Search

In real-world scenarios, identifying the optimal number of clusters in a dataset is a difficult task due to insufficient knowledge. Therefore, the indispensability of sophisticated automatic clustering algorithms for this purpose has been contemplated by some researchers. Several automatic clustering algorithms assisted by quantum-inspired metaheuristics have been developed in recent years. However, the literature lacks definitive documentation of the state-of-the-art quantum-inspired metaheuristic algorithms for automatically clustering datasets. This article presents a brief overview of the automatic clustering process to establish the importance of making the clustering process automatic. The fundamental concepts of the quantum computing paradigm are also presented to highlight the utility of quantum-inspired algorithms. This article thoroughly analyses some algorithms employed to address the automatic clustering of various datasets. The reviewed algorithms were classified according to their main sources of inspiration. In addition, some representative works of each classification were chosen from the existing works. Thirty-six such prominent algorithms were further critically analysed based on their aims, used mechanisms, data specifications, merits and demerits. Comparative results based on the performance and optimal computational time are also presented to critically analyse the reviewed algorithms. As such, this article promises to provide a detailed analysis of the state-of-the-art quantum-inspired metaheuristic algorithms, while highlighting their merits and demerits. [ABSTRACT FROM AUTHOR]

Parallel implementations of algorithms are usually compared with single-core CPU performance. The advantage of multicore vector processors decreases the performance gap between GPU and CPU computation, as shown in many recent pieces of research. With the AVX-512 instruction set, there will be another performance boost for CPU computations. The availability of parallel code running on CPUs made them much easier and more accessible than GPUs. This article compares the performances of parallel implementations of the particle swarm optimization algorithm. The code was written in C++, and we used various techniques to obtain parallel execution through Advanced Vector Extensions. We present the performance on various benchmark functions and different problem configurations. The article describes and compares the performance boost gained from parallel execution on CPU, along with advantages and disadvantages of parallelization techniques. [ABSTRACT FROM AUTHOR]

Network alignment, which is also known as user identity linkage, is a kind of network analysis task that predicts overlapping users between two different social networks. This research direction has attracted much attention from the research community, and it is considered to be one of the most important research directions in the field of social network analysis. There are many different models for finding users that overlap between two networks, but most of these models use separate and different techniques to solve prediction problems, with very little work that has combined them. In this paper, we propose a method that combines different embedding techniques to solve the network alignment problem. Each association network alignment technique has its advantages and disadvantages, so combining them together will take full advantage and can overcome those disadvantages. Our model combines three-level embedding techniques of text-based user attributes, a graph attention network, a graph-drawing embedding technique, and fuzzy c-mean clustering to embed each piece of network information into a low-dimensional representation. We then project them into a common space by using canonical correlation analysis and compute the similarity matrix between them to make predictions. We tested our network alignment model on two real-life datasets, and the experimental results showed that our method can considerably improve the accuracy by about 10–15% compared to the baseline models. In addition, when experimenting with different ratios of training data, our proposed model could also handle the over-fitting problem effectively. [ABSTRACT FROM AUTHOR]

Blockchain has found many applications, apart from Bitcoin, in different fields and it has the potential to be very useful in the satellite communications and space industries. Decentralized and secure protocols for processing and manipulating space transactions of satellite swarms in the form of Space Digital Tokens (SDT) can be built using blockchain technology. Tokenizing space transactions using SDTs will open the door to different new blockchain-based solutions for the advancement of constellation-based satellite communications in the space industry. Developing blockchain solutions using smart contracts could be used in securely authenticating various P2P satellite communications and transactions within/between satellite swarms. To manage and secure these transactions, using the proposed SDT concept, this paper suggested a blockchain-based protocol called Proof of Space Transactions (PoST). This protocol was adopted to manage and authenticate the transactions of satellite constellations in a P2P connection. The PoST protocol was prototyped using the Ethereum blockchain and experimented with to evaluate its performance using four metrics: read latency, read throughput, transaction latency, and transaction throughput. The simulation results clarified the efficiency of the proposed PoST protocol in processing and verifying satellite transactions in a short time according to read and transaction latency results. Moreover, the security results showed that the proposed PoST protocol is secure and efficient in verifying satellite transactions according to true positive rate (TPR), true negative rate (TNR), and accuracy metrics. These findings may shape a real attempt to develop a new generation of Blockchain-based satellite constellation systems. [ABSTRACT FROM AUTHOR]

