Search

Nowadays, deepfake is wreaking havoc on society. Deepfake content is created with the help of artificial intelligence and machine learning to replace one person’s likeness with another person in pictures or recorded videos. Although visual media manipulations are not new, the introduction of deepfakes has marked a breakthrough in creating fake media and information. These manipulated pictures and videos will undoubtedly have an enormous societal impact. Deepfake uses the latest technology like Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) to construct automated methods for creating fake content that is becoming increasingly difficult to detect with the human eye. Therefore, automated solutions employed by DL can be an efficient approach for detecting deepfake. Though the “black-box” nature of the DL system allows for robust predictions, they cannot be completely trustworthy. Explainability is the first step toward achieving transparency, but the existing incapacity of DL to explain its own decisions to human users limits the efficacy of these systems. Though Explainable Artificial Intelligence (XAI) can solve this problem by interpreting the predictions of these systems. This work proposes to provide a comprehensive study of deepfake detection using the DL method and analyze the result of the most effective algorithm with Local Interpretable Model-Agnostic Explanations (LIME) to assure its validity and reliability. This study identifies real and deepfake images using different Convolutional Neural Network (CNN) models to get the best accuracy. It also explains which part of the image caused the model to make a specific classification using the LIME algorithm. To apply the CNN model, the dataset is taken from Kaggle, which includes 70 k real images from the Flickr dataset collected by Nvidia and 70 k fake faces generated by StyleGAN of 256 px in size. For experimental results, Jupyter notebook, TensorFlow, NumPy, and Pandas were used as software, InceptionResnetV2, DenseNet201, InceptionV3, and ResNet152V2 were used as CNN models. All these models’ performances were good enough, such as InceptionV3 gained 99.68% accuracy, ResNet152V2 got an accuracy of 99.19%, and DenseNet201 performed with 99.81% accuracy. However, InceptionResNetV2 achieved the highest accuracy of 99.87%, which was verified later with the LIME algorithm for XAI, where the proposed method performed the best. The obtained results and dependability demonstrate its preference for detecting deepfake images effectively. [ABSTRACT FROM AUTHOR]

This research presents an ultra-wideband (UWB) textile antenna design for body-centric applications. The antenna is printed on a 1 mm thick denim substrate with a 1.7 relative permittivity. The jeans substrate is sandwiched between a partial ground plane and a radiating patch with a Q-shaped slot. The slotted radiating patch is placed above the substrate and measures 27.8 mm × 23.8 mm. In free space, the antenna covers the ultra-wideband spectrum designated by the Federal Communication Commission (FCC). Various parameters of the antenna design were changed for further performance evaluation. Depending on the operating frequency, the antenna's realized gain varied from 2.7 to 5 dB. The antenna achieved high radiation efficiency with an omnidirectional radiation pattern. A parametric study was performed in research on varying antenna substrates and other components of the antenna. The three outermost layers of the human body are used to model a human phantom for on-body simulation. After that, the antenna was placed at five different distances from the phantom. The findings demonstrate that at close distances to the phantom, the antenna's gain and efficiency at lower frequencies are reduced. The antenna's radiation efficiency and gain were much higher at higher frequencies for distances greater than 6 mm. Compared to free space, the antenna's radiation pattern was more omnidirectional, especially at higher frequencies. This antenna is novel, compact and has an ultra wide bandwidth, a maximum of 94.60% radiation efficiency and a 5 dBi gain that will make it a good candidate for body-centric communications. [ABSTRACT FROM AUTHOR]