Search

The innovative trends of cloud computing acquired the interest of several individuals or enterprises that started outsourcing data to the cloud servers. Recently, numerous techniques are introduced for facilitating privacy protection on untrusted cloud platforms. However, the classical privacy-preserving techniques failed to prevent leakage and incur huge information loss. This paper introduces the efficient technique, named the chronological sailfish optimizer (CSFO) algorithm for privacy preservation in cloud computing. The proposed CSFO is devised by integrating the chronological concept in SailFish optimizer. The input data are fed to a privacy-preservation process wherein hamming weight-based RSA and Khatri-Rao products are utilized for data privacy. Here, the hamming weighted-based RSA is determined by combining the sha256 algorithm with the hamming weight with Rivest–Shamir–Adleman (HRSA) system. Hence, an optimization-driven algorithm is utilized to evaluate optimal matrix generation to handle both the utility and the sensitive information. Here, the fitness function is newly devised considering, realism, privacy and fitness. The experimentation is performed using four datasets, like Pathway Interaction Database, Hungarian, Cleveland and Switzerland. The proposed CSFO provided superior performance with maximal privacy of 0.2173, maximal realism 0.9456 and maximal fitness of 0.5416. [ABSTRACT FROM AUTHOR]

Presently, facial image recognition via a thermal camera is a critical phase in numerous fields. Systems using thermal facial images suffer from numerous problems in face identification. In this paper, a model Edge-Aided Generative Adversarial Network (EA-GAN) is introduced to overcome the difficulties of thermal face identification by synthesizing a visible faces image from the thermal version. To enhance the performance of the Conditional Generative Adversarial Network (CGAN) model for the create realistic face images, the edge information extracted from the thermal image has been used as input, thus lead to improving overall the system's achievement. Moreover, a new model is presented in the present work for face identification by integrating two Convolutional Neural Networks (CNN) to achieve high and rapid accuracy rates. Based on the experiments on the Carl dataset for faces, it is indicated that EA-GAN can synthesize visually comfortable and identity-preserving faces; thus, better performance is achieved in comparison with the state-of-the-art approaches for thermal facial identification. [ABSTRACT FROM AUTHOR]

Connectivity is a significant metric to assess the fault tolerance of a network. For a faulty vertex set |$H$|⁠ , the |$h$| -extra connectivity is defined under the assumption that every component of the network removing |$H$| has at least |$h+1$| fault-free vertices. Compared to the traditional connectivity, which is defined under the assumption that the network removing |$H$| is disconnected or trivial, the |$h$| -extra connectivity can better reflect the true fault tolerance of the network. The |$BCube$| is an important server-centric data center network; it has good fault tolerance and scalability. In this paper, our research focuses on the logical structure of |$BCube$|⁠ , named |$BC_{n,k}$|⁠ , which is actually a specific type of generalized hypercubes. We prove that the 3-extra connectivity of |$BC_{n,k}$| is |$4(k+1)(n-1)-4n$| for |$k\geq 4$| and |$n\geq 4$|⁠. [ABSTRACT FROM AUTHOR]

A novel Corona virus disease 2019 (COVID-19) outbreak is declared as the international public health emergency concern by the World Health Organization in the month of March 2020. This viral disease invented from China in the month of December 2019 has previously caused havoc around the world, including India. In this paper, efficient mathematical models using Gustafson–Kessel fuzzy clustering approach for the transmission of the COVID-19 are developed by considering the actual reported cases in the state of Tamil Nadu, India. The results proved a good concord between the reported data and the estimated data given by the proposed models. Moreover, the developed models are also capable to predict the requirements of beds in hospitals on the month of August 2020 in Tamil Nadu, India. Also, this work suggests strictly implementing/extending the complete lockdown for at least 21 days in the month of August 2020 and immediate separation of infected cases are the positive steps to reduce the spread of novel corona virus in Tamil Nadu state, India. [ABSTRACT FROM AUTHOR]

Provable Data Possession (PDP) is of crucial importance in public cloud storage since it allows users to check the integrity of their outsourced data without downloading it. However, the existing PDP schemes, which are based on classical number-theoretic assumptions, are insecure under quantum attacks. In this paper, we propose the first PDP scheme from standard lattices, using a specific leveled fully homomorphic signature (FHS) scheme. To remove the complex key management of PDP cryptosystem on the public key infrastructure (PKI) setting, we employ a specific leveled identity-based (ID-based) FHS scheme to construct the first ID-based PDP scheme from standard lattices. Our two PDP schemes are secure under the standard small integer solution (SIS) assumption, which is conjectured to withstand quantum attacks. Furthermore, we conduct experimental evaluations to validate the feasibility of the proposed PDP schemes in practice. [ABSTRACT FROM AUTHOR]

As a generalization of vertex connectivity, for connected graphs |$G$| and |$T$|⁠ , the |$T$| -structure connectivity |$\kappa (G; T)$| (resp. |$T$| -substructure connectivity |$\kappa ^{s}(G; T)$|⁠) of |$G$| is the minimum cardinality of a set of subgraphs |$F$| of |$G$| that each is isomorphic to |$T$| (resp. to a connected subgraph of |$T$|⁠) so that |$G-F$| is disconnected. For |$n$| -dimensional hypercube |$Q_{n}$|⁠ , Lin et al. showed |$\kappa (Q_{n};K_{1,1})=\kappa ^{s}(Q_{n};K_{1,1})=n-1$| and |$\kappa (Q_{n};K_{1,r})=\kappa ^{s}(Q_{n};K_{1,r})=\lceil \frac{n}{2}\rceil $| for |$2\leq r\leq 3$| and |$n\geq 3$| (Lin, C.-K. Zhang, L.-L. Fan, J.-X. and Wang, D.-J. (2016) Structure connectivity and substructure connectivity of hypercubes. Theor. Comput. Sci. , 634, 97–107). Sabir et al. obtained that |$\kappa (Q_{n};K_{1,4})=\kappa ^{s}(Q_{n};K_{1,4})= \lceil \frac{n}{2}\rceil $| for |$n\geq 6$| and for |$n$| -dimensional folded hypercube |$FQ_{n}$|⁠ , |$\kappa (FQ_{n};K_{1,1})=\kappa ^{s}(FQ_{n};K_{1,1})=n$|⁠ , |$\kappa (FQ_{n};K_{1,r})=\kappa ^{s}(FQ_{n};K_{1,r})= \lceil \frac{n+1}{2}\rceil $| with |$2\leq r\leq 3$| and |$n\geq 7$| (Sabir, E. and Meng, J.(2018) Structure fault tolerance of hypercubes and folded hypercubes. Theor. Comput. Sci. , 711, 44–55). They proposed an open problem of determining |$K_{1,r}$| -structure connectivity of |$Q_n$| and |$FQ_n$| for general |$r$|⁠. In this paper, we obtain that for each integer |$r\geq 2$|⁠ , |$\kappa (Q_{n};K_{1,r})$|   |$=\kappa ^{s}(Q_{n};K_{1,r})$|   |$=\lceil \frac{n}{2}\rceil $| and |$\kappa (FQ_{n};K_{1,r})=\kappa ^{s}(FQ_{n};K_{1,r})= \lceil \frac{n+1}{2}\rceil $| for all integers |$n$| larger than |$r$| in quare scale. For |$4\leq r\leq 6$|⁠ , we separately confirm the above result holds for |$Q_n$| in the remaining cases. [ABSTRACT FROM AUTHOR]

