Search

In recent years, the proliferation of deep learning (DL) techniques has given rise to a significant challenge in the form of deepfake videos, posing a grave threat to the authenticity of media content. With the rapid advancement of DL technology, the creation of convincingly realistic deepfake videos has become increasingly prevalent, raising serious concerns about the potential misuse of such content. Deepfakes have the potential to undermine trust in visual media, with implications for fields as diverse as journalism, entertainment, and security. This study presents an innovative solution by harnessing blockchain-based federated learning (FL) to address this issue, focusing on preserving data source anonymity. The approach combines the strengths of SegCaps and convolutional neural network (CNN) methods for improved image feature extraction, followed by capsule network (CN) training to enhance generalization. A novel data normalization technique is introduced to tackle data heterogeneity stemming from diverse global data sources. Moreover, transfer learning (TL) and preprocessing methods are deployed to elevate DL performance. These efforts culminate in collaborative global model training zfacilitated by blockchain and FL while maintaining the utmost confidentiality of data sources. The effectiveness of our methodology is rigorously tested and validated through extensive experiments. These experiments reveal a substantial improvement in accuracy, with an impressive average increase of 6.6% compared to six benchmark models. Furthermore, our approach demonstrates a 5.1% enhancement in the area under the curve (AUC) metric, underscoring its ability to outperform existing detection methods. These results substantiate the effectiveness of our proposed solution in countering the proliferation of deepfake content. In conclusion, our innovative approach represents a promising avenue for advancing deepfake detection. By leveraging existing data resources and the power of FL and blockchain technology, we address a critical need for media authenticity and security. As the threat of deepfake videos continues to grow, our comprehensive solution provides an effective means to protect the integrity and trustworthiness of visual media, with far-reaching implications for both industry and society. This work stands as a significant step toward countering the deepfake menace and preserving the authenticity of visual content in a rapidly evolving digital landscape. [ABSTRACT FROM AUTHOR]

Nowadays, machine learning (ML) has attained a high level of achievement in many contexts. Considering the significance of ML in medical and bioinformatics owing to its accuracy, many investigators discussed multiple solutions for developing the function of medical and bioinformatics challenges using deep learning (DL) techniques. The importance of DL in Internet of Things (IoT)-based bio- and medical informatics lies in its ability to analyze and interpret large amounts of complex and diverse data in real time, providing insights that can improve healthcare outcomes and increase efficiency in the healthcare industry. Several applications of DL in IoT-based bio- and medical informatics include diagnosis, treatment recommendation, clinical decision support, image analysis, wearable monitoring, and drug discovery. The review aims to comprehensively evaluate and synthesize the existing body of the literature on applying deep learning in the intersection of the IoT with bio- and medical informatics. In this paper, we categorized the most cutting-edge DL solutions for medical and bioinformatics issues into five categories based on the DL technique utilized: convolutional neural network, recurrent neural network, generative adversarial network, multilayer perception, and hybrid methods. A systematic literature review was applied to study each one in terms of effective properties, like the main idea, benefits, drawbacks, methods, simulation environment, and datasets. After that, cutting-edge research on DL approaches and applications for bioinformatics concerns was emphasized. In addition, several challenges that contributed to DL implementation for medical and bioinformatics have been addressed, which are predicted to motivate more studies to develop medical and bioinformatics research progressively. According to the findings, most articles are evaluated using features like accuracy, sensitivity, specificity, F-score, latency, adaptability, and scalability. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) and Deep Learning (DL) have achieved high success in many textual, auditory, medical imaging, and visual recognition patterns. Concerning the importance of ML/DL in recognizing patterns due to its high accuracy, many researchers argued for many solutions for improving pattern recognition performance using ML/DL methods. Due to the importance of the required intelligent pattern recognition of machines needed in image processing and the outstanding role of big data in generating state-of-the-art modern and classical approaches to pattern recognition, we conducted a thorough Systematic Literature Review (SLR) about DL approaches for big data pattern recognition. Therefore, we have discussed different research issues and possible paths in which the abovementioned techniques might help materialize the pattern recognition notion. Similarly, we have classified 60 of the most cutting-edge articles put forward pattern recognition issues into ten categories based on the DL/ML method used: Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Generative Adversarial Network (GAN), Autoencoder (AE), Ensemble Learning (EL), Reinforcement Learning (RL), Random Forest (RF), Multilayer Perception (MLP), Long-Short Term Memory (LSTM), and hybrid methods. SLR method has been used to investigate each one in terms of influential properties such as the main idea, advantages, disadvantages, strategies, simulation environment, datasets, and security issues. The results indicate most of the articles were published in 2021. Moreover, some important parameters such as accuracy, adaptability, fault tolerance, security, scalability, and flexibility were involved in these investigations. [ABSTRACT FROM AUTHOR]

