Search

The High Performance Computing (HPC) applications benefit from the new paradigms for computers, capacity, and adaptable responses provided by cloud computing. For instance, the Hardware as a Service (HaaS) paradigm enables individuals to provide several Virtual Machines (VMs) for applications that need a lot of computing. Any execution error would require re-running applications, which would waste time, money, and energy since the HPC system on the cloud uses a lot of VMs and electrical components. In this research, the execution time on the clock and the cost when mistakes occur, we provided a Proactive Fault Tolerance (PFT) strategy to High Performance Computing systems in the cloud. Additionally, we created an enhanced PFT technique for cloud-based HPC systems. Before predicting a failure, our approach does not depend on a spare node. Also, we created a model cost for running computing-heavy apps on cloud HPC servers. To evaluate the effectiveness of our strategy, we looked at the monetary costs associated with supplying spare nodes and checkpointing PFT. Our experimental findings from a genuine cloud execution environment demonstrate that executing computation-intensive apps in the cloud may lower costs and execution times by up to 30%. Our PFT technique for HPC in the cloud may minimize the occurrence of checkpointing of computation-exhaustive applications by up to fifty percent when compared to existing PFT approaches.

The agenda of this book chapter is to review existing technologies that aid societal health protection and recommend some possible approaches which will assist the mentioned scenario. Automations like big data and artificial intelligence (AI) deployed in healthcare sector can expedite pandemic response in ways that are strenuous to achieve all in all by humans. The sudden epiphany to trace COVID-19 in public has powered the innovation of data dashboards that visually unveil coronavirus epicentres. A cloud-based AI-assisted CT service is being engaged to differentiate pneumonia from the pandemic which dwindles risk factor in the present school of thought of the citizens worldwide. In conclusion, social health protection was an indispensable mechanism in prior to these challenging times and is escalating by prominence for delivering support to individuals during the crisis.

This article deals with a fuzzy hypercompositional structure called fuzzy hyperlattice ordered δ- group ( FHLO δ - G ) , the extension of the fuzzy hypercompositional structure namely fuzzy hyperlattice ordered group (FHLOG). Using FHLO δ - G , we can involve one additional non-empty set δ with FHLOG, which helps to develop new results and applications. The structural characteristics and properties of FHLO δ - G are analysed. Furthermore, an application of FHLO δ - G for ABO blood group system is proposed.

Network intrusion detection system (NIDS) plays a major role in ensuring network security. In this paper, the authors propose a PSO-DNN-based intrusion detection system. The correlation-based feature selection (CFS) applied for feature selection with particle swarm optimization (PSO) as search method and deep neural networks (DNN) for classification of network intrusions. The Adam optimizer is applied for optimizing the learning rate, and softmax classifier is used for classification. The experimentations were duly conducted on the standard benchmark NSL-KDD dataset. The proposed model is validated using 10-fold cross-validation and evaluated using the performance metrics such as accuracy, precision, recall, and F1-score. Also, the results are also compared with DNN and CFS+DNN. The experimental results show that the proposed model performs better compared with other methods considered for comparison.

Medical data transmission is a major challenge in wireless communication to preserve their integrity and coherence. As the transmission takes place at high data rate, the complexity and throughput ...

In this article, an EFS-LSTM, a deep recurrent learning model, is proposed for network intrusion detection systems. The EFS-LSTM model uses ensemble-based feature selection (EFS) and LSTM (Long Short Term Memory) for the classification of network intrusions. The EFS combines five feature selection mechanisms namely, information gain, gain ratio, chi-square, correlation-based feature selection, and symmetric uncertainty-based feature selection. The experiments were conducted using the benchmark NSL-KDD dataset and implemented using Tensor flow and python. The EFS-LSTM classifier is evaluated using the classification performance metrics and also compared with all the 41 features without any feature selection as well as with each individual feature selection techniques and classified using LSTM. The performance study showed that the EFS-LSTM model outperforms better with 99.8% accuracy with a higher detection and less false alarm rates.

The Network Intrusion Detection System (NIDS) assumes a prominent aspect in ensuring network security. It serves better than traditional network security mechanisms, such as firewall systems. The result of the NIDS indicates the enhanced and efficient performance of the algorithms. It is utilized to predict intrusions, and it also has better training times for the algorithms. In this paper, a capable deep learning model using Sparse Auto Encoder (SAE) is proposed. It is a self-taught learning framework. Such a model is a competent unsupervised learning algorithm in reconstructing new feature representation; thus, it diminishes the dimensionality. The SAE requires minimum training time substantially and efficiently enhances the prediction accuracy of Support Vector Regression (SVR) related to attacks. The experiments are administered using the standard intrusion detection dataset NSL-KDD, and therefore, the implementations are performed using python and tensor flow. The proposed model’s effectiveness is estimated with other models viz., the PCA-SVR and SVR models applying prediction metrics such as R2 score, Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), accuracy and also training time. Results validate that the proposed SAE-SVR model has accelerated the training time of SVR and has the edge over the other models weighed in terms of prediction metrics. The model improves the rate of prediction by bringing down the error rates and yields a pioneering research mechanism for predicting the intrusions.

