arXiv subjects

Christos Christodoulou

Publications and source records attributed to Christos Christodoulou.

3 recordsLinked to original sources

arXiv2023

Identifying Misinformation on YouTube through Transcript Contextual Analysis with Transformer Models

Misinformation on YouTube is a significant concern, necessitating robust detection strategies. In this paper, we introduce a novel methodology for video classification, focusing on the veracity of the content. We convert the conventional video classification task into a text classification task by leveraging the textual content derived from the video transcripts. We employ advanced machine learning techniques like transfer learning to solve the classification challenge. Our approach incorporates two forms of transfer learning: (a) fine-tuning base transformer models such as BERT, RoBERTa, and ELECTRA, and (b) few-shot learning using sentence-transformers MPNet and RoBERTa-large. We apply the trained models to three datasets: (a) YouTube Vaccine-misinformation related videos, (b) YouTube Pseudoscience videos, and (c) Fake-News dataset (a collection of articles). Including the Fake-News dataset extended the evaluation of our approach beyond YouTube videos. Using these datasets, we evaluated the models distinguishing valid information from misinformation. The fine-tuned models yielded Matthews Correlation Coefficient>0.81, accuracy>0.90, and F1 score>0.90 in two of three datasets. Interestingly, the few-shot models outperformed the fine-tuned ones by 20% in both Accuracy and F1 score for the YouTube Pseudoscience dataset, highlighting the potential utility of this approach -- especially in the context of limited training data.

cs.CL↗

arXiv2023

Source detection via multi-label classification

Radio source detection through conventional algorithms has been unreliable when trying to solve for large number of sources in the presence of low SINR and less number of snapshots. We address this by reformulating source detection as a multi-class classification problem solved using deep learning frameworks. Incoming waveforms are sampled using a centrosymmetric linear array with omni-directional elements and the normalized upper triangle of the autocorrelation matrix is extracted as the input feature to a modified convolutional neural network with uni-dimensional filters, trained to detect the sources in the presence of both uncorrelated and correlated signals. Two detection algorithms are introduced and referred to as CNNDetector and RadioNet, and subsequently benchmarked against the conventional source detection algorithms. By including preprocessing in forward backward spatial smoothing, RadioNet can also resolve the number of uncorrelated sources in the presence of correlated paths. Finally, the algorithms are stress tested under challenging operational conditions and extensive evaluations are presented showing the efficacy and contributions of the introduced predictive models.

eess.SP↗

arXiv2016

Experimental Demonstration of Degenerate Band Edge in Metallic Periodically-Loaded Circular Waveguide

We experimentally demonstrate for the first time the degenerate band edge (DBE) condition, namely the degeneracy of four Bloch modes, in loaded circular metallic waveguides. The four modes forming the DBE represent a degeneracy of fourth order occurring in a periodic structure where four Bloch modes, two propagating and two evanescent, coalesce. It leads to a very flat wavenumber-frequency dispersion relation, and the finite length structure's quality factor scales as $N^5$ where $N$ is the number of unit cells. The proposed waveguide in which DBE is observed here is designed by periodically loading a circular waveguide with misaligned elliptical metallic rings, supported by a low-index dielectric. We validate the existence of the DBE in such structure using measurements and we report good agreement between full-wave simulation and the measured response of the waveguide near the DBE frequency; taking into account metallic losses. We correlate our finding to theoretical and simulation results utilizing various techniques including dispersion synthesis, as well as observing how quality factor and group delay scale as the structure length increases. Moreover, the reported geometry is only an example of metallic waveguide with DBE: DBE and its characteristics can also be designed in many other kinds of waveguides and various applications can be contemplated as high microwave generation in amplifiers and oscillators based on an electron beam interaction or solid state devices, pulse compressors and microwave sensors.

physics.class-ph↗