The arithmetic and logic unit (ALU) is a key element of complex circuits and an intrinsic part of the most widely recognized complex circuits in digital signal processing. Also, recent attention has been brought to reversible logic and quantum-dot cellular automata (QCA) because of their intrinsic capacity to decrease energy dissipation, which is a crucial need for low-power digital circuits. QCA will be the preferred technology for developing the subsequent generation of digital systems. These technologies played a substantial role in the design of the ALU for operations such as multiplication, subtraction, and division. In developing reversible logic and QCA technologies, the ALU is frequently studied as a central unit. Implementing an efficient ALU with low quantum cost and a small number of cells based on an efficient reversible block can solve all previous issues. Therefore, this research constructs a Feynman gate, a Fredkin gate, and full adder circuits using reversible logic and QCA technology. Using all of the specified circuits, a 20-operation ALU is constructed. The power consumption of the proposed ALU under various energy ranges demonstrated significant improvements over earlier designs. [ABSTRACT FROM AUTHOR]

Digital signal processing (DSP) is used in computer processing to conduct different signal-processing tasks. The DSPs are used in the series numbers representing a continuous variable in a domain such as time, area, or frequency. The multiply-accumulate (MAC) unit is crucial in various DSP applications, including convolution, discrete cosine transform (DCT), Fourier Transform, etc. Thus, all DSPs contain a critical MAC unit in signal processing. The MAC unit conducts multiplication and accumulation operations for continuous and complicated DSP application processes. On the other hand, in the MAC structure, the stability of the circuit and the occupied area pose some significant challenges. However, high-performance quantum technology can easily overcome all the previous shortcomings. Hence, this paper suggests an efficient MAC for DSP applications using a Vedic multiplier, half adder, and accumulator based on quantum technology. All the proposed structures have used a single-layer layout without rotated cells. The suggested architecture is designed and validated based on the QCADesigner 2.0.3 tool. The findings revealed that all the developed circuits have a simple architecture with fewer quantum cells, optimal area, and low latency. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is a network of physical items implanted with software, sensors, etc., to link and exchange data with other devices. These devices vary in complexity from common household items to sophisticated industrial instruments. It would be challenging to choose an appropriate IoT service based on the requirements of the vast pool of accessible services with similar capabilities, given the growth of IoT-based service providers in the market. A suitable selection may be made using quality-of-service (QoS) parameters that characterize a service. IoT has several benefits over traditional communication systems. Also, it is a component of a safe and smart city system known as the Industrial Internet of Things (IIoT) which is particularly useful in the industrial field. However, it suffers from various issues such as high costs, energy consumption, and long delays. The production scheduling problem is one of the main issues in IIoT, and it is an NP-hard problem regarding cost and energy efficiency. Therefore, a meta-heuristic algorithm based on the elephant herd optimization algorithm is proposed to minimize resource costs, conversion costs, and the cost of continuous development delays. By combining the clan updating factor, separating operator, and the proposed algorithm, we created an effective and efficient method to solve the issue of production scheduling. Many experiments are performed to determine the performance of industrial environments. The outcomes demonstrate that the suggested technique can optimize planning and achieve cost reduction, efficient energy consumption, and latency decrease. [ABSTRACT FROM AUTHOR]

Clustering and routing protocols for Internet of Things (IoT) need to consider energy usage and how to reduce it. Unbalanced power usage is a common concern with current solutions to cluster-based routing problems in the IoT ecosystem. This research developed a swarm intelligence-based clustering technique to achieve a more uniform dispersion of cluster heads. The data packets across cluster heads and the sink are routed via a Jaya algorithm. Based on average remaining energy, number of active nodes, number of nodes that have failed or have been removed from the network, and overall network throughput, this combined clustering and routing method's quality has been assessed. The integrative clustering and routing protocol based on the flower pollination algorithm and Jaya algorithm described here exhibit considerable improvements over the current state-of-the-art. The network throughput and the number of the alive node are essential statistics for evaluating IoT in which battery-powered devices periodically acquire surroundings data and transmit gathered samples to a base station. The proposed strategy improved network throughput and the number of dead nodes by at least 14% and 18%, respectively. [ABSTRACT FROM AUTHOR]

