In smart communities, social media has allowed users easy access to multimedia content. With recent advancements in computer vision and natural language processing, machine learning (ML), and deep learning (DL) models have evolved. With advancements in generative adversarial networks (GAN), it has become possible to create fake images/audio/and video streams of a person or use some person’s audio and visual details to fit other environments. Thus, deepfakes are specifically used to disseminate fake information and propaganda on social circles that tarnish the reputation of an individual or an organization. Recently, many surveys have focused on generating and detecting deepfake images, audio, and video streams. Existing surveys are mostly aligned toward detecting deepfake contents, but the generation process is not suitably discussed. To address the survey gap, the paper proposes a comprehensive review of deepfake generation and detection and the different ML/DL approaches to synthesize deepfake contents. We discuss a comparative analysis of deepfake models and public datasets present for deepfake detection purposes. We discuss the implementation challenges and future research directions regarding optimized approaches and models. A unique case study, IBMM is discussed, which presents a multi-modal overview of deepfake detection. The proposed survey would benefit researchers, industry, and academia to study deepfake generation and subsequent detection schemes.

High Voltage Direct Current (HVDC) systems has been an alternative method of transmitting electric power from one location to another with some inherent advantages over AC transmission systems. The efficiency and rated power carrying capacity of direct current transmission lines highly depends on the converter used in transforming the current from one form to another (AC to DC and vice versa). A well configured converter reduces harmonics, increases power transfer capabilities, and reliability in that it offers high tolerance to fault along the line. Different HVDC converter topologies have been proposed, built and utilised all over the world. The two dominant types are the line commutated converter LCC and the voltage source converter VSC. This review paper evaluates these two types of converters, their operational characteristics, power rating capability, control capability and losses. The balance of the paper addresses their applications, advantages, limitations and latest developments with these technologies.

This paper presents the theoretical basis of the control strategy that allows the cell capacitor voltage regulation of the full-bridge modular multilevel converter (FB-MMC) to be controlled independent of its dc-link voltage. The presented control strategy permits operation with reduced dc-link voltage during a permanent pole-to-ground dc fault, and controlled discharge and recharge of the HVDC links during shutdown and restart following clearance of temporary pole-to-pole dc faults. In addition, it allows voltage-source-converter (VSC)-based HVDC links that employ FB-MMC to operate with both positive and negative dc negative dc-link voltages. This feature is well suited for hybrid HVDC networks, where the VSCs operate alongside the line-commutating current source converters, without any compromise to the power reversal at any terminals. The usefulness of the presented control strategy is demonstrated on the full-scale model of the HVDC link that uses FB-MMC with 101 cells/arm, considering the cases of pole-to-ground and pole-to-pole dc faults.

Blockchain technology is becoming increasingly popular because of its applications in various fields. It gives an edge over the traditional centralized methods as it provides decentralization, immutability, integrity, and anonymity. The most popular application of this technology is cryptocurrencies, which showed a massive rise in their popularity and market capitalization in recent years. Individual investors, big institutions, and corporate firms are investing heavily in it. However, the crypto market is less stable than traditional commodity markets. It can be affected by many technical, sentimental, and legal factors, so it is highly volatile, uncertain, and unpredictable. Plenty of research has been done on various cryptocurrencies to forecast accurate prices, but the majority of these approaches can not be applied in real-time. Motivated from the aforementioned discussion, in this paper, we propose a deep-learning-based hybrid model (includes Gated Recurrent Units (GRU) and Long Short Term Memory (LSTM)) to predict the price of Litecoin and Zcash with inter-dependency of the parent coin. The proposed model can be used in real-time scenarios and it is well trained and evaluated using standard data sets. Results illustrate that the proposed model forecasts the prices with high accuracy compared to existing models.

Cryptocurrencies are peer-to-peer-based transaction systems where the data exchanges are secured using the secure hash algorithm (SHA)-256 and message digest (MD)-5 algorithms. The prices of cryptocurrencies are highly volatile and follow stochastic moments and have reached their unpredictable limits. They are commonly used for investment and have become a substitute for other types of investment like metals, estates, and the stock market. Their importance in the market raises the strict requirement for a sturdy forecasting model. However, cryptocurrency price prediction is quite challenging due to its dependency on other cryptocurrencies. Many researchers have used machine learning and deep learning models, and other market sentiment-based models to predict the price of cryptocurrencies. As all the cryptocurrencies belong to a specific class, we can infer that the increase in the price of one cryptocurrency can lead to a price change for other cryptocurrencies. Researchers had also utilized the sentiments from tweets and other social media platforms to increase the performance of their proposed system. Motivated by these, in this paper, we propose a hybrid and robust framework, DL-Gues, for cryptocurrency price prediction, that considers its interdependency on other cryptocurrencies and also on market sentiments. We have considered price prediction of Dash carried out using price history and tweets of Dash, Litecoin, and Bitcoin for various loss functions for validation. Further, to check the usability of DL-GuesS on other cryptocurrencies, we have also inferred results for price prediction of Bitcoin-Cash with the price history and tweets of Bitcoin-Cash, Litecoin, and Bitcoin.