Search

In complex networks, predicting the formation of new connections, or links, within complex networks has been a central challenge, traditionally addressed using graph-based models. These models, however, are limited in their ability to capture higher-order interactions that exist in many real-world networks, such as social, biological, and technological systems. To account for these multi-node interactions, hyper-networks have emerged as a more flexible framework, where hyperedges can connect multiple nodes simultaneously. Traditional link prediction methods often treat all common neighbors equally, overlooking the fact that not all nodes contribute uniformly to the formation of future links. Each node within a network holds a distinct level of importance, which can influence the likelihood of link formation among its neighbors. To address this, we introduce a link prediction approach leveraging hypercentrality measures adapted from traditional centrality metrics such as degree, clustering coefficient, betweenness, and closeness to capture node significance and improve link prediction in hyper-networks. We propose the Link Prediction Based on HyperCentrality in hyper-networks (LPHC) model, which enhances traditional common neighbor and jaccard coefficient of hyper-network frameworks by incorporating centrality scores to account for node importance. Our approach is evaluated across multiple real-world hyper-networks datasets, demonstrating its superiority over traditional link prediction methods. The results show that link prediction in hypercentrality-based models, particularly those utilizing hyperdegree and hyperclustering coefficients for common neighbor and jaccard coefficent approaches in hyper-networks, consistently outperform existing methods in terms of both F1-score and Area Under the Precision-Recall Curve (AUPR), offering a more precise understanding of potential link formations in hyper-networks. The proposed LPHC model consistently outperforms the existing HCN and HJC models across all datasets, achieving an overall improvement of 69% compared to HCN and 68% compared to HJC.

Automatic bird species identification is challenging due to species diversity, image variability, and dataset limitations that often lead to model overfitting. To address these issues, this study introduces a fusion of augmentation techniques to increase dataset diversity and improve model generalization. Unlike previous approaches with fixed augmentation strategies, this study uses Adaptive Inertia Weight Particle Swarm Optimization (AIWPSO) to dynamically select effective combinations of augmentations. In the AIWPSO framework, the inertia weight function guides the optimization process toward an optimal solution. Experiments on the CVIP 2018 Bird Species Challenge dataset show that this adaptive approach significantly improves model performance, boosting training accuracy by 3% and validation accuracy by 25% over prior methods. These results highlight AIWPSO’s advantage in helping models generalize effectively across diverse bird species. Overall, this study demonstrates AIWPSO’s potential to advance automated bird species identification by optimizing data augmentation strategies and enhancing accuracy in complex classification tasks.

Many real-world problems can be modelled in the form of complex networks. Social networks such as research collaboration networks and facebook, biological neural networks such as human brains, biomedical networks such as drug-target interactions and protein-protein interactions, technological networks such as telephone networks, transportation networks and power grids are a few examples of complex networks. Any complex system with entities and interactions existing between the entities can be modelled as a graph mathematically, with nodes representing entities and edges reflecting interactions. In numerous real-world circumstances, interactions are not confined to pair of entities. Majority of these intricate systems inherently possess hypergraph structures, characterized by interactions that extend beyond pairwise connections. Existing studies often transform complex interactions at a higher level into pairwise interactions and subsequently analyze them. This conversion frequently leads to both the loss of information and the inability to reconstruct the original hypergraph from the transformed network with pairwise interactions. One of the most essential tasks that can be performed on these graphs is Link Prediction (LP), which is the task of predicting future edges (links) in a graph. LP in graphs is well investigated. This article presents a novel methodology for predicting links in hypergraphs. Unlike conventional approaches that transform hypergraphs into graphs with pairwise interactions, the proposed method directly leverages the inherent structure of hypergraphs in predicting future interaction between a pair of nodes. This is motivated by the fact that hypergraphs enable the depiction of intricate higher-order relationships through hyperlinks, enhancing their representation. Their capacity to capture complex structural patterns improves predictive capabilities. Node neighborhoods within hypergraphs offer a comprehensive framework for LP, where hyperlinks simplify interactions between nodes across cliques. We propose a novel method of Link Prediction in Hypergraphs (LPH) to predict interactions within hypergraphs, maintaining their original structure without conversion to graphs, thus preserving information integrity. The proposed approach LPH extends local similarity measures like Common Neighbors, Jaccard Coefficient, Adamic Adar, and Resource Allocation, along with a global measure, Katz index, to hypergraphs. LPH’s effectiveness is assessed on six benchmark hyper-networks, employing evaluation metrics such as Area under ROC curve, Precision, and F1-score. The proposed measures of LP on hypergraphs resulted in an average enhancement of 10% in terms of Area under ROC curve compared to contemporary as well as conventional measures. Additionally, there is an average improvement of 70% in precision and around 50% in F1-score. This methodology presents a promising avenue for predicting pairwise interactions within hypergraphs while retaining their inherent structural complexity as well as information integrity.