The amount of data generated is increasing day by day due to the development in remote sensors, and thus it needs concern to increase the accuracy in the classification of the big data. Many classification methods are in practice; however, they limit due to many reasons like its nature for data loss, time complexity, efficiency and accuracy. This paper proposes an effective and optimal data classification approach using the proposed Ant Cat Swarm Optimization-enabled Deep Recurrent Neural Network (ACSO-enabled Deep RNN) by Map Reduce framework, which is the incorporation of Ant Lion Optimization approach and the Cat Swarm Optimization technique. To process feature selection and big data classification, Map Reduce framework is used. The feature selection is performed using Pearson correlation-based Black hole entropy fuzzy clustering. The classification in reducer part is performed using Deep RNN that is trained using a developed ACSO scheme. It classifies the big data based on the reduced dimension features to produce a satisfactory result. The proposed ACSO-based Deep RNN showed improved results with maximal specificity of 0.884, highest accuracy of 0.893, maximal sensitivity of 0.900 and the maximum threat score of 0.827 based on the Cleveland dataset. [ABSTRACT FROM AUTHOR]

Edge centrality has found wide applications in various aspects. Many edge centrality metrics have been proposed, but the crucial issue that how good the discriminating power of a metric is, with respect to other measures, is still open. In this paper, we address the question about the benchmark of the discriminating power of edge centrality metrics. We first use the automorphism concept to define equivalent edges, based on which we introduce a benchmark for the discriminating power of edge centrality measures and develop a fast approach to compare the discriminating power of different measures. According to the benchmark, for a desirable measure, equivalent edges have identical metric scores, while inequivalent edges possess different scores. However, we show that even in a toy graph, inequivalent edges cannot be discriminated by three existing edge centrality metrics. We then present a novel edge centrality metric called forest centrality (FC). Extensive experiments on real-world networks and model networks indicate that FC has better discriminating power than three existing edge centrality metrics. [ABSTRACT FROM AUTHOR]

The security of most lattice-based cryptography schemes are based on two computational hard problems which are the short integer solution (SIS) and learning with errors (LWE) problems. The computational complexity of SIS and LWE problems are related to approximating shortest vector problem and bounded distance decoding (BDD) problem. Approximating BDD is a special case of approximating closest vector problem (CVP). In this paper, we revisit the study for approximating CVP. We give a proof that approximating the CVP over |$\ell _\infty $| -norm (CVP |$_\infty $|⁠) within any constant factor is NP-hard. The result is obtained by the gap-preserving reduction from Min Total Label Cover problem in |$\ell _1$| -norm to to CVP |$_\infty $|⁠. This proof is simpler than known proofs [ 10 ]. [ABSTRACT FROM AUTHOR]

The stream ciphers RCR-64 and RCR-32 designed by Sekar et al. are the most recent additions to the Py-family of stream ciphers, originally designed by Biham et al. The ciphers are among the fastest stream ciphers on software. To the best of our knowledge, the only reported attacks on the ciphers are due to Ding et al. , published in the Journal of Universal Computer Science. In this paper, we review these alleged attacks on the RCR ciphers and show that they are based on non-existent keystream biases stemming from flawed probability calculations. [ABSTRACT FROM AUTHOR]

Rotational-XOR cryptanalysis is a very recent technique for ARX ciphers. In this paper, the probability propagation formula of RX-cryptanalysis in modular addition is extended, and the calculation of RX-difference probability for any rotation parameter (⁠|$0

Electronic voting (e-voting) has been studied for many years. Recently, researchers find that blockchain can provide an alternative secure platform for e-voting systems, because of its properties of tamper resistance and transparency. However, existing blockchain-based schemes either require central authorities to tally ballots or can only handle a limited number of voters. This paper tries to propose a self-tallying e-voting system, i.e. the public can verify the validity of all ballots and tally the ballots without a centralized authority. To achieve this goal, we solve two challenges, namely how to cancel out all random numbers used for ballots and to prove the validity of ballots using a non-interactive zero knowledge proof. Our scheme is proved to be secure and shown to be practical by experiments. [ABSTRACT FROM AUTHOR]

A |$k$| -query locally decodable code (LDC) |$C$| allows one to encode any |$n$| -symbol message |$x$| as a codeword |$C(x)$| of |$N$| symbols such that each symbol of |$x$| can be recovered by looking at |$k$| symbols of |$C(x)$|⁠ , even if a constant fraction of |$C(x)$| has been corrupted. Currently, the best known LDCs are matching vector codes (MVCs). A modulus |$m=p_1^{\alpha _1}p_2^{\alpha _2}\cdots p_r^{\alpha _r}$| may result in an MVC with |$k\leq 2^r$| and |$N=\exp (\exp (O((\log n)^{1-1/r} (\log \log n)^{1/r})))$|⁠. The |$m$| is good if it is possible to have |$k<2^r$|⁠. The good numbers yield more efficient MVCs. Prior to this work, there are only finitely many good numbers. All of them were obtained via computer search and have the form |$m=p_1p_2$|⁠. In this paper, we study good numbers of the form |$m=p_1^{\alpha _1}p_2^{\alpha _2}$|⁠. We show that if |$m=p_1^{\alpha _1}p_2^{\alpha _2}$| is good, then any multiple of |$m$| of the form |$p_1^{\beta _1}p_2^{\beta _2}$| must be good as well. Given a good number |$m=p_1^{\alpha _1}p_2^{\alpha _2}$|⁠ , we show an explicit method of obtaining smaller good numbers that have the same prime divisors. Our approach yields infinitely many new good numbers. [ABSTRACT FROM AUTHOR]

