Muhammet Arif Öztürk - Academia.edu (original) (raw)
Uploads
Papers by Muhammet Arif Öztürk
European Journal of Science and Technology
This paper proposed Mamdani-based Adaptive Neuro-Fuzzy Inference System (MANFIS). In literature, ... more This paper proposed Mamdani-based Adaptive Neuro-Fuzzy Inference System (MANFIS). In literature, there are very applications of Sugeno Adaptive Neuro-Fuzzy Inference System (ANFIS) because of simplicity of the Sugeno defuzzification step. Mamdani defuzzification step is linguistic but the Sugeno defuzzification step has constant and linear functions. So, Mamdani parameters training algorithms given in the open literature are not efficient and give worse results when compared to the Sugeno ANFIS. The proposed Mamdani ANFIS is tested for an equation and to predict vehicle soot emission that soot emission is effective at global warming and melting of sea ice in the Arctic. The proposed Mamdani ANFIS is compared to the Sugeno ANFIS for Least Square Estimation method and Gradient Descent method. The training results show that The Mamdani ANFIS consumes less time and needs less epoch number. It is determined that for Gradient Method, the proposed Mamdani has less training error.
ULUSLARARASI BİLGİ GÜVENLİĞİ MÜHENDİSLİĞİ DERGİSİ
In January 2009, Satoshi Nakamota published "Bitcoin" and this sparked the beginning of a new inf... more In January 2009, Satoshi Nakamota published "Bitcoin" and this sparked the beginning of a new information tehnologies, named blokchain. Despite blockchain technology has already been mentioned as a concept, today this technology is usually identified with Bitcoin. While blokchain and cryptocurreny is thought as the same thing/technology by the many, in fact these two aren't the same thing. Blockchain is the technology that has a more general scope than crytocurrency, while cryptocurrencies is some kind of blockchain that transactions of blockchain deliver coins which can be used like real currencies in the real world. Bitcoin still keeps its status as the most succesful, most used and most expensive crptocurrency. For many years, Bitcoin was thought totally secure, anonymous and private thanks to its using of "public-keyed address" that can be said as Bitcoin identifier. Unfortunately, these addresses is kept in fully public Bitcoin's ledger so Bitcoin cannot be anonymous at all. Because for example, if a malicious node learn an address which belongs to his target, it's totally possible to track all previous transactions of addresses of target. Because of this problem, various methods suggested and developed to increase anonymity. But again, these methods like CoinJoin or Mixin proved to be insufficient against various malicious attacks or academical analysises, so anonymous cryptocurrencies began to emerge as an alternative to Bitcoin. Zcash, Dash, Verge and PIVX anonymous cryptocurrencies are enchanced-forks of Bitcoin while Monero anonymous cryptocurrency is enchanced-fork of Litecoin. In theory, these crytocurrencies present a fully anonymous and private transaction possibility. But in practice, after conducting various analysis these crytocurrencies appeared to be not that "fully" anonymous at all. In this research, Zcash, Dash and Monero will be tried to analyze. After that it will be emphasized whether these anonymous crypytocurrencies are secure and anonymous then why some of these anonymous crypytocurrencies are not anonymous in practise and what can be done about it.
YEŞİLOĞLU'na yardımlarından ötürü arkadaşım Günay YILDIZ'a, öğrenim hayatım boyunca maddi ve mane... more YEŞİLOĞLU'na yardımlarından ötürü arkadaşım Günay YILDIZ'a, öğrenim hayatım boyunca maddi ve manevi desteklerini hiçbir zaman esirgemeyen değerli aileme sonsuz teşekkürlerimi sunarım.
SN Applied Sciences, 2021
In this paper, a new approach for Neuro-Fuzzy Controller (NFC) has been presented and compared to... more In this paper, a new approach for Neuro-Fuzzy Controller (NFC) has been presented and compared to previously defined NFCs given in open literature. The proposed controller is based on an on-line Adaptive Neuro-Fuzzy Inference System (ANFIS) and meticulous analysis through simulations is performed to show its robustness. The performance of Neuro-Fuzzy Controllers (NFC) depends on controller inputs. To show the difference and superiority of the proposed controller, many studies in the open literature are examined and compared. Therefore, the advantages and disadvantages of the Neuro-Fuzzy controller are outlined and an optimum Neuro-Fuzzy controller is structured and presented. To test our developed controller for a nonlinear problem, having coupling effects, a 2 DOF helicopter model is chosen. Also to show the robustness, the controller performance which is applied to a 2 DOF helicopter is investigated and compared with other Neuro-Fuzzy controller structures. To better show NFC perf...
