Elektronik ve Haberleşme Mühendisliği

Bu koleksiyon için kalıcı URI

http://hdl.handle.net/11527/18001

Gözat

Yazar "Cansız, Gökhan" ile Elektronik ve Haberleşme Mühendisliği'a göz atma
  • Öge
    Microwave dielectric property based classification of renal calculi: Application of a kNN algorithm
    (Elsevier, 2019) Saçlı, Banu ; Aydınalp, Cemanur ; Cansız, Gökhan ; joof, Sulayman ; Yılmaz, Tuba ; Çayören, Mehmet ; Önal, Bülent ; Akduman, İbrahim ; Elektronik ve Haberleşme Mühendisliği ; Electronics and Communication Engineering
    The proper management of renal lithiasis presents a challenge, with the recur- rence rate of the disease being as high as 46%. To prevent recurrence, the first step is the accurate categorization of the discarded renal calculi. Currently, the discarded renal calculi type is determined with the X-ray powder diffraction method which requires a cumbersome sample preparation. This work presents a new approach that can enable fast and accurate classification of discarded renal calculi with minimal sample preparation requirements. To do so, first, the measurements of the dielectric properties of naturally formed renal calculi are collected with the open-ended contact probe technique between 500 MHz to 6 GHz with 100 MHz intervals. Cole–Cole parameters are fitted to the measured dielectric properties with the generalized Newton–Raphson method. The re- nal calculi types are classified based on their Cole–Cole parameters as calcium oxalate, cystine, or struvite. The classification is performed using nearest neigh- bors (kNN) machine learning algorithm with the 10 nearest neighbors, where accuracy as high as 98.17% is achieved.
  • Öge
    Microwave dielectric spectroscopy of renal calculi: A large scale study on dielectric properties from 500 MHz to 18 GHz
    (IEEE, 2019) Yılmaz, Tuba ; Saçlı, Banu ; Cansız, Gökhan ; joof, Sulayman ; Aydınalp, Cemanur ; Çayören, Mehmet ; Akduman, İbrahim ; Önal, Bülent ; Elektronik ve Haberleşme Mühendisliği ; Electronics and Communication Engineering
    Inherent dielectric property discrepancy between biological anomalies and healthy tissue enables the microwave diagnostic and therapeutic technologies. To reveal this discrepancy, microwave dielectric properties of many different biological tissues are tabulated. Although the dielectric properties of biological tissues are well documented in the literature, the knowledge on microwave dielectric property behavior of the renal calculi is limited. This work presents ultra wideband dielectric properties of three renal calculi types between 500 MHz to 18 GHz to pave the way for possible application of microwave technologies for diagnosis, treatment, and prevention of urolithiasis. Microwave dielectric spectroscopy is performed on a total of 66 natural stone samples with open-ended coaxial probe technique. The samples belong to three commonly diagnosed renal calculi categories, namely calcium oxalate, cystine, struvite. Analysis of variance (ANOVA) test is performed on fitted Cole-Cole parameters and it was concluded that there is a statistically significant difference between the dielectric properties of the renal calculi types. A patient-to-patient statistical test is also performed and it was concluded that there is no statistical difference between the samples belonging to the same renal calculi category. To this end, based on the relative permittivity discrepancy between the renal calculi types, the category of renal calculi can be identified by measuring the dielectric properties of renal calculi with open-ended coaxial probe technique.