With the galloping progress of the Internet of Things (IoT) and related technologies in multiple facets of science, distribution environments, namely cloud, edge, fog, Internet of Drones (IoD), and Internet of Vehicles (IoV), carry special attention due to their providing a resilient infrastructure in which users can be sure of a secure connection among smart devices in the network. By considering particular parameters which overshadow the resiliency in distributed environments, we found several gaps in the investigated review papers that did not comprehensively touch on significantly related topics as we did. So, based on the resilient and dependable management approaches, we put forward a beneficial evaluation in this regard. As a novel taxonomy of distributed environments, we presented a well-organized classification of distributed systems. At the terminal stage, we selected 37 papers in the research process. We classified our categories into seven divisions and separately investigated each one their main ideas, advantages, challenges, and strategies, checking whether they involved security issues or not, simulation environments, datasets, and their environments to draw a cohesive taxonomy of reliable methods in terms of qualitative in distributed computing environments. This well-performed comparison enables us to evaluate all papers comprehensively and analyze their advantages and drawbacks. The SLR review indicated that security, latency, and fault tolerance are the most frequent parameters utilized in studied papers that show they play pivotal roles in the resiliency management of distributed environments. Most of the articles reviewed were published in 2020 and 2021. Besides, we proposed several future works based on existing deficiencies that can be considered for further studies. [ABSTRACT FROM AUTHOR]

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The morphology algorithms are an exciting field that provides a powerful and unified method applied to image and video processing applications. Also, they have many advantages to give manageable hardware implementations and are widely employed as parts of image processing techniques. On the other hand, Quantum-dot Cellular Automata (QCA) is a promising and novel nanotechnology that contains notable benefits against common technologies in diverse features like extremely small size, low energy loss, and high operation frequency. Besides, schematizing circuits with no info loss or fault-tolerant might be beneficial in reducing power wastage. In the present paper, we suggest a novel fault-tolerant procedure to execute the morphology operations in digital image processing based on QCA. The mentioned fault-tolerant schematization for executing the morphology operations in digital image processing is easy to build. It contains notably lower elements than Complementary Metal Oxide Semiconductor (CMOS) design. Implementation and testing of all circuits are achieved using the QCADesigner tool. The suggested fault-tolerant circuit for morphological dilation/erosion operation attains high fault-tolerant in all cases of defects. [ABSTRACT FROM AUTHOR]

Massive multimedia data are being created due to the rising amount of the Internet and user-generated content, low-cost commodity devices with cameras (like cellphones, surveillance systems, and so on), and the proliferation of social networks, forming a unique type of big data. Several studies have been conducted in this research area using a survey and event analysis approach; however, none has been conducted to investigate the status of knowledge, its features, evolution, and emerging trend of multimedia big data. Therefore, in this paper, a bibliometric study using VOSviewer software is carried out with 1,865 documents from 2008 to 2020. Based on the result, 2013 is the starting year where the total publication excess of 100 articles and the configuration of leading countries, productive organizations, and authors are investigated. The most cited journals, popular publications venues, and hot research topics are also included in the investigations. Our investigation uncovered useful information, such as annual publishing patterns, the hottest research topic, the top 10 important authors and articles, and the most helpful funding organizations and venues. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) comprises many nodes dispersed around a particular target region, and it has lately been applied in a variety of sectors such as smart cities, farming, climatology, smart metering, waste treatment, and others. Even though the IoT has tremendous potential, some difficulties must be addressed. When building the clustering and routing protocol for huge-scale IoT networks, uniform energy usage and optimization are two significant concerns. Clustering and routing are well-known NP-hard optimization challenges applied to the IoT. The ease with which chicken can be implemented has garnered much interest compared to other population-based metaheuristic algorithms in solving optimization problems in the IoT. Aiming to reduce and improve node energy consumption in the IoT network by choosing the most suitable cluster head, the current effort seeks to extend the life of a network by selecting the most appropriate cluster head. A new cost function for homogenous dispersion of cluster heads was proposed in this research, and a good balance among exploration and exploitation search skills to create a node clustering protocol based on chicken search. This procedure is a big step forward from previous state-of-the-art protocols. The number of packets received, the total power consumption, the number of active nodes, and the latency of the suggested integrated clustered routing protocol are all used to evaluate the protocol's overall performance. The proposed strategy has been demonstrated to improve power consumption by at least 16 percent. [ABSTRACT FROM AUTHOR]