Globally, a contemporary trend is towards the realization of sustainable, eco-friendly, miniaturized, and cost-effective sensors. This work focuses on developing a plug-and-play device using inexpensive and biodegradable UV resin fed 3D printing stereolithography (SLA) to produce miniaturized microfluidic platforms for electrochemical sensing. The device consists of three compartments designed to accommodate the 3-electrodes according to the need. SLA 3D printing technique solves these restrictions, making sensors reliable, repeatable, and durable. For electrochemical detection at the point of need or as a lab-on-chip (LoC) platform with minimal sample volume, this work attempts to construct a flexible as well as non-flexible microelectrode setup. The analytical capability of the platform is examined by quantifying nanomolar levels of dopamine in human body fluids. Chronoamperometry and cyclic voltammetry on surface-treated graphene-poly lactic acid (g-PLA) microelectrodes modified with gold nanoparticles are carried out utilizing a handheld potentiostat. The designed device has a linear range of 0.1 to 120 nM with limit of detection and limit of quantification of 0.083 and 0.27 nM, respectively. Various electrode characterizations, including scanning electron microscopy, energy-dispersive X-ray spectroscopy, and electrochemical impedance spectroscopy are carried out. The developed device is finally tested for real-time analysis on human blood and serum samples.

Electric Vehicles (EVs) are at the forefront of the transition to sustainability. Their almost zero tailpipe emissions and contribution to noise pollution make them suitable for minimizing the current levels of environmental pollution. One aspect that hinders the widespread adoption of EVs is the limited availability of Electric Vehicle Charging Stations (EVCS) in remote areas, making the charging costs extremely high. The goal of reducing EV charging cost can be achieved by integrating renewables into a conventional power system. This study proposes a method for optimizing the charging cost by utilizing renewable energy resources for an EVCS in a modified IEEE 33 bus system. This study involves the incorporation of three renewable energy sources: solar, wind and biogas. Energy management between the various sources and the EVCS was achieved through a metaheuristic algorithm-based Energy Management System (MAEMS). The proposed MAEMS was used to develop a dynamic pricing scheme. A techno-economic analysis of the system was conducted. The analysis was performed on the MATLAB-Simulink platform, considering the standards of the Indian EVCS system.

Federated Learning (FL) is a paradigm in distributed machine learning, which has gained significant attention in the recent years especially in the domain of Internet of Things. Federated Learning saves communication bandwidth when compared to centralized machine learning process and is also considered to be privacy preserving as the raw data at the clients need not be transmitted to the server for the FL learning. Recent studies on FL have exposed privacy vulnerabilities particularly in the form of Gradient Leakage Attacks (GLA) in which the adversaries can generate training data of the client from shared gradients or model updates from clients. The available solutions in the literature for GLA based on perturbing the gradients from clients leads to a drop in the performance of the FL system while attempting to preserve privacy. We propose HAFedL, an improved novel hessian aware adaptive privacy preserving FL scheme in which the performance of the model is not significantly affected due to the aspects introduced in the FL architecture to improve the privacy of the model against the GLA. The HAFedL is also robust to the data heterogeneity and device heterogeneity (particularly straggler effect) which may be present in the clients participating in the FL. The performance of HAFedL is tested for two applications- IoT device identification and digit classification. The proposed HAFedL scheme can be utilized in privacy sensitive domains such as smart city applications, Industrial Internet of Things, Internet of Robotic Things, Internet of Medical Things, etc.