This paper proposes an approach to the specification and model checking of a large, important class of distributed algorithms called control algorithms (CAs), which are superimposed on underlying distributed systems (UDSs). The approach is based on rewriting logic by moving from its object level to the meta-level. We introduce the idea of specifying CAs as meta-programs that take the specifications of UDSs and automatically generate the specifications of the UDSs on which the CAs are superimposed (UDS-CAs). Due to many options, such as network topologies, even fixing the number of each kind of entities, such as mobile support stations (MSSs) and mobile hosts (MHs) in a mobile checkpointing algorithm, there are many instances of a UDS. To address the problem, we generate all possible initial states of a UDS for a fixed number of each kind of entities such that some constraints, such as MSSs strongly connected with a wired network, are fulfilled and conduct model checking for each of the initial states. We demonstrate the usefulness by reporting on a case study where a counterexample is found for some specific initial states but not for the other initial states, detecting a subtle flaw lurking in a mobile checkpointing algorithm. [ABSTRACT FROM AUTHOR]

In the past few years, much importance and attention have been attached to completely independent spanning trees (CISTs). Many results, such as edge-disjoint Hamilton cycles, traceability, number of spanning trees, structural properties, topological indices, etc. have been obtained on line graphs, and researchers have applied the line graphs of some interconnection networks such as generalized hypercubes, augmented cubes, crossed cubes, etc. into data center networks, such as SWCube, AQLCube, BCDC, etc. At the meanwhile, few results of CISTs are reported on the line graphs. In this paper, we establish the relation of edge-disjoint spanning trees in an interconnection network |$G$| ' with its line graph |$G$| by proposing a general algorithm for the first time. By this method, more CISTs can be obtained comparing with results in the literature. Then, the decrease of diameter is discussed and simulation experiments are shown on the line graphs of hypercubes. [ABSTRACT FROM AUTHOR]

With the development of 5G, the wireless Internet of Things (IoT) has become possible; how to provide privacy protections for the communication of IoT devices in a more vulnerable wireless transmission environment is a huge challenge. Thus, steganography is introduced as a safe and effective technology. Blockchain systems have been widely used in the area of steganography. Several works attempted to embed covert data into transactions in public blockchain systems such as Bitcoin, Ethereum and Monero. However, most of them merely focus on putting covert data into certain fields in transactions based on cryptographic algorithms. In this paper, a Covert Transaction Recognition (CTR) model is proposed by the Text Convolutional Neural Networks and Back Propagation Neural Networks. When utilizing the covert data-embedded field for recognizing, our CTR model can attain 0.79 precision and 0.83 recall on average for seven covert transaction construction schemes. The precision and recall can increase by at most 43 and 47%, respectively, if other unembedded fields were additionally exploited for recognition. We further propose a Practical Covert Transaction Construction (PCTC) model. This model fixes the contents in the embedded fields of the constructed transactions, and generates the contents in other fields using Generative Adversarial Networks. Experimental results demonstrated that the precision and recall are greatly decreased when identifying the covert transactions generated by our PCTC model. The data underlying this article are available in 'covert-transaction-model', at https://github.com/1997mint/covert-transaction-model. [ABSTRACT FROM AUTHOR]

In the Internet of Things, smart devices are expected to correctly capture and process data from environments, regardless of perturbation and adversarial attacks. Therefore, it is important to guarantee the robustness of their intelligent components, e.g. neural networks, to protect the system from environment perturbation and adversarial attacks. In this paper, we propose a formal verification technique for rigorously proving the robustness of neural networks. Our approach leverages a tight liner approximation technique and constraint substitution, by which we transform the robustness verification problem into an efficiently solvable linear programming problem. Unlike existing approaches, our approach can automatically generate adversarial examples when a neural network fails to verify. Besides, it is general and applicable to more complex neural network architectures such as CNN, LeNet and ResNet. We implement the approach in a prototype tool called WiNR and evaluate it on extensive benchmarks, including Fashion MNIST, CIFAR10 and GTSRB. Experimental results show that WiNR can verify neural networks that contain over 10 000 neurons on one input image in a minute with a 6.28% probability of false positive on average. [ABSTRACT FROM AUTHOR]

Quality of data services is crucial for operational large-scale internet-of-things (IoT) research data infrastructure, in particular when serving large amounts of distributed users. Effectively detecting runtime anomalies and diagnosing their root cause helps to defend against adversarial attacks, thereby essentially boosting system security and robustness of the IoT infrastructure services. However, conventional anomaly detection methods are inadequate when facing the dynamic complexities of these systems. In contrast, supervised machine learning methods are unable to exploit large amounts of data due to the unavailability of labeled data. This paper leverages popular GAN-based generative models and end-to-end one-class classification to improve unsupervised anomaly detection. A novel heterogeneous BiGAN-based anomaly detection model Heterogeneous Temporal Anomaly-reconstruction GAN (HTA-GAN) is proposed to make better use of a one-class classifier and a novel anomaly scoring function. The Generator-Encoder-Discriminator BiGAN structure can lead to practical anomaly score computation and temporal feature capturing. We empirically compare the proposed approach with several state-of-the-art anomaly detection methods on real-world datasets, anomaly benchmarks and synthetic datasets. The results show that HTA-GAN outperforms its competitors and demonstrates better robustness. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet of Things (IoT), network security challenges are becoming more and more complex, and the scale of intrusion attacks against the network is gradually increasing. Therefore, researchers have proposed Intrusion Detection Systems and constantly designed more effective systems to defend against attacks. One issue to consider is using limited computing power to process complex network data efficiently. In this paper, we take the AWID dataset as an example, propose an efficient data processing method to mitigate the interference caused by redundant data and design a lightweight deep learning-based model to analyze and predict the data category. Finally, we achieve an overall accuracy of 99.77% and an accuracy of 97.95% for attacks on the AWID dataset, with a detection rate of 99.98% for the injection attack. Our model has low computational overhead and a fast response time after training, ensuring the feasibility of applying to edge nodes with weak computational power in the IoT. [ABSTRACT FROM AUTHOR]

Federated generative adversarial networks are designed to collaborate across the communication and privacy-constrained edge servers participating in training. However, in the Internet of Things scenario, local updates uploaded by edge servers can lead to the risk of privacy breaches. Gradient-sanitized-based approaches can transmit sanitized sensitive data with strict privacy guarantees, but gradient clipping and perturbation severely degrade convergence performance. In this paper, our proposed algorithm enhances the privacy of terminated raw data through differential privacy before it is transmitted to the edge server. The edge server trains the local generator and discriminator using the perturbed data, which provides privacy guarantees for the gradient attack on the FedGAN without compromising the gradient accuracy. The results of the experimental evaluation show that the algorithm generates images with slightly better quality than that generated by the gradient-sanitized-based approaches while maintaining privacy. [ABSTRACT FROM AUTHOR]