Hadoop is a distributed framework for processing big data. One of the critical parts of Hadoop is YARN, which carries out scheduling and resource management. A scheduling algorithm should consider multiple objectives. However, YARN schedulers do not consider the Service Level Agreement (SLA) and the energy-related issues. The present paper proposes an energy-efficient deadline-aware model for the scheduling problem. The scheduling issue is an NP-hard problem regarding the deadline of applications and reducing energy. Hence, an Energy-efficient Deadline-aware Scheduling Algorithm based on the Moth-Flame Optimization algorithm (EDSA-MFO) is suggested to minimize the energy consumption and execute the application within a given soft deadline. Moreover, the earliest deadline first-based (EDF-based) heuristic approach is proposed to decode a moth into a scheduling solution. The algorithm is implemented for both static and dynamic scheduling. To evaluate the performance of the proposed algorithm, extensive simulations are conducted. The outcomes demonstrated that the suggested method could find near-optimal scheduling. It outperforms the YARN default FIFO scheduler, EDF, the energy-aware greedy algorithm (EAGA), and the deadline-aware energy-efficient MapReduce scheduling algorithm for YARN (EMRSAY) in total cluster energy consumption and meeting job deadline. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) enables intelligent and heterogeneous things to access the Internet and subsequently interact and share info. A service management methodology is required by growing IoT applications and the number of services supplied by various objects. Nevertheless, making decisions, finding, and choosing a service is complex. Therefore, numerous techniques are explored in this regard. This paper employed Flower Pollination Algorithm (FPA) for service discovery and selection in IoT. The FPA is a nature-inspired algorithm that mimics flowering plant pollination behavior. Through a hand-over probability, it is possible to adjust the balance between local and global search properly. The survival of the fittest and the optimal reproducing plants regarding numbers are parts of an optimum plant reproduction strategy. These elements are optimization-oriented and constitute the FPA's basics. The suggested methodology has an excellent performance in minimizing data access time, energy usage and optimizing cost according to simulation findings. [ABSTRACT FROM AUTHOR]

In the distributed database systems, the relations needed by a query can be kept in several locations. This process significantly increases potential corresponding Query Execution Plans (QEP's) for a user query. Henceforth, in addition to the expense of local computing, the charge of transferring data between different cloud sites should also be considered. It does not sound logical to investigate all potential query plans in a high setting like this. The best query plan (regarding cost) must be generated for processing a given query. A new hybrid multi-objective genetic and bat algorithm, a Multi-Objective Genetic Algorithm with BAT (MOGABAT), is used in the present article to produce the best query plans. The functionality comparison is made on different join graph structures, among MOGABAT, Multi-Objective BAT (MOBAT), and Non-dominated Sorting Genetic Algorithm II (NSGA-II). The obtained results have shown that the quality of generated query plans is enhanced for the join graph structures. Nevertheless, more execution time is needed. [ABSTRACT FROM AUTHOR]

Cloud computing enables businesses to decrease the total costs by outsourcing their required services. Therefore, it provides a new challenge of data protection regarding reliability, integrity, and confidentiality because of outsourcing. As a result, cloud security is becoming a key differentiator and competitive edge between cloud providers. Nowadays, the use of blockchain in cloud computing is one of the most common innovations that can solve cloud computing security problems. Blockchain is a decentralized data management technology to provide security, anonymity, and data integrity without any third-party organization. This work presents a comprehensive study of cloud computing security concerns and blockchain solutions to address these concerns. Applying different filters and searching international databases, 21 articles from reputable journals are found and reviewed. We examine cloud security in three categories: data integration, trust, and privacy. The results show that blockchain provides a successful platform in this regard. However, security issues are one of the most important challenges that still need further study. The article also provides a roadmap framework for future research and action. [ABSTRACT FROM AUTHOR]

Internet of things has become an essential principle of human life with the widespread acceptance of intelligent environments, where everyday objects can communicate through the internet. Mobility is the most critical factor in today's internet of things devices to apply in real-world applications. Also, proper routing protocol plays a vital role in communication and reduces devices' energy consumption. The clustering approach is one of the efficient routing techniques to improve energy consumption and enhance network life. Due to the NP-Hard nature of clustering, a krill herd optimization algorithm is proposed in this paper to select the cluster head nodes and intermediate nodes required for routing. The simulation results using NS-3 confirmed that the proposed technique performs better than particle swarm optimization and cuckoo search in terms of network lifetime. The proposed technique increases the total network lifetime by at least 11.1% compared to the current clustering methods. [ABSTRACT FROM AUTHOR]

