic tools for colon cancer but also holds promise for enhancing the early detection and diagnosis of this disease, thereby facilitating timely intervention and improved patient prognosis. Various CNN designs, such as GoogLeNet and ResNet-50, were employed to capture features associated with colon diseases. However, inaccuracies were introduced in both feature extraction and data classification due to the abundance of features. To address this issue, feature reduction techniques were implemented using Fishier Mantis Optimizer algorithms, outperforming alternative methods such as Genetic Algorithms and simulated annealing. Encouraging results were obtained in the evaluation of diverse metrics, including sensitivity, specificity, accuracy, and F1-Score, which were found to be 94.87%, 96.19%, 97.65%, and 96.76%, respectively.
IMPROVING THERMAL AND ELECTRICITY GENERATION PERFORMANCE OF PHOTOVOLTAIC/THERMAL (PV/T) SYSTEMS USING HYBRID NANOFLUID
(2024.01.01) Swese, E.E.O.; Sözen, A.; Rezaeizadeh, R.; Hançerliogullari, A.; Aytaç, I.; Variyenli, H.I.; Çakir, M.T.
Solar energy is a safe and clean source of energy, available on the Earth throughout the year. A photovoltaic/thermal (PV/T) system is a device designed to take solar energy and convert it into electrical/thermal energy. Photovoltaic/ thermal systems can also be useful to produce hot fluid (usually water) along with the generation of electrical energy. In addition, the electric generating performance of PVs increases with heat discharging ability of thermal system, which also prevents overheating in PV systems. Nanofluid is a new generation heat transfer fluid that delivers higher thermal conductivity and heat transfer rate compared to conventional fluids. The thermal conductivity of the nanofluid depends on the size of the nanoparticles, concentration of the nanofluid, and the method of its preparation. In this study, it is aimed to increase the thermal heat transfer of the PV/T system by using hybrid nanofluids, manufactured by adding 0.5% Fe2O3 and Fe3O4 nanoparticles to the water as a working fluid. By using hybrid nanofluids, increase in bidirectional performance along with enhanced cooling is achieved. In the experimental study, more heat was withdrawn from the heated PV panels by utilizing the high thermal conductivity of the hybrid nanofluid, and the best improvement in total efficiency was obtained as 86% for the hybrid nanofluid. With the use of hybrid nanofluids in the cooling circuit, the electrical and thermal efficiency of the PV panel has reached to overall 81% on average basis.
Modeling and Simulation of DC Glow Discharges in the AlGaSb-coupled Ar/H2 2 Hybrid Micro Plasma System
(2024.01.01) Ongun, E.; Utas, S.; Yücel, H.H.; Hançerliogullari, A.
Several studies have been reported on the theoretical and experimental investigation of gas discharge-semiconductor microplasma systems (GDS mu PS). In this study, a two-dimensional fluid model of a micro plasma in a square direct current (DC) glow-discharge chamber is simulated using the finite-element method (FEM) solver COMSOL Multiphysics program based on mixture-averaged diffusion-drift theory of gas discharges and Maxwellian electron energy distribution function. A unique III-antimonide high-Ohmic semi-insulating aluminum gallium antimonide (AlGaSb) with finely digitated electron emission surface is modeled as planar cathode electrode coupled to ITO/SiO 2 planar anode electrode across a gas discharge gap of 100 mu m distance. Argon (Ar) and argon mixed with a molar fraction of 5% hydrogen (Ar/H 2 ) gas media are seperately introduced to the micro gap at sub-atmospheric pressure of 150 Torr, and the cell is driven at 1.0 kV DC by a stationary power source to simulate the transitions from electron field emission state to self-sustained normal glow discharge state. The model is simulated to exhibit the transient physical characteristics of the AlGaSb-Ar/H 2 glow-discharge micro plasma system by solving the spatiotemporal dynamics of various discharge parameters including, electron density, electron energy density, electron current density and electric potential. It has been observed that a fraction of hydrogen addition to argon can be used as an effective tool in modeling application-specific hybrid micro plasma - semiconductor based infrared photodetector devices.
Nonlinear vibration analysis of fluid-conveying cantilever graphene platelet reinforced pipe
(2024.01.01) Ali, B.M.; Akkas, M.; Hançerliogullari, A.; Bohlooli, N.
This paper is motivated by the lack of studies relating to vibration and nonlinear resonance of fluid -conveying cantilever porous GPLR pipes with fractional viscoelastic model resting on nonlinear foundations. A dynamical model of cantilever porous Graphene Platelet Reinforced (GPLR) pipes conveying fluid and resting on nonlinear foundation is proposed, and the vibration, natural frequencies and primary resonant of such system are explored. The pipe body is considered to be composed of GPLR viscoelastic polymeric pipe with porosity in which Halpin -Tsai scheme in conjunction with fractional viscoelastic model is used to govern the construction relation of the nanocomposite pipe. Three different porosity distributions through the pipe thickness are introduced. The harmonic concentrated force is also applied on pipe and excitation frequency is close to the first natural frequency. The governing equation for transverse motion of the pipe is derived by the Hamilton principle and then discretized by the Galerkin procedure. In order to obtain the frequency -response equation, the differential equation is solved with the assumption of small displacement, damping coefficient, and excitation amplitude by the multiple scale method. A parametric sensitivity analysis is carried out to reveal the influence of different parameters, such as nanocomposite pipe properties, fluid velocity and nonlinear viscoelastic foundation coefficients, on the primary resonance and linear natural frequency. Results indicate that the GPLs weight fraction porosity coefficient, fractional derivative order and the retardation time have substantial influences on the dynamic response of the system.