Recommendation systems play an important role in creating personalized content for consumers, improving their overall experiences across several applications. Providing the user with accurate recommendations based on their interests is the recommender system’s primary goal. Collaborative filtering-based recommendations with the help of matrix factorization techniques is very useful in practical uses. Owing to the expanding size of the dataset and as the complexity increases, there arises an issue in delivering accurate recommendations to the users. The efficient functioning of the recommendation system undergoes the scalability challenge in controlling large and varying datasets. This paper introduces an innovative approach by integrating matrix factorization techniques and community detection methods where the scalability in recommendation systems will be addressed. The steps involved in the proposed approach are: 1) The rating matrix is modeled as a bipartite network. 2) Communities are generated from the network. 3) Extract the rating matrices that belong to the communities and apply MF to these matrices in parallel. 4) Merge the predicted rating matrices belonging to the communities and evaluate root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE). In our paper different matrix factorization approaches like basic MF, NMF, SVD++, and FANMF are taken along with the Louvain community detection method for dividing the communities. The experimental analysis is performed on five different diverse datasets to enhance the quality of the recommendation. To determine the method’s efficiency, the evaluation metrics RMSE, MSE, and MAE are used, and the time required to evaluate the computation is also computed. It is observed in the results that almost 95% of our results are proven effective by getting lower RMSE, MSE, and MAE values. Thus, the main aim of the user will be satisfied in getting accurate recommendations based on the user experiences.

Cardiovascular disease is the primary reason for mortality worldwide, responsible for around a third of all deaths. To assist medical professionals in quickly identifying and diagnosing patients, numerous machine learning and data mining techniques are utilized to predict the disease. Many researchers have developed various models to boost the efficiency of these predictions. Feature selection and extraction techniques are utilized to remove unnecessary features from the dataset, thereby reducing computation time and increasing the efficiency of the models. In this study, we introduce a new ensemble Quine McCluskey Binary Classifier (QMBC) technique for identifying patients diagnosed with some form of heart disease and those who are not diagnosed. The QMBC model utilizes an ensemble of seven models, including logistic regression, decision tree, random forest, K-nearest neighbour, naive bayes, support vector machine, and multilayer perceptron, and performs exceptionally well on binary class datasets. We employ feature selection and feature extraction techniques to accelerate the prediction process. We utilize Chi-Square and ANOVA approaches to identify the top 10 features and create a subset of the dataset. We then apply Principal Component Analysis to the subset to identify 9 prime components. We utilize an ensemble of all seven models and the Quine McCluskey technique to obtain the Minimum Boolean expression for the target feature. The results of the seven models ( $x_{0}, x_{1}, x_{2},\ldots, x_{6} $ ) are considered independent features, while the target attribute is dependent. We combine the projected outcomes of the seven ML models and the target feature to form a foaming dataset. We apply the ensemble model to the dataset, utilizing the Quine McCluskey minimum Boolean equation built with an 80:20 train-to-test ratio. Our proposed QMBC model surpasses all current state-of-the-art models and previously suggested methods put forward by various researchers.

In this paper, a novel distance protection methodology that uses apparent impedance and concentric characteristics to identify faults and faulty phases along with power swing condition is proposed. The rate of change of apparent impedance is used to identify the fault or power swing condition. If a fault is detected, the relative location of the apparent impedance of the six distance elements with respect to their concentric characteristics is used to identify the faulty phases. The distance element(s) that compute the correct apparent impedance is(are) then enabled, which then issues the trip signal if the zone criterion is met. The proposed distance protection methodology is validated in Western System Coordinating Council (WSCC) Nine Bus System in MATLAB/Simulink by simulating various fault and power swing conditions. The results from the case studies proved that the proposed distance protection methodology could enable the right distance elements and issue trip signals during common faults and special kinds of faults like evolving and cross-country faults. Compared to others, the distinguishing feature of the proposed algorithm is its ability to identify the exact faulty phases even during special fault conditions like evolving and cross-country faults. The distance relay using the proposed methodology can issue the trip signal within one cycle for common faults and within one and half-cycle for evolving and cross-country faults.