The use of cloud computing and mobile devices is increasing in healthcare service delivery primarily because of the huge storage capacity of cloud, the heterogeneous structure of health data and the user-friendly interfaces on mobile devices. We propose a healthcare delivery scheme where a large knowledge base is stored in the cloud and user responses from mobile devices are input to this knowledge base to reach a preliminary diagnosis of diseases based on patients' symptoms. However, instead of sending every response to the cloud and getting data from cloud server, it may often be desirable to prune a portion of the knowledge base that is stored in a graph form and download in to the mobile devices. Downloading data from cloud depends on the storage, battery power, processor of a mobile device, wireless network bandwidth and cloud processor capacity. In this paper, we focus on developing mathematical expressions involving the above mentioned criteria and show how these parameters are dependent on each other. The expressions built in this paper can be used in real-life scenarios to take decisions regarding the amount of data to be pruned in order to save energy as well as time. [ABSTRACT FROM AUTHOR]

There are several Contact Tracing solutions since the outbreak of SARS COVID-19. All these solutions are localized—specific to a country. The Apps supported by these solutions do not interwork with each other. There are no standards to the proximity data collected by these Apps. Once the international travel restrictions are relaxed, this will become an issue. This paper explores this issue, by addressing one of the key requirements of Contact Tracing solutions. All the current solutions use an Identifier , Proximity Identifier (PID), that anonymously represents the user in the proximity data exchanged. The PID used in these applications varies in their structure, management and properties. This paper first identifies the common desirable properties of PID, including some non-obvious ones for its global application. This identification is essential for the design and development of the Contact Tracing solution that can work across boundaries seamlessly. The paper also evaluates representative solutions from two different design classes against these properties. [ABSTRACT FROM AUTHOR]

The exponential growth of IoT devices and their need to use IPv6 addresses has the potential to create load stress on the existing DNS infrastructure and it is imperative that DNS servers to be deployed on IPv6 networks. The DNS query latency from a particular Internet vantage point for IPv4 and IPv6 network cannot be compared directly due to variations in the number of hops of query on IPv4 and IPv6 communication networks. Moreover, there is no assurance that DNS server in the hierarchy is hosted on a dual-stack. This work brings out the DNS query resolution latency over the IPv4 and IPv6 protocol stacks with better accuracy. The experiments are carried out by setting up a complete DNS hierarchy (ROOT, TLD, STLD, TTLD and recursive resolver) on dual IP stack (IPv4 and IPv6), enabling both forward and reverse lookup tree on a live testbed, ensuring a constant number of hops between the recursive resolver and each of the DNS servers in the hierarchy. This live testbed is a first of its kind and is made available for Internet researchers. The operational issues encountered during this deployment and service provisioning are discussed and documented in this paper. This paper also gives a clear illustration and provides reference guidelines for the DNS hierarchy setup, and also aims to bridge the knowledge gap required for deploying DNS over IPv6. [ABSTRACT FROM AUTHOR]

As a two-dimensional formal method, graph grammar is widely used in defining various visual programming languages. This paper presents a new graph grammar formalism called coordinate graph grammar (CGG). CGG is extended from the edge-based graph grammar (EGG) by introducing the spatial mechanism into the theoretical framework, which consists of continuous coordinate graph grammar (cCGG) and discrete coordinate graph grammar (dCGG). By combining quantitative and qualitative spatial semantics in one framework, CGG provides strong expressiveness and flexibility for specifying various spatial graphs. This paper focuses on several important issues on the new formalism. First, the theoretical framework of CGG is given. Second, two matching algorithms for cCGG and dCGG are proposed, which use the spatial relationships between nodes to narrow down the search space during parsing. Finally, an application of CGG is demonstrated, which generates parsable flowcharts in a uniform layout. [ABSTRACT FROM AUTHOR]

Many disciplines have adopted component-based principles to avail themselves of the many advantages they bring, especially component reusability. In a short time, the component-based architecture became a renown branch in the IT world and the center of interest of many researchers. Much work has been conducted in this context for the verification of component-based applications (CBAs). However, the main focus has been on the structural aspect of such compositions, while the behavioral aspect has seldom been dealt with. In this paper, our goal is to close this gap and propose a formal approach to verify the behavioral correctness of CBAs. We first define a set of requirements to be satisfied by the structure and the behavior of a CBA, represented by a set of interactions that may occur between their components. Then, we build a formal Event-B model to represent these requirements in a rigorous and non-ambiguous way. The use of the Event-B refinement technique allows us to master the complexity of CBAs by introducing their elements in an incremental manner. The correctness of the development is ensured by establishing a set of proof obligations, under the Rodin platform, and also by animating it with the ProB animator/model checker. The approach is illustrated by a running example. [ABSTRACT FROM AUTHOR]

Counter-cryptanalysis uses cryptanalytic techniques to detect cryptanalytic attacks. It was introduced by Stevens with a collision detection algorithm that detects whether a message is one of a colliding message pair constructed using a collision attack. Later, Stevens and Shumow improved the collision detection against SHA-1 by using unavoidable conditions. However, there are no results improving collision detection against MD5 due to its weak diffusion properties. In this paper, an improved collision detection algorithm against MD5 is proposed by using the 14-bit sufficient condition combinations. This leads to the dividing the 223 classes into four sets. Each element, belonging to the first two sets, holds the same sufficient condition combination. Our new algorithm can classify 126 classes efficiently. The runtime is 28.6% of the previous collision detection method. [ABSTRACT FROM AUTHOR]

Background Breast cancer is the most common disease in women, and it is very difficult to detect breast cancer early, so there are fewer reasons to measure women's survival. The purpose of this paper to apply various basic machine learning algorithms on multiple breast cancer datasets and the obtained results combined with an ensemble technique to find whether the datasets getting high accuracy. Methods Five machine learning algorithms such as decision tree, random forest, k-nearest neighbor, support vector clustering (SVC) and logistic regression (LR) are used to achieve high accuracy. In this study, along with five classifiers and voting ensemble methods on three different datasets (Mammographic mass data, Original Wisconsin breast cancer data and Diagnostic Wisconsin breast cancer data) to obtain the predicted accuracy recall, precision and receiver operating characteristic (ROC) curves. The results obtained by three different datasets were compared. Results By applying five classifiers and voting ensemble, the comparison results show that logistic regression, SVC and voting ensemble methods are potentially effective for predicting classification accuracy. The highest value is (Accuracy: 97.13% with ensemble by D2, Precision: 96.90% with ensemble and LR method by D3, Recall: 97.78% with SVC by D3, ROC: 99.93% with LR by D2). Conclusions Machine learning classifiers and ensemble technologies have the potential to identify diseases. The applied method highlights the importance of classifiers and ensemble methods. [ABSTRACT FROM AUTHOR]

