Browsing by Author "Bahcebasi, Akif"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Conference Object
    Citation - WoS: 3
    Citation - Scopus: 6
    Performance Analysis of Different Modulation Schemes for Underwater Acoustic Communications
    (Institute of Electrical and Electronics Engineers Inc., 2018) Bahcebasi, Akif; Güngör, Vehbi Çağrı; Tuna, Gürkan
    There is an increasing interest in using Underwater Acoustic Sensor Networks (UASNs) for various oceanographic applications, such as pollution monitoring, seismic monitoring, environmental data collection, offshore exploration, and tactical surveillance. UASNs rely on acoustic communications; however, the underwater acoustic channel is highly variable and its link quality depends on environmental factors and the locations of the communicating nodes. Therefore, ensuring reliable communication in UASNs is quite difficult. Moreover, path losses and retransmissions lead to the wastage of energy resources and reduce the network lifetime. In this study, we have utilized well-known underwater modulation schemes to analyse and simulate various underwater scenarios with different depth, distance and Bit Error Rate (BER) values in order to make a fair comparison between the modulation schemes and obtain the optimal transmission power. Performance evaluations show that 32-PSK and 16-QAM techniques achieve the minimum energy consumption rates and enhance network lifetime. © 2019 Elsevier B.V., All rights reserved.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 1
    PCB Component Recognition With Semi-Supervised Image Clustering
    (IEEE, 2021) Unal, Ahmet Emin; Tasdemir, Kasim; Bahcebasi, Akif
    Classification of surface mounted devices plays an important role on automated inspection systems of printed component board production. Limited number of publicly available datasets which the components are labeled and high intraclass variance in these datasets causes the supervised approches to be inefficient. In this study a deep learning method, enhanced with an unsupervised clustering system, which uses a small set of labeled data is proposed. The method compared with the current studies and the supervised systems. Most optimized setting reached high accuracy results by outrunning current classification methods.