Missing data are a universal data quality problem in many domains, leading to misleading analysis and inaccurate decisions. Much research has been done to investigate the different mechanisms of missing data and the proper techniques in handling various data types. In the last decade, machine learning has been utilized to replace conventional methods to address the problem of missing values more efficiently. By studying and analyzing recently proposed methods using machine learning approaches, vital adoptions in accuracy, performance, and time consumed can be highlighted. This study aimed to help data analysts and researchers address the limitations of machine learning imputation methods by conducting a systematic literature review to provide a comprehensive overview of using such methods to impute missing values. Novel proposed machine learning approaches used for data imputation are analyzed and summarized to assist researchers in selecting a proper machine learning method based on several factors and settings. The review was performed on research studies published between 2016 and 2021 on adopting machine learning to impute missing values, focusing on their strengths and limitations. A total of 684 research articles from various scientific databases were analyzed using search engines, and 94 of them were selected as primary studies. Finally, several recommendations were given to guide future researchers in applying machine learning to impute missing values.

The Knowledge graph, a multi-relational graph that represents rich factual information among entities of diverse classifications, has gradually become one of the critical tools for knowledge management. However, the existing knowledge graph still has some problems which form hot research topics in recent years. Numerous methods have been proposed based on various representation techniques. Graph Neural Network, a framework that uses deep learning to process graph-structured data directly, has significantly advanced the state-of-the-art in the past few years. This study firstly is aimed at providing a broad, complete as well as comprehensive overview of GNN-based technologies for solving four different KG tasks, including link prediction, knowledge graph alignment, knowledge graph reasoning, and node classification. Further, we also investigated the related artificial intelligence applications of knowledge graphs based on advanced GNN methods, such as recommender systems, question answering, and drug-drug interaction. This review will provide new insights for further study of KG and GNN.

Mining high utility sequential patterns is observed to be a significant research in data mining. Several methods mine the sequential patterns while taking utility values into consideration. The patterns of this type can determine the order in which items were purchased, but not the time interval between them. The time interval among items is important for predicting the most useful real-world circumstances, including retail market basket data analysis, stock market fluctuations, DNA sequence analysis, and so on. There are a very few algorithms for mining sequential patterns those consider both the utility and time interval. However, they assume the same threshold for each item, maintaining the same unit profit. Moreover, with the rapid growth in data, the traditional algorithms cannot handle the big data and are not scalable. To handle this problem, we propose a distributed three phase MapReduce framework that considers multiple utilities and suitable for handling big data. The time constraints are pushed into the algorithm instead of pre-defined intervals. Also, the proposed upper bound minimizes the number of candidate patterns during the mining process. The approach has been tested and the experimental results show its efficiency in terms of run time, memory utilization, and scalability.

Understanding geological differences in a proved reservoir requires precise facies classification. Predicting facies from seismic data is frequently seen as an inverse uncertainty quantification problem in seismic reservoir characterization. Typically, the uncertainty in the model parameters that regulate the geographic distributions is being ignored. The target facies and its uncertainty can be determined by calculating the posterior distribution of the model parameters conditioned on the seismic data under a Bayesian inference framework. It is believed that such facies classification model has a unique set of model parameters that best fits it. The proposed work is unique in that it quantifies the epistemic uncertainty of the predicted facies in blind well conditioned on Seismic Amplitude Versus Offset (AVO-Seismic) attributes in the Bayesian inference framework. Under this framework, parameter uncertainties of the neural net. weights and biases are calculated using their posterior distributions from the ensamble models generated by Marcov-Chains Monte-Carlo (MCMC) by assuming that the prior values of the weights and biases are uninformative. The proposed approach is also demonstrated on Synthetic Amplitude Versus Offset (AVO-Synthetic) dataset (derived from the well log information) and we have found high relevance in the predicted results. For comparision, a plain Deep Learning and Deep learning with Monte Carlo Dropout are employed and the results indicate that our model performs more efficiently comparing to the others indicating the possibility of the model to be used in real world solution to adequate facies classication.

The modular organization of the functional brain connectome implies its functional segregation. Correlation matrices extracted from fMRI data are used as adjacency matrices of the connectome, i.e., the functional connectivity network (FCN). The modular organization of FCN is widely solved using node-community detection methods, albeit with a requirement of edge filtering, mostly. However, network sparsification potentially leads to the loss of correlation information. With no ideal threshold values for edge filtering in literature, there is growing interest in finding communities in the complete weighted network. To address this requirement, we propose the use of exploratory factor analysis (EFA), thus, exploiting the semantics of the correlation matrix. In our recent work on using EFA for FCN analysis, we have proposed a novel consensus-based algorithm using a multiscale approach, where the number of factors $n_{F}$ is treated as the scale. The consensus procedure is employed for transforming the network before performing community detection. Here, we propose a novel extension to our multiscale EFA for finding relevant cliques. We use an ensemble of experiments and extensive quantitative analysis of its outcomes to identify the optimal set of scales for efficient node-partitioning. We perform case studies of datasets of FCN of the human brain at resting state, with different sizes and parcellation atlases (AAL, Schaefer). Our results of consensus communities and cliques correspond to relevant brain activity in its resting state, thus showing the effectiveness of consensus-based multiscale EFA.