The use of fingerprint continues to increase constantly with the propagation of biometric authentication technologies. Fingerprint is today the most widely used biometric modality for human verification and identification, due to its practical use and its discriminative structure that allows to different identities to be easily distinguished. Unfortunately, this emergence has been accompanied by a number of problems and challenges related to identity theft and to security issues in general. To address these concerns, many approaches have been proposed in which only few of them were able to reach an acceptable level of both security and performance. In this paper, we propose a new fingerprint template protection scheme that enhances the security of protected system while preserving performance. The proposed approach is a minutiae-based technique that performs fingerprint matching in a transformed space using irreversible minutiae tetrahedrons. Using the original Fingerprint Verification Competition (FVC) protocol, the provided experimental results on FVC2002 DB1, DB2 and DB3 fingerprint databases have shown satisfactory recognition rates. Our results are compared to some existing techniques that use the same protocol of test. We have proved as well that the proposed scheme meets the requirements of revocability, unlinkability and irreversibility. [ABSTRACT FROM AUTHOR]

Traditional link prediction methods of social network are vulnerable to the influence of network structure and have poor generalization, and only on a small number of networks and evaluation indicators. To improve the stability and accuracy of link prediction, this paper assembles 15 similarity indexes, introduces the idea of stacking into the link prediction of complex networks, and presents a link prediction method (Logistic-regression LightGBM Stacking Link Prediction, LLSLP). Firstly, social network link prediction is regarded as a binary classification problem. Secondly, the hyper parameters of the basic model are determined by using cross-validation and grid searching; thirdly, Logistic-regression and LightGBM are integrated by stacked generalization; Finally, take 10 different networks as practical examples. The feasibility and effectiveness of the proposed method are verified by comparing 7 evaluation indicators. The experimental results show that: the proposed method is not only more than 98.71% higher than the traditional CN (Common Neighbor) and other models are 10.52% higher on average. In addition, compared with the traditional 15 link prediction algorithms, |$F1- score$| value and |$MCC$| (Matthews Correlation Coefficient) value is increased by 3.2% ~ 9.7% and 5.9% ~ 14% respectively. The proposed method has good accuracy and generalization. It can also be applied to recommendation system. [ABSTRACT FROM AUTHOR]

Collaborative filtering (CF) is a well-known and eminent recommendation technique to predict the preference of new users by revealing the structures of historical records of the examined users. Even though CF is effectively adapted in several commercial areas, many limitations still exist, particularly in the sparsity of rating data that raises many issues. This paper devises a novel deep learning strategy for CF to recognize user preferences. Here, black hole entropic fuzzy clustering (BHEFC) is devised for clustering item sequences to form groups with similar item sequences. Moreover, cluster centroids are optimized using the tunicate swarm magnetic optimization algorithm (TSMOA), which is devised by combining tunicate swarm algorithm and magnetic optimization algorithm. After grouping similar items together, the group matching is performed based on a deep convolutional neural network (Deep CNN). Subsequently, the visitor sequence and query sequence are compared using Jaro–Winkler distance, which contributes to the best visitor sequence. From this best visitor sequence, the recommended product is acquired. The proposed TSMOA–BHEFC and Deep CNN outperformed other methods with minimal mean absolute error of 0.200, mean absolute percentage error of 0.198 and root mean square error of 0.447, respectively. [ABSTRACT FROM AUTHOR]

Today, machine learning plays a major role in different branches of the healthcare industry, from prognosis and diagnosis to drug development providing a significant perspective on the medical landscape for disease prevention or treatment and the improvement of human life. Recently, the use of deep neural networks in different machine learning applications has shown a great contribution to the improvement of the accuracy of predictions. In this paper, a novel application of convolutional neural networks on medical prognosis is presented. The proposed method employs a one-dimensional convolutional neural network (1D-CNN) to predict the survivability of breast cancer patients. After further examining the network architecture, a number of 8, 14 and 24 convolutional filters were considered within three layers, respectively, followed by a max-pooling layer after the second and third layers. In addition, regarding the probabilistic nature of the survivability prediction problem, an extra layer was added to the network in order to calculate the probability of the patient survivability. To train the developed 1D-CNN machine, the SEER database as the most reliable repository of cancer survivability was used to retrieve the required training set. After a pre-processing to remove unusable records, a set of 50 000 breast cancer cases including 35 features was prepared for training the machine. Based on the results obtained in this study, the developed machine could reach an accuracy of 85.84%. This accuracy is the highest level of accuracy compared to the previous prediction methods. Furthermore, the mean squared error of the calculated probability was 0.112, which is an acceptable value of error for a probability calculation machine. The output of the developed machine can be used reliably by physicians to make decision about the most appropriate treatment strategy. [ABSTRACT FROM AUTHOR]

Industrial IoT (IIoT) era is evolving rapidly in parallel to the progress in Industry 4.0, which leads factories to increase the engagement with external parties through different communication infrastructures. This brings a larger attack surface and requires the development of new security solutions suitable for IIoT systems. Authentication is a key enabler to prevent the attacks that come from the interactions with the outside world components. Though there are proposed authentication schemes for IoT or machine-to-machine (M2M) applications, they cannot be readily applied for IIoT since manufacturing machines have different features and requirements than generic IT and IoT devices. In this paper, context information is proposed to be used for enhancing the authentication process in the IIoT, where instantaneous electricity consumption measured by smart meters is the main context information used as a dynamic authentication credential. Besides, in our method, existing smart meter infrastructure is utilized for both exchanging credentials over an industrial network and verification of the credentials by trusted components like Supervisory Control and Data Acquisition (SCADA) or Energy Management System (EMS). The proposed method also allows the use of other context information as authentication credentials such as temperature and humidity collected by sensors in the manufacturing environment. [ABSTRACT FROM AUTHOR]

