2 results
Search Results
Now showing 1 - 2 of 2
Article Citation - WoS: 4Citation - Scopus: 6On the Classification of Modulation Schemes Using Higher Order Statistics and Support Vector Machines(Springer, 2022) Coruk, Remziye Busra; Gokdogan, Bengisu Yalcinkaya; Benzaghta, Mohamed; Kara, AliThe recognition of modulation schemes in military and civilian applications is a major task for intelligent receiving systems. Various Automatic Modulation Classification (AMC) algorithms have been developed for this purpose in the literature. However, classification with low computational complexity as well as reasonable processing time is still a challenge. In this paper, a feature-based approach along with various classifiers is employed based on statistical features as well as higher-order moments and cumulants. An over-the-air (OTA) recorded dataset consisting of four analog and ten digital modulation schemes are used for testing the proposed method at 0-20 dB SNR. The overall accuracy for quadratic Support Vector Machine (SVM) is found to be as high as 98% at 10 dB. The comparison of the results with other AMC papers published in the literature indicates that the proposed method present higher accuracy, especially for realistic channel induced OTA dataset.Article Citation - Scopus: 1A Hybrid-Flipped Classroom Approach: Students' Perception and Performance Assessment(Univ Nac Colombia, Fac ingenieria, 2023) Gokdogan, Bengisu Yalcinkaya; Coruk, Remziye Busra; Benzaghta, Mohamed; Kara, AliThis study presents an improved hybrid-flipped classroom (hybrid-FC) education method based on technology-enhanced learning (TEL) along with diluted classes for a course on probability and random processes in engineering. The proposed system was implemented with the participation of two student groups who alternated weekly between attending face-to-face activities and fully online classes as a sanitary measure during the pandemic. The education model was combined with the flipped classroom (FC) approach in order to improve the quality of learning and address the negative effects of remote education. Before the lessons, the students studied the course material, filled a question form, and then took a low- stake online quiz. Then, the students attended a session where the questions reported in the forms were discussed, and they took an online problem-solving session followed by an individual quiz. Class sessions were available to both online and face-to-face students, as well as in the form of video recordings for anyone who missed lessons. Qualitatively and quantitatively, the proposed education method proved to be more effective and comprehensive than conventional online methodologies. The students' performances were evaluated via quizzes and exams measuring the achievement of the course learning outcomes ( CLOs). Weekly pre/post-tests were applied to examine the students' progress in each topic. Midterm and final exams were planned to measure the level of success for all course topics. Additionally, the students' perception was assessed with questionnaires and face-to-face interviews. A performance assessment showed an apparent increase in the success rate, and the students' perception was found to be positive.