European Journal of Science and Technology
This paper proposed Mamdani-based Adaptive Neuro-Fuzzy Inference System (MANFIS). In literature, ... more This paper proposed Mamdani-based Adaptive Neuro-Fuzzy Inference System (MANFIS). In literature, there are very applications of Sugeno Adaptive Neuro-Fuzzy Inference System (ANFIS) because of simplicity of the Sugeno defuzzification step. Mamdani defuzzification step is linguistic but the Sugeno defuzzification step has constant and linear functions. So, Mamdani parameters training algorithms given in the open literature are not efficient and give worse results when compared to the Sugeno ANFIS. The proposed Mamdani ANFIS is tested for an equation and to predict vehicle soot emission that soot emission is effective at global warming and melting of sea ice in the Arctic. The proposed Mamdani ANFIS is compared to the Sugeno ANFIS for Least Square Estimation method and Gradient Descent method. The training results show that The Mamdani ANFIS consumes less time and needs less epoch number. It is determined that for Gradient Method, the proposed Mamdani has less training error.
ULUSLARARASI BİLGİ GÜVENLİĞİ MÜHENDİSLİĞİ DERGİSİ
In January 2009, Satoshi Nakamota published "Bitcoin" and this sparked the beginning of a new inf... more In January 2009, Satoshi Nakamota published "Bitcoin" and this sparked the beginning of a new information tehnologies, named blokchain. Despite blockchain technology has already been mentioned as a concept, today this technology is usually identified with Bitcoin. While blokchain and cryptocurreny is thought as the same thing/technology by the many, in fact these two aren't the same thing. Blockchain is the technology that has a more general scope than crytocurrency, while cryptocurrencies is some kind of blockchain that transactions of blockchain deliver coins which can be used like real currencies in the real world. Bitcoin still keeps its status as the most succesful, most used and most expensive crptocurrency. For many years, Bitcoin was thought totally secure, anonymous and private thanks to its using of "public-keyed address" that can be said as Bitcoin identifier. Unfortunately, these addresses is kept in fully public Bitcoin's ledger so Bitcoin cannot be anonymous at all. Because for example, if a malicious node learn an address which belongs to his target, it's totally possible to track all previous transactions of addresses of target. Because of this problem, various methods suggested and developed to increase anonymity. But again, these methods like CoinJoin or Mixin proved to be insufficient against various malicious attacks or academical analysises, so anonymous cryptocurrencies began to emerge as an alternative to Bitcoin. Zcash, Dash, Verge and PIVX anonymous cryptocurrencies are enchanced-forks of Bitcoin while Monero anonymous cryptocurrency is enchanced-fork of Litecoin. In theory, these crytocurrencies present a fully anonymous and private transaction possibility. But in practice, after conducting various analysis these crytocurrencies appeared to be not that "fully" anonymous at all. In this research, Zcash, Dash and Monero will be tried to analyze. After that it will be emphasized whether these anonymous crypytocurrencies are secure and anonymous then why some of these anonymous crypytocurrencies are not anonymous in practise and what can be done about it.
YEŞİLOĞLU'na yardımlarından ötürü arkadaşım Günay YILDIZ'a, öğrenim hayatım boyunca maddi ve mane... more YEŞİLOĞLU'na yardımlarından ötürü arkadaşım Günay YILDIZ'a, öğrenim hayatım boyunca maddi ve manevi desteklerini hiçbir zaman esirgemeyen değerli aileme sonsuz teşekkürlerimi sunarım.
SN Applied Sciences, 2021
In this paper, a new approach for Neuro-Fuzzy Controller (NFC) has been presented and compared to... more In this paper, a new approach for Neuro-Fuzzy Controller (NFC) has been presented and compared to previously defined NFCs given in open literature. The proposed controller is based on an on-line Adaptive Neuro-Fuzzy Inference System (ANFIS) and meticulous analysis through simulations is performed to show its robustness. The performance of Neuro-Fuzzy Controllers (NFC) depends on controller inputs. To show the difference and superiority of the proposed controller, many studies in the open literature are examined and compared. Therefore, the advantages and disadvantages of the Neuro-Fuzzy controller are outlined and an optimum Neuro-Fuzzy controller is structured and presented. To test our developed controller for a nonlinear problem, having coupling effects, a 2 DOF helicopter model is chosen. Also to show the robustness, the controller performance which is applied to a 2 DOF helicopter is investigated and compared with other Neuro-Fuzzy controller structures. To better show NFC perf...