Crowdsourcing has become increasingly popular in recent years. In order to achieve the optimal task allocation, one of the most important issues is to select more suitable crowdworkers. By leveraging its pervasiveness, social network can be employed as a novel worker recruitment platform. A robust task allocation scheme over the social network could also consider the word-of-mouth (WoM) mode, in which tasks are delivered from workers to workers. In this paper, we discuss an Non-deterministic Polynomial-Hard (NP-Hard) problem, cost-effective and budget-balanced task allocation (CBTA) problem under the WoM mode in social groups. We propose two heuristic algorithms: CB-greedy and CB-local based on greedy strategy and local search technique, respectively. We also prove that the running time of CB-greedy is |$O(m^2\log m)$|⁠ , whereas CB-local utilizing disjoint-set achieves |$O(mn\alpha (m, n))$|⁠ , where |$m$| is the number of edges indicating interactions of social groups, |$n$| is the number of social groups and |$\alpha $| is the inverse Ackerman function. Extensive experiments validate the efficiency and performance of our proposed algorithms. [ABSTRACT FROM AUTHOR]

With the help of a multi-signature scheme, we can reduce the cost of storage and bandwidth in case of many signers signing the same message. Therefore, multi-signature schemes can be used in bitcoin to reduce the size of a blockchain. In this paper, we propose a lattice-based multi-signature scheme with the following highlighted features. Our lattice-based multi-signature scheme supports signature compression and public key aggregation. The only existing lattice-based multi-signature scheme by Kansal and Dutta (Africacrypt, 2020) that supports both signature compression and public key aggregation has communication and storage cost |$\widetilde{\mathcal{O}}(n^2)$|⁠ , whereas our communication and storage cost is |$\mathcal{O}(n)$|⁠. Our multi-signature scheme is in the plain public key model where the special registration of the public key is not necessary and it is secure under the rogue key attack. Our multi-signature scheme is secure under the hardness of ring short integer solution problem in the random oracle model. [ABSTRACT FROM AUTHOR]

Attributable to the rapid growth of information technology, the Internet of Things (IoT) having strong permeability characteristics, huge usage of action and better comprehensive benefits. However, it encourages the development of IoT technology in the detection of structural engineering. Structural health monitoring (SHM) is responsible for identifying techniques and for prototyping systems performing a state diagnosis of structures. Its aim is to prevent sudden civil infrastructure failure as a result of several invisible sources of damage. This paper devises a novel method, namely bat-antlion Optimization dependent generative adversarial network (BALO-based GAN) for monitoring the states of structural health. Here, IoT nodes sense the signals of each channels and sensed data are transmitted to base station (BS) using Monarch-Earthworm (Monarch-EWA)-enabled secure routing protocol that selects the optimal path for the data transmission. After performing the IoT routing, the state of the structural health is monitored at the BS. For SHM, the input signal acquired from the IoT routing phase is fed to the pre-processing step for improving the signal quality for further processing. Then, the feature extraction is performed using fractional-amplitude modulation spectrogram (fractional AMS) for extracting the best features for improving the classification accuracy. The extracted features are adapted by the GAN, which is trained by BALO. The proposed BALO is newly designed by integrating the Bat algorithm and antlion optimizer. The proposed BALO-based GAN showed improved performance with maximal accuracy of 0.912, maximal sensitivity of 0.911, maximal throughput of 0.972 and maximal specificity of 0.913, respectively. [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) is the process of identifying human expressions. People vary in their accuracy at recognizing the emotions of others. Use of technology to help people with emotion recognition is a relatively important research area. Various works have been conducted on automating the recognition of facial expressions. The main intent of this paper is to plan for the FER model with the aid of intelligent techniques. The proposed models consist of steps like data collection, face detection, optimized feature extraction and emotion recognition. Initially, the standard benchmark facial emotion dataset is collected, and it is subjected to face detection. The optimized scale-invariant feature transform (OSIFT) is adopted for feature extraction, in which the key points that are giving unique information are optimized by the hybrid meta-heuristic algorithm. Two meta-heuristic algorithms like spotted hyena optimization and beetle swarm optimization (BSO) are merged to form the proposed spotted hyena-based BSO (SH-BSO). Also, the local tri-directional pattern is extracted, which is further combined with optimized SIFT. Here, the proposed SH-BSO is utilized for optimizing the number of hidden neurons of both deep neural network and convolutional neural network in such a way that the recognition accuracy could attain maximum. [ABSTRACT FROM AUTHOR]

For the multiprocessor systems modeled by interconnection networks, one of the important properties is the characterization of fault tolerability. Connectivity, as an important parameter to evaluate fault tolerability, has witnessed research achievements. To make the evaluation more practical, conditional connectivity has been promisingly proposed. As one kind of conditional connectivity, |$h$| -restricted connectivity of a connected graph |$G$|⁠ , denoted by |$\kappa ^h (G)$|⁠ , is defined as the cardinality of the minimum vertex cut set |$F$| such that |$\delta (G-F)\geq h$|⁠. In this paper, we establish a universally |$h$| -restricted connectivity for a class of hypercube-based compound networks, in which the well-known networks, such as hierarchical cubic network |$HCN(n, n)$| and its generalization complete cubic network |$CCN(n)$|⁠ , are involved. [ABSTRACT FROM AUTHOR]

A redactable consortium blockchain (RCB) can build a trust layer for industrial internet of things (IIoT) so as to enable IIoT to resist certain powerful attacks resulting in improper block content. The redactability is particularly important for blockchains applied in IIoT with valuable or sensitive activities such as financial IoT or energy-trading IoT. Huang et al. proposed a threshold chameleon hash (TCH) scheme and then constructed an accountable-and-sanitizable chameleon signature scheme based on TCH. These two primitives are further used as fundamental modules to build an RCB, which empowers IIoT devices to operate the blockchain in a controllable way. However, our paper shows that Huang et al. 's RCB suffers from a security problem that weakens the crucial redactability. Specifically, we find out that if a transaction in a given block is legally redacted by all authorized sensors who collectively hold the private redacting key, anyone (without any private information) can further redact this redacted transaction and delete any transaction within this redacted block and, meanwhile, any sensor user with a private signing (not redacting) key can insert a forged transaction into this redacted block. We further address this threat by replacing the TCH module in Huang et al. 's RCB with our designed TCH. [ABSTRACT FROM AUTHOR]

