Media synthesis and manipulation has reached unprecedented levels of realism owing to the proliferation of deep learning. Deepfake has been the de-facto tool for media manipulation. Although this technology has potential in the entertainment industry, its threats include political manipulation and bypassing biometric security systems. As a result, deepfake detection has garnered widespread attention among research communities. The intuition is to use deep learning to fix the problems created by deep learning. Although convolutional neural networks have shown their dominance in the filed of pattern recognition, the receptive field-model size dilemma still persists along with the lack of interpretation for such models. While the traditional Gabor function was proposed to fix these problems, it can only generate limited linear Gabor filters which makes it optimal for limited data and applications. The contribution of this paper is quadruple: (i) proposing a unified Gabor function capable of generating linear, elliptical, and circular Gabor filters. (ii) leveraging the back-propagation learning framework to incorporate the proposed function in convolutional neural networks and generate adaptive Gabor filters. (iii) presenting a dual scale large receptive field network for deepfake image recognition. (iv) demonstrating where the proposed model stands in terms of performance and architecture size compared to state-of-the-art models. The proposed model is evaluated on four benchmark datasets: Celeb-DF (v2), DeepFake Detection Challenge Preview, FaceForensics++ and Wilddeepfake. Experimental results show that the proposed adaptive Gabor filters reduce the model size by 64.9% compared to adaptive weighted filters without performance reduction.
Background: The electroencephalogram (EEG) is essential for diagnosing and classifying brain disorders, enabling early medical intervention. Its ability to identify brain abnormalities has increased its clinical use in assessing changes in brain activity. Recent advancements in deep learning have introduced effective methods for interpreting EEG signals, utilizing large datasets for enhanced accuracy. Objective: This study presents a deep learning-based model designed to classify EEG data with better accuracy compared to existing approaches. Methods: The model consists of three key components: data selection, feature extraction, and classification. Data selection employs a windowing technique, while the feature extraction and classification stages use a deep learning framework combining a convolutional neural network (CNN) and a Long Short-Term Memory (LSTM) network. The resulting architecture includes up to 18 layers. The model was evaluated using the Temple University Hospital (TUH) dataset, comprising data from 2785 patients, ensuring its applicability to real-world scenarios. Results: Comparative performance analysis shows that this approach surpasses existing methods in accuracy, sensitivity, and specificity. Conclusions: This study highlights the potential of deep learning in enhancing EEG signal interpretation, offering a pathway to more accurate and efficient diagnoses of brain disorders for clinical applications.
Cognitive Radio (CR) offers a spectrum sharing solution to handle the massive amount of devices operating in the same spectrum. In this work a sub-Nyquist compressive sensing technique is proposed that allows secondary users to sense and utilize idle spectrum. Reconstruction of compressed sparse data is achieved through a dual stage sophisticated reconstruction algorithm. The reconstruction uses a classical fast Orthogonal Matching Persuit (OMP), followed by a new spiking deep Residual neural Network (ResNet) architecture. The proposed architecture is obtained through a novel distributed conversion technique that is proposed to convert deep architectures to a spiking neural networks. The reconstructed data is compared in terms of Peak Signal-to-Noise Ratio (PSNR), Mean Square Error (MSE) and Structural Similarity (SSIM) to the compressed data and the ground truth. Super Resolution Convolutional Neural Network (SRCNN) and a Deep ResNet are also used for reconstruction. The proposed algorithm outperforms SRCNN and the unconverted ResNet, specially at low Channel SNR (CSNR). In addition, the proposed algorithm results in a 68% reduction in both storage and energy requirements, which makes it suitable for implementation on User Equipment (UE).
1 February 2021 in IOP Conference Series: Materials Science and Engineering
In this paper a method for the effective transmission of data, from a Wireless Sensor Network (WSN) in a remote agricultural location with limited connectivity, is proposed; along with a meaningful visualisation of the data at the user end to help in decision making and control of the irrigation system. The paper encompasses three main segments which are data compression, checking for network availability, and user interface. First data compression is implemented to reduce the amount of transmitted data, due to limited connectivity in the area, which is translated in low data rate and high cost of sending the data. Four different techniques are compared: Huffman encoding, Lempel-Ziv-Welsh (LZW), differential encoding, and Run Length Encoding (RLE) to carry out data compression, where Huffman encoding showed the best results when combined with differential encoding. The second phase is the handling of poor network conditions in the agricultural plant by switching between two different communication modes: Mobile data and Short Message Service (SMS). Lastly, the user monitoring centre which is a mobile application that allows the user to monitor and control the agricultural plant remotely. It includes mapping and visualization of temperature and soil moisture data and a control system to control the irrigation system. The solution presents a low-cost alternative for start-up agricultural projects in third world countries, where network instability is an issue and off-the-shelf expensive solutions are not a viable option.
Background: Automatic detection of abnormal electroencephalogram (EEG) signals is essential for supporting clinical screening and reducing human error in EEG interpretation. Although deep learning architectures such as CNN–LSTM have shown promising performance in EEG classification, challenges related to feature variability, non-stationarity, and sensitivity to pathological patterns remain. Our previous work with windowing-based CNN-LSTM architecture achieved strong performance but it did not achieve sufficient sensitivity for reliable clinical application. Methods: To overcome these limitations, we propose an enhanced voting-based ensemble framework that combines five CNN-LSTM base classifiers with a Random Forest (RF) meta-classifier, evaluated using 10-fold cross-validation. Results: The proposed ensemble model achieved a sensitivity of 92.86%, a specificity of 72.3%, and an overall accuracy of 83%, demonstrating competitive and clinically meaningful sensitivity for abnormal EEG detection under the adopted evaluation protocol. Conclusions: These findings demonstrate that integrating multi-model feature extraction with an RF-based voting ensemble improves diagnostic reliability, reduces false negatives, and supports early and accurate detection of brain disorders. This framework not only surpasses existing approaches but also provides a flexible foundation for future advancements in clinical decision support systems.