Medical data transmission is a major challenge in wireless communication to preserve their integrity and coherence. Orthogonal frequency division multiplexing (OFDM) has emerged as a modulation sch...

Soft set theory has been evolved as a completely new mathematical tool for modeling vague concepts. Yong Yang et.al propounded the theory of Multi-fuzzy soft set and its application to deci...

Diagnosis of fetal heart rate is very crucial during the prenatal phase of pregnancy as any delay in the early detection and prevention of anomalies in heart functioning may lead to devastating and...

Structural flexibility of the peptide linker connecting two domains is essential for the functioning of multi-domain complex. Nitric oxide synthase (NOS) isoforms contain the oxygenase and the reductase domains connected by calmodulin binding linker (CBL) region. Additionally, the endothelial NOS (eNOS) isoform contain an auto-inhibitory loop (AI) in the FMN reductase sub-domain which represses the inter-domain electron transfer process. Binding of Ca2+-Calmodulin complex on the CBL region relieves the AI loop repression and facilitates electron transfer from FMN in the reductase domain to the heme in the oxygenase domain. Few experimental studies have reported that in vitro mutation of Serine-615 (S615D) and Serine-633 (S633D) in the FMN reductase sub-domain to aspartic acid increased NO production and increased Ca2+ sensitivity. To understand the role of AI loop in eNOS repression and activation in serine mutants (S615D and S633D), we modelled the FMN reductase sub-domain of human eNOS protein with and without the CBL region. Molecular dynamics simulations performed indicated that the mutant protein AI loop structure was stabilized by salt bridge formed between D615 and R602. It was also found that mutation increased the flexibility of C-terminal residues of eNOS CBL region. The hinge-like movement of the AI loop allowed rotation of the FMN sub-domain clockwise which may favour electron-transfer in the mutant protein. This study provides insight on mutation (S615D and S633D) induced changes in AI loop and increased flexibility of CBL region which may lead to the protein activation and may also facilitate Calmodulin binding at physiological Ca2+ concentration. Graphical Abstract Mutation of amino acid residues contribute to structural changes at molecular level leading to alteration in protein dynamics and its function. Serine-615 and Serine-633 in the auto-inhibitory loop of human eNOS reductase model was mutated to aspartic acid in silico and molecular dynamics simulations of the protein showed that steric hindrance due to mutation altered the auto-inhibitory loop rearrangement and the FMN sub-domain movement favouring electron transfer.

This chapter presents an ensemble-based feature selection with long short-term memory (LSTM) model. A deep recurrent learning model is proposed for classifying network intrusion. This model uses ensemble-based feature selection (EFS) for selecting the appropriate features from the dataset and long short-term memory for the classification of network intrusions. The EFS combines five feature selection techniques, namely information gain, gain ratio, chi-square, correlation-based feature selection, and symmetric uncertainty-based feature selection. The experiments were conducted using the standard benchmark NSL-KDD dataset and implemented using tensor flow and python. The proposed model is evaluated using the classification performance metrics and also compared with all the 41 features without any feature selection as well as with each individual feature selection technique and classified using LSTM. The performance study showed that the proposed model performs better, with 99.8% accuracy, with a higher detection and lower false alarm rates.

The structure of lattice in interval valued hesitant fuzzy soft set was implemented in 2018. In our previous work, the pivotal properties of L-IVHFSS and the effect of its nature in the problem of decision making was explored. In this paper, we appraised the operations of L-IVHFSS and the new conception of Contra-L-IVHFSS. Also the inference of duality in L-IVHFSS and Contra-L-IVHFSS were examined.

In 2019, we have initiated the theory of lattice ordered multi-fuzzy soft sets (ℒℳℱ𝒮 𝒮 ) and its application in Forecasting process. In this paper, our aim is to propose the idea of Anti-lattice ordered multi-fuzzy soft sets (𝒜 ℒℳℱ𝒮 𝒮 ) and also establish the operations of 𝒜 ℒℳℱ𝒮𝒮. Moreover, as an application of 𝒜 ℒℳℱ𝒮𝒮 is developed.

The usage of Internet technology is drastically growing day by day. With this enormous raise, a considerable volume of data generated. Therefore, network security is also receiving its attention to secure from attacks. The intrusion detection system (IDS) performs an essential part in the particular domain of network security. This research work aims at evaluating the performance of shallow learning and deep learning methods, which are the subsets of machine learning algorithms. The implementation appropriately employed utilizing standard benchmark NSL-KDD dataset [10]. The experimentation involves 4 shallow learning algorithms and deep neural networks utilizing Tensor flow and python. The experimental results evaluated employing classification metrics, such as Accuracy, Precision, Recall, and F1-score.