Opinion mining from medical forums such as health check-ups is sparking growing interest and a stimulating area for natural language processing. This allows for a better understanding of patient health status and drug reactions while generating new knowledge for health care professionals and drug manufacturers, which helps improve the quality of service and produce more effective treatments. In this paper, the researchers present a framework of opinions classification of drug reviews. The objective of this work is to find the best model for analyzing patients' emotions about drugs. In this sense, the researchers oppose classical text vectorization methods (bag of words, term frequency-inverse document frequency) and word embedding methods (Word2vec, GloVe) for classical opinion mining face to modern machine learning tools with the Convolutional Neural Network (CNN), the Recurrent Neural Networks (Long Short-term Memory and Bidirectional Long Short-Term Memory). Experiments results show that the best model for drug reviews was achieved by CNN based on the Skip-gram model (85% accuracy). Experiments have led to conclude that the performance of a given model will depend on the type of dataset used, on feature representation and better collaboration between classifiers and feature extraction methods. [ABSTRACT FROM AUTHOR]

Many graph products have been applied to generate complex networks with striking properties observed in real-world systems. In this paper, we propose a simple generative model for simplicial networks by iteratively using edge corona product. We present a comprehensive analysis of the structural properties of the network model, including degree distribution, diameter, clustering coefficient, as well as distribution of clique sizes, obtaining explicit expressions for these relevant quantities, which agree with the behaviors found in diverse real networks. Moreover, we obtain exact expressions for all the eigenvalues and their associated multiplicities of the normalized Laplacian matrix, based on which we derive explicit formulas for mixing time, mean hitting time and the number of spanning trees. Thus, as previous models generated by other graph products, our model is also an exactly solvable one, whose structural properties can be analytically treated. More interestingly, the expressions for the spectra of our model are also exactly determined, which is sharp contrast to previous models whose spectra can only be given recursively at most. This advantage makes our model a good test bed and an ideal substrate network for studying dynamical processes, especially those closely related to the spectra of normalized Laplacian matrix, in order to uncover the influences of simplicial structure on these processes. [ABSTRACT FROM AUTHOR]

Deoxys-BC is an internal tweakable block cipher of the authenticated encryption algorithm Deoxys, which is a third-round finalist in the CAESAR competition. In this paper, we study the property of Deoxys-BC, such as the subtweakey difference cancelation and the freedom of the tweak. Combining the differential enumeration technique with these properties, the authors achieve the key-recovery attacks on Deoxys-BC under the meet-in-the-middle attack. As a result, we get an attack on 9-round Deoxys-BC-128-128 by constructing a 6-round meet-in-the-middle distinguisher with |$2^{113}$| plaintext–tweak combinations, |$2^{97}$| Deoxys-BC blocks and |$2^{121.6}$| 9-round Deoxys-BC-128-128 encryptions. We also present an attack on 11-round Deoxys-BC-256-128 for the first time by constructing a 7-round meet-in-the-middle distinguisher with |$2^{113}$| plaintext-tweak combinations, |$2^{226}$| Deoxys-BC blocks and |$2^{251}$| 11-round Deoxys-BC-256-128 encryptions. [ABSTRACT FROM AUTHOR]

Reliability evaluation of interconnection networks is of significant importance to the design and maintenance of interconnection networks. The extra connectivity is an important parameter for the reliability evaluation of interconnection networks and is a generalization of the traditional connectivity. Let |$g\geq 0$| be an integer and |$G$| be a connected graph; the |$g$| -extra connectivity of |$G$| is the minimum cardinality of a set of vertices in |$G$|⁠ , if it exists, whose removal disconnects |$G$| and leaves every component with more than |$g$| vertices. Determining the |$g$| -extra connectivity is still an unsolved problem in many interconnection networks. Let |$n$|⁠ , |$k$| be positive integers. Let |$Q_{n,k}\, (1 \leq k \leq n-1)$| denote the |$(n, k)$| -enhanced hypercube. In this paper, we determine the |$g$| -extra connectivity of |$Q_{n,k}$| is |$(n+1)(g+1)-\frac{g(g+3)}{2}$| for |$0\leq g\leq n-k-1$|⁠ , |$4\leq k\leq n-5\,(n\geq 9)$|⁠. Some previous results in [Zhang, M. and Zhou, J. (2015) On g-extra connectivity of folded hypercubes. Theor. Comput. Sci. , 593, 146–153.] and [Sabir, E. Mamut, A. and Vumar, E. (2019) The extra connectivity of the enhanced hypercubes. Theor. Comput. Sci. , 799, 22–31.] are extended. [ABSTRACT FROM AUTHOR]

This paper investigates the security of counter mode encryption with authentication tag (COMET), one of the 32 second-round candidates in National Institute of Standards and Technology's lightweight cryptography standardization process, against differential cryptanalysis. CHAM-64/128 is a block cipher chosen as one of the underlying block ciphers in COMET for hardware-oriented applications, and a differential characteristic with a high probability for CHAM-64/128 is useful for forgery attacks on COMET. However, we find that the optimal |$\mathbf{39}$| -round differential characteristic for CHAM-64/128 proposed by Roh et al. , which is the longest differential characteristic of CHAM-64/128, is invalid. Then, we propose a new method of distinguishing an |$\mathbf{m}$| -bit block cipher from an |$\mathbf{m}$| -bit random permutation using a differential characteristic with a probability not higher than |$\mathbf{2^{-m}}$|⁠. Using our method, we use two |$\mathbf{39}$| -round differential characteristics with a probability of |$\mathbf{2^{-64}}$| for CHAM-64/128 to distinguish |$\mathbf{39}$| -round-reduced CHAM-64/128 from a |$\mathbf{64}$| -bit random permutation, respectively. Furthermore, we refine the probabilities of two differentials with the same input and output differential masks as the two |$\mathbf{39}$| -round differential characteristics, respectively. Finally, we present the first forgery attacks on COMET with the two differentials without using weak keys. Our forgery attacks follow the nonce-misuse scenario. It should be noticed that this attack does not invalidate the security claims of the designers. [ABSTRACT FROM AUTHOR]

Millions of new domain names are registered every day, but a large proportion of them are malicious and usually discovered and blacklisted after the crime has been committed. In order to improve the security of domain name registration, this paper proposes a lightweight detection method based on the AdaBoost to identify malicious domain names, which focuses on proactively detecting malicious domain names by exploring the abnormal WHOIS records. The domain name registries and registrars can adopt the proposed method as the first layer of defense to identify malicious domains on the domain registration stage. Extensive experiments on a large-scale database demonstrate that the proposed approach achieves satisfactory results on various malicious domain names. [ABSTRACT FROM AUTHOR]