Currently, research work is primarily dependent on the collection of large sets of data from systems and making predictions based on the knowledge obtained from the data, which is generally termed as ‘data mining’. These data mining algorithms are of great importance in improving the performance of different applications. In this regard, Machine Learning (ML) algorithms have been demonstrated to be excellent tools to cope with difficult problems. In this paper, a classification learner based supervised ML algorithm is proposed for intentional islanding of DERs based on the live data collected from supervisory control and data acquisition (SCADA) system in post disaster situations. Literature presents various islanding detection techniques and also intentional islanding algorithms to address different problems in AC networks. These algorithms majorly work based on the control of current source or voltage source inverters. On the other hand, a low voltage DC distribution system allowing the removal of inverter is proposed, which is supposed to be more advantageous by reducing losses and is also economical when working with DERs. In this paper, ML based intentional islanding algorithm for DERs based low voltage DC distribution system is proposed by considering the effects of natural disasters. The learner models trained are fine tree, linear SVM, quadratic SVM and Gaussian SVM. The training of fine tree model is achieved with higher accuracy of 99.8%. The main objective of this work is to achieve a faster and accurate decision making. The performance of the ML based intentional islanding algorithm is compared with the earlier proposed artificial intelligence (AI) based intentional islanding algorithms. The AI algorithms proposed earlier are fuzzy inference systems (FIS), artificial neural networks (ANN) and adaptive network based fuzzy inference system (ANFIS). The comparison shows that, the decision making with ML based intentional islanding algorithm is faster and accurate than all other algorithms.

A rapid increase in heart disease has occurred in recent years, which might be the result of unhealthy food, mental stress, genetic issues, and a sedentary lifestyle. There are many advanced automated diagnosis systems for heart disease prediction proposed in recent studies, but most of them focus only on feature preprocessing, some focus on feature selection, and some only on improving the predictive accuracy. In this study, we focus on every aspect that may have an influence on the final performance of the system, i.e., to avoid overfitting and underfitting problems or to solve network configuration issues and optimization problems. We introduce an optimally configured and improved deep belief network named OCI-DBN to solve these problems and improve the performance of the system. We used the Ruzzo-Tompa approach to remove those features that are not contributing enough to improve system performance. To find an optimal network configuration, we proposed a stacked genetic algorithm that stacks two genetic algorithms to give an optimally configured DBN. An analysis of a RBM and DBN trained is performed to give an insight how the system works. Six metrics were used to evaluate the proposed method, including accuracy, sensitivity, specificity, precision, F1 score, and Matthew's correlation coefficient. The experimental results are compared with other state-of-the-art methods, and OCI-DBN shows a better performance. The validation results assure that the proposed method can provide reliable recommendations to heart disease patients by improving the accuracy of heart disease predictions by up to 94.61%.

The integration of communications with different scales, diverse radio access technologies, and various network resources renders next-generation wireless networks (NGWNs) highly heterogeneous and dynamic. Emerging use cases and applications, such as machine to machine communications, autonomous driving, and factory automation, have stringent requirements in terms of reliability, latency, throughput, and so on. Such requirements pose new challenges to architecture design, network management, and resource orchestration in NGWNs. Starting from illustrating these challenges, this paper aims at providing a good understanding of the overall architecture of NGWNs and three specific research problems under this architecture. First, we introduce a network-slicing based architecture and explain why and where artificial intelligence (AI) should be incorporated into this architecture. Second, the motivation, research challenges, existing works, and potential future directions related to applying AI-based approaches in three research problems are described in detail, i.e., flexible radio access network slicing, automated radio access technology selection, and mobile edge caching and content delivery. In summary, this paper highlights the benefits and potentials of AI-based approaches in the research of NGWNs.