Off-grid power systems are often used to supply electricity to remote households, cottages, or small industries, comprising small renewable energy systems, typically a photovoltaic plant whose energy supply is stochastic in nature, without electricity distributions. This approach is economically viable and conforms to the requirements of the European Green Deal and the Fit for 55 package. Furthermore, these systems are associated with a lower short circuit power as compared with distribution grid traditional power plants. The power quality parameters (PQPs) of such small-scale off-grid systems are largely determined by the inverter's ability to handle the impact of a device; however, this makes it difficult to accurately forecast the PQPs. To address this issue, this work compared prediction models for the PQPs as a function of the meteorological conditions regarding the off-grid systems for small-scale households in Central Europe. To this end, seven models—the artificial neural network (ANN), linear regression (LR), interaction linear regression (ILR), quadratic linear regression (QLR), pure quadratic linear regression (PQLR), the bagging decision tree (DT), and the boosting DT—were considered for forecasting four PQPs: frequency, the amplitude of the voltage, total harmonic distortion of the voltage ( T H D u ), and current ( T H D i ). The computation times of these forecasting models and their accuracies were also compared. Each forecasting model was used to forecast the PQPs for three sunny days in August. As a result of the study, the most accurate methods for forecasting are DTs. The ANN requires the longest computational time, and conversely, the LR takes the shortest computational time. Notably, this work aimed to predict poor PQPs that could cause all the equipment in off-grid systems to respond in advance to disturbances. This study is expected to be beneficial for the off-grid systems of small households and the substations included in existing smart grids. [ABSTRACT FROM AUTHOR]

The fight against the COVID-19 pandemic still involves many struggles and challenges. The greatest challenge that most governments are currently facing is the lack of a precise, accurate, and automated mechanism for detecting and tracking new COVID-19 cases. In response to this challenge, this study proposes the first blockchain-based system, called the COVID-19 contact tracing system (CCTS), to verify, track, and detect new cases of COVID-19. The proposed system consists of four integrated components: an infection verifier subsystem, a mass surveillance subsystem, a P2P mobile application, and a blockchain platform for managing all transactions between the three subsystem models. To investigate the performance of the proposed system, CCTS has been simulated and tested against a created dataset consisting of 300 confirmed cases and 2539 contacts. Based on the metrics of the confusion matrix (i.e., recall, precision, accuracy, and F1 Score), the detection evaluation results proved that the proposed blockchain-based system achieved an average of accuracy of 75.79% and a false discovery rate (FDR) of 0.004 in recognizing persons in contact with COVID-19 patients within two different areas of infection covered by GPS. Moreover, the simulation results also demonstrated the success of the proposed system in performing self-estimation of infection probabilities and sending and receiving infection alerts in P2P communications in crowds of people by users. The infection probability results have been calculated using the binomial distribution function technique. This result can be considered unique compared with other similar systems in the literature. The new system could support governments, health authorities, and citizens in making critical decisions regarding infection detection, prediction, tracking, and avoiding the COVID-19 outbreak. Moreover, the functionality of the proposed CCTS can be adapted to work against any other similar pandemics in the future. [ABSTRACT FROM AUTHOR]

The study of power load forecasting is gaining greater significance nowadays, particularly with the use and integration of renewable power sources and external power stations. Power forecasting is an important task in the planning, control, and operation of utility power systems. In addition, load forecasting (LF) aims to estimate the power or energy needed to meet the required power or energy to supply the specific load. In this article, we introduce, review and compare different power load forecasting techniques. Our goal is to help in the process of explaining the problem of power load forecasting via brief descriptions of the proposed methods applied in the last decade. The study reviews previous research that deals with the design of intelligent systems for power forecasting using various methods. The methods are organized into five groups—Artificial Neural Network (ANN), Support Vector Regression, Decision Tree (DT), Linear Regression (LR), and Fuzzy Sets (FS). This way, the review provides a clear concept of power load forecasting for the purposes of future research and study. [ABSTRACT FROM AUTHOR]