The Peer to Peer-Cloud (P2P-Cloud) is a suitable alternative to distributed cloud-based or peer-to-peer (P2P)-based content on a large scale. The P2P-Cloud is used in many applications such as IPTV, Video-On-Demand, and so on. In the P2P-Cloud network, overload is a common problem during overcrowds. If a node receives many requests simultaneously, the node may not be able to respond quickly to user requests, and this access latency in P2P-Cloud networks is a major problem for their users. The replication method in P2P-Cloud environments reduces the time to access and uses network bandwidth by making multiple data copies in diverse locations. The replication improves access to the information and increases the reliability of the system. The data replication's main problem is identifying the best possible placement of replica data nodes based on user requests for data access time and an NP-hard optimization problem. This paper proposes a new replica replacement to improve average access time and replica cost using fuzzy logic and Ant Colony Optimization algorithm. Ants can find the shortest path to discover the optimal node to place the duplicate file with the least access time latency. The fuzzy module evaluates the historical information of each node to analyze the pheromone value per iteration. The fuzzy membership function is also used to determine each node's degree based on the four characteristics. The simulation results showed that the access time and replica cost are improved compared to other replica replacement algorithms. [ABSTRACT FROM AUTHOR]

Some of the vital problems around the conventional CMOS technology are leakage-power consumption, physical-scalability limits, and short-channel effects. These deficiencies have led to many studies about nano-scale designs. Quantum dot cellular automata (QCA) is a potential answer in nanotechnology. Scholars have considered the four-dot squared cell as the main factor in the QCA. Also, a full-adder is a fundamental unit in every digital system. However, the importance of cell and area consumption limitation in circuit designing has been completely ignored in most of the related studies. Therefore, in this paper, we have offered a one-bit multi-layer full-adder cell. The practical accuracy of the proposed circuits has been assessed using QCADesigner. According to the obtained results and the design, the presented design has efficient cell usage against all the prior designs regarding cell counts and area occupation, leading to around 7% improvement in cell number than the common full-adder design. The simulation outcomes have also shown that the introduced design has excellent efficiency regarding cell and area aspects. [ABSTRACT FROM AUTHOR]

Quantum-dot Cellular Automata (QCA) is novel prominent nanotechnology. It promises a substitution to Complementary Metal–Oxide–Semiconductor (CMOS) technology with a higher scale integration, smaller size, faster speed, higher switching frequency, and lower power consumption. It also causes digital circuits to be schematized with incredible velocity and density. The full adder, compressor, and multiplier circuits are the basic units in the QCA technology. Compressors are an important class of arithmetic circuits, and researchers can use quantum compressors in the structure of complex systems. In this paper, first, a novel three-input multi-layer full-adder in QCA technology is designed, and based on it, a new multi-layer 4:2 compressor is presented. The proposed QCA-based full-adder and compressor uses an XOR gate. The proposed design offers good performance regarding the delay, area size, and cell number comparing to the existing ones. Also, in this gate, the output signal is not enclosed, and we can use it easily. The accuracy of the suggested circuits has been assessed with the utilization of QCADesigner 2.0.3. The results show that the proposed 4:2 compressor architecture utilizes 75 cell and 1.25 clock phases, which are efficient than other designs. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is a new information technology sector in which each device may receive and distribute data across a network. Industrial IoT (IIoT) and related areas, such as Industrial Wireless Networks (IWNs), big data, and cloud computing, have made significant strides recently. Using IIoT requires a reliable and effective data collection system, such as a spanning tree. Many previous spanning tree algorithms ignore failure and mobility. In such cases, the spanning tree is broken, making data delivery to the base station difficult. This study proposes an algorithm to construct an optimal spanning tree by combining an artificial bee colony, genetic operators, and density correlation degree to make suitable trees. The trees’ fitness is measured using hop count distances of the devices from the base station, residual energy of the devices, and their mobility probabilities in this technique. The simulation outcomes highlight the enhanced data collection reliability achieved by the suggested algorithm when compared to established methods like the Reliable Spanning Tree (RST) construction algorithm in IIoT and the Hop Count Distance (HCD) based construction algorithm. This proposed algorithm shows improved reliability across diverse node numbers, considering key parameters including reliability, energy consumption, displacement probability, and distance. [ABSTRACT FROM AUTHOR]