Yazar "Yusuf, Aminu" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Geometric optimization of thermoelectric generator using genetic algorithm considering contact resistance and Thomson effect
    (Wiley, 2021) Yusuf, Aminu; Bayhan, Nevra; Ibrahim, Abdullahi Abdu; Tiryaki, Hasan; Ballıkaya, Sedat
    Contact resistance and Thomson heat are the two major factors in the analysis of thermoelectric modules that are often being ignored. Each of these factors has an adverse effect on the output performance of a thermoelectric module. In this study, expression for maximum power output that includes both the contact resistance and the Thomson effect has been optimized using genetic algorithm to obtain the optimum geometric parameters of a thermoelectric generator. Each leg has electrical and thermal contact resistances of 2 x 10(-9) Omega m(2) and 1.8 x 10(-4) m(2) K/W, respectively. The results of the optimization for the maximum power output and the energy conversion efficiency for Skutterudites thermoelectric materials operating at a maximum temperature difference of 500 K are 30.1 W and 9.87%, respectively. When only the contact resistances are not included, the results rise by 19.4% for the maximum power output and 11.65% for the energy conversion efficiency. When only the Thomson heat is not included, the result rise by 2.66% for the maximum power output and 5.67% for the energy conversion efficiency. These two factors should always be considered in the analysis of thermoelectric modules, neglecting them can lead to an overestimation of the output performance.
  • [ X ]
    Öğe
    Novel semi-supervised learning approach for descriptor generation using artificial neural networks
    (Springer, 2022) Alwindawi, Alla Fikrat; Uçan, Osman Nuri; Ibrahim, Abdullahi A.; Yusuf, Aminu
    The rise of machine learning and neural networks has opened many doors for making various arduous real-life tasks far more accessible, in addition to their ability to analyze vast amounts of data that are considered to be impossible for humans to process. Neural networks are an essential topic as they can be applied in many real-life applications, such as image, video and sound matching, making them a very attractive research area. Numerous methods and approaches are available for training neural networks, but this paper is concerned with only the semi-supervised training approach, for which a new ‘‘enhanced semi-supervised’’ learning method is proposed. Semi-supervised learning means that machines, such as computers, can learn in the presence of datasets that are both labeled and unlabeled. In contrast, the supervised learning approach can be applicable with labeled data only. A novel semi-supervised learning approach for descriptor generation using artificial neural networks is proposed to control the values that are output by the neural network. However, no interaction with the assignment of these values to each input group occurs, nor is the space where the output values belong utilized. Thus, this method seeks to provide a more efficient learning approach with a more even distribution of the output throughout the output field of space, resulting in a more effective learning approach. The handwritten digit experiment showed an accuracy of 85.27%, while Alzheimer’s detection experiment recorded an accuracy of 99.27%. The results after applying the proposed method to two sets of experimental data revealed a significant improvement in accuracy compared with the use of Siamese neural networks in different applications.