AREF YELGHI

Makale | 2021 | Doğuş Üniversitesi Dergisi

Günümüze gelindiğinde devletlerin finansal gereksinimlerinin giderilmesi içinbaşvurdukları önemli yollardan biri tahvil ihracıdır. Türkiye’de tahvil piyasasındanen çok devletin yararlandığı görülmektedir. Literatürde ekonomik büyüme ile hissesenedi piyasası ve kredi arasında birçok çalışma bulunurken tahvil piyasası ile ilgilioldukça az çalışma yapılmıştır. Finansal piyasalarında tahvil piyasası önemli payalması ve ekonomik büyümesinde etkisi ne ölçüde oluğu merak edilmektedir. Sondönemlerde tahvil piyasasının gelişimi hem ulusal hem uluslararası piyasada hızkazanmıştır. Bu çalışmada Türkiye tahvil piyasasını ile ekonomik büyüme ara . . .sındakiuzun dönem ilişkisini incelemesini amaçlanmaktadır. Araştırmada Peseran vediğerleri (1999), Peseran ve Shin (2001) önerdiği ARDL modelindenyararlanılmaktadır. Çalışmada Uluslararası Toplam Borçlanma Senetleri/ GSYİHoranı, Toplam Ulusal Borçlanma Senetleri/GSYİH oranı ile büyüme oranı 2000Q1-2017Q4 yılları arasındaki mevsimsel veriler kullanılmaktadır. Bulgularda büyüme iledevlet tahvilleri arasında ilişkisi, pozitif ve eş bütünleşik sonucu ortaya çıkmaktadır.Dolaysıyla devlet tahvil ihracı ile Türkiye ekonomisine katkı sağlayabilir Daha fazlası Daha az

AREF YELGHI

Makale | 2022 | Conference Proceedings

In recent years, many applications based on the Neural Network, Neuro-Fuzzy, and optimization algorithms have been more common for solving regression and classification problems. In the Adaptive Neuro-fuzzy inference system(ANFIS), many researchers used the adaption of metaheuristic algorithms with ANFIS to propose the best estimation model. However, many researchers only focused on the experiment without the demonstration mathematical or indicating which characteristic of optimization algorithm, during the run, affect and settable in coordination with ANFIS. The paper provides an adaption of metaheuristic algorithms with ANFIS whic . . .h has been performed by considering accuracy parameters in layer 1 and layer 4 for the estimation problem. It is integrated six well-known metaheuristic algorithms and extracting the characteristic of them. In the experiment, the metaheuristic algorithms based on the evolutionary computation have been demonstrated more stable than swarm intelligence methods in tuning parameters of ANFIS. © 2022 IEEE Daha fazlası Daha az

AREF YELGHI

Makale | 2022 | Conference Proceedings

The aim of this study is to provide a novel method routing in ad hoc networks using ant colony algorithm. Hence for this study the researcher attempts to discover and create routes with less number of crossings, nodes sustainable and less energy transfer, to reduce latency end-to-end, save bandwidth and to extend the life and increase the lifetime of the network nodes. Research methodology for simulation algorithm has been OPNET software. Therefore, the proposed algorithm's performance was compared with one of the most routing algorithms in mobile ad hoc networks Ant Hoc Net. The results showed that the proposed algorithm compared w . . .ith Ant Hoc Net has more end-to-end delay, more package shipping, and less routing overhead can reduce energy consumption and thus increases the lifetime of the network nodes. The results of this study indicate that the latency end-to-end, saving bandwidth and increasing lifetime of nodes and network lifetime can be predicted by the proposed algorithm. © 2022 IEEE Daha fazlası Daha az

AREF YELGHI

Makale | 2023 | Studies in Computational Intelligence , pp.109 - 126

Recent work has attempted to determine the appropriate global minimum for complex problems. The paper presents a population and direct-based swarm optimization algorithm called the happiness optimizer (HPO) algorithm. An HPO algorithm is designed based on personal behavior and demonstrated in 30 and 100 dimensions on benchmark functions. The model includes four questions: “what do you want?”, “what do you have?”, “what do others have?”, and “what happened?”, which guide the development of a happiness behavior model. By considering the balancing between exploration and exploitation operators in the search space problem, efficiency, r . . .obustness, and stability were demonstrated for synthetic and real cases. For comparison, our proposed algorithm and some well-known algorithms will be 30 times applied on the benchmark functions and then compared with statistical value and Wilcoxon signed-rank test. As a consequence, the performance, reliability, and stability of our work have been demonstrated better than the others. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG Daha fazlası Daha az