As the backbone of the domain name system (DNS), DNS resolvers are essential to the Internet. Nowadays, the measurement of DNS resolvers, especially open DNS resolvers, has become a research focus. Previous research works show that DNS responses returned from some open DNS resolvers are not expected for clients and the Internet. We call these DNS responses 'unexpected DNS responses'. Research on unexpected DNS responses is beneficial to the research, usage and management of open DNS resolvers. This paper explores unexpected DNS responses returned from open DNS resolvers in terms of identification and classification to better understand the behaviours of open DNS resolvers. First, an identification method is proposed to identify all kinds of DNS responses from each section of DNS messages. Second, a classification method is proposed to classify unexpected DNS responses by their influences on clients and the Internet. Furthermore, an efficient identification and classification method is proposed to simplify the above process. Among about 9 million responding open DNS resolvers in the experiments on the IPv4 address space, about 40% return unexpected DNS responses. Experimental results show that the proposed methods can identify and classify all kinds of DNS responses returned from open DNS resolvers. [ABSTRACT FROM AUTHOR]

This paper aims to develop a novel deep learning concept to deal with video inpainting. Initially, motion tracking is performed, which is the process of determining motion vectors that describe the transformation from adjacent frames in a video sequence. Further, the regions or patches of each frame are categorized using the optimized recurrent neural network (RNN), in which the region is split into a smooth and structure region. It is performed using the texture feature called grey-level co-occurrence matrix. The filling of the smooth region is accomplished by replacing with the mean pixels of unmasked region, and the structure region is done by optimized patch matching approach based on scale-invariant feature transform (SIFT). The main objective optimized patch matching is based on the minimized Euclidean distance between the extracted SIFT features of the original patch and reference patch, and the certain patch is inpainted by the optimized patch. Here, the hybridization of two meta-heuristic algorithms like cuckoo search algorithm and multi-verse optimization (MVO) called Cuckoo Search-based MVO is used to optimize the RNN and patch matching. Finally, the experimental results verify the reliability of the proposed algorithm over existing algorithms. [ABSTRACT FROM AUTHOR]

NewHope cryptosystem is one of the second-round submissions of the National Institute of Standards and Technology post-quantum cryptography standardization process, which is a suite of two key encapsulation mechanisms based on the ring-learning with errors (LWE) problem. It has received much attention from the research community due to its small key size and high efficiency. Recently, three key mismatch attacks are proposed against NewHope under the condition of key reuse. They do not solve the ring-LWE instance directly but exploit the leakage of secret information. As far as we know, the best result is given by Okada et al. ((2020) Improving Key Mismatch Attack on NewHope with Fewer Queries. In Proc. of the 25th Australasian Conf. on Information Security and Privacy , Perth, WA, Australia, November 30–December 2, pp. 505–524. Springer Cham, Switzerland), which recovers the whole secret with a success probability of |$97\%$| and |$233,803$| average queries. In this paper, we further improve the key mismatch attack of NewHope by reducing the average queries to |$106,577$| and raising the success probability to |$100\%$|⁠. Moreover, we analyze the key mismatch attack without key reuse for the first time and we propose a combinatorial attack against NewHope1024. The total complexity of the combinatorial attack is |$2^{253}$|⁠ , which is lower than the complexity of primal attack and the claimed security strength of NewHope1024. [ABSTRACT FROM AUTHOR]

Image thresholding is an important and efficient image segmentation technique, which is crucial and essential for image analysis and computer vision. In this paper, we proposed a new image thresholding method based on entropy and parzen window (PW) estimation. First, the probability of each gray-level distribution is approximate by using the PW estimation. Second, by combining the obtained probability information with entropic information of the foreground and background, a new objective function is created. At last, the ideal threshold value is obtained by optimizing the objective function. By comparing with some classical thresholding methods, such as inter class variance method (OTSU), minimum error thresholding method (MET), Kapur's entropy based method (KAPUR) and the recent methods that take spatial information into consideration (2D-D histogram method, GLLV histogram method and Gabor histogram method), the proposed method, experiment on 10 images (one synthetic image, four nondestructive testing images and five real-world images), presents a better performance on the accuracy, robustness and visual effect of segmentation. [ABSTRACT FROM AUTHOR]

Connectivity and diagnosability are two crucial subjects for a network's ability to tolerate and diagnose faulty processors. The |$r$| -component connectivity |$c\kappa _{r}(G)$| of a network |$G$| is the minimum number of vertices whose deletion results in a graph with at least |$r$| components. The |$r$| -component diagnosability |$ct_{r}(G)$| of a network |$G$| is the maximum number of faulty vertices that the system can guarantee to identify under the condition that there exist at least |$r$| fault-free components. This paper first establishes that the |$(r+1)$| -component connectivity of |$k$| -ary |$n$| -cube |$Q^{k}_{n}$| is |$c\kappa _{r+1}(Q^{k}_{n})=-\frac{1}{2}r^{2}+\Big(2n-\frac{1}{2}\Big)r+1$| for |$n\geq 2$|⁠ , |$k\geq 4$| and |$1\leq r\leq n$|⁠. In view of |$c\kappa _{r+1}(Q^{k}_{n})$|⁠ , we prove that the |$(r+1)$| -component diagnosabilities of |$k$| -ary |$n$| -cube |$Q^{k}_{n}$| under the PMC model and MM* model are |$ct_{r+1}(Q^{k}_{n})=-\frac{1}{2}r^{2}+\Big(2n-\frac{3}{2}\Big)r+2n$| for |$n\geq 4$|⁠ , |$k\geq 4$| and |$1\leq r\leq n-1$|⁠. [ABSTRACT FROM AUTHOR]

This paper proposes an effective classification method named Rider Chicken Optimization Algorithm-based Recurrent Neural Network (RCOA-based RNN) to perform big data classification in spark architecture. Initially, the input data are collected from the network by the master node and then forwarded to the slave node. These nodes are responsible for storing the data and performing computations. The features are effectively selected in the slave node using the proposed RCOA. The selected features are forwarded to the master node. The big data classification is achieved in the master node by using the RNN classifier, and the training of the classifier is done using the proposed RCOA algorithm, which is the integration of the Rider optimization algorithm (ROA) with the standard Chicken Swarm Optimization (CSO). The experimentation is done by using the Switzerland dataset, Cleveland dataset, Hungarian dataset and Skin disease dataset, in which the proposed RCOA-based RNN attained better performance based on the quantitative properties, such as sensitivity, accuracy and specificity with the values of 9.3E+01%, 9.4E+01% and 9.3E+01% using Hungarian dataset. The existing learning methods failed to address the complex classification problems at a reasonable time, which is overcome by the proposed method. [ABSTRACT FROM AUTHOR]